# LABLOOP W07 — measured extraction agent: full learning notebook

Prepared 2026-09-23 for Peter Ciancaglini. This is a study and execution guide; it does not record that you completed the work. Keep your existing notes, commitments, progress and evidence. Write actual results in the existing evidence register, not into the illustrative examples below.

[Original weekly brief](./specs.md) · [Commitment](./commitment.md) · [Evidence](./evidence.md) · [Review](./review.md) · [Notebook index and export guide](../../NOTEBOOKS.md) · [NotebookLM upload text](./notebooklm.txt)

[Previous notebook](../week-06-human-gold-standard/learning-notebook.md) · [Next notebook](../week-08-technical-report-gate/learning-notebook.md)

## 1. The week in plain language: what, why and where it leads

Now the reading robot must produce structured answers and justify where they came from. Valid JSON only proves the shape is parseable. A number may still have the wrong unit, belong to another experiment or be absent from the source. You will measure extraction field by field so that a strong overall score cannot hide a dangerous weak field.

**Your systems, software and AI connection.** This is an AI service with contracts, adapters, observable failures and a test boundary. The scientific contribution is its measured behavior on a defined literature sample. Better prompts are useful only when their effect is measured without consuming the final test set.

**Dependency map from the existing programme.**

- ← **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.

**Gate and proof required by the current weekly specification.**

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.

The milestones are targets, not predictions of success. A prepared notebook, generated visual, course completion or draft paper is not a substitute for the required evidence. Your final profile should connect a clear scientific question to working software, trustworthy data, measured comparisons, documented limitations and your own contribution.

## 2. Before starting: locate inputs and repair only the needed foundations

- [Week 06](../week-06-human-gold-standard/specs.md): inspect its actual evidence and review; source/code artifacts must exist before the dependent task begins.

1. Open the existing commitment and previous review/evidence. Identify which required inputs are present, missing or stale. A folder name does not prove its project is complete.
2. Locate the canonical code/data repository and note its current version. The coordinating files named below live in this weekly folder; implementations and measured outputs belong in the canonical project, linked from evidence.md.
3. Read the plain-language explanation and worked example before selecting sources. Try the small calculation or reasoning exercise on paper. Mark any unfamiliar symbol or word.
4. Use the relevant refresher below inside your allocated study time. Say the idea aloud in your own words, work one example and connect it to a named output. Park material that does not unblock this week.
5. Write the next physical action in TODAY.md and start the allocated block. If a human, dataset or external event is missing, continue independent preparation and mark the dependent task pending.

You have professional experience and are rebuilding dormant foundations; unfamiliar notation is a repairable gap. For each equation, identify the question, read every symbol aloud, attach units, substitute small numbers and only then translate it to code.

## 3. Foundation refreshers you can use without another notebook

### From papers to trustworthy experimental records

A paper is a document; an experiment is a specific tested condition or comparison; a measurement is a value associated with that experiment. They require different identifiers. **Provenance** is the trail from a stored value to the document/version, paragraph, sentence or table cell that supports it. Preserve that trail even after normalization.

Missingness has several causes. “Not reported” means the source was inspected and did not provide the field under your rules. “Not extracted” means the pipeline failed or omitted it. “Inaccessible” means you could not inspect the required source. Collapsing them into a blank cell can create a false scientific conclusion about reporting quality. An LLM’s confident answer is not source evidence.

Annotation guidelines make interpretation rules explicit. Independent annotators apply the rules separately; agreement is measured before **adjudication**, the later process of resolving differences. A gold set is a checked reference with known limitations, not an infallible oracle. Corpus selection, annotation coverage and scoring choices all belong in Paper 1’s methods. Read a paper as question → experimental unit → method → observed result → limitation; record an abstract-only access limitation when full methods are unavailable.

### Independent evidence, baselines and leakage

An **observation** is a recorded value; an **independent experimental unit** is the entity whose variation supports your generalization claim. Many timestamps from one batch, fields from one paper, relatives in a protein family or wells from one biological sample are related. Split and analyze at the unit appropriate to the question.

