From c1a15c45c5970955ac78b012c1d1a7bda32cae85 Mon Sep 17 00:00:00 2001 From: Ed_ Date: Sun, 21 Jun 2026 15:41:38 -0400 Subject: [PATCH] conductor(tracks): scaffold plan.md + metadata.json + state.toml for 12 child + 1 synthesis tracks --- .../metadata.json | 64 +++++++++++++++++++ .../plan.md | 60 +++++++++++++++++ .../state.toml | 36 +++++++++++ .../metadata.json | 64 +++++++++++++++++++ .../plan.md | 60 +++++++++++++++++ .../state.toml | 36 +++++++++++ .../metadata.json | 63 ++++++++++++++++++ .../plan.md | 62 ++++++++++++++++++ .../state.toml | 35 ++++++++++ .../metadata.json | 63 ++++++++++++++++++ .../plan.md | 62 ++++++++++++++++++ .../state.toml | 35 ++++++++++ .../metadata.json | 64 +++++++++++++++++++ .../plan.md | 60 +++++++++++++++++ .../state.toml | 36 +++++++++++ .../metadata.json | 64 +++++++++++++++++++ .../plan.md | 60 +++++++++++++++++ .../state.toml | 36 +++++++++++ .../metadata.json | 64 +++++++++++++++++++ .../plan.md | 60 +++++++++++++++++ .../state.toml | 36 +++++++++++ .../metadata.json | 64 +++++++++++++++++++ .../plan.md | 60 +++++++++++++++++ .../state.toml | 36 +++++++++++ .../metadata.json | 64 +++++++++++++++++++ .../plan.md | 60 +++++++++++++++++ .../state.toml | 36 +++++++++++ .../metadata.json | 64 +++++++++++++++++++ .../plan.md | 60 +++++++++++++++++ .../state.toml | 36 +++++++++++ .../metadata.json | 64 +++++++++++++++++++ .../plan.md | 60 +++++++++++++++++ .../state.toml | 36 +++++++++++ .../metadata.json | 64 +++++++++++++++++++ .../plan.md | 60 +++++++++++++++++ .../state.toml | 36 +++++++++++ .../metadata.json | 46 +++++++++++++ .../state.toml | 36 +++++++++++ 38 files changed, 2002 insertions(+) create mode 100644 conductor/tracks/video_analysis_brain_counterintuitive_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_brain_counterintuitive_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_brain_counterintuitive_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_creikey_dl_cv_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_creikey_dl_cv_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_creikey_dl_cv_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_cs229_building_llms_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_cs229_building_llms_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_cs229_building_llms_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_cs336_architectures_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_cs336_architectures_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_cs336_architectures_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_entropy_epiplexity_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_entropy_epiplexity_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_entropy_epiplexity_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_free_lunches_levin_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_free_lunches_levin_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_free_lunches_levin_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_generic_systems_fields_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_generic_systems_fields_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_generic_systems_fields_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_multiscale_hoffman_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_multiscale_hoffman_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_multiscale_hoffman_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_neural_dynamics_miller_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_neural_dynamics_miller_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_neural_dynamics_miller_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_probability_logic_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_probability_logic_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_probability_logic_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/plan.md create mode 100644 conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/state.toml create mode 100644 conductor/tracks/video_analysis_synthesis_20260621/metadata.json create mode 100644 conductor/tracks/video_analysis_synthesis_20260621/state.toml diff --git a/conductor/tracks/video_analysis_brain_counterintuitive_20260621/metadata.json b/conductor/tracks/video_analysis_brain_counterintuitive_20260621/metadata.json new file mode 100644 index 00000000..a035d12c --- /dev/null +++ b/conductor/tracks/video_analysis_brain_counterintuitive_20260621/metadata.json @@ -0,0 +1,64 @@ +{ + "track_id": "video_analysis_brain_counterintuitive_20260621", + "name": "The Most Counterintuitive Way to Build a Brain", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621", + "video_analysis_free_lunches_levin_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "C", + "youtube_id": "cDxtFtoQVNc", + "youtube_url": "https://youtu.be/cDxtFtoQVNc", + "author": null, + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-brain_counterintuitive", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "low", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_brain_counterintuitive_20260621/plan.md b/conductor/tracks/video_analysis_brain_counterintuitive_20260621/plan.md new file mode 100644 index 00000000..51dcdf13 --- /dev/null +++ b/conductor/tracks/video_analysis_brain_counterintuitive_20260621/plan.md @@ -0,0 +1,60 @@ +# Plan: video_analysis_brain_counterintuitive_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *The Most Counterintuitive Way to Build a Brain* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #8 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/cDxtFtoQVNc (YouTube ID `cDxtFtoQVNc`) +**Cluster:** C (Biological / cognitive / generic systems) +**Author:** (unknown) + +--- + +## Phase 1: Acquire + +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/cDxtFtoQVNc artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/cDxtFtoQVNc artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_brain_counterintuitive_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_brain_counterintuitive_20260621/state.toml b/conductor/tracks/video_analysis_brain_counterintuitive_20260621/state.toml new file mode 100644 index 00000000..f008c654 --- /dev/null +++ b/conductor/tracks/video_analysis_brain_counterintuitive_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_brain_counterintuitive_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_brain_counterintuitive_20260621" +name = "The Most Counterintuitive Way to Build a Brain" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" +video_analysis_free_lunches_levin_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_creikey_dl_cv_20260621/metadata.json b/conductor/tracks/video_analysis_creikey_dl_cv_20260621/metadata.json new file mode 100644 index 00000000..cfb44538 --- /dev/null +++ b/conductor/tracks/video_analysis_creikey_dl_cv_20260621/metadata.json @@ -0,0 +1,64 @@ +{ + "track_id": "video_analysis_creikey_dl_cv_20260621", + "name": "Creikey - Deep Learning and Computer Vision for Game Developers (BSC 2025)", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621", + "video_analysis_cs336_architectures_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "D", + "youtube_id": "yxkUvXs-hoQ", + "youtube_url": "https://youtu.be/yxkUvXs-hoQ", + "author": "Creikey", + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-creikey_dl_cv", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "low", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_creikey_dl_cv_20260621/plan.md b/conductor/tracks/video_analysis_creikey_dl_cv_20260621/plan.md new file mode 100644 index 00000000..b7757b53 --- /dev/null +++ b/conductor/tracks/video_analysis_creikey_dl_cv_20260621/plan.md @@ -0,0 +1,60 @@ +# Plan: video_analysis_creikey_dl_cv_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *Creikey - Deep Learning and Computer Vision for Game Developers (BSC 2025)* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #12 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/yxkUvXs-hoQ (YouTube ID `yxkUvXs-hoQ`) +**Cluster:** D (Applied / practical) +**Author:** Creikey + +--- + +## Phase 1: Acquire + +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/yxkUvXs-hoQ artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/yxkUvXs-hoQ artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_creikey_dl_cv_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_creikey_dl_cv_20260621/state.toml b/conductor/tracks/video_analysis_creikey_dl_cv_20260621/state.toml new file mode 100644 index 00000000..e39a5da9 --- /dev/null +++ b/conductor/tracks/video_analysis_creikey_dl_cv_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_creikey_dl_cv_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_creikey_dl_cv_20260621" +name = "Creikey - Deep Learning and Computer Vision for Game Developers (BSC 2025)" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" +video_analysis_cs336_architectures_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_cs229_building_llms_20260621/metadata.json b/conductor/tracks/video_analysis_cs229_building_llms_20260621/metadata.json new file mode 100644 index 00000000..c4989567 --- /dev/null +++ b/conductor/tracks/video_analysis_cs229_building_llms_20260621/metadata.json @@ -0,0 +1,63 @@ +{ + "track_id": "video_analysis_cs229_building_llms_20260621", + "name": "Stanford CS229 - Building Large Language Models (LLMs)", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "E", + "youtube_id": "9vM4p9NN0Ts", + "youtube_url": "https://youtu.be/9vM4p9NN0Ts", + "author": "Stanford CS229", + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-cs229_building_llms", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "high", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_cs229_building_llms_20260621/plan.md b/conductor/tracks/video_analysis_cs229_building_llms_20260621/plan.md new file mode 100644 index 00000000..1c49372c --- /dev/null +++ b/conductor/tracks/video_analysis_cs229_building_llms_20260621/plan.md @@ -0,0 +1,62 @@ +# Plan: video_analysis_cs229_building_llms_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *Stanford CS229 - Building Large Language Models (LLMs)* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #1 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/9vM4p9NN0Ts (YouTube ID `9vM4p9NN0Ts`) +**Cluster:** E (Stanford course VODs >1hr) +**Author:** Stanford CS229 + +--- + +## Phase 1: Acquire + + +- [ ] **Step 0: yt-dlp access verification (R5).