Week 17 — paper 2 complete experiments

This week delivers the three concrete artifacts below and the supporting learning/branding/opportunity pack. The scientific or commercial outcome follows the preserved source brief, while the acceptance checks make its evidence testable. The career objective is to turn this work into something a scientist, hiring manager or buyer can inspect.

• Scientific/build priority: Run mechanistic/pure ML/hybrid by 5/10/20/50 training batches by five seeds with separate training, calibration and test groups.
• Public/profile priority: Draft learning-curve post using the observed pattern; do not reuse the master's assumed hybrid-wins headline.
• Career/relationship/commercial priority: Share the experiment summary with the prospective endorser/reviewer; continue weekly protein-paper notes for partner selection.

Read v6 · Week 17 · Paper 2 experiments, complete before Monday. It carries this week's v5 brief unchanged and adds the Welcome analogy, Learn it (▶ core and ＋ deeper sources), Run it (repos with a 20-40 minute exercise), the NotebookLM kit and the mentor check below. Standing v6 rules: resource rules, NotebookLM protocol, chapter anatomy. v6 adds depth only; it does not change a goal, gate, output or the 600-minute cap, so this specification still governs execution.

Act IV · Threads: B, M, BL, EL (literacy) · Next gate: 20

Where this week sits. - ← From: week 12 harness and hybrid v0, week 16 conformal intervals, week 4 batch-wise CV, week 3 hours-to-detection. - → Feeds: week 18 (Paper 2 draft), week 20 (arXiv), weeks 21-22 (the Meltome baseline you start today becomes Paper 3's baseline table). - ⟳ Returns in: Paper 2 figures; JOSS (wk 36) as the showcase usage of batchlens.

Goals. - 🎯 This week: full learning-curve experiment with seeds and coverage; transfer to faulty batches; paper-2 repo with make figs; batchlens v0.3 + Z4; ESM-2 + ridge baseline number on Meltome. - 🏁 Next milestone: Gate 20 (Paper 2 on arXiv). - 🌟 Final: the result that answers "when does biology help the model?".

Mentor check. "I can show the learning curve and say, with an interval, below how many batches the hybrid model is the better bet."

• Week 12: inspect its actual evidence and review; source/code artifacts must exist before the dependent task begins.
• Week 16: inspect its actual evidence and review; source/code artifacts must exist before the dependent task begins.
• Read commitment, evidence, review and the current root TODAY/PROGRESS/QUESTIONS files.
• Read this week's chapter, v6 · Week 17 · Paper 2 experiments, complete, then the standing sections: Part 0 · how to use the document, Part 3 · the scientific thesis, Part 4 · curriculum, Part 8 · the prompt pack and Part 9 · branding and endorsement. The same sections exist in the v5 master, which remains the governing sequence; v6 reproduces them and adds depth. Retained commercial/instrument details come from v4.
• Inspect the actual canonical repository state, available data, existing figures and required human/external inputs. Never assume a previous week succeeded from its folder name.
• Verify current resource links, versions, dataset rights and any live company/venue information before relying on them. Use source catalog; explicitly record inaccessible resources.

The model must turn these into exact physical actions using the observed files and available inputs. Each 90-minute block includes start/stop rituals. All calls, posts, debugging, reading and exercises consume this same capacity.

The source lists more material than necessarily fits. Select exact excerpts for the learning objective and park the remainder; no full-course completion requirement.

Biology/domain unit

Source unit: B17 · Enzyme stability and engineering

Material: FLIP benchmark paper (Dallago et al. 2021, "FLIP: Benchmark tasks in fitness landscape inference for proteins"); Meltome atlas paper (Jarzab et al. 2020)

Produce: Meltome split loaded; baseline on 1,000 sequences

Understanding check: You know what "thermostability" is measured as

During preparation, write one worked example connected to the week's actual task, one exercise with a separate answer key and five questions. Peter supplies answers; score explanation quality and flag misconceptions in QUESTIONS. Numeric/scientific conclusions require actual data or explicitly synthetic teaching values.

AI/scientific-method unit

Source unit: M17 · Deep learning for proteins

Material: MIT 6.874 protein lecture; Hugging Face ESM model card (facebook/esm2_t33_650M_UR50D)

Produce: Embedding + ridge head on Meltome

Understanding check: Baseline number exists

Use the prompt pack: P1 explanation ladder, P2 concept-to-project bridge and P3 quiz. Coding practice belongs within the allocated study/build block. Where the source asks for a favorable scientific result, substitute an honest measured comparison as explained below.

Founder/scientist paper

Select one verified founder/scientific-lead paper relevant to this week's domain. Use P11; save the question, method, numerical result with context, data workflow, three author questions and one connection sentence in founder-paper.md. Keep abstract-only access limitations explicit. On source weeks with no study, prioritize the commercial/submission task and log any skipped digest.

These filenames are outputs to prepare during this week's execution; this scaffold does not claim they already exist. Drafts and measured results have different states. Technical code/data stay in the canonical project repository and are referenced from these coordinating files.

