Measured extraction agent

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: Implement schema-constrained extraction with provenance and fake/API/local adapters; smoke-test five development papers and log model/prompt versions.
• Public/profile priority: Prepare per-field evaluation chart and one failure example with permissible source quotation.
• Career/relationship/commercial priority: Show a narrow evaluation question to a domain reviewer; prepare feedback requests without implying validation already happened.

Read v6 · Week 7 · The extraction agent, measured 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 II · Threads: B, M, FL · Next gate: 8

Where this week sits. - ← From: week 5 schema, week 6 gold set, your Vara telemetry habits. - → Feeds: week 8 (F1 table public), week 9 (you pick the cheapest backend that meets the F1 floor), week 14 (the calibrated judge for fuzzy fields), week 15 (M15 evaluation writing), week 34-35 (local vs cloud comparison for labdocs). - ⟳ Returns in: Paper 1 Table 2 (per-field precision/recall/F1) and in every Loop Audit prototype.

Goals. - 🎯 This week: agent extracts 5 papers with provenance; eval/score.py prints per-field P/R/F1 for 50 papers; one round of error analysis logged with before/after. - 🏁 Next milestone: Gate 8. - 🌟 Final: the method section reviewers of Paper 1 will test hardest.

Mentor check. "I can read my own F1 table aloud, say why the worst field fails, and explain why tuning on the gold set is dangerous."

• Week 06: 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 7 · The extraction agent, measured, 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.

Biology/domain unit

Source unit: B7 · Protein structure and enzyme kinetics

Material: MIT OCW 7.016 Introductory Biology (Fall 2018) lectures on protein structure and enzymes — ocw.mit.edu (search 7.016); Khan Academy "Enzyme kinetics"

Produce: Michaelis-Menten fitted in Python to a public dataset

Understanding check: You can fit Km and Vmax and say what they mean

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: M7 · Bayesian models

Material: Statistical Rethinking 2024 lectures 3-4

Produce: A simple Bayesian regression in PyMC or numpyro on titer data

Understanding check: You can read a credible interval

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.

Branding: Prepare per-field evaluation chart and one failure example with permissible source quotation.

Opportunity action: Show a narrow evaluation question to a domain reviewer; prepare feedback requests without implying validation already happened.

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.

The original gold set cannot be repeatedly tuned on and still serve as an untouched test set. Report prompt-development and final evaluation sets separately.

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: 8. Complete the acceptance checklist below; do not promote reputation from a draft.

• Monday artifact satisfies: Invalid JSON, absent values and unsupported evidence fail visibly.
• Wednesday artifact satisfies: Each field has counts and scoring rules; development scores are not called held-out performance.
• Friday artifact satisfies: Unchanged held-out data and a backend decision with quality/cost evidence are recorded.
• 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 F1 table, whatever it says.

Operational first step if stalled: open extraction-runbook.md, 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 07 of this LABLOOP execution plan.
Read execution-plan/specs.md, execution-plan/DECISIONS.md,
execution-plan/GATES.md and
execution-plan/weeks/week-07-measured-extraction-agent/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 07 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 7 · The extraction agent, measured. The following is source planning text, not a claim of completion. Apply the explicit evidence corrections in this specification and DECISIONS.md.

Week 7 · The extraction agent, measured

• Goal: first per-field precision and recall.
• Tue (B7): MIT 7.016 protein lectures; Michaelis-Menten fitted.
• Thu (M7): Statistical Rethinking L3-4.
• Build: Mon: extract/agent.py: one paper in, schema JSON out with provenance; Claude via API and local Qwen 7B as two backends; --fake backend for tests. Done when 5 papers extract. Wed: eval/score.py: per-field exact and fuzzy match against the gold set, precision/recall/F1, confusion by field. Done when the table prints for 50 papers. Fri: error analysis: the 5 worst fields, why; one round of prompt and schema fixes; re-score. Log both numbers.
• Sun: L-Sun: "An LLM read 50 papers; here is where it was wrong" with the per-field table. L-Wed.
• Only one thing: the F1 table, whatever it says.