conductor(tracks): scaffold plan.md + metadata.json + state.toml for 12 child + 1 synthesis tracks

This commit is contained in:
ed
2026-06-21 15:41:38 -04:00
parent 548c4fef63
commit c1a15c45c5
38 changed files with 2002 additions and 0 deletions
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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
@@ -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
@@ -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"
]
}
@@ -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" }