WEEK 09 · Mon 16 Nov → Sun 22 Nov 2026
UNDERSTAND · PRACTICE · KEEP EVIDENCE
Read the week in plain language, refresh the foundations, follow each challenge step by step, and check what evidence to keep. Includes worked examples, answer keys and prompts for visual study resources.
Use this within your existing weekly blocks. Your learning completion and research evidence remain in your current tracker and week files.
START HERE · 2 MINUTES
STATUS
| Deliverable | Acceptance | State |
|---|---|---|
corpus-scale-manifest.csvBuild |
Expand the screened corpus toward 2,000 papers; deduplicate preprint/journal versions and record exclusions and license restrictions. Acceptance: Every included paper has a stable identity and eligible full text. | |
extraction-cost-report.csvBuild |
Run the selected backend with resumable jobs, retry limits, caching, quality checks and a small paid pilot before bulk execution. Acceptance: Success/failure counts, token or local-runtime use and measured cost are recorded. | |
completeness-table.csvBuild |
Produce the field completeness table by organism/year with a manually checked missingness sample. Acceptance: Not reported, not extracted and unavailable full text remain separate categories. | |
study-notes.mdLearning create ＋ |
Selected exact free resources; bounded lesson/exercise; separate solution; quiz and grading rubric; Peter's answers and gaps when executed | |
founder-paper.mdFounder papers create ＋ |
Verified source and P11 digest; authentic question and connection sentence; access limitations | |
branding-pack.mdBranding create ＋ |
Wednesday note, Sunday build log, X adaptation, figure/caption/alt text and the week's special asset; each claim linked to real proof | |
opportunity-actions.mdOpportunities create ＋ |
Qualified target/role, source/date, ladder stage, next action, message/interview/proposal draft and actual status | |
evidence.mdEvidence & review open & edit ↗ |
Actual paths/URLs, versions, checks/metrics, preparation versus execution state and external receipts when applicable | |
review.mdEvidence & review open & edit ↗ |
Checklist, learning assessment, gate status, shortfalls, next actions and carryover |
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.
600 MINUTES MAXIMUM
Target. Expand the screened corpus toward 2,000 papers; deduplicate preprint/journal versions and record exclusions and license restrictions. Stop when: Every included paper has a stable identity and eligible full text.
No material for Monday — this is a pure build day. Need something to study instead? →
Target. NPTEL "Bioreactors" (IIT Madras, Prof. G. K. Suraishkumar), lectures 1-3 — nptel.ac.in (verify current playlist); MIT OCW 10.37 lecture notes on bioreactors as backup Produce: Mass balances for batch, fed-batch, continuous in a notebook
Do these in this order — the plan's own sequence:
Target. Run the selected backend with resumable jobs, retry limits, caching, quality checks and a small paid pilot before bulk execution. Stop when: Success/failure counts, token or local-runtime use and measured cost are recorded. Reserve the last 10 minutes for the optional Wednesday note.
No material for Wednesday — this is a pure build day. Need something to study instead? →
Target. Karpathy, "Building makemore" (part 1) Select material/exercise that fits 60 minutes; use the last 30 for the founder paper.
Do these in this order — the plan's own sequence:
Target. Produce the field completeness table by organism/year with a manually checked missingness sample. Stop when: Not reported, not extracted and unavailable full text remain separate categories.
No material for Friday — this is a pure build day. Need something to study instead? →
Target. 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.
Optional, only if the day went well:
Target. 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.
No material for Sunday — this is a pure build day. Need something to study instead? →
Spare pockets, repo exercises and anything the plan lists without a day. Take them in this order when a day finishes early.
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.
WHAT TO WATCH, READ AND RUN
Scaling is where program managers shine and scientists often stumble. Going from 50 to 2,000 papers is not "run the loop 40 times"; it is a production run with a budget, a quality floor and a cost table. You set the floor in week 7 (the minimum F1 you accept); now you choose the cheapest backend that clears it, exactly like choosing a supplier who meets the spec at the lowest price. When the 2,000 JSONs land, you bu…
0 of 10 finished · give me one to start now → · open in the deck →
In the plan's running order: each card says which block it belongs to and what has to come before it. The seven-day plan lists the same cards under the day that owns them.
