WP44: specialist briefs E-H; compile 213 pages
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
5 changed files +52 −0
added
agents/briefs/AGENT_E_SPECIALIST.md
+13 −0
@@ -0,0 +1,13 @@ | ||
| 1 | +# Brief — Agent E (AI Research Specialist), Phase 5 | |
| 2 | + | |
| 3 | +Scope: large language models, foundation models, multimodal AI, generative AI, AI agents, reinforcement learning, machine-learning theory, deep-learning architectures, AI safety and alignment. Area directories: ai_ml. Manuscript target: Part V — The Artificial Intelligence Transformation (file manuscript/sections/part05_ai.tex — you write the | |
| 4 | +disciplinary synthesis there; for Part VII the two specialists write separate files part07a_theory.tex / part07b_security.tex | |
| 5 | +that the director merges). Follow agents/briefs/SPECIALIST_REVIEW_TEMPLATE.md and agents/briefs/WRITER_COMMON.md. | |
| 6 | +Inputs: literature_synthesis/landmarks/<area>_landmarks.csv and <area>_abstracts.jsonl for your areas; results/graph/category_counts_yearly.csv, | |
| 7 | +category_flows_yearly.csv, results/bibliometrics/cagr_by_category.csv, results/econometrics/breaks.csv (rows cat_<id>), results/emerging/*.csv, | |
| 8 | +data/processed/graph/extraction/extractions_*.jsonl (knowledge-graph extractions with provenance, if present), manuscript/references_all.bib. | |
| 9 | +Deliverables: literature_synthesis/<agent_dir>/{claims.csv, contributions.csv, review.md, open_problems.csv} AND the LaTeX section | |
| 10 | +(20–35 pages) that turns review.md into manuscript prose with \citep keys (verify new ones), figures/tables referenced by label | |
| 11 | +(do not create figures; list the ones you need in your report), numbers only through macros of manuscript/tables/numbers.tex | |
| 12 | +or by citing the result file in a footnote when no macro exists. Distinguish established / contested / speculative; never call a | |
| 13 | +preprint peer-reviewed; abstracts are not full texts. Budget: ≤ 25 lines report at the end. | |
added
agents/briefs/AGENT_F_SPECIALIST.md
+13 −0
@@ -0,0 +1,13 @@ | ||
| 1 | +# Brief — Agent F (Systems Specialist), Phase 5 | |
| 2 | + | |
| 3 | +Scope: database systems, information retrieval, distributed, cloud and edge computing, computer networks, computer architecture, AI accelerators, operating systems, quantum computing, sustainable computing. Area directories: data_distributed+hardware_emerging. Manuscript target: Part VI — Systems and Computing Infrastructure (file manuscript/sections/part06_systems.tex — you write the | |
| 4 | +disciplinary synthesis there; for Part VII the two specialists write separate files part07a_theory.tex / part07b_security.tex | |
| 5 | +that the director merges). Follow agents/briefs/SPECIALIST_REVIEW_TEMPLATE.md and agents/briefs/WRITER_COMMON.md. | |
| 6 | +Inputs: literature_synthesis/landmarks/<area>_landmarks.csv and <area>_abstracts.jsonl for your areas; results/graph/category_counts_yearly.csv, | |
| 7 | +category_flows_yearly.csv, results/bibliometrics/cagr_by_category.csv, results/econometrics/breaks.csv (rows cat_<id>), results/emerging/*.csv, | |
| 8 | +data/processed/graph/extraction/extractions_*.jsonl (knowledge-graph extractions with provenance, if present), manuscript/references_all.bib. | |
| 9 | +Deliverables: literature_synthesis/<agent_dir>/{claims.csv, contributions.csv, review.md, open_problems.csv} AND the LaTeX section | |
| 10 | +(20–35 pages) that turns review.md into manuscript prose with \citep keys (verify new ones), figures/tables referenced by label | |
| 11 | +(do not create figures; list the ones you need in your report), numbers only through macros of manuscript/tables/numbers.tex | |
| 12 | +or by citing the result file in a footnote when no macro exists. Distinguish established / contested / speculative; never call a | |