** Run `uv run yt-dlp --simulate https://youtu.be/9vM4p9NN0Ts` to confirm yt-dlp can fetch metadata. If it fails (HTTP 401/403), fall back to manual transcript sourcing or escalate per umbrella spec §13 R5. +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/9vM4p9NN0Ts artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/9vM4p9NN0Ts artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_cs229_building_llms_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_cs229_building_llms_20260621/state.toml b/conductor/tracks/video_analysis_cs229_building_llms_20260621/state.toml new file mode 100644 index 00000000..3422c4dc --- /dev/null +++ b/conductor/tracks/video_analysis_cs229_building_llms_20260621/state.toml @@ -0,0 +1,35 @@ +# Track state for video_analysis_cs229_building_llms_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_cs229_building_llms_20260621" +name = "Stanford CS229 - Building Large Language Models (LLMs)" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_cs336_architectures_20260621/metadata.json b/conductor/tracks/video_analysis_cs336_architectures_20260621/metadata.json new file mode 100644 index 00000000..113dcfda --- /dev/null +++ b/conductor/tracks/video_analysis_cs336_architectures_20260621/metadata.json @@ -0,0 +1,63 @@ +{ + "track_id": "video_analysis_cs336_architectures_20260621", + "name": "Stanford CS336 Lecture 3: Architectures", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "E", + "youtube_id": "lVynu4bo1rY", + "youtube_url": "https://youtu.be/lVynu4bo1rY", + "author": "Stanford CS336 Spring 2026", + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-cs336_architectures", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "high", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_cs336_architectures_20260621/plan.md b/conductor/tracks/video_analysis_cs336_architectures_20260621/plan.md new file mode 100644 index 00000000..58f65f6f --- /dev/null +++ b/conductor/tracks/video_analysis_cs336_architectures_20260621/plan.md @@ -0,0 +1,62 @@ +# Plan: video_analysis_cs336_architectures_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *Stanford CS336 Lecture 3: Architectures* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #11 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/lVynu4bo1rY (YouTube ID `lVynu4bo1rY`) +**Cluster:** E (Stanford course VODs >1hr) +**Author:** Stanford CS336 Spring 2026 + +--- + +## Phase 1: Acquire + + +- [ ] **Step 0: yt-dlp access verification (R5).** Run `uv run yt-dlp --simulate https://youtu.be/lVynu4bo1rY` to confirm yt-dlp can fetch metadata. If it fails (HTTP 401/403), fall back to manual transcript sourcing or escalate per umbrella spec §13 R5. +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/lVynu4bo1rY artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/lVynu4bo1rY artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_cs336_architectures_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_cs336_architectures_20260621/state.toml b/conductor/tracks/video_analysis_cs336_architectures_20260621/state.toml new file mode 100644 index 00000000..f131b420 --- /dev/null +++ b/conductor/tracks/video_analysis_cs336_architectures_20260621/state.toml @@ -0,0 +1,35 @@ +# Track state for video_analysis_cs336_architectures_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_cs336_architectures_20260621" +name = "Stanford CS336 Lecture 3: Architectures" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_entropy_epiplexity_20260621/metadata.json b/conductor/tracks/video_analysis_entropy_epiplexity_20260621/metadata.json new file mode 100644 index 00000000..5a55e5bb --- /dev/null +++ b/conductor/tracks/video_analysis_entropy_epiplexity_20260621/metadata.json @@ -0,0 +1,64 @@ +{ + "track_id": "video_analysis_entropy_epiplexity_20260621", + "name": "From Entropy to Epiplexity", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621", + "video_analysis_cs229_building_llms_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "A", + "youtube_id": "_U8AwUq_aJQ", + "youtube_url": "https://youtu.be/_U8AwUq_aJQ", + "author": "Andrew Wilson and Marc Finzi", + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-entropy_epiplexity", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "low", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_entropy_epiplexity_20260621/plan.md b/conductor/tracks/video_analysis_entropy_epiplexity_20260621/plan.md new file mode 100644 index 00000000..94d879e2 --- /dev/null +++ b/conductor/tracks/video_analysis_entropy_epiplexity_20260621/plan.md @@ -0,0 +1,60 @@ +# Plan: video_analysis_entropy_epiplexity_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *From Entropy to Epiplexity* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #3 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/_U8AwUq_aJQ (YouTube ID `_U8AwUq_aJQ`) +**Cluster:** A (Math & information-theoretic foundations) +**Author:** Andrew Wilson and Marc Finzi + +--- + +## Phase 1: Acquire + +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/_U8AwUq_aJQ artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/_U8AwUq_aJQ artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_entropy_epiplexity_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_entropy_epiplexity_20260621/state.toml b/conductor/tracks/video_analysis_entropy_epiplexity_20260621/state.toml new file mode 100644 index 00000000..9e663385 --- /dev/null +++ b/conductor/tracks/video_analysis_entropy_epiplexity_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_entropy_epiplexity_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_entropy_epiplexity_20260621" +name = "From Entropy to Epiplexity" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" +video_analysis_cs229_building_llms_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_free_lunches_levin_20260621/metadata.json b/conductor/tracks/video_analysis_free_lunches_levin_20260621/metadata.json new file mode 100644 index 00000000..7923e40e --- /dev/null +++ b/conductor/tracks/video_analysis_free_lunches_levin_20260621/metadata.json @@ -0,0 +1,64 @@ +{ + "track_id": "video_analysis_free_lunches_levin_20260621", + "name": "Free Lunches: Model Systems for Studying the Agential Gifts from the Platonic Space", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621", + "video_analysis_score_dynamics_giorgini_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "B", + "youtube_id": "K8BmMU1Tm-I", + "youtube_url": "https://youtu.be/K8BmMU1Tm-I", + "author": "Michael Levin", + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-free_lunches_levin", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "low", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_free_lunches_levin_20260621/plan.md b/conductor/tracks/video_analysis_free_lunches_levin_20260621/plan.md new file mode 100644 index 00000000..ab627e35 --- /dev/null +++ b/conductor/tracks/video_analysis_free_lunches_levin_20260621/plan.md @@ -0,0 +1,60 @@ +# Plan: video_analysis_free_lunches_levin_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *Free Lunches: Model Systems for Studying the Agential Gifts from the Platonic Space* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #6 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/K8BmMU1Tm-I (YouTube ID `K8BmMU1Tm-I`) +**Cluster:** B (Platonic / geometric AI representations) +**Author:** Michael Levin + +--- + +## Phase 1: Acquire + +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/K8BmMU1Tm-I artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/K8BmMU1Tm-I artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_free_lunches_levin_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_free_lunches_levin_20260621/state.toml b/conductor/tracks/video_analysis_free_lunches_levin_20260621/state.toml new file mode 100644 index 00000000..81dd3ed1 --- /dev/null +++ b/conductor/tracks/video_analysis_free_lunches_levin_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_free_lunches_levin_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_free_lunches_levin_20260621" +name = "Free Lunches: Model Systems for Studying the Agential Gifts from the Platonic Space" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" +video_analysis_score_dynamics_giorgini_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_generic_systems_fields_20260621/metadata.json b/conductor/tracks/video_analysis_generic_systems_fields_20260621/metadata.json new file mode 100644 index 00000000..b3f8bb84 --- /dev/null +++ b/conductor/tracks/video_analysis_generic_systems_fields_20260621/metadata.json @@ -0,0 +1,64 @@ +{ + "track_id": "video_analysis_generic_systems_fields_20260621", + "name": "Interesting Behavior by Generic Systems", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621", + "video_analysis_free_lunches_levin_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "C", + "youtube_id": "QeMajYvhEbI", + "youtube_url": "https://youtu.be/QeMajYvhEbI", + "author": "Chris Fields", + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-generic_systems_fields", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "low", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_generic_systems_fields_20260621/plan.md b/conductor/tracks/video_analysis_generic_systems_fields_20260621/plan.md new file mode 100644 index 00000000..ca8365fd --- /dev/null +++ b/conductor/tracks/video_analysis_generic_systems_fields_20260621/plan.md @@ -0,0 +1,60 @@ +# Plan: video_analysis_generic_systems_fields_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *Interesting Behavior by Generic Systems* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #7 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/QeMajYvhEbI (YouTube ID `QeMajYvhEbI`) +**Cluster:** C (Biological / cognitive / generic systems) +**Author:** Chris Fields + +--- + +## Phase 1: Acquire + +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/QeMajYvhEbI artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/QeMajYvhEbI artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_generic_systems_fields_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_generic_systems_fields_20260621/state.toml b/conductor/tracks/video_analysis_generic_systems_fields_20260621/state.toml new file mode 100644 index 00000000..ec5aca17 --- /dev/null +++ b/conductor/tracks/video_analysis_generic_systems_fields_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_generic_systems_fields_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_generic_systems_fields_20260621" +name = "Interesting Behavior by Generic Systems" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" +video_analysis_free_lunches_levin_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_multiscale_hoffman_20260621/metadata.json b/conductor/tracks/video_analysis_multiscale_hoffman_20260621/metadata.json new file mode 100644 index 00000000..4acd5099 --- /dev/null +++ b/conductor/tracks/video_analysis_multiscale_hoffman_20260621/metadata.json @@ -0,0 +1,64 @@ +{ + "track_id": "video_analysis_multiscale_hoffman_20260621", + "name": "A Multiscale Logic of Collective Intelligence", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621", + "video_analysis_free_lunches_levin_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "C", + "youtube_id": "YnfaT5APPB0", + "youtube_url": "https://youtu.be/YnfaT5APPB0", + "author": "Donald Hoffman and Chetan Prakash", + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-multiscale_hoffman", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "low", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_multiscale_hoffman_20260621/plan.md b/conductor/tracks/video_analysis_multiscale_hoffman_20260621/plan.md new file mode 100644 index 00000000..0054f9ef --- /dev/null +++ b/conductor/tracks/video_analysis_multiscale_hoffman_20260621/plan.md @@ -0,0 +1,60 @@ +# Plan: video_analysis_multiscale_hoffman_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *A Multiscale Logic of Collective Intelligence* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #10 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/YnfaT5APPB0 (YouTube ID `YnfaT5APPB0`) +**Cluster:** C (Biological / cognitive / generic systems) +**Author:** Donald Hoffman and Chetan Prakash + +--- + +## Phase 1: Acquire + +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/YnfaT5APPB0 artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/YnfaT5APPB0 artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_multiscale_hoffman_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_multiscale_hoffman_20260621/state.toml b/conductor/tracks/video_analysis_multiscale_hoffman_20260621/state.toml new file mode 100644 index 00000000..2f39c57f --- /dev/null +++ b/conductor/tracks/video_analysis_multiscale_hoffman_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_multiscale_hoffman_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_multiscale_hoffman_20260621" +name = "A Multiscale Logic of Collective Intelligence" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" +video_analysis_free_lunches_levin_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_neural_dynamics_miller_20260621/metadata.json b/conductor/tracks/video_analysis_neural_dynamics_miller_20260621/metadata.json new file mode 100644 index 00000000..87fae743 --- /dev/null +++ b/conductor/tracks/video_analysis_neural_dynamics_miller_20260621/metadata.json @@ -0,0 +1,64 @@ +{ + "track_id": "video_analysis_neural_dynamics_miller_20260621", + "name": "Cognition Emerges from Neural Dynamics", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621", + "video_analysis_free_lunches_levin_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "C", + "youtube_id": "0BS-BzEFTXA", + "youtube_url": "https://youtu.be/0BS-BzEFTXA", + "author": "Earl Miller", + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-neural_dynamics_miller", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "low", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_neural_dynamics_miller_20260621/plan.md b/conductor/tracks/video_analysis_neural_dynamics_miller_20260621/plan.md new file mode 100644 index 00000000..74e8f0aa --- /dev/null +++ b/conductor/tracks/video_analysis_neural_dynamics_miller_20260621/plan.md @@ -0,0 +1,60 @@ +# Plan: video_analysis_neural_dynamics_miller_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *Cognition Emerges from Neural Dynamics* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #9 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/0BS-BzEFTXA (YouTube ID `0BS-BzEFTXA`) +**Cluster:** C (Biological / cognitive / generic systems) +**Author:** Earl Miller + +--- + +## Phase 1: Acquire + +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/0BS-BzEFTXA artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/0BS-BzEFTXA artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_neural_dynamics_miller_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_neural_dynamics_miller_20260621/state.toml b/conductor/tracks/video_analysis_neural_dynamics_miller_20260621/state.toml new file mode 100644 index 00000000..61f686b4 --- /dev/null +++ b/conductor/tracks/video_analysis_neural_dynamics_miller_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_neural_dynamics_miller_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_neural_dynamics_miller_20260621" +name = "Cognition Emerges from Neural Dynamics" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" +video_analysis_free_lunches_levin_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/metadata.json b/conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/metadata.json new file mode 100644 index 00000000..2aef2944 --- /dev/null +++ b/conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/metadata.json @@ -0,0 +1,64 @@ +{ + "track_id": "video_analysis_platonic_intelligence_kumar_20260621", + "name": "Towards a Platonic Intelligence with Unified Factored Representations", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621", + "video_analysis_score_dynamics_giorgini_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "B", + "youtube_id": "1mXUFweWOug", + "youtube_url": "https://youtu.be/1mXUFweWOug", + "author": "Akarsh