# Week 14 commitment

State: UNCONFIRMED. Owner: Peter Ciancaglini. [Specification](./specs.md)

Start date: not set. End date: not set. Available hours: confirm (planned ceiling 10).
Primary outcome: paper 1 full draft.
Minimum that keeps the next gate alive: Methods section.

## Deliverables to commit

- [ ] `paper-1-introduction.md`: Each contribution corresponds to an implemented method or measured result.
- [ ] `paper-1-methods.md`: A reader can identify data versions, splits, prompts, annotators and scoring rules.
- [ ] `paper-1-results.md`: Effect sizes and denominators accompany comparisons; judge output is not ground truth.
- [ ] Bounded learning exercise and personal teach-back.
- [ ] Evidence-backed branding and opportunity pack.
- [ ] Sunday review and next physical action.

## Proposed calendar

| Day | Minutes | Physical action / outcome | Actual slot | Done |
|---|---:|---|---|---|
| Mon | 90 | Write introduction and related work from verified sources, stating novelty or extension accurately. | Not set | [ ] |
| Tue | 90 | Multiple-testing correction applied to a FermLit comparison | Not set | [ ] |
| Wed | 90 | Write reproducible corpus, schema, annotation, extraction and evaluation methods with availability statement. Last ten minutes: optional note. | Not set | [ ] |
| Thu | 90 | Calibrated judge for FermLit fields Include relevant founder-paper work within this block. | Not set | [ ] |
| Fri | 90 | Write results and limitations, apply the planned multiple-testing correction and evaluate any fuzzy-field judge against humans. | Not set | [ ] |
| Sat | 90 | Resolve critical spillover; long-form draft if due; sandbox only if done. | Not set | [ ] |
| Sun | 60 | Build log, evidence, gap review, next actions. | Not set | [ ] |

## Dependency and capacity check

- Missing essential inputs: not yet inspected.
- Human/external dependency, owner and expected date: not yet inspected.
- Week-specific constraint: Do not use an LLM judge to erase strain-level mistakes or support a reporting-completeness claim without manual validation. Unsupported hypotheses stay in limitations or future work.
- Existing session authorization for external actions or spending: not assessed; local planning only at scaffold creation.
- Scope to cut first: optional polish/additional examples; preserve scientific validity.
- If the forecast exceeds available time: record a concrete reduced scope or revised delivery proposal before committing.

Peter's commitment / adjustments: pending.
Reviewing model and date: pending.