feat(research-areas): refresh all ResearchAreas pages for matrix completeness#35
Open
benjibromberg wants to merge 7 commits into
Open
feat(research-areas): refresh all ResearchAreas pages for matrix completeness#35benjibromberg wants to merge 7 commits into
benjibromberg wants to merge 7 commits into
Conversation
…ations Expand the Scaffolding stub into the full deep-dive template: thematic sections (mould/scaffold geometry surrogates; mechanical & print-quality prediction), clickable Papers.md anchors for refs #19/#20/#34/#35, a Tools and data section, an open-challenges analysis, and a Further reading footer. Every claim grounded in the cited papers' full text and passed both adversarial reviewers (citation + claim).
…ded citations Reconcile the page against its full matrix column (refs #1-3, #15-18, #21, #23-25, #58, #169-170): thematic clusters (Bayesian optimization, hybrid surrogate/evolutionary search, active learning, explainable feature selection), clickable Papers.md anchors, Tools and data and open-challenges sections, and a Further reading footer. Kanda (#16) is framed as protocol- not media-optimization per its full text. Every claim grounded in source full text via the caail Zotero library; passed both adversarial reviewers (the one flagged 'first' superlative removed).
…ded citations Reconcile against the matrix column (refs #7, #29-33, #59, #61-62): thematic sections (soft sensors; CFD-surrogate acceleration; small-data fermentation prediction; reduced metabolic models/digital twins; autonomous experimentation), clickable Papers.md anchors, Tools and data and open-challenges sections, and a Further reading footer. The microbial-vs-mammalian framing is grounded in the corpus. Ref #33's claim is held to its catalogued title (full text paywalled). Passed both adversarial reviewers; #29 (CFD error) and #31 (GA objective) corrected to match source full text.
…unded citations Expand the 3-paragraph stub to cover the full ~32-paper matrix column: single-cell characterization, biological foundation models (MLM / autoregressive / cross-species / LLM-native), perturbation-response prediction, genetic-part design, and autonomous cell-engineering agents, plus a cross-cutting section. DNABERT (#6) framed as a masked-LM model and Mathieu (#60) surfaced as the one explicitly cultivated-meat study, both per full text. Clickable Papers.md anchors, Software/Datasets/ Databases cross-links, Tools and data, open-challenges, Further reading. Passed citation review and both halves of the claim review.
…y Prediction Weave in the matrix-column papers missing from the page: a new 'Computational prediction of taste and off-flavor' section covering the Niv-lab bitterness lineage (BitterPredict #102, BitterIntense #103, BitterMatch #104, BitterMasS #105), plus texture (#171) and image-based freshness QC (#195) in the applied section. Grounded in source full text; passed citation review and claim review (model-list enumeration corrected to be non-exhaustive).
…I Evaluation Cover the matrix-column benchmarks missing from the page: a new 'General-purpose frontier benchmarks (capability context)' subsection (SWE-bench #155, GPQA #156, MMLU-Pro #157, Humanity's Last Exam #158, FrontierScience #159) framed honestly as capability context rather than biology evals, plus SciHorizon-Gene #164 (cell-state benchmarks) and MeatScan #196 (domain-specific). Cross-linked to existing Datasets/Benchmarks.md and Databases.md leaderboard entries. Passed citation review and claim review (SciHorizon-Gene axes corrected to all four, 'literature influence' restored).
Weave the missing AI Tooling-column papers into their clusters: discovery agents (Co-Scientist #153, Robin #154, ERA #166), domain-specific agents (Talk2Biomodels/T2KG #167), robot scientists (the original King 2004 Robot Scientist #182), agent infrastructure (BioContextAI #133, Aviary #160, SciAtlas #162), chemistry agents (ether0 #161, MoleCode #163), and the 'other methodology' section (Epicure #197 plus the Gu CHI human-AI-verification studies #151/#152, framed accurately as HCI studies, not agents). Also fix a pre-existing broken Further-reading anchor (Talks section lives in Talks.md, not OtherResources.md). Passed citation review and claim review (King-2004 headword corrected from 'Adam' to 'The Robot Scientist'; agent order fixed).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What & why
The
ResearchAreas/*.mddeep-dives behind thePapers.mdmatrix had drifted into two tiers: four mature pages and four near-empty stubs that covered only a fraction of their matrix columns (e.g. Cellular Engineering's column spans ~32 papers; its prose covered ~6). This PR brings all eight pages up to the mature template and reconciles each against its matrix column, so every paper assigned to a column is now represented in that column's page.How it was built (grounding + adversarial review)
Every factual claim is grounded in the paper's full text, pulled from the locally-synced caail Zotero group library (
localhost:23119) rather than abstracts — per the repo's AI-agent convention. Every drafted/edited page then passed the repo's two read-only adversarial reviewer subagents before commit (writer ≠ reviewer):caail-citation-reviewer— every(… ref #N)anchor resolves to the rightPapers.mdID with matching author/year, and everySoftware.md/Databases.md/Datasets//Talks.mdcross-link resolves.caail-claim-reviewer— every count, metric, method description, and identity claim checked against source full text.The review caught and fixed real issues, e.g. a contradicted CFD cross-validation figure (Bioprocess #29), a GA-objective drift (#31), an unsupported "first" superlative (Media #1), incomplete enumerations (Sensory #171, AIEval #164 SciHorizon-Gene), and a King-2004 headword ("Adam" → "The Robot Scientist").
Per-page coverage
Verification
Papers.md#Nanchors across the 8 pages resolve to existing IDs (0 dangling).pnpm --dir site buildsucceeds — all 8/research-areas/*pages render.Follow-ups (out of scope here — not modifying
Papers.md)Grounding surfaced a few likely matrix-placement nuances to consider in a separate PR: #34 Andrews 2025 sits in the SVM row but uses a genetic algorithm + DL surrogate (no SVM); #6 DNABERT sits in Deep Learning though it is a masked-LM model; #60 Mathieu and #145 MetaGEM are placed among foundation models but are an interactome perspective and a metabolic-model reconstruction respectively. The prose describes each accurately; the matrix cells were left untouched.
🤖 Generated with Claude Code