Kumar", + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-platonic_intelligence_kumar", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "low", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/plan.md b/conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/plan.md new file mode 100644 index 00000000..cc7eb042 --- /dev/null +++ b/conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/plan.md @@ -0,0 +1,60 @@ +# Plan: video_analysis_platonic_intelligence_kumar_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *Towards a Platonic Intelligence with Unified Factored Representations* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #5 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/1mXUFweWOug (YouTube ID `1mXUFweWOug`) +**Cluster:** B (Platonic / geometric AI representations) +**Author:** Akarsh Kumar + +--- + +## Phase 1: Acquire + +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/1mXUFweWOug artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/1mXUFweWOug artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_platonic_intelligence_kumar_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/state.toml b/conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/state.toml new file mode 100644 index 00000000..47a6571b --- /dev/null +++ b/conductor/tracks/video_analysis_platonic_intelligence_kumar_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_platonic_intelligence_kumar_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_platonic_intelligence_kumar_20260621" +name = "Towards a Platonic Intelligence with Unified Factored Representations" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" +video_analysis_score_dynamics_giorgini_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_probability_logic_20260621/metadata.json b/conductor/tracks/video_analysis_probability_logic_20260621/metadata.json new file mode 100644 index 00000000..7b08b285 --- /dev/null +++ b/conductor/tracks/video_analysis_probability_logic_20260621/metadata.json @@ -0,0 +1,64 @@ +{ + "track_id": "video_analysis_probability_logic_20260621", + "name": "Probability Theory is an Extension of Logic", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621", + "video_analysis_cs229_building_llms_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "A", + "youtube_id": "0yF9TvMeAzM", + "youtube_url": "https://youtu.be/0yF9TvMeAzM", + "author": null, + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-probability_logic", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "low", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_probability_logic_20260621/plan.md b/conductor/tracks/video_analysis_probability_logic_20260621/plan.md new file mode 100644 index 00000000..facd8e8a --- /dev/null +++ b/conductor/tracks/video_analysis_probability_logic_20260621/plan.md @@ -0,0 +1,60 @@ +# Plan: video_analysis_probability_logic_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *Probability Theory is an Extension of Logic* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #2 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/0yF9TvMeAzM (YouTube ID `0yF9TvMeAzM`) +**Cluster:** A (Math & information-theoretic foundations) +**Author:** (unknown) + +--- + +## Phase 1: Acquire + +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/0yF9TvMeAzM artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/0yF9TvMeAzM artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_probability_logic_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_probability_logic_20260621/state.toml b/conductor/tracks/video_analysis_probability_logic_20260621/state.toml new file mode 100644 index 00000000..858b8f08 --- /dev/null +++ b/conductor/tracks/video_analysis_probability_logic_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_probability_logic_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_probability_logic_20260621" +name = "Probability Theory is an Extension of Logic" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" +video_analysis_cs229_building_llms_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/metadata.json b/conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/metadata.json new file mode 100644 index 00000000..ad6a2faa --- /dev/null +++ b/conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/metadata.json @@ -0,0 +1,64 @@ +{ + "track_id": "video_analysis_score_dynamics_giorgini_20260621", + "name": "Learning Dynamics from Statistics: a score-based approach", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_campaign_20260621", + "video_analysis_cs229_building_llms_20260621" + ], + "blocks": [], + "priority": "A", + "type": "per-child research track (Pass 1 of 3)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "cluster": "A", + "youtube_id": "P75iVMmbqQk", + "youtube_url": "https://youtu.be/P75iVMmbqQk", + "author": "Ludovico Giorgini", + "scope": { + "new_files": [ + "artifacts/transcript.json", + "artifacts/ocr.md", + "artifacts/frames/*.jpg", + "artifacts/extraction_meta.json", + "artifacts/video.mp4 (gitignored)", + "artifacts/video.log", + "report.md (1000-10000 LOC target)", + "summary.md (200-400 words)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "phase_1": "1 task: acquire (transcript + download)", + "phase_2": "1 task: keyframes extraction", + "phase_3": "1 task: OCR", + "phase_4": "1 task: synthesis (delegate to Tier 3 worker)", + "phase_5": "1 task: verification", + "summary": "5 tasks per child. 