# LABLOOP W12 — endorsement and hybrid model: 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-11-fermlit-dataset-engineering/learning-notebook.md) · [Next notebook](../week-13-fermlit-release-and-paper-outline/learning-notebook.md)

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

A hybrid model combines a mechanistic prediction with a learned correction. The mechanism encodes your stated process assumptions; the ML component learns systematic residual errors from training data. This week also opens real endorsement conversations. An endorsement is an external process with its own eligibility and timing, so it cannot be inferred from having a manuscript.

**Your systems, software and AI connection.** Your Week 01 simulator becomes a component in a larger model architecture. Comparing mechanism-only, ML-only and hybrid models is an ablation: it tests what each component contributes. The experiment harness becomes the backbone of Paper 2, while a clear scientific summary helps potential collaborators evaluate your work.

**Dependency map from the existing programme.**

- ← **From:** week 1 Monod simulator (the engineer), week 8 LightGBM soft sensor (the analyst), week 4 batch-wise CV, week 8 technical report (proof of seriousness for endorsers).
- → **Feeds:** week 17 (full learning-curve experiment), week 18 (Paper 2 draft), weeks 19-20 (endorsement closes), week 27 (pharma vocabulary in the Loop Audit offer).
- ⟳ **Returns in:** Paper 2's central figure; the Part 9.5 routes.

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

This is an enabling week. Its deliverables feed the next scheduled gate: 13. 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 08](../week-08-technical-report-gate/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

### Rates, derivatives, integrals and gradients from the beginning

A **variable** is a named quantity that can change. A **function** is a rule: give it an input and it returns an output. If X(t) is biomass at time t, the derivative dX/dt means “how fast biomass is changing now.” Read dX/dt as one rate, not a mysterious fraction you must memorize. If biomass rises from 1 to 1.6 g/L in two hours, its average rate over that interval is (1.6−1)/2=0.3 g/L/hour; the instantaneous rate may differ.

An **integral** adds many small contributions. If a pump feeds 2 L/hour for three hours, the accumulated feed is 6 L. For changing feed F(t), write added volume = integral of F(t) dt. Numerically, sum F at each short interval times that interval’s duration. Liters/hour times hours gives liters. Smaller steps can improve an approximation; they do not repair a wrong equation. An **ODE**, ordinary differential equation, defines a rate in terms of the current states and time. A solver starts with known initial states and accumulates their rates to estimate the trajectory.

A **gradient** collects derivatives with respect to several adjustable parameters. It points toward local increase; gradient descent steps the other way to reduce an error/loss. For loss L=(w−3)^2, the derivative is 2(w−3). At w=1 the derivative is −4; subtracting 0.1×(−4) gives w=1.4, closer to 3. This is the bridge from a hill analogy to model fitting. You need interpretation, units and small calculations before formal proofs. Optional repair: read the rectangles-and-area introduction in [OpenStax Calculus 5.1](https://openstax.org/books/calculus-volume-1/pages/5-1-approximating-areas), within the existing study block.

### 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.

### How a professional research claim earns trust

Use a chain you can inspect: **question → source data → method → output → interpretation → limitation**. A claim is a sentence someone could challenge. An artifact is the file, figure, release or record that supports it. Verification explains how you checked the artifact. A screenshot can show a graph existed; code, inputs and commands allow someone to recreate it.

Every experiment needs the question or exploratory label, independent unit, data origin/rights/version/hash, baseline, split, code/config/seed, command, outputs, errors and interpretation. Keep synthetic teaching examples separate from programme results. Every public/career claim also needs your actual contribution and the correct state: prepared, sent/submitted, public, reviewed, accepted or paid/delivered.

Keep evidence in the weekly register with links to canonical project files. A DOI identifies an object; it is not peer review. A contact is not a collaborator; a submission receipt is not acceptance. These distinctions strengthen your profile because a scientist, recruiter or buyer can trust the claims that are supported. Learning evidence is personal too: explain a concept without notes, perform a small calculation, reproduce an output and identify a failure. A prepared notebook does not mean you have completed the week.

## 4. This week’s specific study bridge

Domain B12: PAT concerns timely process understanding/measurement; a critical quality attribute is a product property that must be controlled, and a critical process parameter can affect such attributes. Study these as vocabulary with current official sources, not a compliance claim. AI M12: SINDy fits sparse combinations of candidate functions to estimated dynamics. If the function library cannot represent S/(Ks+S), exact Monod recovery is not assured. Record derivative noise, library and identifiability, and report what the experiment actually recovers.

