1# CLAUDE.md — UQO Working Paper 4423> Mandate pasted verbatim by the principal investigator on 2026-11-02 ("fait ce projet rigoureusement"). The paste was4> truncated by the terminal inside §14 (after "The corpus is documented and reproduc"); the executing agent completed §145> from the acceptance criteria implied by §1–§13 and recorded the completion in `protocol/amendments.csv` (A-000).6> Operational decisions are in `RESEARCH_PLAN.md`; progress in `PROJECT_STATUS.md`.78## Project Identity910**Working Paper:** WP44 — UQO Working Paper Series1112**Proposed Title:** *The Post-ChatGPT Computer Science Revolution: A Comprehensive Systematic Mapping, Bibliometric Analysis, and Knowledge Graph of Computer Science Research, 2022–2026*1314**Research period:** November 30, 2022 – November 2, 20261516**Historical baseline:** January 1, 2018 – November 29, 20221718**Primary language:** English1920**Target manuscript:** 300–500 pages, including extensive technical appendices.2122**Scientific objective:** Produce one of the most comprehensive, rigorously documented, reproducible computational mappings of contemporary computer science research.2324The ambition is to build an original scientific contribution, not merely a long literature summary.2526Never claim that this is the largest review ever conducted without independently establishing that claim.2728---2930# 1. NON-NEGOTIABLE SCIENTIFIC REQUIREMENTS3132The project must:33341. Collect authentic bibliographic records from verifiable scientific databases.352. Build a unified, deduplicated corpus with persistent identifiers.363. Cover the complete breadth of computer science rather than focusing exclusively on artificial intelligence.374. Identify the most influential research contributions across the observation period.385. Analyze research trajectories, citation structures, technological convergence, and emerging paradigms.396. Distinguish theoretical contributions, methodological innovations, empirical findings, benchmarks, and engineering demonstrations.407. Critically evaluate conflicting findings and limitations.418. Produce an evidence-linked scientific manuscript.429. Make the methodology reproducible.4310. Release permissible data, code, figures, and metadata in machine-readable formats.4445**Strict integrity rules:**4647- Never fabricate references, DOI identifiers, citation counts, experiments, or results.48- Never invent paper content when only metadata is available.49- Never treat an abstract as equivalent to a full-text review.50- Never classify unverified model-generated summaries as scientific evidence.51- Never interpret temporal association as causation.52- Never describe an unpublished preprint as peer-reviewed.53- Never fabricate statistical significance.54- Record unavailable or inaccessible data explicitly.55- Maintain human-review checkpoints for scientific conclusions.5657# 2. PROJECT SCALE5859Initial engineering targets:6061- 1,000,000+ candidate bibliographic records, subject to actual availability.62- 100,000+ deeply classified research records.63- 10,000+ high-priority papers for detailed evidence extraction, subject to lawful full-text access.64- 1,000+ landmark papers for intensive critical synthesis.65- 30+ computer science research categories.66- 100+ publication-quality figures.67- 100+ analytical tables.68- 300–500 manuscript pages including appendices.6970These are planning targets, not guaranteed outcomes.7172Corpus size must never take precedence over validity, relevance, or quality.7374# 3. SCIENTIFIC DATA SOURCES7576Prioritize:7778- DBLP79- OpenAlex80- Semantic Scholar Academic Graph81- arXiv82- Crossref83- ACL Anthology84- Open-access conference proceedings85- Institutional repositories86- Publicly available benchmark repositories8788Before ingestion, verify current API specifications, rate limits, licensing, authentication, bulk-access policies, and redistribution permissions.8990Prefer official snapshots and documented bulk datasets for large-scale ingestion.9192Never bypass access controls or publisher restrictions.9394# 4. RESEARCH TAXONOMY9596Build a hierarchical taxonomy including:97981. Large Language Models992. Foundation Models1003. Multimodal AI1014. Generative AI1025. AI Agents and Autonomous Systems1036. Reinforcement Learning1047. Machine Learning Theory1058. Deep Learning Architectures1069. Computer Vision10710. Natural Language Processing10811. Speech and Audio Computing10912. Robotics11013. Human-Computer Interaction11114. Software Engineering11215. Programming Languages11316. Compilers11417. Formal