12 children total = 60 tasks in campaign." + }, + "verification_criteria": [ + "All 7 deliverable artifacts present (transcript.json, video.log, frames/, extraction_meta.json, ocr.md, report.md, summary.md)", + "report.md is 1000-10000 LOC markdown", + "summary.md is 200-400 words", + "All 8 report sections populated (TL;DR, Key Concepts, Frame Analysis, Transcript Highlights, Math/Theoretical Content, Connections, Open Questions, References)", + "Idempotency check passes", + "Per-task commits with git notes" + ], + "risk_register": [ + { + "id": "R5-score_dynamics_giorgini", + "title": "yt-dlp access failure (oEmbed returned 401 for E-cluster videos)", + "likelihood": "low", + "scope_impact": "Phase 1 Acquire blocked if yt-dlp also fails", + "mitigation": "Phase 1 Step 0 verifies yt-dlp access before downloading. Fall back to manual transcript sourcing if yt-dlp fails." + } + ], + "user_directives": [ + "1000-10000 LOC markdown per video report (per user 2026-06-21)", + "Lossless preservation: transcripts (JSON), frames (raw images), OCR (plain text) must be preserved in machine-readable form", + "Cross-references: forward + backward to other children in the campaign" + ] +} diff --git a/conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/plan.md b/conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/plan.md new file mode 100644 index 00000000..6babc8e8 --- /dev/null +++ b/conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/plan.md @@ -0,0 +1,60 @@ +# Plan: video_analysis_score_dynamics_giorgini_20260621 + +> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox syntax for tracking. + +**Goal:** Execute the 5-phase pipeline (Acquire → Keyframes → OCR → Synthesis → Verification) for *Learning Dynamics from Statistics: a score-based approach* and ship `report.md` (1000-10000 LOC) + `summary.md` (200-400 words). + +**Parent:** This is child #4 of the [video_analysis_campaign_20260621](../../video_analysis_campaign_20260621/) umbrella. + +**Source:** https://youtu.be/P75iVMmbqQk (YouTube ID `P75iVMmbqQk`) +**Cluster:** A (Math & information-theoretic foundations) +**Author:** Ludovico Giorgini + +--- + +## Phase 1: Acquire + +- [ ] **Step 1: Run extract_transcript.py** + - `uv run python scripts/video_analysis/extract_transcript.py https://youtu.be/P75iVMmbqQk artifacts/transcript.json` + - Commit `artifacts/transcript.json` atomically. +- [ ] **Step 2: Run download_video.py** + - `uv run python scripts/video_analysis/download_video.py https://youtu.be/P75iVMmbqQk artifacts/video.mp4` + - Commit `artifacts/video.mp4` (gitignored) + `artifacts/video.log` atomically. + +## Phase 2: Keyframes + +- [ ] **Step 1: Run extract_keyframes.py** + - `uv run python scripts/video_analysis/extract_keyframes.py artifacts/video.mp4 artifacts/frames --threshold 0.4` + - Commit `artifacts/frames/*.jpg` + `artifacts/extraction_meta.json` atomically. +- [ ] **Step 2: Manual review** — flag any frames that look wrong. + +## Phase 3: OCR + +- [ ] **Step 1: Run ocr_frames.py** + - `uv run python scripts/video_analysis/ocr_frames.py artifacts/frames artifacts/ocr.md --backend winsdk` + - Commit `artifacts/ocr.md` atomically. +- [ ] **Step 2: Spot-check OCR quality.** + +## Phase 4: Synthesis (DELEGATE TO TIER 3 WORKER) + +- [ ] **Step 1: Delegate report writing** + - Inputs: `artifacts/transcript.json` + `artifacts/ocr.md` + `artifacts/frames/*.jpg` + - Output: `report.md` (1000-10000 LOC) + `summary.md` (200-400 words) + - 8-section structure per umbrella spec §FR6 + - Cross-references to other children (forward + backward) +- [ ] **Step 2: Human review + iterate** + +## Phase 5: Verification + +- [ ] **Step 1: Idempotency check** — re-run scripts, confirm outputs match modulo timestamps +- [ ] **Step 2: Audit checklist** — every section of `report.md` populated, no "TBD" +- [ ] **Step 3: Write end-of-track report** at `docs/reports/TRACK_COMPLETION_video_analysis_score_dynamics_giorgini_20260621.md` +- [ ] **Step 4: Update state.toml** to `status = "completed"` + +## Self-review + +- [ ] `report.md` is 1000-10000 LOC markdown +- [ ] `summary.md` is 200-400 words +- [ ] All 7 deliverable artifacts present +- [ ] All 8 report sections populated +- [ ] Per-task commits with git notes diff --git a/conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/state.toml b/conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/state.toml new file mode 100644 index 00000000..b933eb6a --- /dev/null +++ b/conductor/tracks/video_analysis_score_dynamics_giorgini_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_score_dynamics_giorgini_20260621 +# Updated by Tier 2 Tech Lead (during execution) + +[meta] +track_id = "video_analysis_score_dynamics_giorgini_20260621" +name = "Learning Dynamics from Statistics: a score-based approach" +status = "active" +current_phase = 1 # Phase 1 = Acquire (first execution phase) +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_campaign_20260621 = "shipped" +video_analysis_cs229_building_llms_20260621 = "shipped" + +[blocks] +# Depends-on: umbrella + cluster-blockers + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Acquire (transcript + download)" } +phase_2 = { status = "pending", checkpointsha = "", name = "Keyframes