### Biology/domain assignment retained from the plan

Source unit: B12 · Downstream, PAT and QbD

Material: FDA PAT guidance (2004) — fda.gov; ICH Q8(R2) sections 1-2 — ich.org

Produce: Glossary: CPP, CQA, design space, golden batch, in your words

Understanding check: You can hold a conversation with a pharma QA manager

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

Source unit: M12 · Data-driven dynamics

Material: Brunton & Kutz, *Data-Driven Science and Engineering*, ch. 7 (SINDy) — databookuw.com (free PDF + YouTube "Steve Brunton")

Produce: SINDy recovers Monod from simulator data

Understanding check: You can say what "system identification" is

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-W12%20Notebook) or [the complete weekly deck](http://127.0.0.1:5000/learn?week=12). 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 |
|---|---|---|---|
| [Brunton, Proctor & Kutz — search; resolve first](https://duckduckgo.com/?q=Brunton%2C+Proctor+%26+Kutz) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-6f7f35ec) | core / Monday | Build-block reading · Brunton, Proctor & Kutz (2016), "Discovering governing equations from data by sparse identification of nonlinear dynamical systems", PNAS 113(15):3932-3937 (abstract + figure 1) | 30 min (estimate) |
| [FDA — search; resolve first](https://duckduckgo.com/?q=FDA) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-acccc343) | core / Tuesday | FDA (2004) PAT — A Framework for Innovative Pharmaceutical Development, Manufacturing, and Quality Assurance — fda.gov/media/71012/download (read sections I-IV, 45 min) | 45 min |
| [ICH Q8(R2) — source](https://ich.org) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-07f7d66b) | core / Tuesday | ICH Q8(R2) sections 1-2 (ich.org) (15 min). Write the glossary | 15 min |
| [Brunton & Kutz, Data-Driven Science and Engineering (2nd ed.), ch. 7 on SINDy — databookuw.com (… — source](https://databookuw.com) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-d51d6d78) | core / Thursday | Brunton & Kutz, Data-Driven Science and Engineering (2nd ed.), ch. 7 on SINDy — databookuw.com (free PDF) (40 min) + Steve Brunton "Sparse Identification of Nonlinear Dynamics (SINDy)" (YouTube, 30 min) | 40 min |
| [Narayanan et al. (2020), "Bioprocessing in the digital age: the role of process models" — search; resolve first](https://scholar.google.com/scholar?q=Narayanan+et+al.+%282020%29%2C+%22Bioprocessing+in+the+digital+age%3A+the+role+of+process+models%22) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-7c8cb0db) | deeper / Saturday · sandbox, optional | Narayanan et al. (2020), "Bioprocessing in the digital age: the role of process models", Biotechnology Journal 15(1):e1900172 | 30 min (estimate) |
| [Sansana et al. (2021), "Recent trends on hybrid modeling for Industry 4.0" — search; resolve first](https://scholar.google.com/scholar?q=Sansana+et+al.+%282021%29%2C+%22Recent+trends+on+hybrid+modeling+for+Industry+4.0%22) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-6fc394c9) | deeper / Saturday · sandbox, optional | Sansana et al. (2021), "Recent trends on hybrid modeling for Industry 4.0", Computers & Chemical Engineering 151:107365 | 30 min (estimate) |
| [arXiv endorsement page — source](https://info.arxiv.org/help/endorsement.html) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-f0968fdf) | deeper / Saturday · sandbox, optional | arXiv endorsement page — info.arxiv.org/help/endorsement.html (read once, carefully) | 30 min (estimate) |
| [Steve Brunton "Physics Informed Machine Learning" series — search; resolve first](https://www.youtube.com/results?search_query=Steve+Brunton+%22Physics+Informed+Machine+Learning%22+series) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-d814aaa9) | deeper / Saturday · sandbox, optional | Steve Brunton "Physics Informed Machine Learning" series (YouTube), first 2 videos | 15 min (estimate) |
| [dynamicslab/pysindy — source](https://github.com/dynamicslab/pysindy) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-b4643581) | run / Any block this week — the plan names no day | Colab: examples/tutorial_1; then feed it X and S from your simulator and see whether it recovers a Monod-like term | 30 min |
| [dynamicslab/databook_python — source](https://github.com/dynamicslab/databook_python) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-57874838) | run / Any block this week — the plan names no day | The book's Python notebooks for chapter 7 (SINDy) in Colab | 30 min |
| [jrcramos/Hybrid-modeling-of-bioreactor-with-LSTM — source](https://github.com/jrcramos/Hybrid-modeling-of-bioreactor-with-LSTM) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-b12afcf2) | run / Any block this week — the plan names no day | Read the README and model structure; a published example of "mechanistic + neural" for cell culture to compare against your "Monod + GBM" | 30 min |
| [casadi/casadi — source](https://github.com/casadi/casadi) · [card](http://127.0.0.1:5000/learn?week=12#card-w12-d1de1587) | run / Any block this week — the plan names no day | Optional: fit Monod parameters per batch with an optimizer; only if scipy.optimize struggles | 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 | Prepare three endorsement/collaboration routes with verified category eligibility, paper summaries and the best available evidence link. Stop when: Three specific messages are ready; record actual sending and replies only if performed. |
| Tuesday | 90 min | FDA PAT guidance (2004) — fda.gov; ICH Q8(R2) sections 1-2 — ich.org Produce: Glossary: CPP, CQA, design space, golden batch, in your words |
| Wednesday | 90 min | Fit a mechanistic baseline and residual GBM using training data and information available at prediction time; compare on ten training batches. Stop when: Mechanistic, pure ML and hybrid feature/target definitions are explicit. Reserve the last 10 minutes for the optional Wednesday note. |
| Thursday | 90 min | Brunton & Kutz, *Data-Driven Science and Engineering*, ch. 7 (SINDy) — databookuw.com (free PDF + YouTube "Steve Brunton") Select material/exercise that fits 60 minutes; use the last 30 for the founder paper. |
| Friday | 90 min | Build the 5/10/20/50-batch, five-seed learning-curve harness with fixed held-out groups and feasible data counts. Stop when: A smoke run validates split isolation; full results may finish in week 17. |
| 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 — `endorsement-route.md`