Verification11518. Algorithms and Data Structures11619. Computational Complexity11720. Database Systems11821. Information Retrieval11922. Distributed Computing12023. Cloud Computing12124. Edge Computing12225. Computer Networks12326. Cybersecurity12427. Applied Cryptography12528. Blockchain Systems12629. Computer Architecture12730. Accelerators and AI Hardware12831. Operating Systems12932. Quantum Computing13033. Scientific Computing13134. Computational Biology13235. Computer Graphics13336. Privacy-Preserving Computation13437. Federated Learning13538. AI Safety and Alignment13639. Sustainable Computing13740. Autonomous Scientific Discovery138139Allow papers to belong to multiple categories.140141Construct an extensible hierarchical ontology rather than a flat keyword classification.142143# 5. SCIENTIFIC QUESTIONS144145The paper must investigate:146147**RQ1:** How has the volume and composition of computer science research evolved since November 2022?148149**RQ2:** Which subfields have experienced the strongest acceleration or structural change?150151**RQ3:** Which publications introduced the most influential methodological or theoretical contributions?152153**RQ4:** How have citation networks and interdisciplinary knowledge flows evolved?154155**RQ5:** Has the emergence of foundation models changed the relationship between previously distinct computer science disciplines?156157**RQ6:** How have research institutions, countries, and collaboration networks changed?158159**RQ7:** Which research areas demonstrate genuine breakthroughs versus incremental benchmark improvements?160161**RQ8:** Which scientific problems remain unresolved despite rapid publication growth?162163**RQ9:** How have reproducibility, open-source availability, and evaluation standards evolved?164165**RQ10:** Can computational models detect emerging scientific paradigms before they become dominant?166167# 6. RESEARCH METHODOLOGY168169Implement multiple complementary analytical approaches.170171## 6.1 Systematic Mapping172173Follow a preregistered protocol where practical.174175Use PRISMA 2020 reporting principles where applicable.176177Document:178179- Search strategies180- Database coverage181- Eligibility criteria182- Deduplication183- Screening decisions184- Full-text availability185- Exclusion reasons186- Quality assessment187- Final synthesis populations188189Separate broad bibliometric mapping from focused systematic reviews.190191## 6.2 Bibliometric Analysis192193Estimate:194195- Publication growth196- Citation growth197- Field-normalized impact198- Citation velocity199- Collaboration networks200- Institutional influence201- Country-level participation202- Venue concentration203- Citation inequality204- Research topic diversification205206Account for citation-age bias, database coverage, and preprint duplication.207208## 6.3 Semantic Research Mapping209210Use scientific document embeddings, topic modeling, hierarchical clustering, and temporal semantic analysis.211212Compare multiple embedding approaches and validate topic stability.213214Construct a dynamic semantic atlas of computer science.215216## 6.4 Scientific Knowledge Graph217218Create nodes for:219220- Papers221- Authors222- Institutions223- Venues224- Research topics225- Algorithms226- Models227- Datasets228- Benchmarks229- Scientific claims230231Create evidence-supported relationships including:232233- Cites234- Extends235- Evaluates236- Contradicts237- Reproduces238- Uses dataset239- Introduces method240- Addresses research problem241242Every inferred relationship must include provenance, confidence, and verification status.243244## 6.5 Structural Change Analysis245246Use interrupted time-series models, changepoint detection, dynamic network models, and appropriate robustness checks.247248The November 2022 boundary is a historical reference point, not proof of a causal ChatGPT effect.249250Include pre-period trend diagnostics, placebo breakpoints, alternative event dates, and sensitivity analysis.251252## 6.6 Emerging Research Detection253254Develop an original computational framework for identifying emerging scientific fields.255256Candidate signals:257258- Abnormal publication growth259- Semantic novelty260- Citation acceleration261- Interdisciplinary connectivity262- Methodological adoption263- Benchmark proliferation264- Open-source ecosystem activity265266Evaluate the framework retrospectively using temporally separated training and test periods.267268Avoid look-ahead bias.269270# 7. AUTONOMOUS RESEARCH AGENTS271272Use Claude