extraction" } +phase_3 = { status = "pending", checkpointsha = "", name = "OCR" } +phase_4 = { status = "pending", checkpointsha = "", name = "Synthesis (Tier 3 worker)" } +phase_5 = { status = "pending", checkpointsha = "", name = "Verification" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Run extract_transcript.py + download_video.py. Commit artifacts atomically." } +t2_1 = { status = "pending", commit_sha = "", description = "Run extract_keyframes.py with threshold 0.4. Manual review of frames." } +t3_1 = { status = "pending", commit_sha = "", description = "Run ocr_frames.py. Spot-check OCR." } +t4_1 = { status = "pending", commit_sha = "", description = "Delegate report.md (1000-10000 LOC) + summary.md (200-400 words) to Tier 3 worker." } +t5_1 = { status = "pending", commit_sha = "", description = "Idempotency check + audit + end-of-track report." } + +[verification] +all_artifacts_present = false +report_loc_target_met = false +summary_word_count_met = false +end_of_track_report_committed = false diff --git a/conductor/tracks/video_analysis_synthesis_20260621/metadata.json b/conductor/tracks/video_analysis_synthesis_20260621/metadata.json new file mode 100644 index 00000000..657aeebc --- /dev/null +++ b/conductor/tracks/video_analysis_synthesis_20260621/metadata.json @@ -0,0 +1,46 @@ +{ + "track_id": "video_analysis_synthesis_20260621", + "name": "Video Analysis Campaign Synthesis (cross-cutting)", + "created": "2026-06-21", + "status": "spec_approved", + "blocked_by": [ + "video_analysis_cs229_building_llms_20260621", + "video_analysis_probability_logic_20260621", + "video_analysis_entropy_epiplexity_20260621", + "video_analysis_score_dynamics_giorgini_20260621", + "video_analysis_platonic_intelligence_kumar_20260621", + "video_analysis_free_lunches_levin_20260621", + "video_analysis_generic_systems_fields_20260621", + "video_analysis_brain_counterintuitive_20260621", + "video_analysis_neural_dynamics_miller_20260621", + "video_analysis_multiscale_hoffman_20260621", + "video_analysis_cs336_architectures_20260621", + "video_analysis_creikey_dl_cv_20260621" + ], + "blocks": [], + "priority": "A", + "type": "synthesis (cross-cutting report consuming all 12 children)", + "parent": "video_analysis_campaign_20260621", + "domain": "meta-tooling (research artifacts; no manual_slop src/ changes)", + "scope": { + "new_files": [ + "per_video_summary.md (one paragraph 150-250 words per video)", + "report.md (6-section cross-cutting synthesis)" + ], + "modified_files": [], + "deleted_files": [] + }, + "estimated_effort": { + "method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.", + "summary": "1 task: delegate synthesis to Tier 3 worker. Consumes all 12 children's report.md + summary.md." + }, + "verification_criteria": [ + "per_video_summary.md has 12 paragraphs (one per child)", + "report.md has 6 sections: Theme Matrix, Cross-Video Concept Map, 5-10 Takeaways, Math Prereq Graph, Open Research Questions, Next-Watch List", + "All 12 child tracks shipped (each with their report.md + summary.md)" + ], + "user_directives": [ + "1000-5000 LOC synthesis report (less than per-video because heavy lifting is in children)", + "Lossless preservation directive applies here too \u2014 DO NOT over-summarize; Pass 2 will compress" + ] +} diff --git a/conductor/tracks/video_analysis_synthesis_20260621/state.toml b/conductor/tracks/video_analysis_synthesis_20260621/state.toml new file mode 100644 index 00000000..c4c13621 --- /dev/null +++ b/conductor/tracks/video_analysis_synthesis_20260621/state.toml @@ -0,0 +1,36 @@ +# Track state for video_analysis_synthesis_20260621 + +[meta] +track_id = "video_analysis_synthesis_20260621" +name = "Video Analysis Campaign Synthesis" +status = "active" +current_phase = 1 +last_updated = "2026-06-21" + +[blocked_by] +video_analysis_cs229_building_llms_20260621 = "shipped" +video_analysis_probability_logic_20260621 = "shipped" +video_analysis_entropy_epiplexity_20260621 = "shipped" +video_analysis_score_dynamics_giorgini_20260621 = "shipped" +video_analysis_platonic_intelligence_kumar_20260621 = "shipped" +video_analysis_free_lunches_levin_20260621 = "shipped" +video_analysis_generic_systems_fields_20260621 = "shipped" +video_analysis_brain_counterintuitive_20260621 = "shipped" +video_analysis_neural_dynamics_miller_20260621 = "shipped" +video_analysis_multiscale_hoffman_20260621 = "shipped" +video_analysis_cs336_architectures_20260621 = "shipped" +video_analysis_creikey_dl_cv_20260621 = "shipped" + +[blocks] + +[phases] +phase_1 = { status = "pending", checkpointsha = "", name = "Verify all 12 children shipped" } +phase_2 = { status = "pending", checkpointsha = "", name = "Delegate synthesis to Tier 3 worker" } +phase_3 = { status = "pending", checkpointsha = "", name = "Human review + iterate" } +phase_4 = { status = "pending", checkpointsha = "", name = "End-of-track report" } + +[tasks] +t1_1 = { status = "pending", commit_sha = "", description = "Verify all 12 children have report.md + summary.md" } +t2_1 = { status = "pending", commit_sha = "", description = "Delegate synthesis (per_video_summary.md + report.md) to Tier 3 worker" } +t3_1 = { status = "pending", commit_sha = "", description = "Human review + iterate" } +t4_1 = { status = "pending", commit_sha = "", description = "Write end-of-track report" }