SPB Git

spb/ai-atlas

Public
History of docs Clear filter
page 1
  1. Sat, Sep 12, 2026 3

    1. Connectors + registry on the canonical ontology (Stream B): artifacts, effort variants as configurations, benchmark families, identity helper
      …
      Hugging Face: repositories are models or artifacts (quantization / conversion / packaging) with `canonical` → base model (base_model tag or
      analysed name, family org), `family` hints, canonical licence (+license_raw), `access: gated|open` instead of openness=restricted,
      weights_available + derived openness, modalities from pipeline tags, parameter_count kept on artifacts only; converters `publish`, never `develop`.
      Leaderboards: Artificial Analysis / LiveBench / aider / SWE-bench fold effort variants ("(xhigh)", "-thinking-64k-high-effort", non-reasoning)
      into the base model with the setting in config; LiveBench categories become `livebench-<category>` benchmarks; aider well-formed rate →
      `aider-polyglot-well-formed`; AA GPQA → gpqa-diamond, τ² → Telecom; trust_level / variant / run_group on every result; bookkeeping out of config;
      free-text tags are aliases, identifiers only for trusted pinned vendor ids. New shared `connectors/_identity.py` (provider prefixes, first-party
      patterns, effort stripping with size-tier guard, family hints).
      Registry: benchmarks gain family / variant / version / family_head / canonical metric / bounds / higher_is_better / harness / comparability_note +
      14 entries (gpqa-diamond, aime-2024, swe-bench-pro, arc-agi-2, terminal-bench-2, mmteb, livebench ×7, aider-polyglot-well-formed); seed writes them
      and `variant_of` relations, org_kind from `kind`. Organisations: kind + country fields, upstage / stepfun / kwaipilot / kuaishou / thinking-machines /
      lg-ai-research / xiaomi / inclusionai entries with hub aliases. Repositories: canonical kinds, agents (agent_kind) and tools get their own entity types.
      OpenRouter: prices booked on the OpenRouter provider only (features.upstream_provider), `created` → openrouter_listed_at (no release_date),
      canonical modalities, identity helper. Provider pricing: fireworks_model_id (+ legacy scheme), org from the id, family hints.
      Labs: no hard-coded Anthropic modalities/tool constants (table-driven), Google pdf → document + google_model_id, canonical licence/status/
      capabilities/api_aliases helpers in labs/_common.py, family_model hints everywhere. arXiv/OpenReview: researchers only with an identifier
      (ORCID / OpenReview profile). GitHub/PyPI: canonical kind (+kind_raw), licence keys. docs/CONNECTORS.md rewritten on the canonical vocabulary.
      
      Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
      Simon-Pierre Boucher · 1 file +106 −21
    2. aia canonicalize: duplicates → variants → artifacts → families → licences → taxonomy → results → events → anomalies (dry-run by default, idempotent --apply); aia anomalies; aia quarantine list|release|discard
      …
      Every step plans from reads and reports counts + examples; --apply executes the plan through merge_entities / upsert_relation / a tier-2
      derived FactWriter. No deletes, snapshots untouched, a second --apply is a no-op. Optional entity scope for targeted runs and tests.
      docs/CANONICALIZATION.md documents every rule, what is never done, counting rules and how to re-run.
      
      Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
      Simon-Pierre Boucher · 1 file +176
  2. Fri, Sep 11, 2026 5

    1. Simon-Pierre Boucher · 1 file +88 −22
    2. Simon-Pierre Boucher · 1 file +31
    3. Simon-Pierre Boucher · 1 file +54
    4. Simon-Pierre Boucher · 3 files +358
Menu

Theme