L1: de-literalise make_tables.py/export_stats.py; generated notes, macros (numbers.tex), prompt/regex from the snapshot, Table 12 longtable, figures (integer ticks, y from 0, per-issuer panel); stats.json never rewritten

Items: FIRC0001-AI_C-11, FIRC0001-ECON-09, FIRC0001-EDIT-17, FIRC0001-DATA-15, FIRC0001-ECON-13, FIRC0001-EDIT-14, FIRC0001-ADVE-13, FIRC0001-DATA-10, FIRC0001-EDIT-23, FIRC0001-ADVE-16, FIRC0001-AI_C-17, FIRC0001-ECON-18, FIRC0001-LITE-12, FIRC0001-DATA-01, FIRC0001-THEO-13; L2/L3 fragments: FIRC0001-ADVE-10, FIRC0001-AI_C-10, FIRC0001-DATA-06, FIRC0001-ECON-07, FIRC0001-EDIT-13, FIRC0001-LITE-08, FIRC0001-THEO-11, FIRC0001-THEO-12, FIRC0001-AI_C-15, FIRC0001-DATA-07, FIRC0001-EDIT-21, FIRC0001-AI_C-16, FIRC0001-EDIT-22, FIRC0001-EDIT-24, FIRC0001-LITE-07, FIRC0001-ADVE-06.
export_stats.py edited only (run by N13 on M3U96b): run parameters from logs/ledger, new keys and dumps, read_only + threads=4.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

Simon-Pierre Boucher committed 23 h ago (Nov 5, 2026) parent 7fde8a2 Browse files

40 changed files +2,735 −157

modified code/export_stats.py +115 −16

		`@@ -1,24 +1,54 @@`
1	1	"""Export every number used in the working paper from the two DuckDB databases (run on the master node).
2	2
3		−Usage (on M3U96b): ~/UQO_RESEARCH_DB/.venv/bin/python export_stats.py ~/UQO_RESEARCH_DB <out_dir>
4		−Writes CSV files (one per table) + stats.json. Nothing is hand-edited downstream.
	3	+Usage (on M3U96b): nice -n 10 env OMP_NUM_THREADS=4 ~/UQO_RESEARCH_DB/.venv/bin/python -I export_stats.py ~/UQO_RESEARCH_DB <out_dir> [--skip-slow]
	4	+Writes CSV files (one per table) + stats.json. Nothing is hand-edited downstream, and no number is typed in this file:
	5	+every value is a query result, a log/regex read (None when absent) or an explicit None flagged in the output.
	6	+Both connections are opened read_only=True; threads=4; nothing is written under the repository.
	7	+--skip-slow omits the candidate-gate scan over the whole ledger (gate_pass_total / calls_by_form) and the bootstrap.
5	8	"""
6		−import csv, json, sys
	9	+import csv, json, random, re, statistics, sys
	10	+from datetime import timedelta
7	11	from pathlib import Path
8	12	import duckdb
9	13
10		−root = Path(sys.argv[1]); out = Path(sys.argv[2]); out.mkdir(parents=True, exist_ok=True)
	14	+SEED = 20261105
	15	+BOOT_B = 1000
	16	+args = [a for a in sys.argv[1:] if not a.startswith("--")]
	17	+SKIP_SLOW = "--skip-slow" in sys.argv
	18	+root = Path(args[0]); out = Path(args[1]); out.mkdir(parents=True, exist_ok=True)
11	19	edgar = duckdb.connect(str(root / "data/duckdb/edgar_research.duckdb"), read_only=True)
12	20	spid = duckdb.connect(str(root / "project-db/data/db/spid.duckdb"), read_only=True)
	21	+for con in (edgar, spid):
	22	+ con.execute("SET threads=4"); con.execute("SET memory_limit='16GB'")
13	23	# the src_* views stored in spid.duckdb point to the master node's parquet corpus (valid here)
14	24	S = {}
15	25
	26	+
16	27	def dump(name, con, sql):
17	28	cur = con.execute(sql); cols = [d[0] for d in cur.description]; rows = cur.fetchall()
18	29	with open(out / f"{name}.csv", "w", newline="") as f:
19	30	w = csv.writer(f); w.writerow(cols); w.writerows(rows)
20	31	print(f"{name}: {len(rows)} rows"); return rows
21	32
	33	+
	34	+def one(con, sql):
	35	+ return con.execute(sql).fetchone()[0]
	36	+
	37	+
	38	+def grep_first(path, pattern, cast=str):
	39	+ """First regex group found in a log file, or None when the file or the pattern is absent."""
	40	+ p = root / path
	41	+ if not p.exists(): return None
	42	+ m = re.search(pattern, p.read_text(errors="replace"))
	43	+ return cast(m.group(1)) if m else None
	44	+
	45	+
	46	+def grep_count(path, pattern):
	47	+ p = root / path
	48	+ if not p.exists(): return None
	49	+ return len(re.findall(pattern, p.read_text(errors="replace")))
	50	+
	51	+
22	52	# ---- universe reconciliation -------------------------------------------------
23	53	uni = json.load(open(root / "data/metadata/universe.json"))
24	54	ru = json.load(open(root / "data/metadata/russell3000_constituents.json"))
		`@@ -31,10 +61,15 @@ S["universe"] = {"built_at": uni["built_at"], "n": uni["count"], "n_sp500": uni[`
31	61	"both": sum(1 for c in uni["constituents"] if c["in_sp500"] and c["in_russell3000"]),
32	62	"sp_only": sum(1 for c in uni["constituents"] if c["in_sp500"] and not c["in_russell3000"]),
33	63	"ru_only": sum(1 for c in uni["constituents"] if not c["in_sp500"] and c["in_russell3000"])}
34		−S["issuers_with_filings"] = edgar.execute("select count(distinct cik) from filings").fetchone()[0]
35		−S["issuers_without_filings"] = edgar.execute("select count(*) from companies c where not exists (select 1 from filings f where f.cik=c.cik)").fetchone()[0]
	64	+S["sp500_ciks"] = len({c["cik"] for c in sp["constituents"]}) if "constituents" in sp else None
	65	+# the iShares holdings file is not archived with the repository: the equity-line count is not reconstructible here
	66	+holdings = sorted((root / "data/metadata").glob("holding"))
	67	+S["iwv_equity_lines"] = None if not holdings else sum(1 for _ in open(holdings[0])) # replaced by a parse if the file is ever archived
	68	+S["iwv_holdings_file_archived"] = bool(holdings)
	69	+S["issuers_with_filings"] = one(edgar, "select count(distinct cik) from filings")
	70	+S["issuers_without_filings"] = one(edgar, "select count(*) from companies c where not exists (select 1 from filings f where f.cik=c.cik)")
36	71	dump("issuers_without_filings", edgar, "select ticker, company_name, sector, in_sp500, in_russell3000 from companies c where not exists (select 1 from filings f where f.cik=c.cik) order by ticker")
37		−S["issuers_with_projects"] = spid.execute("select count(distinct cik) from projects").fetchone()[0]
	72	+S["issuers_with_projects"] = one(spid, "select count(distinct cik) from projects")
38	73
39	74	# ---- corpus -------------------------------------------------------------------
40	75	dump("filings_by_form", edgar, "select form_type, count(*) n, min(filing_date) first, max(filing_date) last, round(sum(file_size_bytes)/1e9,1) gb from filings group by 1 order by 1")
		`@@ -44,23 +79,70 @@ dump("parse_status", edgar, "select form_type, parse_status, count(*) n from fil`
44	79	dump("sections_by_form", edgar, "select f.form_type, count(*) sections, round(avg(s.word_count)) mean_words, round(median(s.word_count)) median_words from filing_sections s join filings f using(accession_number) group by 1 order by 1")
45	80	dump("sections_10k_by_item", edgar, "select s.section_name, count(*) n, round(median(s.word_count)) median_words from filing_sections s join filings f using(accession_number) where f.form_type='10-K' group by 1 order by 2 desc")
46	81	S["chunks"] = edgar.execute("select count(*), round(avg(word_count),1) from filing_chunks").fetchone()
47		−S["embeddings"] = edgar.execute("select count(*) from embeddings_metadata").fetchone()[0]
48		−S["sections_total"] = edgar.execute("select count(*) from filing_sections").fetchone()[0]
49		−S["filings_total"] = edgar.execute("select count(*) from filings").fetchone()[0]