**Training data** fit the model. **Development/validation data** guide choices. **Calibration data** set a threshold or interval under a defined procedure. **Test data** are reserved for the final specified evaluation. These roles may be implemented through carefully designed cross-validation, but their purposes must remain separate. **Leakage** occurs when unavailable information influences a prediction or evaluation—future samples, test-derived scaling, duplicated papers or close sequence relatives can all cause it. [The scikit-learn pitfalls guide](https://scikit-learn.org/stable/common_pitfalls.html) documents preprocessing and leakage traps.

A **baseline** is a simple, relevant reference method. Compare models on the same target, units, observation cutoff and independent groups. Record a split manifest and freeze preprocessing rules before testing. A fixed random seed makes a procedure repeatable; it does not make a bad split valid. When test errors guide a revision, label that test as reused/development and reserve new evidence for the next independent claim. A negative result is still a completed, useful experiment.

### Probability and evaluation without hidden arithmetic

A probability expresses uncertainty about an event under a model or data-generating process. A frequency needs a denominator: 8 successful cases out of 10 is 0.8, but ten related observations do not become ten independent experiments. Conditional probability means “among cases where this condition holds.” Do not swap the condition: the probability of an alarm given a fault is different from the probability of a fault given an alarm.

Bayesian updating combines a prior assumption with the likelihood of observations to obtain a posterior. In a teaching coin model, a uniform Beta(1,1) prior and three heads/one tail give Beta(4,2), whose mean is 4/6. The observations change the belief without eliminating uncertainty. Real data need a defensible likelihood and prior, not just this convenient formula.

For extraction, **precision**=correct extracted items/all extracted items; **recall**=correct extracted items/all reference items. **F1** balances the two: 2TP/(2TP+FP+FN). TP means true positive, FP false positive, FN false negative. Define what “correct item” means for each field, including units, numeric tolerance and source support. Specify behavior when a denominator is zero. A single overall score can conceal a weak field, so show field-level counts.

## 4. This week’s specific study bridge

Biology B7: Michaelis–Menten uses v=Vmax*S/(Km+S); Km has concentration units and v=Vmax/2 when S=Km. Fit only if the available substrate range and observations support the parameters. AI M7: Bayesian regression describes distributions over model parameters and predictions under a prior/likelihood. Plot a credible interval and a predictive interval and explain why they answer different questions. A narrow interval under a poor model does not guarantee truth.

### Biology/domain assignment retained from the plan

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

### AI/scientific-method assignment retained from the plan

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

These inherited chapter/lecture lists are resource menus. Select the subsection that answers the named understanding check. Do not add full-course viewing to the 600-minute week. The source/stash section below supplies the existing locators and marks searches as searches.

## 5. Resource stashes: open, study, apply and retain

Open [this week’s resource stash](http://127.0.0.1:5000/learn?stash=LABLOOP-W07%20Notebook) or [the complete weekly deck](http://127.0.0.1:5000/learn?week=7). These addresses work when the local cockpit runs on its default port; use its current address if you changed it. The public source links below also work independently of the cockpit. The weekly stash groups the existing cards; saving a card does not mark it studied.

Use **core** resources first, **run** resources when implementing a specific step, and **deeper** resources only after the critical work fits. Read the stated scope with one question in mind, then produce the note/calculation/artifact before opening another source. Times are inherited estimates, not extra allocations or a promise that every resource fits. Some cards contain an entire course or repository: use only the named topic/exercise.

**Source status.** This catalog preserves the programme’s resources. Direct links are locators, not a claim that all content was freshly inspected. Search links still need an exact source selected. The [source-check log](../../notebooks/source-checks.md) records the targeted checks and corrected FLIP locator; verify mutable versions, access rights, venues, roles and costs when executing. A NotebookLM upload does not automatically import every linked page.

