conductor(deob_umbrella): Initialize Pass 2 de-obfuscation campaign umbrella

Pass 2 of 3 multi-pass research campaign. 5 folders total (1 umbrella + 1 warmup + 3 phase children).
- Umbrella spec.md (~400 lines): full design, philosophy, 3-layer deliverable, verification
- Multi-pass framing: Pass 1 = extraction (done), Pass 2 = de-obfuscation (this), Pass 3 = projection (future user-led)
- De-obfuscation philosophy: constructive type theory + Wildberger finitism + boundedness for knowledge + cycles/iteration explicit + etymology-aware
- 4 verification criteria: lossless, bounded, constructively typed, etymology-cited
- Multi-layer deliverable per video: translation (side-by-side) + replacement (re-encoded) + decoder (per-term etymology)
- Phase 0: USER action item (gather 3-10 samples of past de-obfuscation notes)
This commit is contained in:
ed
2026-06-23 00:06:51 -04:00
parent 2b9f7376e0
commit 59ba8ff2ba
5 changed files with 741 additions and 0 deletions
@@ -0,0 +1,188 @@
{
"track_id": "video_analysis_deob_20260621",
"name": "Video Analysis De-obfuscation Campaign (Pass 2 of 3)",
"created": "2026-06-21",
"status": "spec_approved",
"blocked_by": [],
"blocks": [
"video_analysis_deob_warmup_20260621"
],
"priority": "A",
"rationale": "User-blocking Pass 2 of the 3-pass research campaign. De-obfuscates the 12 Pass 1 deep-dive reports via the user's constructive type-theoretic re-encoding DSL. Lossless preservation directive (carries from Pass 1). 5 folders: 1 warmup (precursor) + 1 umbrella + 3 phase children (lexicon/pilot/apply). Multi-layer deliverable per video: translation (side-by-side) + replacement (re-encoded) + decoder (per-term etymology).",
"type": "multi-track research campaign (1 umbrella + 1 warmup + 3 phase children = 5 folders)",
"domain": "meta-tooling (research deliverable + LLM operational spec; no manual_slop src/ changes)",
"scope": {
"new_folders": [
"conductor/tracks/video_analysis_deob_20260621/",
"conductor/tracks/video_analysis_deob_warmup_20260621/",
"conductor/tracks/video_analysis_deob_lexicon_20260621/",
"conductor/tracks/video_analysis_deob_pilot_20260621/",
"conductor/tracks/video_analysis_deob_apply_20260621/"
],
"new_files_umbrella": [
"spec.md",
"plan.md",
"metadata.json",
"state.toml",
"README.md"
],
"new_files_warmup": [
"spec.md",
"plan.md",
"metadata.json",
"state.toml",
"samples/<user-provided-files> (gitignored)",
"report.md (the design philosophy + lexicon + dedup maps)",
"prompt_template.md (the LLM-direct operational spec)"
],
"new_files_per_child": [
"spec.md (lightweight)"
],
"new_files_pilot": [
"artifacts/cs229_building_llms/translation.md",
"artifacts/cs229_building_llms/deobfuscated.md",
"artifacts/cs229_building_llms/decoder.md",
"artifacts/entropy_epiplexity/translation.md",
"artifacts/entropy_epiplexity/deobfuscated.md",
"artifacts/entropy_epiplexity/decoder.md",
"pilot_report.md"
],
"new_files_apply": [
"artifacts/<10 remaining slugs>/translation.md (×10)",
"artifacts/<10 remaining slugs>/deobfuscated.md (×10)",
"artifacts/<10 remaining slugs>/decoder.md (×10)",
"artifacts/synthesis/translation.md",
"artifacts/synthesis/deobfuscated.md",
"artifacts/synthesis/decoder.md",
"apply_report.md"
],
"modified_files": [
"conductor/tracks/video_analysis_campaign_20260621/spec.md (§11.1 updated to reference this campaign)",
"conductor/tracks.md (add row for this campaign)",
"conductor/chronology.md (5 new rows after campaign ships)"
],
"deleted_files": [],
"gitignored_patterns": [
"conductor/tracks/video_analysis_deob_warmup_20260621/samples/** (user's past notes are local-only)"
]
},
"estimated_effort": {
"method": "scope (per conductor/workflow.md Tier 1 Track Initialization Rules). NO day estimates.",
"phase_0": "1 USER action item (gather samples)",
"phase_1": "5 tasks: warmup initialization, sample survey, report.md (~1000-3000 LOC), prompt_template.md (~200-500 LOC), user approval",
"phase_2": "4 tasks: lexicon child init, refine warmup's draft, produce lexicon.md + terms_catalog.md + dedup_map.md, user approval",
"phase_3": "5 tasks: pilot child init, apply to 2 videos, write pilot_report.md, user approval",
"phase_4": "4 tasks: apply child init, apply to 10+1 outputs, write apply_report.md",
"phase_5": "6 tasks: closeout (README update, state.toml, end-of-track report, archive move, chronology, tracks.md)",
"summary": "5 track folders, 1 user action item, 13 deliverable files (2 pilot + 11 apply, each 3-layer), 4 reports (warmup report, warmup template, pilot, apply), 5 closeout tasks. No day estimates per project convention."