50		−S["raw_gb"] = edgar.execute("select round(sum(file_size_bytes)/1e9,1) from filings").fetchone()[0]
	82	+S["embeddings"] = one(edgar, "select count(*) from embeddings_metadata")
	83	+S["sections_total"] = one(edgar, "select count(*) from filing_sections")
	84	+S["filings_total"] = one(edgar, "select count(*) from filings")
	85	+S["raw_gb"] = one(edgar, "select round(sum(file_size_bytes)/1e9,1) from filings")
	86	+S["filing_date_range"] = [str(x) for x in edgar.execute("select min(filing_date), max(filing_date) from filings").fetchone()]
	87	+S["annual_panel_firms"] = one(edgar, "select count(distinct cik) from annual_panel")
51	88	dump("companies_by_sector", edgar, "select sector, count() n, count() filter (where in_sp500) sp500, count(*) filter (where in_russell3000) russell from companies group by 1 order by 2 desc")
52	89	dump("companies_by_shard", edgar, "select shard_node, count(*) n from companies group by 1 order by 1")
53	90	dump("factor_tables", edgar, "select 'chunk_scores' t, count() n from chunk_scores union all select 'filing_scores', count() from filing_scores union all select 'annual_panel', count() from annual_panel union all select 'quarterly_panel', count() from quarterly_panel")
54	91
55	92	# ---- extraction ledger --------------------------------------------------------
56	93	dump("ledger_by_form", spid, "select v.form_type, count() sections, count() filter (where e.n_mentions>0) with_mentions, sum(e.n_mentions) mentions, count(distinct v.cik) issuers from extracted_sections e join v_sections v using(section_id) group by 1 order by 1")
57		−S["ledger_total"] = spid.execute("select count(*) from extracted_sections").fetchone()[0]
	94	+S["ledger_total"] = one(spid, "select count(*) from extracted_sections")
58	95	dump("ledger_10k_items", spid, "select v.section_name, count(*) n, sum(e.n_mentions) mentions from extracted_sections e join v_sections v using(section_id) where v.form_type='10-K' group by 1 order by 2 desc")
59	96	dump("ledger_10q_items", spid, "select v.section_name, count(*) n, sum(e.n_mentions) mentions from extracted_sections e join v_sections v using(section_id) where v.form_type='10-Q' group by 1 order by 2 desc")
	97	+S["ledger_10k_mdna_median_words"] = one(spid, "select round(median(v.word_count)) from extracted_sections e join v_sections v using(section_id) where v.form_type='10-K' and v.section_name='md_and_a'")
	98	+S["ledger_backends"] = [r[0] for r in spid.execute("select distinct backend from extracted_sections order by 1").fetchall()]
	99	+# the two runs are separated by the backfilled block: every June row was re-inserted at one timestamp (min(extracted_at))
	100	+t0, t1 = spid.execute("select min(extracted_at), max(extracted_at) from extracted_sections").fetchone()
	101	+S["extracted_at_range"] = [str(t0), str(t1)]
	102	+S["backfilled_rows"], S["backfilled_mentions"] = spid.execute("select count(*), sum(n_mentions) from extracted_sections where extracted_at = (select min(extracted_at) from extracted_sections)").fetchone()
	103	+S["backfilled_rows_under_30_words"] = one(spid, "select count(*) from extracted_sections e join v_sections v using(section_id) where e.extracted_at = (select min(extracted_at) from extracted_sections) and v.word_count < 30")
	104	+S["october_rows"] = S["ledger_total"] - S["backfilled_rows"]
	105	+# outage = the largest gap between consecutive distinct ledger timestamps of the October run (no window is typed here)
	106	+gap = spid.execute("""with t as (select distinct extracted_at ts from extracted_sections where extracted_at > (select min(extracted_at) from extracted_sections)),
	107	+ g as (select ts, lag(ts) over (order by ts) prev from t) select prev, ts, epoch(ts - prev)/3600.0 h from g where prev is not null order by h desc limit 1""").fetchone()
	108	+S["outage"] = {"start": str(gap[0]), "end": str(gap[1]), "hours": round(gap[2], 2)} if gap else None
	109	+wall_h = (t1 - t0).total_seconds() / 3600.0
	110	+S["october_wall_clock_hours"] = round(wall_h, 2)
	111	+S["october_effective_sections_per_second"] = round(S["october_rows"] / ((wall_h - (gap[2] if gap else 0.0)) * 3600.0), 1)
	112	+S["conf_exact_default_count"] = one(spid, "select count(*) from project_mentions where round(confidence,3) = 0.600")
	113	+S["conf_min_by_run"] = spid.execute("""select min(m.confidence) filter (where e.extracted_at = (select min(extracted_at) from extracted_sections)),
	114	+ min(m.confidence) filter (where e.extracted_at > (select min(extracted_at) from extracted_sections)) from project_mentions m join extracted_sections e using(section_id)""").fetchone()
	115	+S["amount_raw_deviations"] = one(spid, "select count(*) from project_mentions where amount_usd is not null and amount_raw <> '$' \|\| format('{:,.0f}', amount_usd)")
	116	+dump("ledger_collisions", spid, """select e.section_id, e.accession_number, e.n_mentions ledger_n, count(m.mention_id) stored_n, e.n_mentions - count(m.mention_id) overwritten
	117	+ from extracted_sections e left join project_mentions m using(section_id) group by 1,2,3 having e.n_mentions > count(m.mention_id) order by 5 desc, 1""")
	118	+dump("cohort_by_run", spid, """select case when e.extracted_at = (select min(extracted_at) from extracted_sections) then 'backfilled (June run)' else 'October run' end run,
	119	+ v.form_type, count() sections, count() filter (where e.n_mentions>0) with_mentions, sum(e.n_mentions) mentions, count(distinct v.cik) issuers
	120	+ from extracted_sections e join v_sections v using(section_id) group by 1,2 order by 1,2""")
	121	+# run parameters are read from the logs (regex); None when the log does not carry them
	122	+S["spid_runs"] = {
	123	+ "sp500_run": {"log": "project-db/logs/extract.log", "date": grep_first("project-db/logs/extract.log", r"(\d{4}-\d{2}-\d{2})"),
	124	+ "model": grep_first("project-db/logs/extract.log", r"(gpt-4o-mini[\w-]*)"), "workers": grep_first("project-db/logs/extract.log", r"workers=(\d+)", int),
	125	+ "batch": grep_first("project-db/logs/extract.log", r"batch=(\d+)", int), "ciks": grep_first("project-db/logs/extract.log", r"CIKs total=(\d+)", int),
	126	+ "sections_logged": grep_first("project-db/logs/extract.log", r"sections=(\d+)", int), "ledger_rows_backfilled": S["backfilled_rows"],
	127	+ "mentions_backfilled": S["backfilled_mentions"], "llm_call_failed": grep_count("project-db/logs/extract.log", r"LLM call failed")},
	128	+ "russell_run": {"log": "data/logs/spid_extract.log", "model": grep_first("data/logs/spid_extract.log", r"(gpt-4o-mini-\d{4}-\d{2}-\d{2})"),
	129	+ "workers": grep_first("data/logs/spid_extract.log", r"workers=(\d+)", int), "ledger_rows": S["october_rows"],
	130	+ "extracted_at_first": str(t0), "extracted_at_last": str(t1), "llm_call_failed": grep_count("data/logs/spid_extract.log", r"LLM call failed"),
	131	+ "section_failed": grep_count("data/logs/spid_extract.log", r"section failed")}}
	132	+if not SKIP_SLOW:
	133	+ # true call denominator: sections whose text passes the candidate gate (llm.py returns [] before any call otherwise)
	134	+ gate = r"\b(project\|initiative\|program\|invest\|expan\|construct\|build\|launch\|develop\|deploy\|implement\|acqui\|partner\|facilit\|capacity\|capital\|migrat\|transform\|pipeline\|plant\|data ?cent\|automat\|sustainab\|renewable\|restructur)\w*"