| Card and source | Tier / slot | Scope or task from the existing resource | Time guide |
|---|---|---|---|
| [Zheng et al. (2023), "Judging LLM-as-a-judge with MT-Bench and Chatbot Arena" — search; resolve first](https://scholar.google.com/scholar?q=Zheng+et+al.+%282023%29%2C+%22Judging+LLM-as-a-judge+with+MT-Bench+and+Chatbot+Arena%22) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-2c28a4d3) | core / Monday | Build-block reading · Zheng et al. (2023), "Judging LLM-as-a-judge with MT-Bench and Chatbot Arena", NeurIPS Datasets & Benchmarks, sections 1-3 (judge biases you must avoid in week 14) | 30 min (estimate) |
| [MIT OCW 7.016 lectures on protein structure and enzymes — source](https://ocw.mit.edu/courses/7-016-introductory-biology-fall-2018) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-4acaabda) | core / Tuesday | MIT OCW 7.016 lectures on protein structure and enzymes (ocw.mit.edu/courses/7-016-introductory-biology-fall-2018), ~50 min | 50 min |
| [Khan Academy "Steady states and the Michaelis Menten equation" — search; resolve first](https://www.youtube.com/results?search_query=Khan+Academy+%22Steady+states+and+the+Michaelis+Menten+equation%22) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-451d639e) | core / Tuesday | Khan Academy "Steady states and the Michaelis Menten equation" (MCAT section) (15 min) | 15 min |
| [Statistical Rethinking 2024 — search; resolve first](https://www.youtube.com/results?search_query=Statistical+Rethinking+2024) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-3bae0522) | core / Thursday | Statistical Rethinking 2024 lectures 3-4 (YouTube, 75 min) | 75 min |
| [Anthropic Claude Cookbooks (github.com/anthropics/claude-cookbooks) — "extracting structured JSON" — source](https://github.com/anthropics/claude-cookbooks) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-c0d19840) | deeper / Saturday · sandbox, optional | Anthropic Claude Cookbooks (github.com/anthropics/claude-cookbooks) — "extracting structured JSON" and "tool use" recipes | 30 min (estimate) |
| [DSPy (Stanford NLP) documentation "Optimizers" — search; resolve first](https://duckduckgo.com/?q=DSPy+%28Stanford+NLP%29+documentation+%22Optimizers%22) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-0d5c6614) | deeper / Saturday · sandbox, optional | DSPy (Stanford NLP) documentation "Optimizers" — how to tune prompts against a metric instead of by feel | 30 min (estimate) |
| [Karpathy, "Deep Dive into LLMs like ChatGPT" — search; resolve first](https://www.youtube.com/results?search_query=Karpathy%2C+%22Deep+Dive+into+LLMs+like+ChatGPT%22) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-c65c1caf) | deeper / Saturday · sandbox, optional | Karpathy, "Deep Dive into LLMs like ChatGPT" (YouTube, 3.5 h; watch the first hour on hallucination and tool use) | 300 min |
| [Ninja Nerd "Enzyme kinetics" lecture — search; resolve first](https://www.youtube.com/results?search_query=Ninja+Nerd+%22Enzyme+kinetics%22+lecture) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-d8bc7865) | deeper / Saturday · sandbox, optional | Ninja Nerd "Enzyme kinetics" lecture (YouTube) for Michaelis-Menten in depth | 15 min (estimate) |
| [567-labs/instructor — source](https://github.com/567-labs/instructor) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-8a245682) | run / Any block this week — the plan names no day | Define your schema as a Pydantic model and let instructor enforce valid JSON from Claude and Ollama; kills 80% of parsing bugs | 30 min |
| [google/langextract — source](https://github.com/google/langextract) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-3abc821b) | run / Any block this week — the plan names no day | Run an example in examples/notebooks with a local Ollama model; compare its grounded spans with your provenance sentences | 30 min |
| [stanfordnlp/dspy — source](https://github.com/stanfordnlp/dspy) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-badaf2a2) | run / Any block this week — the plan names no day | Tutorial on "information extraction" in the docs: define a signature, a metric (your F1), and let an optimizer improve the prompt. Only after your manual baseline exists | 30 min |
| [lmfit/lmfit-py — source](https://github.com/lmfit/lmfit-py) · [card](http://127.0.0.1:5000/learn?week=7#card-w07-0d2655c3) | run / Any block this week — the plan names no day | Fit Michaelis-Menten to a small public dataset with confidence intervals on Km and Vmax | 30 min |

### A bounded way to read a scientist’s paper

Use the founder-paper slot only where scheduled. Select a paper relevant to this week through the existing resources or a verified author profile; record title, authors, year, exact URL and what full text you could access. In 30 minutes: 5 for the question and experimental unit; 10 for one relevant methods passage and figure; 10 for a digest; 5 for three questions. Your digest should say question → method → measured result with N/units → limitation → connection to this week’s artifact. If you only read the abstract, say so and leave inaccessible methods/results unknown. This notebook has not read a future partner paper on your behalf.

