{
 "_about": "Values that no query over the exported data can reproduce. Each carries its source. Read by code/make_tables.py; never used as a measurement.",
 "iwv_equity_lines_reported": {
  "value": 2587,
  "source": "count reported by the build log of scripts/build_universe.py (2026-10-27); the iShares latest-holdings.csv used by the build is not archived (verified on M3U96b, Stage D feasibility report); not reconstructible",
  "status": "not reconstructible from archived artefacts"
 },
 "small_n_threshold": {
  "value": 50,
  "source": "presentation rule adopted in the Stage D plan (L1): medians resting on fewer than 50 projects with an amount are printed in grey with their N",
  "status": "convention"
 },
 "brief_definition": {
  "value": "the research-design brief, i.e. the specification of required tables, keys and validation gates against which \\texttt{docs/implementation\\_audit.md} audits the build",
  "source": "usage in docs/implementation_audit.md and paper/sections/resolution.tex; wording to be confirmed by the authors (Stage E)",
  "status": "author to confirm"
 },
 "snippet_chars": {
  "value": 170,
  "source": "presentation rule of Table 9 (first characters of the stored snippet shown)",
  "status": "convention"
 },
 "png_dpi": {
  "value": 200,
  "source": "raster resolution of the PNG copies used by code/tex2docx",
  "status": "convention"
 },
 "acq_new_docs": {
  "value": "about 400{,}000",
  "source": "author-reported run fact (docs/research_log.md, 2026-10-27/28); the orchestrator and acquisition logs are not archived with the paper; not reconstructible",
  "status": "author-reported"
 },
 "acq_hours": {
  "value": "seven",
  "source": "author-reported run fact (docs/research_log.md, 2026-10-27/28); the orchestrator and acquisition logs are not archived with the paper; not reconstructible",
  "status": "author-reported"
 },
 "acq_req_per_sec": {
  "value": "17",
  "source": "author-reported run fact (docs/research_log.md, 2026-10-27/28); the orchestrator and acquisition logs are not archived with the paper; not reconstructible",
  "status": "author-reported"
 },
 "acq_nodes": {
  "value": "ten",
  "source": "docs/research_log.md 2026-10-27 (10 MacLustr nodes + 1 external gateway)",
  "status": "author-reported"
 },
 "acq_node_rate": {
  "value": "0.9",
  "source": "author-reported run fact (docs/research_log.md, 2026-10-27/28); the orchestrator and acquisition logs are not archived with the paper; not reconstructible (requests per second per node)",
  "status": "author-reported"
 },
 "acq_gateway_rate": {
  "value": "one",
  "source": "author-reported run fact (docs/research_log.md, 2026-10-27/28); the orchestrator and acquisition logs are not archived with the paper; not reconstructible (requests per second per shard on the gateway)",
  "status": "author-reported"
 },
 "parse_filings_per_sec": {
  "value": "100",
  "source": "author-reported run fact (docs/research_log.md, 2026-10-27/28); the orchestrator and acquisition logs are not archived with the paper; not reconstructible",
  "status": "author-reported"
 },
 "parse_minutes_range": {
  "value": "five to thirteen",
  "source": "author-reported run fact (docs/research_log.md, 2026-10-27/28); the orchestrator and acquisition logs are not archived with the paper; not reconstructible",
  "status": "author-reported"
 },
 "embed_minutes_range": {
  "value": "15--40",
  "source": "author-reported run fact (docs/research_log.md, 2026-10-27/28); the orchestrator and acquisition logs are not archived with the paper; not reconstructible",
  "status": "author-reported"
 },
 "merge_minutes": {
  "value": "seven",
  "source": "author-reported run fact (docs/research_log.md, 2026-10-27/28); the orchestrator and acquisition logs are not archived with the paper; not reconstructible",
  "status": "author-reported"
 },
 "total_cost_usd": {
  "value": "775",
  "source": "author-reported total of the October 2026 extraction (docs/research_log.md); the API invoice is not archived",
  "status": "author-reported"
 },
 "stability_sections": {
  "value": "500",
  "source": "X1 protocol of peer_reviews/FIRC-0001/consolidated_review.md §6 item 11 (500 sections x 3 re-submissions); not executed (AR-LLM-1 not granted)",
  "status": "protocol constant"
 },
 "stability_calls": {
  "value": "about 2{,}500",
  "source": "consolidated_review.md §6 item 11 (cost estimate of the X1/X2 protocol); not executed",
  "status": "protocol constant"
 },
 "annotation_frame_mb": {
  "value": "77",
  "source": "size of the full-text frames kept on the node (M3U96b:~/firc0001_review/frames/, N11 implemented_changes.md); not shipped",
  "status": "node artefact"
 },
 "embedding_dim": {
  "value": "384",
  "source": "all-MiniLM-L6-v2 embedding dimension (scripts/build_embeddings.py default model)",
  "status": "model constant"
 },
 "factor_anchors": {
  "value": "8",
  "source": "src/factors/anchors.py registry (thematic anchors), as described in docs/research_log.md",
  "status": "code constant"
 },
 "tenk_sections_max": {
  "value": "fourteen",
  "source": "src/parsing/section_extractor.py FORM_10K_SECTIONS (Items 1 to 9B)",
  "status": "code constant"
 },
 "tenq_sections_n": {
  "value": "seven",
  "source": "src/parsing/section_extractor.py FORM_10Q_SECTIONS",
  "status": "code constant"
 },
 "corpus_parquet_gb": {
  "value": "29.1",
  "source": "N0 schema probe (results/n0_probe, commit 7680606): parquet corpus 1,342,283 sections / 29.1 GB on the master node",
  "status": "node measurement"
 }
}