	135	+ cb = dump("calls_by_form", spid, f"""select v.form_type, count() ledgered, count() filter (where regexp_matches(v.text, '{gate}', 'i')) gate_pass,
	136	+ count(*) filter (where regexp_matches(v.text, '{gate}', 'i') and e.n_mentions>0) productive
	137	+ from extracted_sections e join v_sections v using(section_id) group by 1 order by 1""")
	138	+ S["gate_pass_total"] = sum(r[2] for r in cb)
	139	+ S["calls_by_form"] = {r[0]: r[2] for r in cb}
	140	+else:
	141	+ S["gate_pass_total"] = None; S["calls_by_form"] = None
60	142
61	143	# ---- mentions / projects ------------------------------------------------------
62		−S["mentions"] = spid.execute("select count(*) from project_mentions").fetchone()[0]
63		−S["projects"] = spid.execute("select count(*) from projects").fetchone()[0]
	144	+S["mentions"] = one(spid, "select count(*) from project_mentions")
	145	+S["projects"] = one(spid, "select count(*) from projects")
64	146	dump("mentions_by_form", spid, "select form_type, count(*) n, round(avg(confidence),3) mean_conf from project_mentions group by 1 order by 2 desc")
65	147	dump("mentions_by_year", spid, "select extract(year from filing_date)::int yr, count(*) mentions, count(distinct cik) issuers from project_mentions group by 1 order by 1")
66	148	dump("projects_by_type", spid, "select project_type, count() n, round(100.0count()/(select count() from projects),1) pct, count(*) filter (where total_amount_usd is not null) with_amount, round(median(total_amount_usd)/1e6,1) median_amount_musd, round(avg(n_mentions),2) mean_mentions from projects group by 1 order by 2 desc")
		`@@ -72,13 +154,30 @@ dump("projects_per_issuer", spid, "select quantile_cont(n, [0.1,0.25,0.5,0.75,0.`
72	154	dump("projects_by_index", spid, "select co.in_sp500, co.in_russell3000, count(*) projects, count(distinct p.cik) issuers from projects p join src_companies co on p.cik=co.cik group by 1,2")
73	155	dump("confidence_dist", spid, "select round(confidence,1) conf, count(*) n from project_mentions group by 1 order by 1")
74	156	dump("amount_dist", spid, "select quantile_cont(total_amount_usd, [0.1,0.25,0.5,0.75,0.9,0.99]) q, count(*) n, round(sum(total_amount_usd)/1e9,1) sum_gusd from projects where total_amount_usd is not null")
	157	+S["amount_total_median_musd"] = one(spid, "select round(median(total_amount_usd)/1e6,1) from projects where total_amount_usd is not null")
	158	+S["amount_max"] = one(spid, "select max(total_amount_usd) from projects")
	159	+S["amount_ge_50b"] = one(spid, "select count(*) from projects where total_amount_usd >= 50e9")
	160	+S["amount_ge_1t"] = one(spid, "select count(*) from projects where total_amount_usd >= 1e12")
	161	+S["amount_le_zero"] = one(spid, "select count(*) from projects where total_amount_usd <= 0")
75	162	dump("duration", spid, "select case when last_year is null or first_year is null then 'unknown' when last_year=first_year then '0' when last_year-first_year<=2 then '1-2' when last_year-first_year<=5 then '3-5' else '>5' end span_years, count(*) n from projects group by 1 order by 1")
76	163	dump("kg", spid, "select 'nodes' k, node_type, count() n from kg_nodes group by 1,2 union all select 'edges', rel, count() from kg_edges group by 1,2 order by 1,3 desc")
77	164	dump("top_issuers", spid, "select ticker, company_name, sector, count(*) projects from projects group by 1,2,3 order by 4 desc limit 15")
78	165	dump("example_provenance", spid, "select p.project_id, p.ticker, p.project_name, p.project_type, p.status, p.total_amount_usd, p.n_mentions, p.first_seen, p.last_seen, t.accession_number, t.filing_date, t.form_type, t.status m_status, t.amount_usd, t.confidence, t.snippet from projects p join project_timeline t using(project_id) where p.n_mentions between 4 and 8 and p.total_amount_usd > 5e8 and p.project_type in ('plant_construction','data_center') order by p.n_filings desc, p.project_id, t.filing_date limit 24")
79	166	S["mentions_fields"] = spid.execute("select count() filter (where amount_usd is not null) amt, count() filter (where len(locations)>0) loc, count() filter (where len(technologies)>0) tech, count() filter (where len(partners)>0) partner, count() filter (where len(years)>0) yrs, count() from project_mentions").fetchone()
80	167	S["projects_fields"] = spid.execute("select count() filter (where total_amount_usd is not null), count() filter (where canonical_location is not null), count() filter (where len(technologies)>0), count() from projects").fetchone()
81		−S["spid_runs"] = {"sp500_run": "2026-06 (gpt-4o-mini, 16 workers, 153,894 sections)", "russell_run": "2026-10-27/28 (gpt-4o-mini-2024-07-18, 48 workers, 968,134 sections)"}
82		−S["extracted_at_range"] = [str(x) for x in spid.execute("select min(extracted_at), max(extracted_at) from extracted_sections").fetchone()]
	168	+S["fiscal_year_null_mentions"] = one(spid, "select count(*) from project_mentions where fiscal_year is null")
	169	+
	170	+# ---- bootstrap CI of the per-type median amount (percentile bootstrap, seeded) ----
	171	+if not SKIP_SLOW:
	172	+ rng = random.Random(SEED)
	173	+ with open(out / "projects_by_type_ci.csv", "w", newline="") as f:
	174	+ w = csv.writer(f); w.writerow(["project_type", "n", "median", "ci_low", "ci_high", "B", "seed"])
	175	+ for ptype, in spid.execute("select project_type from projects group by 1 order by count(*) desc").fetchall():
	176	+ vals = [r[0] for r in spid.execute("select total_amount_usd from projects where total_amount_usd is not null and project_type = ?", [ptype]).fetchall()]
	177	+ if not vals: w.writerow([ptype, 0, None, None, None, BOOT_B, SEED]); continue
	178	+ meds = sorted(statistics.median(rng.choices(vals, k=len(vals))) for _ in range(BOOT_B))
	179	+ w.writerow([ptype, len(vals), statistics.median(vals), meds[int(0.025 * BOOT_B)], meds[min(int(0.975 * BOOT_B), BOOT_B - 1)], BOOT_B, SEED])
	180	+ print("projects_by_type_ci: written")
	181	+
83	182	json.dump(S, open(out / "stats.json", "w"), indent=2, default=str)
84	183	print(json.dumps(S, indent=1, default=str)[:3000])

modified code/make_tables.py +573 −61

		`@@ -1,25 +1,82 @@`
1		−"""Build every LaTeX table and figure of the paper from data/*.csv (no hand-typed numbers)."""
2		−import csv, json
	1	+"""Build every LaTeX table, figure and inline-number macro of the paper from the exported data.
	2	+
	3	+Inputs (read-only):
	4	+ data/*.csv, data/stats.json exports of code/export_stats.py (node, DuckDB read-only)
	5	+ data/documented_inputs.json the few values that no query can reproduce (each with its source)
	6	+ data/datamodel_audit.csv rows of the data-model audit table (Appendix C)
	7	+ code/audit/spid_snapshot/{llm,rules,taxonomy}.py frozen pipeline snapshot (prompt, gate regex, taxonomy)
	8	+ results/*/.csv Stage D audit outputs (optional; tables are skipped when absent)
	9	+Outputs:
	10	+ paper/tables/.tex, paper/figures/.pdf, paper/tables/numbers.tex (SPID... macros for inline numbers),
	11	+ results/inline_numbers.json (macro -> value, source, formula), data/example_project.json.
	12	+No numeric literal is typed in this file; stats.json is never rewritten.