## 6. Seven-day runbook: what to do, why and when to stop

Use the original weekly allocation: six 90-minute days plus a 60-minute Sunday, totaling 600 minutes. Reading this notebook, creating study visuals, debugging, calls and evidence recording all consume that same capacity. This is a reference you open section by section, not an additional course to finish before building.

| Day | Budget | Existing target and stopping condition |
|---|---:|---|
| Monday | 90 min | Implement schema-constrained extraction with provenance and fake/API/local adapters; smoke-test five development papers and log model/prompt versions. Stop when: Invalid JSON, absent values and unsupported evidence fail visibly. |
| Tuesday | 90 min | 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 |
| Wednesday | 90 min | Implement field-specific precision/recall/F1, numeric unit/tolerance checks and provenance correctness on frozen paper-level splits. Stop when: Each field has counts and scoring rules; development scores are not called held-out performance. Reserve the last 10 minutes for the optional Wednesday note. |
| Thursday | 90 min | Statistical Rethinking 2024 lectures 3-4 Select material/exercise that fits 60 minutes; use the last 30 for the founder paper. |
| Friday | 90 min | Inspect five worst fields, make one development-only revision, compare before/after, and choose a documented per-field floor and cost budget for scale-up. Stop when: Unchanged held-out data and a backend decision with quality/cost evidence are recorded. |
| Saturday | 90 min | Resolve the earliest critical spillover or dependency. Prepare any long-form publication draft from existing figures here if needed. Sandbox only after commitments are met. |
| Sunday | 60 min | 20 min build-log draft/publication when authorized; 5 min evidence/checklist; 20 min source-grounded gap review; 15 min next week's six physical actions. |

### Monday challenge — `extraction-runbook.md`

**Do these steps in order.**

1. Define one extractor interface that accepts a document and schema version and returns records plus source locators or explicit failure.
2. Provide fake, API and local adapters as feasible.
3. Test five development papers.
4. Validate field types, allowed units, experiment associations and whether quoted evidence actually occurs in the source.
5. Save model identifier, prompt text/hash, generation settings, parser version and raw response.
6. Do not silently repair invented evidence into a successful record.

**Why this matters.** This output closes the input/question part of the week’s evidence chain. Its acceptance criterion below determines whether the result can support the next milestone.

**Output and acceptance from the specification:** Implement schema-constrained extraction with provenance and fake/API/local adapters; smoke-test five development papers and log model/prompt versions. Acceptance: Invalid JSON, absent values and unsupported evidence fail visibly.

**Block allocation:** 2 minutes open the current inputs and write the immediate action; 78 minutes carry out the steps above; 7 minutes check the acceptance criterion and record output paths/errors; 3 minutes write the next action. These sum to 90 minutes. Stop at the limit and record the exact next step rather than silently expanding the week.

**Evidence to retain:** the artifact or pending-state runbook, input/output paths, version/configuration, the check performed, observed result or exact failure, and your interpretation. Put the link in evidence.md. An intended filename is not proof that a measured output exists.


### Wednesday challenge — `evaluation-protocol.md`

**Do these steps in order.**

1. Freeze paper-level development/test assignments from the human gold.
2. For each field define exact matching or a justified numeric tolerance after valid unit conversion.
3. Count true positives, false positives and false negatives, keeping support and missingness visible.
4. Score provenance correctness separately from value correctness.
5. Implement a small hand-scored fixture before scoring a corpus; compare the machine counts with the hand calculation.

**Why this matters.** This output closes the implementation/measurement part of the week’s evidence chain. Its acceptance criterion below determines whether the result can support the next milestone.

**Output and acceptance from the specification:** Implement field-specific precision/recall/F1, numeric unit/tolerance checks and provenance correctness on frozen paper-level splits. Acceptance: Each field has counts and scoring rules; development scores are not called held-out performance.

**Block allocation:** 2 minutes open the current inputs and write the immediate action; 68 minutes carry out the steps above; 7 minutes check the acceptance criterion and record output paths/errors; 3 minutes write the next action. The remaining 10 minutes are the optional Wednesday note; reclaim them for the critical task if necessary. These sum to 90 minutes. Stop at the limit and record the exact next step rather than silently expanding the week.