**Do these steps in order.**

1. Prepare three distinct endorsement/collaboration routes from verifiable scientific relationships.
2. For each, save current category requirements, a concise paper summary, the strongest existing evidence link and one specific request.
3. Keep sent, replied and endorsed states separate.
4. Use the official endorsement source to verify eligibility when acting; an encouraging conversation does not automatically grant submission endorsement.

**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:** Prepare three endorsement/collaboration routes with verified category eligibility, paper summaries and the best available evidence link. Acceptance: Three specific messages are ready; record actual sending and replies only if performed.

**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 — `hybrid-design.md`

**Do these steps in order.**

1. Define a common target and observation cutoff for all three models.
2. Fit mechanistic parameters on training data only.
3. Compute training residuals r=y−mechanistic_prediction and fit the residual model using valid training features.
4. At prediction time add the mechanism output and residual prediction.
5. Explain how residuals used for fitting were obtained and whether out-of-fold predictions are needed to avoid optimistic training artifacts.
6. Compare on the small training/development setup without calling it final performance.

**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:** Fit a mechanistic baseline and residual GBM using training data and information available at prediction time; compare on ten training batches. Acceptance: Mechanistic, pure ML and hybrid feature/target definitions are explicit.

**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 — `experiment-matrix.csv`

**Do these steps in order.**

1. Write the experiment matrix: three model families × four training sizes (5,10,20,50 batches) × five seeds = 60 combinations.
2. Fix held-out calibration/test batches and sample training subsets only from the training pool.
3. Mark impossible sizes if too few eligible batches exist.
4. Save config, seed, feature rules, command and failure state per run.
5. Execute a tiny smoke subset to check group isolation and output columns before the Week 17 full run.

**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:** Build the 5/10/20/50-batch, five-seed learning-curve harness with fixed held-out groups and feasible data counts. Acceptance: A smoke run validates split isolation; full results may finish in week 17.

**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 hybrid prediction: mechanism predicts 8 g/L and the residual model predicts +1.5 g/L, so the hybrid predicts 9.5 g/L. If actual titer is 9, the hybrid error is 0.5 and mechanism error is 1. A different case can worsen; one example cannot establish improvement.

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

Can you fit a held-out batch’s mechanistic parameters to its entire measured trajectory and then claim an early forecast on that batch?

Your answer: ____________________

Your connection to `endorsement-route.md`: ____________________

### Answer key

No. The fitted parameters contain future information. Estimate global parameters from training data, or use a documented online update restricted to observations genuinely available before the prediction cutoff.

### 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 `endorsement-route.md` or its preparation instructions. What exact input, action, output and acceptance check make it inspectable?
4. What could make `hybrid-design.md` look convincing while still being wrong? Use the week-specific risk below and name the evidence needed to detect it.
5. What does `experiment-matrix.csv` 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: 13. Complete the acceptance checklist below; do not promote reputation from a draft.

- [ ] Monday artifact satisfies: Three specific messages are ready; record actual sending and replies only if performed.
- [ ] Wednesday artifact satisfies: Mechanistic, pure ML and hybrid feature/target definitions are explicit.
- [ ] Friday artifact satisfies: A smoke run validates split isolation; full results may finish in week 17.
- [ ] 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

Fitting mechanistic parameters to a full held-out trajectory leaks future labels. SINDy needs an appropriate function library and identifiability check; recovering exact Monod kinetics is an experiment, not a guaranteed study outcome.

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 three endorsement messages.

Operational first step if stalled: open `endorsement-route.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-W12 · endorsement and hybrid model**.
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 mechanism-only, ML-only and mechanism-plus-residual paths sharing the same train/test boundary.

### Copy-ready prompts

**Concept map / infographic**

> Using only the sources in LABLOOP-W12, explain “endorsement and hybrid model” to an adult software/systems/AI professional rebuilding science foundations after twenty years. Draw mechanism-only, ML-only and mechanism-plus-residual paths sharing the same train/test boundary. 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 12: 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 12 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 12. 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.