	13	+Usage: python3 -I code/make_tables.py [--out SCRATCH_DIR] (--out is used by tests/)
	14	+"""
	15	+import argparse, ast, csv, json, math, re, sys
3	16	from pathlib import Path
4	17	import matplotlib
5	18	matplotlib.use("Agg")
6	19	import matplotlib.pyplot as plt
	20	+from matplotlib.ticker import MaxNLocator
7	21
8	22	ROOT = Path(__file__).resolve().parent.parent
9		−D, T, F = ROOT / "data", ROOT / "paper" / "tables", ROOT / "paper" / "figures"
10		−T.mkdir(exist_ok=True); F.mkdir(exist_ok=True)
11		−S = json.load(open(D / "stats.json"))
	23	+ap = argparse.ArgumentParser()
	24	+ap.add_argument("--out", default=None, help="scratch root; tables/, figures/, results/ are created under it (tests)")
	25	+ARGS = ap.parse_args()
	26	+D = ROOT / "data"
	27	+R = ROOT / "results"
	28	+SNAP = ROOT / "code" / "audit" / "spid_snapshot"
	29	+OUT = Path(ARGS.out) if ARGS.out else ROOT / "paper"
	30	+T, F = OUT / "tables", OUT / "figures"
	31	+RES_OUT = (Path(ARGS.out) / "results") if ARGS.out else R
	32	+DATA_OUT = (Path(ARGS.out) / "data") if ARGS.out else D
	33	+for p in (T, F, RES_OUT, DATA_OUT):
	34	+ p.mkdir(parents=True, exist_ok=True)
	35	+
	36	+S = json.load(open(D / "stats.json")) # read-only
	37	+DI = json.load(open(D / "documented_inputs.json")) if (D / "documented_inputs.json").exists() else {}
	38	+INLINE = {} # macro -> {value, source, formula}
12	39
13		−def rows(name):
14		− with open(D / f"{name}.csv") as f:
	40	+
	41	+def rows(name, base=D):
	42	+ with open(base / f"{name}.csv", newline="") as f:
15	43	return list(csv.DictReader(f))
16	44
	45	+
17	46	def n(x, d=0):
18	47	x = float(x)
19	48	return f"{x:,.{d}f}".replace(",", "{,}")
20	49
	50	+
21	51	def w(name, body):
22		− (T / name).write_text(body); print("table", name)
	52	+ (T / name).write_text(body if body.endswith("\n") else body + "\n")
	53	+ print("table", name)
	54	+
	55	+
	56	+def esc(s):
	57	+ return (str(s).replace("\\", "\\textbackslash{}").replace("&", "\\&").replace("%", "\\%")
	58	+ .replace("$", "\\$").replace("_", "\\_").replace("#", "\\#"))
	59	+
	60	+
	61	+_DIGITS = {"0": "Zero", "1": "One", "2": "Two", "3": "Three", "4": "Four", "5": "Five", "6": "Six", "7": "Seven", "8": "Eight", "9": "Nine"}
	62	+
	63	+
	64	+def macro(name, value, source, formula):
	65	+ """Register an inline number: \\SPID<name> in paper/tables/numbers.tex (control sequences allow letters only)."""
	66	+ name = "".join(_DIGITS.get(ch, ch) for ch in name if ch.isalnum())
	67	+ INLINE[name] = {"value": value, "source": source, "formula": formula}
	68	+
	69	+
	70	+def di(key):
	71	+ """Documented input (value + source) or None."""
	72	+ e = DI.get(key)
	73	+ return None if e is None else e.get("value")
	74	+
	75	+
	76	+def di_source(key):
	77	+ e = DI.get(key)
	78	+ return "" if e is None else e.get("source", "")
	79	+
23	80
24	81	LAB = {"ma_integration": "M\\&A / integration", "capex_program": "Capital expenditure program", "partnership": "Strategic partnership",
25	82	"geographic_expansion": "Geographic expansion", "plant_construction": "Plant / site construction", "cost_reduction": "Cost reduction / restructuring",
		`@@ -29,16 +86,30 @@ LAB = {"ma_integration": "M\\&A / integration", "capex_program": "Capital expend`
29	86	"sustainability": "Sustainability / ESG", "supply_chain": "Supply-chain initiative", "data_center": "Data center", "energy_transition": "Energy transition / renewables",
30	87	"ai_initiative": "AI / ML initiative", "automation": "Automation / robotics", "cloud_migration": "Cloud migration"}
31	88
32		−# ---- Table: universe reconciliation ----
	89	+# ---- Table 1: universe reconciliation ----------------------------------------
33	90	U = S["universe"]
	91	+iwv_lines = S.get("iwv_equity_lines") # exported by export_stats.py when the holdings file is archived
	92	+iwv_src = "stats.json:iwv_equity_lines (export_stats.py)"
	93	+if iwv_lines is None:
	94	+ iwv_lines = di("iwv_equity_lines_reported"); iwv_src = di_source("iwv_equity_lines_reported")
	95	+if iwv_lines is not None:
	96	+ row1_label = (f"iShares IWV holdings file, equity lines with a ticker (as of {U['russell_holdings_as_of']}); "
	97	+ "count reported by the build log, source file not archived" if "not archived" in iwv_src
	98	+ else f"iShares IWV holdings file, equity lines with a ticker (as of {U['russell_holdings_as_of']})")
	99	+ row1_val = n(iwv_lines)
	100	+else:
	101	+ row1_label = f"iShares IWV holdings file, equity lines with a ticker (as of {U['russell_holdings_as_of']}); source file not archived"
	102	+ row1_val = "--"
	103	+macro("iwvEquityLines", row1_val, iwv_src, "documented input or stats.json")
	104	+sp500_ciks = S.get("sp500_ciks", U.get("n_sp500"))
34	105	w("tab_reconciliation.tex", f"""\\begin{{tabular}}{{lr}}
35	106	\\toprule
36	107	Step & Count \\\\
37	108	\\midrule
38		−iShares IWV holdings file, equity lines with a ticker (as of {U['russell_holdings_as_of']}) & 2{{,}}587 \\\\
	109	+{row1_label} & {row1_val} \\\\
39	110	\\quad of which mapped to an SEC CIK (CVRs, escrow lines and FDIC-only banks excluded) & {n(U['russell_equity_lines_mapped'])} \\\\
40	111	\\quad distinct CIKs (share classes collapsed) & {n(U['russell_distinct_ciks'])} \\\\
41		−S\\&P~500 constituents, cached snapshot of {U['sp500_fetched_at'][:10]} (500 CIKs) & {n(U['sp500_rows'])} \\\\
	112	+S\\&P~500 constituents, cached snapshot of {U['sp500_fetched_at'][:10]} ({n(sp500_ciks)} CIKs) & {n(U['sp500_rows'])} \\\\
42	113	\\midrule
43	114	Merged issuer universe (distinct CIKs) & {n(U['n'])} \\\\
44	115	\\quad in both lists & {n(U['both'])} \\\\
		`@@ -50,85 +121,288 @@ Issuers without any such filing (foreign private issuers filing 20-F/40-F, FDIC-`
50	121	Issuers with at least one resolved project & {n(S['issuers_with_projects'])} \\\\
51	122	\\bottomrule
52	123	\\end{{tabular}}""")
	124	+macro("universeN", n(U["n"]), "stats.json:universe.n", "count")
	125	+macro("russellDistinctCiks", n(U["russell_distinct_ciks"]), "stats.json:universe.russell_distinct_ciks", "count")
	126	+macro("russellMappedLines", n(U["russell_equity_lines_mapped"]), "stats.json:universe.russell_equity_lines_mapped", "count")
	127	+macro("russellUnmatched", n(U["russell_unmatched"]), "stats.json:universe.russell_unmatched", "len(unmatched)")
	128	+# Russell 3000 coverage of the proxy (L5): only if results/russell_coverage.json holds a retrieved constituent count
	129	+rc_path = R / "russell_coverage.json"
	130	+if rc_path.exists():
	131	+ rc = json.load(open(rc_path))
	132	+ if rc.get("index_constituents") is not None:
	133	+ cov = 100.0 * U["russell_distinct_ciks"] / rc["index_constituents"]
	134	+ macro("russellIndexConstituents", n(rc["index_constituents"]), "results/russell_coverage.json:index_constituents", rc.get("source_url", ""))