**Evidence to retain:** the artifact or pending-state runbook, input/output paths, version/configuration, the check performed, observed result or exact failure, and your interpretation. Put the link in evidence.md. An intended filename is not proof that a measured output exists.


### Friday challenge — `error-analysis.md`

**Do these steps in order.**

1. Rank development errors by field and inspect five weak fields with their source passages.
2. Classify cause: missed text, wrong experiment, unit error, hallucination or annotation ambiguity.
3. Change one rule or prompt based on development evidence and rerun the same development set.
4. Record cost, latency and failures.
5. Set field-specific scale-up criteria before testing; if a critical field remains weak, route it to manual review or keep scaling blocked.

**Why this matters.** This output closes the verification/handoff part of the week’s evidence chain. Its acceptance criterion below determines whether the result can support the next milestone.

**Output and acceptance from the specification:** Inspect five worst fields, make one development-only revision, compare before/after, and choose a documented per-field floor and cost budget for scale-up. Acceptance: Unchanged held-out data and a backend decision with quality/cost evidence are recorded.

**Block allocation:** 2 minutes open the current inputs and write the immediate action; 78 minutes carry out the steps above; 7 minutes check the acceptance criterion and record output paths/errors; 3 minutes write the next action. These sum to 90 minutes. Stop at the limit and record the exact next step rather than silently expanding the week.

**Evidence to retain:** the artifact or pending-state runbook, input/output paths, version/configuration, the check performed, observed result or exact failure, and your interpretation. Put the link in evidence.md. An intended filename is not proof that a measured output exists.


### Tuesday — rebuild the domain concept through an output

1. Spend 10 minutes recalling what you know and listing the specific confusing words in the domain assignment above.
2. Spend up to 35 minutes on the relevant source subsection. Pause to define each term using the actual data or artifact, not only an analogy.
3. Spend 30 minutes producing the assigned note, drawing, calculation or bounded exercise. Label invented teaching numbers as synthetic. For applied weeks, use the exercise/decision in the current challenge.
4. Spend 10 minutes explaining what the concept changes in this week’s work. Record the explanation or write five sentences without looking.
5. Spend 5 minutes saving the output and one unresolved question. These 90 minutes include opening/closing rituals. For a source week with no new coursework, apply this rhythm to its named operational material.

### Thursday — connect the model or decision to the domain

Use 5 minutes to recall the concept, 20 for the smallest relevant source section, 25 for one calculation/code application, 5 to explain it without notes and 5 to log the result. Use the remaining 30 for the scheduled founder-paper digest. If the inherited list is longer than the block, park the rest.

Write one bridge sentence: “I use [concept] in [specific artifact] because it prevents or enables [specific behavior].” Then point to the corresponding field, equation, comparison or paragraph. If you cannot locate the connection, return to the smallest worked example rather than opening more resources.

### Saturday — repair the earliest dependency, then prepare study visuals

Start by reading unresolved acceptance items and choose the one that blocks the next milestone. Spend 2 minutes choosing it, 58 minutes fixing or preparing the smallest checkable result, 7 minutes checking the result and 3 minutes recording the handoff. If critical work is complete, use the remaining 20 minutes to import this notebook or prepare the next week’s sources and request one visual. If not, use those 20 minutes on the dependency. Optional sources and polish move to PARKING.md. A visual study aid does not replace the missing artifact.

### Sunday — review and make next week startable

Use 20 minutes to draft a build log from one actual figure, result or failure, with correct publication state; 5 minutes to update evidence and checklist; 20 minutes to attempt the recall questions and review gaps; 15 minutes to write six next physical actions with filenames and needed inputs. Keep the original gate target and record any revised forecast separately. Actual external publishing follows the authorization available in that execution session.

## 7. Worked example, practice and separate answer key

### Worked teaching example

Synthetic count example: 8 correct extracted values, 2 wrong extractions and 4 missed reference values give precision=8/(8+2)=0.80 and recall=8/(8+4)=0.667. F1=2*8/(2*8+2+4)=0.727. A correct value with a fabricated citation still fails provenance evaluation.

These are illustrative reasoning examples or explicitly synthetic numbers, not measurements obtained for your research. Recreate the calculation or reasoning before applying it to actual inputs.