NPTEL Bioreactors (Suraishkumar, IIT Madras), lectures 1-3 — nptel.ac.in/courses/102106053 (also on YouTube; ~75 min at 1.25x). Notebook: batch, fed-batch and continuous balances
In: LABLOOP-W09 Notebook
Karpathy, "The spelled-out intro to language modeling: building makemore" (YouTube, ~2 h; first 75 min Thursday)
In: LABLOOP-W09 Notebook
Saturday sandbox
MIT OCW 10.37 Chemical and Biological Reaction Engineering (Spring 2007), lecture notes on bioreactors — ocw.mit.edu/courses/10-37-chemical-and-biological-reaction-engineering-spring-2007
In: LABLOOP-W09 Notebook
Saturday sandbox · after MIT OCW 10.37 Chemical and Biological Reaction Engineering
Coursera Industrial Biotechnology (University of Manchester), module on fermentation processes
In: LABLOOP-W09 Notebook
Saturday sandbox · after Coursera Industrial Biotechnology
LearnChemE "mass balance" screencasts (YouTube)
In: LABLOOP-W09 Notebook
Saturday sandbox · after LearnChemE "mass balance" screencasts
Karpathy "Intro to Large Language Models" (YouTube, 1 h) for a bird's-eye view
In: LABLOOP-W09 Notebook
Run makemore.py on a text file of 2,000 organism names extracted by FermLit; sample new "organisms" for fun
In: LABLOOP-W09 Notebook
lectures/makemore part 1 notebook in Colab
In: LABLOOP-W09 Notebook
Read the "Tutorial" page; model your batch extraction as an eval task with logged cost and tokens (the Vara telemetry idea, done by a government AI institute)
In: LABLOOP-W09 Notebook
Benchmark tokens/second of your local Qwen 7B on 20 papers; add the row to the cost table
In: LABLOOP-W09 Notebook
READ FIRST
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.
READ FIRST
Read v6 · Week 9 · FermLit at scale 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 III · Threads: B, M, FL · Next gate: 13
Where this week sits. - ← From: weeks 5-7 (corpus, schema, measured agent), week 1 (your mass balances). - → Feeds: week 10 (descriptive analysis on 2,000 records), week 11 (reporting-completeness as a formal result), week 13 (dataset release), weeks 14-16 (Paper 1 Results). - ⟳ Returns in: Paper 1 figure 1 (completeness by field), and in every LinkedIn post that says "X% of papers do not report pH".
Goals. - 🎯 This week: 2,000 papers extracted within the F1 floor, a cost table, and a completeness table per field. - 🏁 Next milestone: Gate 13 (FermLit v0.5 public, Paper 1 skeleton). - 🌟 Final: the reporting-completeness finding that makes Paper 1 more than a dataset.
Mentor check. "I can say what fraction of 2,000 fermentation papers report each key parameter, and why that number is trustworthy."
OPEN WHEN NEEDED
READ FIRST
Source unit: B9 · Bioreactors I: modes and balances
Material: NPTEL "Bioreactors" (IIT Madras, Prof. G. K. Suraishkumar), lectures 1-3 — nptel.ac.in (verify current playlist); MIT OCW 10.37 lecture notes on bioreactors as backup
Produce: Mass balances for batch, fed-batch, continuous in a notebook
Understanding check: Your simulator's equations match the lecture's
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.
Source unit: M9 · Language models from scratch
Material: Karpathy, "Building makemore" (part 1)
Produce: Bigram model on organism names from FermLit
Understanding check: You know what a language model is, in 200 lines
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.
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.
OPEN WHEN NEEDED
Branding: Draft corpus-scale results with actual N and uncertainty around automated completeness estimates.
Opportunity action: Share a relevant organism-level preliminary figure with an existing contact after verifying source rights and results.
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.
OPEN WHEN NEEDED
Two thousand is a target, not an inclusion rule. Automated failure is not evidence that authors omitted a field; disclose selection bias and stop runs at the agreed budget.
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.
READ FIRST
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.
READ FIRST
Source-preserving minimum: the completeness table.
Operational first step if stalled: open corpus-scale-manifest.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.
OPEN WHEN NEEDED
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.
OPEN WHEN NEEDED
Prepare Week 09 of this LABLOOP execution plan.
Read execution-plan/specs.md, execution-plan/DECISIONS.md,
execution-plan/GATES.md and
execution-plan/weeks/week-09-fermlit-scale-up/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 09 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.
OPEN WHEN NEEDED
v6 reproduces this brief unchanged inside v6 · Week 9 · FermLit at scale. The following is source planning text, not a claim of completion. Apply the explicit evidence corrections in this specification and DECISIONS.md.
