# Video Analysis De-obfuscation Campaign (2026-06-21) — Pass 2 of 3

**Status:** Active (spec approved 2026-06-21)
**Owner:** Tier 1 Orchestrator (umbrella spec); Tier 2 Tech Lead (per-track execution)
**Type:** Multi-track research campaign (5 folders total)
**User-as-source:** The warmup is blocked on the user providing samples (Phase 0).

This is **Pass 2 of 3** in the research campaign to penetrate the AI field. See [spec.md](./spec.md) for the full design and the user's de-obfuscation philosophy (constructive type theory, bounded forms, cycles/iteration explicit, etymology-aware).

## Children

### Precursor (standalone, not a child of this umbrella)

| | Track | Status | Notes |
|---|-------|--------|-------|
| Warmup | [../video_analysis_deob_warmup_20260621/](../video_analysis_deob_warmup_20260621/) | [ ] | Produces `report.md` + `prompt_template.md` from the user's past samples. User must provide samples first. **Blocks the 3 children below.** |

### Phase children (3)

| # | Track | Status | Input | Output |
|---|-------|--------|-------|--------|
| 1 | [../video_analysis_deob_lexicon_20260621/](../video_analysis_deob_lexicon_20260621/) | [ ] | Warmup's `report.md` + `prompt_template.md` | `lexicon.md` + `terms_catalog.md` + `dedup_map.md` |
| 2 | [../video_analysis_deob_pilot_20260621/](../video_analysis_deob_pilot_20260621/) | [ ] | Lexicon + 2 Pass 1 reports (`cs229_building_llms`, `entropy_epiplexity`) | 2× 3-layer deliverables + `pilot_report.md` |
| 3 | [../video_analysis_deob_apply_20260621/](../video_analysis_deob_apply_20260621/) | [ ] | Refined lexicon + 10 Pass 1 reports + 1 synthesis | 11× 3-layer deliverables + `apply_report.md` |

## Dependency graph

```
WARMUP (precursor) ──► PHASE 1 (lexicon) ──► PHASE 2 (pilot) ──► PHASE 3 (apply)
        │                    │                    │                    │
        └────────────────────┴────────────────────┴────────────────────┘
                                  blocked_by chain
```

## Status legend

- `[ ]` not started
- `[~]` in progress
- `[x]` shipped
- `[!]` blocked

## Cluster / phase legend

- **Warmup** — research-style track; produces the initial lexicon + LLM prompt template
- **Phase 1 (lexicon)** — refines the warmup's draft into a codified operational spec
- **Phase 2 (pilot)** — applies the lexicon to 2 videos (1 foundational + 1 math-heavy) for validation
- **Phase 3 (apply)** — applies the refined lexicon to the remaining 10 + synthesis

## Multi-layer deliverable (per video)

For each de-obfuscated video, the output is 3 files in `artifacts/<slug>/`:
1. **`translation.md`** — side-by-side table: original expression ↔ re-encoded form
2. **`deobfuscated.md`** — the re-encoded report (replacement; same 8-section structure as Pass 1)
3. **`decoder.md`** — per-term decoder: form anchor, etymology, definition history, link to original section

## Verification (4 criteria per deliverable)

- **Lossless** — every Pass 1 concept is represented
- **Bounded** — no `∞_val` or `∞_card`; all values are finite forms
- **Constructively typed** — every expression has a type
- **Etymology-cited** — every new term has a 1-line origin + 1-line definition history in the decoder

## See also

- [spec.md](./spec.md) — full design (15 sections, ~400 lines)
- [plan.md](./plan.md) — campaign-level plan
- [metadata.json](./metadata.json) — scope, risk register, verification criteria
- [state.toml](./state.toml) — current phase + task tracking
- `../video_analysis_campaign_20260621/spec.md` §0, §11 — multi-pass framing (Pass 1 → Pass 2 handoff)
- `../intent_dsl_survey_20260612/report_v1.2.md` — sibling DSL (tool-verb DSL for AI agents; shares philosophy but is for tool verbs, not math re-encoding)