### Your exercise — answer before reading the solution

If you change the prompt after reading every test error, can the next score on the same papers be called an untouched test result?

Your answer: ____________________

Your connection to `extraction-runbook.md`: ____________________

### Answer key

No. Those papers have become development evidence. Keep the old result as a historical test observation, label the new one development/reused-test, and obtain a fresh held-out set before making a new independent performance claim.

### Five recall questions and grading guide

1. Explain this week’s purpose to a 15-year-old in three sentences. What real scientific or professional decision does it support?
2. Solve the exercise above and explain each assumption or unit, rather than copying the answer.
3. Open `extraction-runbook.md` or its preparation instructions. What exact input, action, output and acceptance check make it inspectable?
4. What could make `evaluation-protocol.md` look convincing while still being wrong? Use the week-specific risk below and name the evidence needed to detect it.
5. What does `error-analysis.md` pass to the next milestone, and which claim remains unsupported until external or measured evidence exists?

Grade each answer 0 (missing/wrong), 1 (correct but vague or needs prompting), or 2 (correct, explained in your own words and tied to a concrete artifact/example). The purpose/bridge supports Q1; the separate key supports Q2; the runbook and contracts support Q3–Q5. Aim for at least 8/10 with no unresolved misconception about provenance, independence, measured versus predicted results or external status. This is a study-readiness check, not permission to pass the research gate. Save your actual score and gaps; this prepared notebook does not assign them.

## 8. Research evidence and professional profile

### What your weekly evidence record should contain

Copy the blank structure below into the existing evidence.md only when working the task. Keep earlier entries. Use actual values or PENDING with a reason; never copy illustrative numbers as results.

| Evidence field | Your actual entry |
|---|---|
| Question/decision and why it matters | PENDING |
| Artifact name, canonical path and version | PENDING |
| Input origin, access date, rights, version/checksum | PENDING |
| Unit of analysis / target / relevant units | PENDING |
| Method, baseline, assumptions and split or decision rule | PENDING |
| Command/config/seed or document review procedure | PENDING |
| Observed output, independent N and uncertainty where relevant | PENDING |
| Check performed, failures and negative findings | PENDING |
| Interpretation and what the evidence does not establish | PENDING |
| Your contribution and model/human/partner contributions | PENDING |
| External event state and dated receipt/link, if applicable | PENDING |
| Next action, owner and dependency | PENDING |

For documentary or commercial work, replace nonapplicable experimental fields with the actual verification (for example, source-to-claim audit or agreed scope/receipt); write “not applicable” with a reason instead of inventing a metric. For experiments, retain raw data, scripts/configs, per-case results and generated figures in the canonical project. Evidence.md is the index, not a substitute for those artifacts.

### Make the skill-to-proof connection

Complete this sentence from real work: “I used [systems/software/AI capability] to answer [scientific/workflow question], implemented [artifact], checked it using [method], observed [result with context], and found [limitation]. My contribution was [specific work].” This becomes an honest portfolio/interview story. A failed experiment with a sound diagnosis is also evidence of research judgment.

The Week 40 profile should let a reader follow your claims to data/code/releases, manuscripts with exact status, independent feedback, collaboration and actual delivery. Keep a brief record now so you do not reconstruct a research history from memory later.

## 9. Completion checklist, misconceptions and recovery

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.

### Notebook study checklist

- [ ] I can describe the week’s question and its connection to my systems/software/AI work.
- [ ] I repaired the specific prerequisite I needed and completed the worked exercise myself.
- [ ] I used the selected stash sources and saved an applied note rather than only a viewing history.
- [ ] Each challenge has the specified output and a recorded acceptance check, or an explicit missing dependency.
- [ ] I retained source versions, units, split/decision rules, failures and limitations where applicable.
- [ ] I can distinguish illustrative, simulated, predicted and measured information in my work.
- [ ] My research/profile claims link to real evidence and use the correct external status.
- [ ] I recorded actual recall performance, next actions and any unmet gate requirement.

### The specific trap to avoid this week

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.

### Recovery without losing the programme’s meaning

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](../../../LABLOOP-Master-Plan-v6.md#part-8--the-prompt-pack-copy-paste-fill-the-brackets): 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.

