execution-plan/weeks/week-17-paper-2-complete-experiments/commitment.md · UPDATED 2026-09-16

Week 17 commitment

3 parts420 words 6 checkboxes — tick them, they save to the file

State: UNCONFIRMED. Owner: Peter Ciancaglini. Specification

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.

↑ Back to top

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	[ ]

↑ Back to top

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.

↑ Back to top