	135	+ macro("russellProxyCoveragePct", f"{cov:.1f}", "results/russell_coverage.json", "100 * russell_distinct_ciks / index_constituents")
	136	+ if rc.get("fund_holdings_count") is not None:
	137	+ macro("iwvHoldingsCount", n(rc["fund_holdings_count"]), "results/russell_coverage.json:fund_holdings_count", rc.get("fund_source_url", ""))
	138	+ if rc.get("replication_method"):
	139	+ macro("iwvReplicationMethod", esc(rc["replication_method"]), "results/russell_coverage.json:replication_method", rc.get("fund_source_url", ""))
53	140
54		−# ---- Table: filings by form ----
	141	+# ---- Table 2: filings by form --------------------------------------------------
55	142	fb = rows("filings_by_form"); ps = rows("parse_status")
56	143	err = {}
57	144	for r in ps:
58	145	err.setdefault(r["form_type"], {})[r["parse_status"]] = int(r["n"])
	146	+fdr = S.get("filing_date_range") or [min(r["first"] for r in fb), max(r["last"] for r in fb)]
	147	+macro("filingDateFirst", fdr[0], "stats.json:filing_date_range or min(filings_by_form.first)", "min")
	148	+macro("filingDateLast", fdr[1], "stats.json:filing_date_range or max(filings_by_form.last)", "max")
59	149	body = "\\begin{tabular}{lrrrrr}\n\\toprule\nForm & Filings & First filing & Last filing & Raw HTML (GB) & Not parsed \\\\\n\\midrule\n"
60	150	for r in fb:
61	151	e = err.get(r["form_type"], {}); notp = e.get("error", 0) + e.get("missing", 0)
62	152	body += f"{r['form_type']} & {n(r['n'])} & {r['first']} & {r['last']} & {float(r['gb']):.1f} & {notp} \\\\\n"
63		−body += f"\\midrule\nTotal & {n(S['filings_total'])} & 2010-01-04 & 2026-10-27 & {S['raw_gb']:.1f} & {sum(e.get('error',0)+e.get('missing',0) for e in err.values())} \\\\\n\\bottomrule\n\\end{{tabular}}"
	153	+not_parsed = sum(e.get("error", 0) + e.get("missing", 0) for e in err.values())
	154	+missing = sum(e.get("missing", 0) for e in err.values())
	155	+body += f"\\midrule\nTotal & {n(S['filings_total'])} & {fdr[0]} & {fdr[1]} & {S['raw_gb']:.1f} & {not_parsed} \\\\\n\\bottomrule\n\\end{{tabular}}"
64	156	w("tab_filings.tex", body)
	157	+macro("filingsTotal", n(S["filings_total"]), "stats.json:filings_total", "count")
	158	+macro("filingsNotParsed", str(not_parsed), "data/parse_status.csv", "sum(error)+sum(missing)")
	159	+macro("filingsMissingOnDisk", str(missing), "data/parse_status.csv", "sum(missing)")
	160	+macro("rawGb", f"{S['raw_gb']:.1f}", "stats.json:raw_gb", "sum(file_size_bytes)/1e9")
65	161
66		−# ---- Table: coverage by year ----
67		−iy = rows("issuers_by_year"); fy = rows("filings_by_year_form"); py = {r["yr"]: r for r in rows("projects_by_first_seen_year")}; my = {r["yr"]: r for r in rows("mentions_by_year")}
	162	+# ---- Table: coverage by year ----------------------------------------------------
	163	+iy = rows("issuers_by_year"); fy = rows("filings_by_year_form")
	164	+py = {r["yr"]: r for r in rows("projects_by_first_seen_year")}; my = {r["yr"]: r for r in rows("mentions_by_year")}
68	165	byf = {}
69	166	for r in fy: byf.setdefault(r["yr"], {})[r["form_type"]] = r["n"]
70		−body = "\\begin{tabular}{lrrrrrrr}\n\\toprule\nYear & Issuers & 10-K & 10-Q & 8-K & Mentions & Issuers w/ mentions & Projects first seen \\\\\n\\midrule\n"
	167	+body = "\\begin{tabular}{lrrrrrrrr}\n\\toprule\nYear & Issuers & 10-K & 10-Q & 8-K & Mentions & Issuers w/ mentions & Mentions per issuer & Projects first seen \\\\\n\\midrule\n"
71	168	for r in iy:
72		− y = r["yr"]; b = byf[y]
73		− body += f"{y} & {n(r['issuers'])} & {n(b['10-K'])} & {n(b['10-Q'])} & {n(b['8-K'])} & {n(my[y]['mentions'])} & {n(my[y]['issuers'])} & {n(py[y]['n'])} \\\\\n"
	169	+ y = r["yr"]; b = byf[y]; mpi = int(my[y]["mentions"]) / int(my[y]["issuers"])
	170	+ body += f"{y} & {n(r['issuers'])} & {n(b['10-K'])} & {n(b['10-Q'])} & {n(b['8-K'])} & {n(my[y]['mentions'])} & {n(my[y]['issuers'])} & {mpi:.1f} & {n(py[y]['n'])} \\\\\n"
74	171	body += "\\bottomrule\n\\end{tabular}"
75	172	w("tab_coverage_year.tex", body)
	173	+yrs_all = sorted(int(r["yr"]) for r in iy)
	174	+y_first, y_last = yrs_all[0], yrs_all[-1]
	175	+inner = [y for y in yrs_all if y_first < y < y_last] # exclude the left-censored first year and the partial last year
	176	+fs_inner = [int(py[str(y)]["n"]) for y in inner]
	177	+macro("firstSeenYearMin", str(inner[0]), "data/projects_by_first_seen_year.csv", "first full year after the left-censored start")
	178	+macro("firstSeenYearMax", str(inner[-1]), "data/projects_by_first_seen_year.csv", "last full year before the partial final year")
	179	+macro("firstSeenRangeInner", f"{n(min(fs_inner))}--{n(max(fs_inner))}", "data/projects_by_first_seen_year.csv", f"min/max of projects first seen, {inner[0]}--{inner[-1]}")
	180	+macro("firstSeenFirstYear", n(py[str(y_first)]["n"]), "data/projects_by_first_seen_year.csv", f"projects first seen in {y_first} (left-censored)")
	181	+macro("firstSeenInnerMean", n(sum(fs_inner) / len(fs_inner)), "data/projects_by_first_seen_year.csv", f"mean {inner[0]}--{inner[-1]}")
	182	+macro("mentionsFirstYear", n(my[str(y_first)]["mentions"]), "data/mentions_by_year.csv", f"mentions in {y_first}")
	183	+macro("mentionsLastFullYear", n(my[str(inner[-1])]["mentions"]), "data/mentions_by_year.csv", f"mentions in {inner[-1]}")
	184	+macro("issuersWithMentionsFirstYear", n(my[str(y_first)]["issuers"]), "data/mentions_by_year.csv", f"issuers with mentions in {y_first}")
	185	+macro("issuersWithMentionsLastFullYear", n(my[str(inner[-1])]["issuers"]), "data/mentions_by_year.csv", f"issuers with mentions in {inner[-1]}")
	186	+macro("mentionsPerIssuerFirstYear", f"{int(my[str(y_first)]['mentions'])/int(my[str(y_first)]['issuers']):.1f}", "data/mentions_by_year.csv", "mentions/issuers")
	187	+macro("mentionsPerIssuerLastFullYear", f"{int(my[str(inner[-1])]['mentions'])/int(my[str(inner[-1])]['issuers']):.1f}", "data/mentions_by_year.csv", "mentions/issuers")
	188	+macro("lastYear", str(y_last), "data/issuers_by_year.csv", "max year (partial)")
76	189
77		−# ---- Table: sections and extraction ledger ----
	190	+# ---- Table 3: sections and extraction ledger -----------------------------------
78	191	sb = {r["form_type"]: r for r in rows("sections_by_form")}; lb = rows("ledger_by_form")
79		−body = "\\begin{tabular}{lrrrrrr}\n\\toprule\nForm & Parsed sections & Median words & Sections sent to the extractor & Sections with $\\geq 1$ mention & Mentions & Issuers \\\\\n\\midrule\n"
80		−tot = [0, 0, 0, 0]
	192	+mf = {r["form_type"]: int(r["n"]) for r in rows("mentions_by_form")}
	193	+calls = {}
	194	+t3 = R / "ledger" / "table3_ledger_vs_stored.csv"
	195	+if t3.exists():
	196	+ calls = {r["form_type"]: int(float(r["calls"])) for r in rows(t3.stem, t3.parent) if r.get("calls")}
	197	+cc = " & Gate-passing calls" if calls else ""