If a prerequisite concept is missing, use the first ten minutes to define it and work one tiny example. If hardware or access fails, use the allowed offline/synthetic preparation and label its scope. If a person, public identifier or payment is required, keep that event pending and finish independent work. A smaller preparation result preserves momentum; it does not replace an unmet gate.

## 10. NotebookLM import and visual study kit

1. Create a notebook named **LABLOOP-W07 · measured extraction agent**.
2. Upload this week’s `notebooklm.txt` or `learning-notebook.md`, or paste the complete text as a source. Upload one copy, not both. [Google’s source-import guidance](https://support.google.com/notebooklm/answer/16215270?hl=en) documents text/Markdown and pasted-text sources.
3. Add the exact core source pages or permitted PDFs you selected in Section 5 as separate sources. Linked pages and local cockpit stashes are not recursively imported. Inspect what was actually imported; a video may require an available transcript. You do not need all 454 programme cards in one notebook.
4. When you execute the week, add your own notes, permitted code excerpts, results and review as separate clearly named sources. Use “Measured — …” only for actual measurements. Keep sensitive partner/client records within their permitted use.
5. Request one study output at a time using the prompts below; use the available Studio feature or ask chat for the equivalent outline. Interface/features can vary. Inspect units, labels, citations and the separation between planned and achieved work before studying or sharing a generated visual.

### Week-specific visual brief

Draw the extraction pipeline with two separate checks—schema validity and source support—and a confusion-count table for one field.

### Copy-ready prompts

**Concept map / infographic**

> Using only the sources in LABLOOP-W07, explain “measured extraction agent” to an adult software/systems/AI professional rebuilding science foundations after twenty years. Draw the extraction pipeline with two separate checks—schema validity and source support—and a confusion-count table for one field. Label each arrow with why it exists. Define every technical term at first use. Connect prerequisite → current challenge → evidence → next milestone. Mark targets, synthetic teaching numbers and measured results distinctly. Cite sources; identify missing evidence instead of inventing it.

**Visual lesson / slides**

> Create an eight-panel visual lesson for Week 07: 1 purpose, 2 needed foundations, 3 one worked example with units, 4 Monday challenge, 5 Wednesday challenge, 6 Friday challenge, 7 common failure and verification, 8 evidence checklist and next milestone. Use simple explanations suitable for a 15-year-old without talking down to an experienced professional. Put detailed speaker notes under each panel. Use the exact artifact filenames and acceptance criteria in this notebook.

**Audio or video study script**

> Teach Week 07 as a guided conversation: what, why, when and how. Explain the mathematical/scientific idea in words before notation. Pause for me to answer the exercise without revealing the solution; then walk through it. Connect my software experience to the scientific question. End with a rehearsal of what evidence I must retain, not a claim that I have already completed the work.

**Flashcards and quiz**

> Make twelve cards: four term/meaning/example cards, four how/why steps from the actual challenges, two unit/assumption checks and two evidence/misconception checks. Then ask five open questions one at a time. Grade each 0–2 using the notebook rubric, explain any error, and cite the relevant section. Do not infer my competence from the existence of the notebook.

**Research review rehearsal**

> Act as a careful research reviewer for Week 07. Ask me to defend the question, inputs, independent unit or decision basis, baseline, method, uncertainty, failure cases and scope of the claim. Use only supplied evidence. Distinguish a preparation artifact from a measured result and an external event. Finish with a claim-to-evidence table and the three smallest actions needed to close real gaps.

## 11. Source and ownership notes

This notebook adds explanation and runbooks to the existing plan. The [weekly specification](./specs.md), [programme decisions](../../DECISIONS.md) and [gates](../../GATES.md) retain authority over sequence, scope and acceptance. The [v6 master](../../../LABLOOP-Master-Plan-v6.md) supplies the dependency map and inherited resource cards; the [source catalog](../../SOURCES.md) records their history. The teaching examples and explanatory bridge are preparation material, not executed findings.

Existing files and learning progress remain separate. Dates stay relative until you choose actual commitments. Peter owns learning, personal claims, scientific responsibility and external relationships; independent humans own their actual annotation/review contributions and partner laboratories own their laboratory execution. This notebook prepares the steps; it does not publish, contact, spend, submit or perform the programme on your behalf.