research-wiki

name research-wiki description Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map. argument-hint [subcommand: init|ingest|sync|query|update|lint|stats] allowed-tools Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply Research Wiki: Persistent Research Knowledge Base Subcommand: $ARGUMENTS Overview The research wiki is a persistent, per-project knowledge base that accumulates structured knowledge across the entire ARIS research lifecycle. Unlike one-off literature surveys that are used and forgotten, the wiki compounds — every paper read, idea tested, experiment run, and review received makes the wiki smarter. Inspired by Karpathy's LLM Wiki pattern : compile knowledge once, keep it current, don't re-derive on every query. Core Concepts Four Entity Types Entity Directory Node ID format What it represents Paper papers/ paper:<slug> A published or preprint research paper Idea ideas/ idea:<id> A research idea (proposed, tested, or failed) Experiment experiments/ exp:<id> A concrete experiment run with results Claim claims/ claim:<id> A theorem/headline with an honest PROOF status — born via /proof-checker (see Hook 4) Typed Relationships ( graph/edges.jsonl ) Edge type From → To Meaning extends paper → paper Builds on prior work contradicts paper → paper Disagrees with results/claims addresses_gap paper|idea → gap Targets a known field gap inspired_by idea → paper Idea sourced from this paper tested_by idea|claim → exp Tested in this experiment supports exp → claim|idea Experiment confirms claim invalidates exp → claim|idea Experiment disproves claim supersedes paper → paper Newer work replaces older Edges are stored in graph/edges.jsonl only. The ## Connections section on each page is auto-generated from the graph — never hand-edit it. Capture hygiene (anti-self-poisoning) Before persisting an idea / claim / experiment note, screen it for operational noise that would harden into a self-cited falsehood (see shared-references/capture-antipatterns.md ). Resolve the helper via the canonical chain (integration-contract §2): .aris/tools/capture_filter.py → tools/capture_filter.py → $ARIS_REPO/tools/capture_filter.py (warn-and-skip if unresolved). Run python3 <capture_filter> - on the note text; if it flags env-failure / transient-error / negative-tool-claim , do NOT store it as a durable node — rewrite it to the fix / missing config / workaround , or drop it. Never store "codex/gemini/the reviewer can't do X" — that gets loaded into every future session and cited against the agent long after the real cause is gone. (The wiki's "failed ideas → anti-repeat memory" is the GOOD inverse: a class-level research finding, not operational noise.) Wiki Directory Structure research-wiki/ index.md # categorical index (auto-generated) log.md # append-only timeline gap_map.md # field gaps with stable IDs (G1, G2, ...) query_pack.md # compressed summary for /idea-creator (auto-generated, max 8000 chars) papers/ <slug>.md # one page per paper ideas/ <idea_id>.md # one page per idea experiments/ <exp_id>.md # one page per experiment claims/ <claim_id>.md # one page per testable claim graph/ edges.jsonl # materialized current relationship graph Subcommands Helper resolution (run before any subcommand below) All wiki operations except plain directory bootstrap go through a single canonical helper, tools/research_wiki.py . Skills that touch the wiki must resolve $WIKI_SCRIPT via the chain below — never hard-code python3 tools/research_wiki.py … . Hard-coding silently fails when the project does not have tools/ on disk (the post- install_aris.sh default), which is exactly the failure mode that left a real user's research-wiki/ empty for a week. cd " $(git rev-parse --show-toplevel 2>/dev/null || pwd) " || exit 1 ARIS_REPO= " ${ARIS_REPO:-$(awk -F'\t' '$1=="repo_root"{print $2; exit} ' .aris/installed-skills.txt 2>/dev/null)}" if [ -z " ${ARIS_REPO:-} " ] && [ -f " $HOME /.aris/repo" ]; then ARIS_REPO=$( cat " $HOME /.aris/repo" 2>/dev/null) || true fi WIKI_SCRIPT= ".aris/tools/research_wiki.py" [ -f " $WIKI_SCRIPT " ] || WIKI_SCRIPT= "tools/research_wiki.py" [ -f " $WIKI_SCRIPT " ] || { [ -n " ${ARIS_REPO:-} " ] && WIKI_SCRIPT= " $ARIS_REPO /tools/research_wiki.py" ; } [ -f " $WIKI_SCRIPT " ] || { echo "ERROR: research_wiki.py not found at .aris/tools/, tools/, \$ARIS_REPO/tools/, or via ~/.aris/repo." >&2 echo " Fix one of:" >&2 echo " 1. rerun 'bash tools/install_aris.sh' from the ARIS repo (creates .aris/tools symlink, refreshes ~/.aris/repo)" >&2 echo " 2. rerun 'bash tools/smart_update.sh' (refreshes ~/.aris/repo)" >&2 echo " 3. export ARIS_REPO=<path-to-ARIS-repo>" >&2 echo " 4. cp <ARIS-repo>/tools/research_wiki.py tools/" >&2 exit 1 } /research-wiki itself is the wiki tool — if the helper is missing the skill hard-fails . Caller skills that update the wiki as a side effect ( /idea-creator , /result-to-claim , /research-lit , /arxiv , /alphaxiv , /deepxiv , /semantic-scholar , /exa-search ) use the same chain but warn-and-skip instead of hard-failing — their primary output (idea list, claim verdict, paper summary) must still be delivered to the user. /research-wiki init Initialize the wiki for the current project. After resolving $WIKI_SCRIPT per the chain above: python3 " $WIKI_SCRIPT " init research-wiki/ The helper creates research-wiki/{papers,ideas,experiments,claims,graph}/ plus index.md , log.md , gap_map.md , query_pack.md , and graph/edges.jsonl , then appends "Wiki initialized" to log.md . (Earlier versions of this skill described a prose-only init that omitted query_pack.md — that drifted from the helper and made /idea-creator 's Phase 0 query-pack check