# Week 17 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 2 complete experiments.
Minimum that keeps the next gate alive: the learning curves with seeds.

## Deliverables to commit

- [ ] `paper-2-results.csv`: All 60 planned model-size-seed combinations have results or explicit failure reasons.
- [ ] `paper-2-transfer.csv`: Coverage on shifted faults is measured, not guaranteed; test information does not tune models.
- [ ] `paper-2-reproducibility.md`: A bounded reproduction command and full-run command are documented with resource estimates.
- [ ] 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 | Run mechanistic/pure ML/hybrid by 5/10/20/50 training batches by five seeds with separate training, calibration and test groups. | Not set | [ ] |
| Tue | 90 | Meltome split loaded; baseline on 1,000 sequences | Not set | [ ] |
| Wed | 90 | Evaluate faulty-batch transfer and monitoring timing; report prediction errors, interval coverage/width, false alarms and misses. Last ten minutes: optional note. | Not set | [ ] |
| Thu | 90 | Embedding + ridge head on Meltome Include relevant founder-paper work within this block. | Not set | [ ] |
| Fri | 90 | Freeze configs, splits and figures; package batchlens v0.3 and Z4 materials in the canonical Paper 2 repository. | 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: Meltome targets and engineered-enzyme thermostability may differ. Keep early protein baselines separate from Paper 2 and avoid selecting results based on hoped-for wins.
- 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.