| 13 | +preprint peer-reviewed; abstracts are not full texts. Budget: ≤ 25 lines report at the end. | |
added
agents/briefs/AGENT_G_SPECIALIST.md
+13 −0
@@ -0,0 +1,13 @@ | ||
| 1 | +# Brief — Agent G (Theory Specialist), Phase 5 | |
| 2 | + | |
| 3 | +Scope: algorithms and data structures, computational complexity, programming languages, compilers, formal verification, software engineering. Area directories: theory+software_pl. Manuscript target: Part VII — Theory, Algorithms, and Security (theory half) (file manuscript/sections/part07_theory_security.tex — you write the | |
| 4 | +disciplinary synthesis there; for Part VII the two specialists write separate files part07a_theory.tex / part07b_security.tex | |
| 5 | +that the director merges). Follow agents/briefs/SPECIALIST_REVIEW_TEMPLATE.md and agents/briefs/WRITER_COMMON.md. | |
| 6 | +Inputs: literature_synthesis/landmarks/<area>_landmarks.csv and <area>_abstracts.jsonl for your areas; results/graph/category_counts_yearly.csv, | |
| 7 | +category_flows_yearly.csv, results/bibliometrics/cagr_by_category.csv, results/econometrics/breaks.csv (rows cat_<id>), results/emerging/*.csv, | |
| 8 | +data/processed/graph/extraction/extractions_*.jsonl (knowledge-graph extractions with provenance, if present), manuscript/references_all.bib. | |
| 9 | +Deliverables: literature_synthesis/<agent_dir>/{claims.csv, contributions.csv, review.md, open_problems.csv} AND the LaTeX section | |
| 10 | +(20–35 pages) that turns review.md into manuscript prose with \citep keys (verify new ones), figures/tables referenced by label | |
| 11 | +(do not create figures; list the ones you need in your report), numbers only through macros of manuscript/tables/numbers.tex | |
| 12 | +or by citing the result file in a footnote when no macro exists. Distinguish established / contested / speculative; never call a | |
| 13 | +preprint peer-reviewed; abstracts are not full texts. Budget: ≤ 25 lines report at the end. | |
added
agents/briefs/AGENT_H_SPECIALIST.md
+13 −0
@@ -0,0 +1,13 @@ | ||
| 1 | +# Brief — Agent H (Security Specialist), Phase 5 | |
| 2 | + | |
| 3 | +Scope: cybersecurity, applied cryptography, blockchain systems, privacy-preserving computation, federated learning. Area directories: security_privacy. Manuscript target: Part VII — Theory, Algorithms, and Security (security half) (file manuscript/sections/part07_theory_security.tex — you write the | |
| 4 | +disciplinary synthesis there; for Part VII the two specialists write separate files part07a_theory.tex / part07b_security.tex | |
| 5 | +that the director merges). Follow agents/briefs/SPECIALIST_REVIEW_TEMPLATE.md and agents/briefs/WRITER_COMMON.md. | |
| 6 | +Inputs: literature_synthesis/landmarks/<area>_landmarks.csv and <area>_abstracts.jsonl for your areas; results/graph/category_counts_yearly.csv, | |
| 7 | +category_flows_yearly.csv, results/bibliometrics/cagr_by_category.csv, results/econometrics/breaks.csv (rows cat_<id>), results/emerging/*.csv, | |
| 8 | +data/processed/graph/extraction/extractions_*.jsonl (knowledge-graph extractions with provenance, if present), manuscript/references_all.bib. | |
| 9 | +Deliverables: literature_synthesis/<agent_dir>/{claims.csv, contributions.csv, review.md, open_problems.csv} AND the LaTeX section | |
| 10 | +(20–35 pages) that turns review.md into manuscript prose with \citep keys (verify new ones), figures/tables referenced by label | |
| 11 | +(do not create figures; list the ones you need in your report), numbers only through macros of manuscript/tables/numbers.tex | |
| 12 | +or by citing the result file in a footnote when no macro exists. Distinguish established / contested / speculative; never call a | |
| 13 | +preprint peer-reviewed; abstracts are not full texts. Budget: ≤ 25 lines report at the end. | |
modified
manuscript/main.pdf
+0 −0
Binary file not shown.