	198	+body = ("\\begin{tabular}{lrrrr" + ("r" if calls else "") + "rrr}\n\\toprule\nForm & Parsed sections & Median words & Ledgered sections ($\\geq$ 30 words)" + cc + " & "
	199	+ "Sections with $\\geq 1$ mention & Mentions returned by the model (ledger) & Mentions stored & Issuers \\\\\n\\midrule\n")
	200	+tot = [0, 0, 0, 0, 0]; gap_by_form = {}
81	201	for r in lb:
82		− s = sb[r["form_type"]]
83		− body += f"{r['form_type']} & {n(s['sections'])} & {n(s['median_words'])} & {n(r['sections'])} & {n(r['with_mentions'])} & {n(r['mentions'])} & {n(r['issuers'])} \\\\\n"
84		− tot[0] += int(s["sections"]); tot[1] += int(r["sections"]); tot[2] += int(r["with_mentions"]); tot[3] += int(r["mentions"])
85		−body += f"\\midrule\nTotal & {n(tot[0])} & & {n(tot[1])} & {n(tot[2])} & {n(tot[3])} & {n(S['issuers_with_filings'])} \\\\\n\\bottomrule\n\\end{{tabular}}"
	202	+ s = sb[r["form_type"]]; stored = mf[r["form_type"]]
	203	+ gap_by_form[r["form_type"]] = int(r["mentions"]) - stored
	204	+ cv = f" & {n(calls[r['form_type']])}" if calls else ""
	205	+ body += (f"{r['form_type']} & {n(s['sections'])} & {n(s['median_words'])} & {n(r['sections'])}{cv} & {n(r['with_mentions'])} & "
	206	+ f"{n(r['mentions'])} & {n(stored)} & {n(r['issuers'])} \\\\\n")
	207	+ tot[0] += int(s["sections"]); tot[1] += int(r["sections"]); tot[2] += int(r["with_mentions"]); tot[3] += int(r["mentions"]); tot[4] += stored
	208	+ctot = f" & {n(sum(calls.values()))}" if calls else ""
	209	+body += (f"\\midrule\nTotal & {n(tot[0])} & & {n(tot[1])}{ctot} & {n(tot[2])} & {n(tot[3])} & {n(tot[4])} & {n(S['issuers_with_filings'])}$^{{\\dagger}}$ \\\\\n"
	210	+ "\\bottomrule\n\\end{tabular}")
	211	+if calls:
	212	+ for ft, v in calls.items():
	213	+ macro(f"calls{ft}", n(v), "results/ledger/table3_ledger_vs_stored.csv", f"calls where form_type={ft}")
86	214	w("tab_sections.tex", body)
	215	+ledger_gap = tot[3] - tot[4]
	216	+gap_txt = ", ".join(f"{k} {v}" for k, v in gap_by_form.items())
	217	+coll_sections = None
	218	+for cand in (R / "ledger" / "ledger_collisions.csv", D / "ledger_collisions.csv"):
	219	+ if cand.exists():
	220	+ with open(cand, newline="") as f:
	221	+ coll_sections = sum(1 for _ in csv.DictReader(f))
	222	+ break
	223	+note = (f"\\item ``Ledgered sections'' counts rows of the \\texttt{{extracted\\_sections}} ledger (sections with at least 30 words; "
	224	+ f"for 10-Ks restricted to the items of Table~\\ref{{tab:items}}); the ledger does not record whether the candidate gate "
	225	+ f"passed or whether the API call succeeded, so this is not a count of calls"
	226	+ + (f"; ``Gate-passing calls'' recomputes the candidate gate of Appendix~\\ref{{app:prompt}} over the ledgered text ({n(sum(calls.values()))} sections reached the model)" if calls else "")
	227	+ + ". ``Mentions returned by the model'' is "
	228	+ f"$\\sum$\\texttt{{n\\_mentions}} over the ledger ({n(tot[3])}); ``Mentions stored'' is the row count of "
	229	+ f"\\texttt{{project\\_mentions}} ({n(tot[4])}). The difference of {n(ledger_gap)} ({gap_txt})"
	230	+ + (f", spread over {n(coll_sections)} sections," if coll_sections else "")
	231	+ + " is the number of mentions overwritten by mention-identifier collisions before storage (Section~\\ref{sec:construct}). "
	232	+ f"$^{{\\dagger}}$Issuers with at least one filing of any form, not a column sum.\n")
	233	+w("tab_sections_note.tex", note)
	234	+macro("ledgerTotal", n(S["ledger_total"]), "stats.json:ledger_total", "count(extracted_sections)")
	235	+macro("ledgerMentionsReturned", n(tot[3]), "data/ledger_by_form.csv", "sum(mentions)")
	236	+macro("ledgerGap", n(ledger_gap), "data/ledger_by_form.csv, data/mentions_by_form.csv", "sum(ledger mentions) - sum(stored mentions)")
	237	+macro("ledgerGapByForm", gap_txt, "data/ledger_by_form.csv, data/mentions_by_form.csv", "per form")
	238	+for ft in ("8-K", "10-K", "10-Q"):
	239	+ key = ft.replace("-", "")
	240	+ macro(f"mentionsStored{key}", n(mf[ft]), "data/mentions_by_form.csv", f"n where form_type={ft}")
	241	+ lr = next(r for r in lb if r["form_type"] == ft)
	242	+ macro(f"mentionsLedger{key}", n(lr["mentions"]), "data/ledger_by_form.csv", f"mentions where form_type={ft}")
	243	+ macro(f"ledgerSections{key}", n(lr["sections"]), "data/ledger_by_form.csv", f"sections where form_type={ft}")
	244	+productive = tot[2]
	245	+macro("productiveSections", n(productive), "data/ledger_by_form.csv", "sum(with_mentions)")
	246	+macro("productiveShareLedger", f"{100productive/S['ledger_total']:.1f}", "data/ledger_by_form.csv, stats.json", "100productive/ledger_total")
	247	+macro("mentionsPerLedgerSection", f"{S['mentions']/S['ledger_total']:.2f}", "stats.json", "mentions/ledger_total")
	248	+macro("mentionsPerProductiveSection", f"{S['mentions']/productive:.2f}", "stats.json, data/ledger_by_form.csv", "mentions/productive")
	249	+gate_total = S.get("gate_pass_total")
	250	+gt_path = R / "ledger" / "gate_pass_totals.json"
	251	+if not gate_total and gt_path.exists():
	252	+ gt = json.load(open(gt_path))
	253	+ gate_total = next((gt[k] for k in ("calls", "gate_pass", "calls_total", "gate_pass_total") if isinstance(gt.get(k), (int, float))), None)
	254	+if gate_total:
	255	+ g = gate_total
	256	+ S = dict(S); S["gate_pass_total"] = g # local copy only; stats.json is never written
	257	+ macro("gatePassTotal", n(g), "stats.json:gate_pass_total", "regexp_matches(_PROJECT_GATE) over the ledger")
	258	+ macro("productiveShareCalls", f"{100productive/g:.1f}", "stats.json:gate_pass_total", "100productive/gate_pass_total")
	259	+ macro("mentionsPerCall", f"{S['mentions']/g:.2f}", "stats.json:gate_pass_total", "mentions/gate_pass_total")
87	260
88		−# ---- Table: 10-K / 10-Q items in scope ----
89		−body = "\\begin{tabular}{llrr}\n\\toprule\nForm & Section (item) & Sections extracted & Mentions \\\\\n\\midrule\n"
90		−for r in rows("ledger_10k_items"): body += f"10-K & \\texttt{{{r['section_name'].replace('_','\\_')}}} & {n(r['n'])} & {n(r['mentions'])} \\\\\n"
91		−body += "\\midrule\n"
92		−for r in rows("ledger_10q_items"): body += f"10-Q & \\texttt{{{r['section_name'].replace('_','\\_')}}} & {n(r['n'])} & {n(r['mentions'])} \\\\\n"
	261	+# ---- Table 4: 10-K / 10-Q items in scope ----------------------------------------
	262	+gp = None
	263	+for cand in (R / "ledger" / "gate_pass_by_form_item.csv",):
	264	+ if cand.exists():
	265	+ gp = {}
	266	+ for r in rows(cand.stem, cand.parent):
	267	+ fk = next((r[c] for c in r if c in ("form", "form_type")), None)
	268	+ ik = next((r[c] for c in r if c in ("item", "section_name")), None)
	269	+ gk = r.get("calls", next((r[c] for c in r if "gate_pass" in c.lower()), None))
	270	+ if fk and ik and gk not in (None, ""):