Code subagents with explicit responsibilities.273274**Agent A — Research Director:** Coordinates the scientific program and validates deliverables.275276**Agent B — Bibliographic Acquisition:** Collects metadata through legitimate APIs and snapshots.277278**Agent C — Data Engineering:** Builds normalized databases and reproducible ingestion pipelines.279280**Agent D — Taxonomy Architect:** Constructs the computer science ontology.281282**Agent E — AI Research Specialist:** Reviews AI, machine learning, foundation models, and agents.283284**Agent F — Systems Specialist:** Reviews distributed systems, operating systems, databases, and hardware.285286**Agent G — Theory Specialist:** Reviews algorithms, complexity, formal methods, and programming languages.287288**Agent H — Security Specialist:** Reviews cybersecurity, privacy, and cryptography.289290**Agent I — Bibliometrician:** Conducts citation and collaboration analyses.291292**Agent J — Econometrician:** Designs temporal models, statistical inference, and robustness tests.293294**Agent K — Scientific Critic:** Challenges unsupported claims and methodological weaknesses.295296**Agent L — Academic Writer:** Produces publication-quality scientific prose.297298**Agent M — LaTeX Engineer:** Manages equations, references, tables, figures, and compilation.299300**Agent N — Reproducibility Auditor:** Independently validates computations and evidence.301302**Agent O — Visualization Specialist:** Creates publication-quality research graphics.303304Agents must exchange structured artifacts, not undocumented conversational summaries.305306No agent may approve its own unverified scientific findings.307308# 8. MACLUSTR INFRASTRUCTURE309310Discover the available compute nodes, CPU, GPU, memory, storage, networking, and existing services before implementation.311312Use distributed execution only when it materially improves throughput.313314Suggested stack:315316- Python317- DuckDB318- PostgreSQL319- Parquet and Apache Arrow320- Polars321- NetworkX or igraph322- Scientific embedding models323- Vector search324- PyTorch where appropriate325- LaTeX326- Git327- Containerized reproducible pipelines328329Use incremental ingestion, checkpointing, resumable processing, and content hashes.330331Preserve immutable raw-source snapshots.332333Implement job-level provenance, retry logic, and resource monitoring.334335Do not assume access to credentials or services before testing them.336337# 9. MANUSCRIPT STRUCTURE338339Produce the following major parts.340341**Part I — Introduction and Scientific Motivation**342343Explain the research problem, historical context, contributions, and scope.344345**Part II — The Evolution of Computer Science**346347Provide the conceptual and historical background needed to interpret post-2022 developments.348349**Part III — Data and Systematic Review Protocol**350351Explain corpus construction, source coverage, deduplication, eligibility, and research integrity.352353**Part IV — Computational Methodology**354355Develop the mathematical framework for bibliometrics, semantic mapping, networks, and structural-change analysis.356357**Part V — The Artificial Intelligence Transformation**358359Critically synthesize foundation models, multimodal learning, agents, reasoning, efficiency, evaluation, and safety.360361**Part VI — Systems and Computing Infrastructure**362363Review hardware, distributed systems, databases, networks, and operating systems.364365**Part VII — Theory, Algorithms, and Security**366367Review theoretical computer science, formal methods, cryptography, and cybersecurity.368369**Part VIII — Scientific Knowledge Networks**370371Analyze authors, institutions, citations, interdisciplinarity, and knowledge diffusion.372373**Part IX — Empirical Results**374375Present all verified quantitative findings with publication-quality figures and tables.376377**Part X — The Next Research Frontiers**378379Identify unresolved scientific problems, competing hypotheses, and testable research directions.380381**Part XI — Discussion and Conclusion**382383Explain contributions, limitations, generalizability, and implications for computer science.384385**Appendices A–Z**386387Include detailed taxonomy, search strategies, mathematical derivations, robustness checks, data dictionaries, supplementary tables, figure documentation, and reproducibility instructions.388389Do not pad the manuscript to meet page targets.390391# 10. ACADEMIC WRITING STANDARD392393Write in formal, precise, technically sophisticated academic English.394395Target