During preparation, future measured tables get column definitions, input requirements and run instructions with PENDING status. During execution, replace pending values only with measured outputs. Do not create realistic-looking fake evidence.

Branding: Draft learning-curve post using the observed pattern; do not reuse the master's assumed hybrid-wins headline.

Opportunity action: Share the experiment summary with the prospective endorser/reviewer; continue weekly protein-paper notes for partner selection.

Use career asset contracts. Publish at most the agreed cadence; one figure and one supported number or admitted failure can support multiple drafts. In long-form weeks, prepare a 1,500–2,500-word article from existing evidence within the build/buffer allocation. In release/demo weeks, prepare a 60-second script: problem, input, command/action, result, limitation and proof link.

Verify individuals, jobs and affiliations at execution time. The GridX list and v4 company map are research seeds, not current facts. Do not reveal named company weaknesses or employer/client confidential information. Keep drafted/sent/replied/booked/held statuses separate. The planning request alone does not authorize external messages or publication; honor explicit authorization in the execution session.

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.

Apply the root scientific evidence contract: provenance; meaningful independent splits; no future-data leakage; baseline comparison; actual denominators/uncertainty; failed cases; human review where required. State whether data are simulated, public experimental, synthetic or partner-provided.

Keep source gates intact, and log scope/time conflicts in review. Missing people, money, access or results must not be replaced with invented evidence. Reduce optional polish first. A specific essential external dependency stays pending while independent preparation continues.

This is an enabling week. Its deliverables feed the next scheduled gate: 20. Complete the acceptance checklist below; do not promote reputation from a draft.

• Monday artifact satisfies: All 60 planned model-size-seed combinations have results or explicit failure reasons.
• Wednesday artifact satisfies: Coverage on shifted faults is measured, not guaranteed; test information does not tune models.
• Friday artifact satisfies: A bounded reproduction command and full-run command are documented with resource estimates.
• Study pack is prepared; Peter's actual learning/quiz result is recorded separately.
• Branding and opportunity drafts use supported claims and the correct external-action state.
• Reproduction or document checks are recorded with file/version references.
• This week's special gate, if any, has real evidence or remains explicitly pending.
• Review, root progress/log and the next physical action are updated.

Source-preserving minimum: the learning curves with seeds.

Operational first step if stalled: open paper-2-results.csv, write the required inputs and produce the smallest checkable example in ten minutes. If a more urgent missing gate dependency controls the week, use the source minimum above.

If the full week does not fit, use P14: retain one gate-critical deliverable and one directly supporting study exercise; record what is skipped versus moved. Do not mark the original full gate passed merely because the minimum was completed. After a missed week, reforecast from actual evidence and avoid a second unexamined lost week.

In review, state exactly what exists, what was verified, what Peter can now explain, which external events remain pending, where the canonical code/data live, and the next file/function or draft paragraph to touch. Link each fact to evidence. Carry scientific assumptions, split definitions and rights constraints forward explicitly.

Prepare Week 17 of this LABLOOP execution plan.
Read execution-plan/specs.md, execution-plan/DECISIONS.md,
execution-plan/GATES.md and
execution-plan/weeks/week-17-paper-2-complete-experiments/specs.md, commitment.md, evidence.md and review.md.
Read prior prerequisite reviews and inspect actual repository/data state.
Use v5 as the governing sequence, the v6 Week 17 chapter
(LABLOOP-Master-Plan-v6.md) as the deeper walkthrough, and v4 only for
retained details.
Produce the full local preparation pack and the exact week-specific files named
in the artifact table. Give me a bounded lesson with exercises/answer key,
daily physical actions, technical runbook or draft, branding drafts and
career/commercial actions. Keep the total to 600 minutes.
Separate prepared artifacts from measured results and my learning completion.
Verify sources and do not invent metrics, citations, papers, people or outcomes.
Do not execute external communications, publication or spending unless the
current session already authorizes the specific action.
Finish by updating evidence/review and TODAY with the next physical action.

v6 reproduces this brief unchanged inside v6 · Week 17 · Paper 2 experiments, complete. The following is source planning text, not a claim of completion. Apply the explicit evidence corrections in this specification and DECISIONS.md.

Week 17 · Paper 2 experiments, complete

• Goal: every number in Paper 2 exists.
• Tue (B17): FLIP + Meltome papers; Meltome split loaded.
• Thu (M17): ESM-2 embeddings + ridge head on Meltome; baseline number.
• Build: [ ] Mon: full learning-curve experiment (mechanistic, pure ML, hybrid × 5/10/20/50 batches × 5 seeds), conformal intervals, coverage. [ ] Wed: transfer to faulty batches; hours-to-detection with each model. [ ] Fri: paper-2 repo with make figs; batchlens v0.3 + Z4.
• Sun: L-Sun: "Hybrid wins below 20 batches, loses above 50: the full curve". L-Wed.
• Only one thing: the learning curves with seeds.