	271	+ gp[(fk, ik)] = gp.get((fk, ik), 0) + int(float(gk)) # summed over runs (backfilled + October)
	272	+cols = "llrr" + ("r" if gp else "")
	273	+body = f"\\begin{{tabular}}{{{cols}}}\n\\toprule\nForm & Section (item) & Ledgered sections & Mentions" + (" & Gate passed (calls)" if gp else "") + " \\\\\n\\midrule\n"
	274	+for form, name in (("10-K", "ledger_10k_items"), ("10-Q", "ledger_10q_items")):
	275	+ for r in rows(name):
	276	+ extra = f" & {n(gp[(form, r['section_name'])])}" if gp and (form, r["section_name"]) in gp else (" & --" if gp else "")
	277	+ body += f"{form} & \\texttt{{{r['section_name'].replace('_', '\\_')}}} & {n(r['n'])} & {n(r['mentions'])}{extra} \\\\\n"
	278	+ if form == "10-K": body += "\\midrule\n"
93	279	body += "\\bottomrule\n\\end{tabular}"
94	280	w("tab_items.tex", body)
	281	+k10 = {r["section_name"]: r for r in rows("ledger_10k_items")}; q10 = {r["section_name"]: r for r in rows("ledger_10q_items")}
	282	+for key, src in (("tenKmdnaMentions", k10.get("md_and_a")), ("tenQmdnaMentions", q10.get("md_and_a")), ("tenKbusinessMentions", k10.get("business")),
	283	+ ("tenQfinancialStatementsMentions", q10.get("financial_statements"))):
	284	+ if src: macro(key, n(src["mentions"]), "data/ledger_10k_items.csv / ledger_10q_items.csv", "mentions by item")
	285	+if k10.get("full_body"): macro("tenKfullBodyRows", n(k10["full_body"]["n"]), "data/ledger_10k_items.csv", "n where section_name=full_body")
95	286
96		−# ---- Table: projects by type ----
	287	+# ---- Table 5: projects by type ---------------------------------------------------
97	288	pt = rows("projects_by_type")
98		−body = "\\begin{tabular}{llrrrrr}\n\\toprule\nCode & Category & Projects & Share (\\%) & With amount & Median amount (M USD) & Mentions / project \\\\\n\\midrule\n"
	289	+ci = {}
	290	+ci_path = D / "projects_by_type_ci.csv"
	291	+if ci_path.exists():
	292	+ for r in rows("projects_by_type_ci"):
	293	+ lo = next((r[c] for c in r if c.lower() in ("ci_low", "lo", "ci_lo", "median_ci_low")), None)
	294	+ hi = next((r[c] for c in r if c.lower() in ("ci_high", "hi", "ci_hi", "median_ci_high")), None)
	295	+ if lo not in (None, "") and hi not in (None, ""):
	296	+ ci[r["project_type"]] = (float(lo), float(hi))
	297	+small_n = di("small_n_threshold") or 50
	298	+# the threshold itself is a documented presentation rule (data/documented_inputs.json), not a measurement
	299	+ad = rows("amount_dist")[0]; q = json.loads(ad["q"])
	300	+total_median = S.get("amount_total_median_musd", q[2] / 1e6)
	301	+om = {}
	302	+om_path = R / "resolver" / "overmerge_by_type.csv"
	303	+if om_path.exists():
	304	+ om = {r["project_type"]: r for r in rows(om_path.stem, om_path.parent)}
	305	+oc = " & $\\geq 3$ distinct names (\\%)" if om else ""
	306	+body = ("\\begin{tabular}{llrrrrrr" + ("r" if om else "") + "}\n\\toprule\nCode & Category & Projects & Share (\\%) & With amount ($N$) & Median amount (M USD) & "
	307	+ "95\\% CI of the median & Mentions / project" + oc + " \\\\\n\\midrule\n")
	308	+pct_sum = 0.0; greyed = []
99	309	for r in pt:
100		− body += f"\\texttt{{{r['project_type'].replace('_','\\_')}}} & {LAB[r['project_type']]} & {n(r['n'])} & {r['pct']} & {n(r['with_amount'])} & {n(r['median_amount_musd'],1)} & {float(r['mean_mentions']):.2f} \\\\\n"
101		−body += f"\\midrule\n & Total & {n(S['projects'])} & 100.0 & {n(S['projects_fields'][0])} & 128.5 & {S['mentions']/S['projects']:.2f} \\\\\n\\bottomrule\n\\end{{tabular}}"
	310	+ pct_sum += float(r["pct"]); N = int(r["with_amount"])
	311	+ med = n(r["median_amount_musd"], 1)
	312	+ if N < small_n:
	313	+ med = f"\\textcolor{{gray}}{{{med}}}"; greyed.append(r["project_type"])
	314	+ cic = f"{ci[r['project_type']][0]/1e6:,.1f}--{ci[r['project_type']][1]/1e6:,.1f}".replace(",", "{,}") if r["project_type"] in ci else "--"
	315	+ ov = f" & {float(om[r['project_type']]['pct_ge3_names']):.1f}" if om and r["project_type"] in om else (" & --" if om else "")
	316	+ body += (f"\\texttt{{{r['project_type'].replace('_', '\\_')}}} & {LAB[r['project_type']]} & {n(r['n'])} & {r['pct']} & {n(N)} & {med} & {cic} & "
	317	+ f"{float(r['mean_mentions']):.2f}{ov} \\\\\n")
	318	+body += (f"\\midrule\n & Total & {n(S['projects'])} & {pct_sum:.1f} & {n(S['projects_fields'][0])} & {n(total_median, 1)} & -- & "
	319	+ f"{S['mentions']/S['projects']:.2f}" + (" & " if om else "") + f" \\\\\n\\bottomrule\n\\end{{tabular}}")
102	320	w("tab_types.tex", body)
	321	+note = (f"\\item Shares are rounded to one decimal and sum to {pct_sum:.1f}. ``With amount'' counts projects for which at least one mention carries a USD "
	322	+ f"figure; ``median amount'' is the median across those projects of the largest amount cited (Section~\\ref{{sec:amounts}} on why amounts are never summed). "
	323	+ f"Medians printed in grey rest on fewer than {small_n} projects with an amount ({', '.join('\\texttt{' + g.replace('_', '\\_') + '}' for g in greyed)}) "
	324	+ "and should not be quoted without their $N$. "
	325	+ + ("The 95\\% interval of the median is a percentile bootstrap (\\texttt{data/projects\\_by\\_type\\_ci.csv}). " if ci
	326	+ else "The 95\\% interval column is filled when \\texttt{data/projects\\_by\\_type\\_ci.csv} (bootstrap on the node) is present. ")
	327	+ + ("``$\\geq 3$ distinct names'' is the share of projects of the category whose mentions carry three or more distinct project names "
	328	+ "(over-merge indicator of the resolution key, \\texttt{results/resolver/overmerge\\_by\\_type.csv}).\n" if om else "\n"))
	329	+w("tab_types_note.tex", note)
	330	+macro("typesPctSum", f"{pct_sum:.1f}", "data/projects_by_type.csv", "sum(pct)")
	331	+macro("amountMedianMusd", n(total_median, 1), "stats.json:amount_total_median_musd or data/amount_dist.csv", "median(total_amount_usd)/1e6")
	332	+macro("smallNThreshold", str(small_n), "data/documented_inputs.json:small_n_threshold", "presentation rule")
	333	+macro("smallNCategories", ", ".join(greyed), "data/projects_by_type.csv", f"with_amount < {small_n}")
	334	+ptd = {r["project_type"]: r for r in pt}
	335	+for code in ("data_center", "ai_initiative", "cloud_migration", "automation", "ma_integration", "capex_program", "partnership", "geographic_expansion", "plant_construction"):
	336	+ if code in ptd:
	337	+ cam = "".join(p.capitalize() for p in code.split("_"))
	338	+ macro(f"share{cam}", ptd[code]["pct"], "data/projects_by_type.csv", f"pct where project_type={code}")
	339	+ macro(f"n{cam}", n(ptd[code]["n"]), "data/projects_by_type.csv", f"n where project_type={code}")
	340	+ macro(f"withAmount{cam}", n(ptd[code]["with_amount"]), "data/projects_by_type.csv", f"with_amount where project_type={code}")
	341	+ macro(f"medianAmount{cam}", n(ptd[code]["median_amount_musd"], 1), "data/projects_by_type.csv", f"median_amount_musd where project_type={code}")
