spb/firc0001_uqo

1{2 "_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.",3 "iwv_equity_lines_reported": {4  "value": 2587,5  "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",6  "status": "not reconstructible from archived artefacts"7 },8 "small_n_threshold": {9  "value": 50,10  "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",11  "status": "convention"12 },13 "brief_definition": {14  "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",15  "source": "usage in docs/implementation_audit.md and paper/sections/resolution.tex; wording to be confirmed by the authors (Stage E)",16  "status": "author to confirm"17 },18 "snippet_chars": {19  "value": 170,20  "source": "presentation rule of Table 9 (first characters of the stored snippet shown)",21  "status": "convention"22 },23 "png_dpi": {24  "value": 200,25  "source": "raster resolution of the PNG copies used by code/tex2docx",26  "status": "convention"27 },28 "acq_new_docs": {29  "value": "about 400{,}000",30  "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",31  "status": "author-reported"32 },33 "acq_hours": {34  "value": "seven",35  "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",36  "status": "author-reported"37 },38 "acq_req_per_sec": {39  "value": "17",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",41  "status": "author-reported"42 },43 "acq_nodes": {44  "value": "ten",45  "source": "docs/research_log.md 2026-10-27 (10 MacLustr nodes + 1 external gateway)",46  "status": "author-reported"47 },48 "acq_node_rate": {49  "value": "0.9",50  "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)",51  "status": "author-reported"52 },53 "acq_gateway_rate": {54  "value": "one",55  "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)",56  "status": "author-reported"57 },58 "parse_filings_per_sec": {59  "value": "100",60  "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",61  "status": "author-reported"62 },63 "parse_minutes_range": {64  "value": "five to thirteen",65  "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",66  "status": "author-reported"67 },68 "embed_minutes_range": {69  "value": "15--40",70  "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",71  "status": "author-reported"72 },73 "merge_minutes": {74  "value": "seven",75  "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",76  "status": "author-reported"77 },78 "total_cost_usd": {79  "value": "775",80  "source": "author-reported total of the October 2026 extraction (docs/research_log.md); the API invoice is not archived",81  "status": "author-reported"82 },83 "stability_sections": {84  "value": "500",85  "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)",86  "status": "protocol constant"87 },88 "stability_calls": {89  "value": "about 2{,}500",90  "source": "consolidated_review.md §6 item 11 (cost estimate of the X1/X2 protocol); not executed",91  "status": "protocol constant"92 },93 "annotation_frame_mb": {94  "value": "77",95  "source": "size of the full-text frames kept on the node (M3U96b:~/firc0001_review/frames/, N11 implemented_changes.md); not shipped",96  "status": "node artefact"97 },98 "embedding_dim": {99  "value": "384",100  "source": "all-MiniLM-L6-v2 embedding dimension (scripts/build_embeddings.py default model)",101  "status": "model constant"102 },103 "factor_anchors": {104  "value": "8",105  "source": "src/factors/anchors.py registry (thematic anchors), as described in docs/research_log.md",106  "status": "code constant"107 },108 "tenk_sections_max": {109  "value": "fourteen",110  "source": "src/parsing/section_extractor.py FORM_10K_SECTIONS (Items 1 to 9B)",111  "status": "code constant"112 },113 "tenq_sections_n": {114  "value": "seven",115  "source": "src/parsing/section_extractor.py FORM_10Q_SECTIONS",116  "status": "code constant"117 },118 "corpus_parquet_gb": {119  "value": "29.1",120  "source": "N0 schema probe (results/n0_probe, commit 7680606): parquet corpus 1,342,283 sections / 29.1 GB on the master node",121  "status": "node measurement"122 }123}