the scholarly standards of leading computer science journals and major survey venues.396397The writing must:398399- Critically compare competing approaches.400- Distinguish established findings from speculation.401- Present meaningful mathematical notation.402- Explain assumptions and limitations.403- Integrate citations into the scientific argument.404- Avoid promotional or exaggerated language.405- Avoid repetitive AI-generated prose.406- Include genuine original synthesis.407408All references must be resolved to verified bibliographic records.409410# 11. FIGURES AND TABLES411412Create publication-quality visualizations including:413414- Annual and monthly publication trends415- Research domain growth416- Dynamic topic maps417- Citation networks418- Scientific influence distributions419- Institutional collaboration networks420- Country-level research activity421- Topic emergence and decline422- Interdisciplinary knowledge flows423- Methodological genealogy diagrams424- Structural-break estimates425- Benchmark evolution426- Research reproducibility indicators427- Uncertainty and robustness visualizations428429All figures must be generated from reproducible scripts.430431Use vector formats when appropriate.432433No decorative or fabricated empirical graphics.434435# 12. OUTPUT STRUCTURE436437Create:438439```text440WP44/441├── CLAUDE.md442├── README.md443├── manuscript/444│ ├── main.tex445│ ├── sections/446│ ├── appendices/447│ └── references.bib448├── data/449│ ├── raw/450│ ├── processed/451│ └── metadata/452├── ingestion/453├── taxonomy/454├── embeddings/455├── knowledge_graph/456├── bibliometrics/457├── econometrics/458├── systematic_review/459├── literature_synthesis/460├── figures/461├── tables/462├── experiments/463├── agents/464├── tests/465├── reports/466└── reproducibility/467```468469# 13. EXECUTION PHASES470471**Phase 0 — Feasibility and Scientific Protocol**472473Audit available infrastructure, verify data sources, define inclusion criteria, and prepare the research protocol.474475**Phase 1 — Bibliographic Corpus**476477Build ingestion pipelines and create the deduplicated research database.478479**Phase 2 — Scientific Taxonomy**480481Classify the corpus and validate the ontology using manually reviewed samples.482483**Phase 3 — Knowledge Graph**484485Construct citation, semantic, institutional, and methodological relationships.486487**Phase 4 — Statistical Research**488489Estimate bibliometric trends, network measures, and temporal models.490491**Phase 5 — Critical Literature Synthesis**492493Generate evidence-grounded disciplinary reviews and reconcile conflicting findings.494495**Phase 6 — Original Scientific Contribution**496497Develop and validate the emerging-research detection framework.498499**Phase 7 — Manuscript Construction**500501Write the full LaTeX paper and comprehensive appendices.502503**Phase 8 — Independent Scientific Audit**504505Use independent review agents to verify citations, statistical results, claims, equations, and reproducibility.506507**Phase 9 — Final Research Release**508509Compile the final PDF, archive reproducibility artifacts, prepare the dataset documentation, and produce a release-ready research repository.510511Do not advance to the next phase until required validation checks pass.512513# 14. ACCEPTANCE CRITERIA514515The project is complete only when:516517- The corpus is documented and reproduc[ible — paste truncated here. Completed by the executing agent (A-000):]518- The corpus is documented and reproducible from the immutable raw snapshots, with record counts at every PRISMA stage.519- Every quantitative claim in the manuscript traces to a script, an input artefact and a result file.520- Every reference in `references.bib` resolves to a verified bibliographic record (DOI, arXiv ID or OpenAlex ID checked).521- The taxonomy has been validated on a manually reviewed sample with reported agreement statistics.522- Structural-change results include pre-trend diagnostics, placebo breakpoints and sensitivity analyses.523- The emerging-research detection framework has been evaluated out-of-time without look-ahead.524- Independent audit agents have verified citations, statistics, equations and reproducibility, and their reports are archived.525- The LaTeX manuscript compiles without unresolved references, and the release repository contains code, metadata,526 figures, tables and documentation under an explicit licence.527- Human-review checkpoints for scientific conclusions are recorded and any unreviewed conclusion is flagged as such.528