fall through to a rebuild_query_pack invocation that, under the old hard-coded path, silently failed. Delegating init to the helper is the single source of truth for the wiki schema.) /research-wiki ingest "<paper title>" — arxiv: <id> Add a paper to the wiki. This subcommand is thin wrapping around python3 "$WIKI_SCRIPT" ingest_paper … , which is the single implementation of paper ingest in ARIS (per shared-references/integration-contract.md — one helper, no copies). The helper does all of: Fetch metadata — queries the arXiv Atom API when --arxiv-id is given Generate slug — <first_author_last_name><year>_<keyword> Check dedup — skip an existing page unless --update-on-exist Create page — papers/<slug>.md with the schema below Rebuild index.md and query_pack.md Append log.md Edge extraction (step 5/8 in the old manual flow) is not in ingest_paper ; do it as a follow-up with add_edge per relationship identified: # arXiv-known paper python3 " $WIKI_SCRIPT " ingest_paper research-wiki/ \ --arxiv-id 2501.12345 --thesis "One-line claim from abstract." # Venue paper with no arXiv mirror python3 " $WIKI_SCRIPT " ingest_paper research-wiki/ \ --title "Attention Is All You Need" \ --authors "Ashish Vaswani, Noam Shazeer, …" --year 2017 --venue "NeurIPS" # Manual edge after ingest python3 " $WIKI_SCRIPT " add_edge research-wiki/ \ --from "paper:vaswani2017_attention_all_you" \ --to "paper:chen2025_factorized_gap" \ -- type "extends" --evidence "Section 3.2: adapts the encoder block …" Other skills ( /research-lit , /arxiv , /alphaxiv , /deepxiv , /semantic-scholar , /exa-search ) call the same helper directly in their own last step — they don't re-route through /research-wiki ingest as a subcommand, so they don't need an LLM roundtrip. /research-wiki sync — arxiv-ids <id1>,<id2>,... Batch backfill: ingest one or more arXiv IDs that were read earlier without being ingested (e.g., because research-wiki/ was set up after the reading happened, or a hook didn't fire). # Explicit list python3 " $WIKI_SCRIPT " sync research-wiki/ \ --arxiv-ids 2310.06770,1706.03762 # From a file (one id per line, # comments ok) python3 " $WIKI_SCRIPT " sync research-wiki/ --from-file ids.txt Dedup is handled per-id; already-ingested papers are skipped silently. This is the recommended manual repair step (see integration contract §5 Backfill). sync does not scan session traces — callers declare the ids explicitly. Paper page schema (exactly what ingest_paper emits — do not handwrite alternative fields; lint will flag drift): --- type: paper node _id: paper: < slug > title: " < full title > " authors: ["First A. Author", "Second B. Author"] year: 2025 venue: "arXiv" external_ ids: arxiv: "2501.12345" doi: null s2: null tags: ["tag1", "tag2"] added: 2026-04-07T10:12:00Z --- # < full title > ## One-line thesis [Single sentence capturing the paper's core contribution] ## Problem / Gap ## Method ## Key Results ## Assumptions ## Limitations / Failure Modes ## Reusable Ingredients [Techniques, datasets, or insights that could be repurposed] ## Open Questions ## Claims [Reference claim pages: claim:C1, claim:C2, etc.] ## Connections [AUTO-GENERATED from graph/edges.jsonl — do not edit manually] ## Relevance to This Project [Why this paper matters for our specific research direction] Additionally, when the paper was ingested via --arxiv-id and the arXiv API returned an abstract, the helper appends an ## Abstract (original) section after Relevance to This Project containing the raw abstract text as a blockquote. Manual ingests (no --arxiv-id ) do not include this section. /research-wiki query "<topic>" Generate query_pack.md — a compressed, context-window-friendly summary: Fixed budget (max 8000 chars / ~2000 tokens): Section Budget Content Project direction full sections Structured extraction from RESEARCH_BRIEF.md by ## heading (Problem / Constraints / Direction / Background / Non-Goals / Domain Knowledge / Existing Results), in priority order. No per-field char cap — the 8000-char assembly loop is the only safety net. Falls back to a flat 600-char slice if the brief uses no known headings. Top 5 gaps 1200 chars From gap_map.md, ranked by: unresolved + linked ideas + failed experiments Paper clusters 1600 chars 3-5 clusters by tag overlap, 2-3 sentences each Failed ideas 1400 chars Always included — highest anti-repetition value Top papers 1800 chars 8-12 pages ranked by: linked gaps, linked ideas, centrality, relevance flag Active chains 900 chars limitation → opportunity relationship chains Open unknowns 500 chars Unresolved questions across the wiki Pruning priority (when over budget): low-ranked papers > cluster detail > chain detail. Never prune failed ideas or top gaps first. Key rule: Read from short fields only (frontmatter, one-line thesis, gap summary, failure note). Do not summarize full page bodies every time. /research-wiki update <node_id> — <field>: <value> Update a specific entity: /research-wiki update paper:chen2025 — relevance: core /research-wiki update idea:001 — outcome: negative /research-wiki update claim:C1 — status: refuted After any update: rebuild query_pack.md , update log.md . /research-wiki lint Health check the wiki: Orphan pages — entities with zero edges Stale claims — claims still status: drafted or status: unproven older than 14 days Contradictions — claims with both supports and invalidates edges Missing connections — papers sharing 2+ tags but no explicit relationship Dead ideas — stage: proposed ideas that were never tested Sparse pages — pages with 3+ empty sections Output a LINT_REPORT.md with suggested fixes. /research-wiki stats Quick overview: 📚 Research Wiki Stats