},
"verification_criteria": [
"Warmup shipped with report.md + prompt_template.md (and the user has approved the lexicon)",
"Phase 1 (lexicon) shipped with lexicon.md + terms_catalog.md + dedup_map.md",
"Phase 2 (pilot) shipped with 2 deobfuscated deliverables (each 3-layer) + pilot_report.md",
"Phase 3 (apply) shipped with 11 deobfuscated deliverables (each 3-layer) + apply_report.md",
"Each deliverable passes the 4 verification criteria: lossless, bounded, constructively typed, etymology-cited",
"Umbrella state.toml updated to status = 'completed'",
"End-of-track report at docs/reports/TRACK_COMPLETION_video_analysis_deob_20260621.md",
"All 5 folders move to conductor/archive/ per the project's archiving convention",
"conductor/chronology.md updated with 5 new rows",
"No new src/*.py files created (per AGENTS.md File Size and Naming Convention)",
"No new pyproject.toml dependencies"
],
"risk_register": [
{
"id": "R1",
"title": "User cannot provide samples in time",
"likelihood": "medium",
"scope_impact": "Warmup blocked",
"mitigation": "User can provide partial samples (1-2 examples); warmup can use them as a starter lexicon"
},
{
"id": "R2",
"title": "User's samples don't have enough de-obfuscation patterns",
"likelihood": "medium",
"scope_impact": "Warmup produces a thin lexicon",
"mitigation": "Phase 1 (lexicon) extends the warmup's draft with constructive type theory defaults"
},
{
"id": "R3",
"title": "Lexicon can't capture a concept in bounded form",
"likelihood": "medium",
"scope_impact": "Some concepts remain 'indefinite — see original'",
"mitigation": "Document the gap; don't force a translation. The 4 verification criteria allow 'etymology-cited' but not 'forced'"
},
{
"id": "R4",
"title": "Pilot reveals the lexicon is overfit to the user's style",
"likelihood": "low",
"scope_impact": "Refinement needed in Phase 2",
"mitigation": "pilot_report.md captures gaps; Phase 3 uses the refined lexicon"
},
{
"id": "R5",
"title": "The 3-layer deliverable format is too verbose for some videos",
"likelihood": "low",
"scope_impact": "Adjust per video",
"mitigation": "Format is a template, not a rigid structure; some sections may be smaller"
},
{
"id": "R6",
"title": "Tier 2 attempts to invent the lexicon without the user's samples",
"likelihood": "low (if user samples present)",
"scope_impact": "Lexicon is invented, not evidence-based",
"mitigation": "Warmup spec is explicit: 'consume user samples FIRST; lexicon is evidence-based'"
},
{
"id": "R7",
"title": "Pass 3 needs the de-obfuscated outputs but Pass 2 isn't done",
"likelihood": "high (timeline)",
"scope_impact": "Pass 3 blocked",
"mitigation": "This campaign's 'lossless preservation' ensures Pass 3 has all the input it needs once Pass 2 ships"
},
{
"id": "R8",
"title": "The user changes their mind about the philosophy mid-campaign",
"likelihood": "low",
"scope_impact": "Pilot reveals the shift; lexicon is updated",
"mitigation": "pilot_report.md is the checkpoint for user review"
}
],
"architecture_reference": {
"primary_documents": [
"conductor/workflow.md (track convention, per-task commits, git notes, verification protocol)",
"conductor/code_styleguides/python.md (1-space indent, type hints, no comments - IF code is written)",
"conductor/code_styleguides/error_handling.md (Result[T] pattern - IF code is written)",
"AGENTS.md (artifact isolation, file naming, no new src/<thing>.py)"
],
"related_tracks": [
"conductor/tracks/intent_dsl_survey_20260612/ (sibling DSL: tool-verb DSL for AI agents, shares philosophy)",
"conductor/tracks/video_analysis_campaign_20260621/ (Pass 1 - the input to de-obfuscate)",
"conductor/tracks/nagent_review_20260608/ (research-track precedent)",
"conductor/tracks/fable_review_20260617/ (research-track precedent)"
],
"styleguides_applied": [
"agent_memory_dimensions.md (Pass 2 produces a 'knowledge' memory artifact)",
"knowledge_artifacts.md (knowledge harvest pattern; relevant to the de-obfuscation's durable nature)"
]
},
"deferred_to_followup_tracks": [
{
"title": "Pass 3: Projection to user's applied domain",
"description": "Apply Pass 2's de-obfuscated outputs to the user's preferred code style. Influences: handmade/data-oriented/GPGPU (Timothy Lottes, Onat Türkçüoğlu, Jebrim) + user's own caveats.",
"track_status": "not started - blocked by this campaign",
"blocker_action_item": "User must articulate 'own caveats' before Pass 3 starts (per Pass 1 spec §11.2)"
}
],
"regressions_and_pre_existing_failures": [],
"pre_existing_failures_remaining": [],
"user_directives": [
"Unorthodox knowledge curation philosophy (2026-06-21)",
"Constructive type theory + Wildberger-style finitism as foundation (2026-06-21)",
"Boundedness required for direct knowledge; cycles/iteration allowed but expressed explicitly (2026-06-21)",
"Multi-layer deliverable per video (translation + replacement + decoder) (2026-06-21)",
"Warmup is the precursor; lexicon is evidence-based from user's past samples (2026-06-21)",
"Report + prompt template as the warmup output (2026-06-21)",
"5 folders at conductor/tracks/ level, hybrid umbrella structure (2026-06-21)",
"No day estimates per conductor/workflow.md Tier 1 Track Initialization Rules"
]
}