WEEK FILES
State: UNCONFIRMED. Owner: Peter Ciancaglini. Specification
Start date: not set. End date: not set. Available hours: confirm (planned ceiling 10). Primary outcome: fermlit scale up. Minimum that keeps the next gate alive: the completeness table.
corpus-scale-manifest.csv: Every included paper has a stable identity and eligible full text.extraction-cost-report.csv: Success/failure counts, token or local-runtime use and measured cost are recorded.completeness-table.csv: Not reported, not extracted and unavailable full text remain separate categories.| Day | Minutes | Physical action / outcome | Actual slot | Done |
|---|---|---|---|---|
| Mon | 90 | Expand the screened corpus toward 2,000 papers; deduplicate preprint/journal versions and record exclusions and license restrictions. | Not set | ☐ |
| Tue | 90 | Mass balances for batch, fed-batch, continuous in a notebook | Not set | ☐ |
| Wed | 90 | Run the selected backend with resumable jobs, retry limits, caching, quality checks and a small paid pilot before bulk execution. Last ten minutes: optional note. | Not set | ☐ |
| Thu | 90 | Bigram model on organism names from FermLit Include relevant founder-paper work within this block. | Not set | ☐ |
| Fri | 90 | Produce the field completeness table by organism/year with a manually checked missingness sample. | Not set | ☐ |
| Sat | 90 | Resolve critical spillover; long-form draft if due; sandbox only if done. | Not set | ☐ |
| Sun | 60 | Build log, evidence, gap review, next actions. | Not set | ☐ |
Peter's commitment / adjustments: pending. Reviewing model and date: pending.
Execution state: NOT_STARTED. Specification This file is a blank register with planned artifact names; none of the rows prove completion.
| Item | Path / URL / version | State | Verification / actual result | Verified by / date |
|---|---|---|---|---|
| corpus-scale-manifest.csv | Not created | NOT_STARTED | Pending: Every included paper has a stable identity and eligible full text. | — |
| extraction-cost-report.csv | Not created | NOT_STARTED | Pending: Success/failure counts, token or local-runtime use and measured cost are recorded. | — |
| completeness-table.csv | Not created | NOT_STARTED | Pending: Not reported, not extracted and unavailable full text remain separate categories. | — |
| Learning exercise / Peter's quiz | Not created | NOT_STARTED | Peter's actual answers required | — |
| Founder paper digest | Not created | NOT_STARTED | Source/content and access checked | — |
| Branding pack | Not created | NOT_STARTED | Claims audited; drafted/public status distinct | — |
| Opportunity actions | Not created | NOT_STARTED | Drafted/sent/replied/booked/held distinct | — |
| Question / metric | Dataset, N and unit | Split / seed / config | Command or verification method | Output path and measured value | Uncertainty / limitation |
|---|---|---|---|---|---|
| Date | Action / counterpart | Receipt or private reference | State | Next action / date |
|---|---|---|---|---|
Peter's teach-back / quiz score: not assessed. Scientific assumptions and deviations: none recorded yet. Budget allocated / spent: not assessed / no spend recorded. Missing evidence and responsible owner: pending inspection.
Do not put API keys, source full texts with restricted rights, client data or invoice personal details in a public version of this register. Keep private evidence references private.
Review status: NOT_REVIEWED. Specification · Evidence
What Peter can explain or reproduce now: not assessed. Quiz / teach-back gaps: not assessed. Measured result and limitations: pending. Best evidence link for a scientist/recruiter/buyer: pending. What failed or changed, and why: pending.
Gate requirement: No standalone gate; check this week's acceptance criteria and next gate dependencies. Gate status: NOT_STARTED. Original target week: See next gate in specs. Actual completion date / forecast: not set. Missing external evidence: pending inspection. Blocks completed / 7: not recorded. Days with commits / 7: not recorded. Sunday build log / optional Wednesday note: not recorded. Founder conversations cumulative: not recorded. Earned evidence level and proof: not assessed. Consecutive lost weeks: not assessed.
Week-specific risk to revisit: Two thousand is a target, not an inclusion rule. Automated failure is not evidence that authors omitted a field; disclose selection bias and stop runs at the agreed budget.
Continue / recover / blocked: not decided. Retain as the minimum: the completeness table. Skipped permanently with reason: none recorded. Carryover with owner, dependency and target week: none recorded. Canonical repository paths and versions: pending. Data permissions, split definitions or assumptions to preserve: pending. External action authorization that still applies: not assessed. Next physical action, exact file/function/paragraph: pending. Updates to root PROGRESS / LOG / TODAY completed: ☐
YOUR SPACE