	342	+tech = [c for c in ("data_center", "ai_initiative", "cloud_migration", "automation") if c in ptd]
	343	+macro("techCategoriesCountRange", f"{n(min(int(ptd[c]['n']) for c in tech))}--{n(max(int(ptd[c]['n']) for c in tech))}", "data/projects_by_type.csv", "min/max n over " + ", ".join(tech))
103	344
104		−# ---- Table: by sector ----
	345	+# ---- Table 6: by sector -------------------------------------------------------------
105	346	cs = {r["sector"]: r for r in rows("companies_by_sector")}
	347	+sec = rows("projects_by_sector")
106	348	body = "\\begin{tabular}{lrrrrr}\n\\toprule\nGICS sector (iShares) & Issuers in universe & of which S\\&P~500 & Issuers with projects & Projects & Projects per issuer \\\\\n\\midrule\n"
107		−for r in rows("projects_by_sector"):
	349	+for r in sec:
108	350	c = cs.get(r["sector"], {"n": "", "sp500": ""})
109	351	body += f"{r['sector']} & {n(c['n']) if c['n'] else ''} & {n(c['sp500']) if c['sp500'] else ''} & {n(r['issuers'])} & {n(r['n'])} & {float(r['per_issuer']):.1f} \\\\\n"
110	352	body += "\\bottomrule\n\\end{tabular}"
111	353	w("tab_sectors.tex", body)
	354	+secd = {r["sector"]: r for r in sec}
	355	+top4 = sorted(sec, key=lambda r: -float(r["per_issuer"]))[:4]
	356	+vals = [float(r["per_issuer"]) for r in top4]
	357	+macro("sectorTopFourPerIssuerRange", f"{math.floor(min(vals))}--{math.ceil(max(vals))}", "data/projects_by_sector.csv", "floor(min)/ceil(max) of per_issuer over the four highest sectors: " + ", ".join(r["sector"] for r in top4))
	358	+macro("sectorTopFourNames", ", ".join(r["sector"].lower() for r in top4), "data/projects_by_sector.csv", "four highest per_issuer")
	359	+if "Financials" in secd: macro("sectorFinancialsPerIssuer", f"{round(float(secd['Financials']['per_issuer']))}", "data/projects_by_sector.csv", "round(per_issuer) for Financials")
	360	+for name in ("Health Care", "Industrials"):
	361	+ if name in secd:
	362	+ cam = name.replace(" ", "")
	363	+ macro(f"sectorProjects{cam}", n(secd[name]["n"]), "data/projects_by_sector.csv", f"n for {name}")
	364	+ macro(f"sectorIssuers{cam}", n(secd[name]["issuers"]), "data/projects_by_sector.csv", f"issuers for {name}")
112	365
113		−# ---- Table: status, mention buckets, duration, confidence ----
	366	+# ---- Table 7: status, mention buckets, duration ----------------------------------------
114	367	st = rows("projects_by_status"); mb = rows("mentions_per_project"); du = rows("duration"); cf = rows("confidence_dist")
115	368	body = "\\begin{tabular}{lr@{\\hspace{2em}}lr@{\\hspace{2em}}lr}\n\\toprule\nLatest status & Projects & Mentions per project & Projects & Span of cited years & Projects \\\\\n\\midrule\n"
116		−du_order = ["0", "1-2", "3-5", ">5", "unknown"]; dus = {r["span_years"]: r["n"] for r in du}
	369	+du_order = ["0", "1-2", "3-5", ">5", "unknown"]; dus = {r["span_years"]: int(r["n"]) for r in du}
117	370	rowsn = max(len(st), len(mb), len(du_order))
118	371	for i in range(rowsn):
119		− a = f"\\texttt{{{st[i]['status'].replace('_','\\_')}}} & {n(st[i]['n'])}" if i < len(st) else "&"
	372	+ a = f"\\texttt{{{st[i]['status'].replace('_', '\\_')}}} & {n(st[i]['n'])}" if i < len(st) else "&"
120	373	b = f"{mb[i]['bucket']} & {n(mb[i]['n'])}" if i < len(mb) else "&"
121		− c = f"{du_order[i].replace('>','$>$')} years & {n(dus[du_order[i]])}" if i < len(du_order) else "&"
	374	+ c = f"{du_order[i].replace('>', '$>$')} years & {n(dus[du_order[i]])}" if i < len(du_order) else "&"
122	375	body += f"{a} & {b} & {c} \\\\\n"
123	376	body += "\\bottomrule\n\\end{tabular}"
124	377	w("tab_status.tex", body)
	378	+P = S["projects"]; known = P - dus["unknown"]
	379	+macro("spanKnownN", n(known), "data/duration.csv", "projects - unknown")
	380	+macro("spanUnknownN", n(dus["unknown"]), "data/duration.csv", "n where span_years=unknown")
	381	+macro("spanUnknownShareAll", f"{100dus['unknown']/P:.1f}", "data/duration.csv", "100unknown/projects")
	382	+macro("spanZeroShareAll", f"{100dus['0']/P:.1f}", "data/duration.csv", "100n(0)/projects")
	383	+macro("spanZeroShareKnown", f"{100dus['0']/known:.1f}", "data/duration.csv", "100n(0)/(projects-unknown)")
	384	+macro("spanOverFiveShareAll", f"{100dus['>5']/P:.1f}", "data/duration.csv", "100n(>5)/projects")
	385	+macro("spanOverFiveShareKnown", f"{100dus['>5']/known:.1f}", "data/duration.csv", "100n(>5)/(projects-unknown)")
	386	+for r in st:
	387	+ macro("statusShare" + "".join(p.capitalize() for p in r["status"].split("_")), r["pct"], "data/projects_by_status.csv", f"pct where status={r['status']}")
	388	+mbd = {r["bucket"]: int(r["n"]) for r in mb}
	389	+macro("singleMentionShare", f"{100mbd['1']/P:.1f}", "data/mentions_per_project.csv", "100n(bucket=1)/projects")
	390	+macro("overTenMentionShare", f"{100mbd['>10']/P:.1f}", "data/mentions_per_project.csv", "100n(bucket=>10)/projects")
	391	+
	392	+# ---- confidence ---------------------------------------------------------------------
125	393	body = "\\begin{tabular}{lr}\n\\toprule\nSelf-reported confidence (rounded) & Mentions \\\\\n\\midrule\n"
126	394	for r in cf: body += f"{r['conf']} & {n(r['n'])} \\\\\n"
127	395	body += "\\bottomrule\n\\end{tabular}"
128	396	w("tab_confidence.tex", body)
	397	+M = S["mentions"]; cfd = {float(r["conf"]): int(r["n"]) for r in cf}
	398	+macro("confShareOne", f"{100cfd.get(1.0, 0)/M:.1f}", "data/confidence_dist.csv", "100n(conf=1.0)/mentions")
	399	+macro("confShareNine", f"{100cfd.get(0.9, 0)/M:.1f}", "data/confidence_dist.csv", "100n(conf=0.9)/mentions")
	400	+macro("confShareLeSix", f"{100sum(v for k, v in cfd.items() if k <= 0.6)/M:.1f}", "data/confidence_dist.csv", "100n(conf<=0.6)/mentions")
	401	+if S.get("conf_exact_default_count") is not None:
	402	+ macro("confExactDefaultCount", n(S["conf_exact_default_count"]), "stats.json:conf_exact_default_count", "count(round(confidence,3)=0.600)")
129	403
130		−# ---- Table: amounts ----
131		−ad = rows("amount_dist")[0]; q = json.loads(ad["q"]); ppi = json.loads(rows("projects_per_issuer")[0]["q"])
	404	+# ---- Table 8: amounts ----------------------------------------------------------------
	405	+ppi = json.loads(rows("projects_per_issuer")[0]["q"])
132	406	body = f"""\\begin{{tabular}}{{lrrrrrr}}
133	407	\\toprule
134	408	& P10 & P25 & Median & P75 & P90 & P99 \\\\
		`@@ -138,58 +412,296 @@ Projects per issuer ($N$ = {n(S['issuers_with_projects'])}) & {ppi[0]:.0f} & {pp`
138	412	\\bottomrule
139	413	\\end{{tabular}}""".replace(",", "{,}")
140	414	w("tab_amounts.tex", body)
	415	+macro("amountMentions", n(S["mentions_fields"][0]), "stats.json:mentions_fields[0]", "count(amount_usd is not null)")
	416	+macro("amountMentionsShare", f"{100S['mentions_fields'][0]/M:.1f}", "stats.json", "100mentions_fields[0]/mentions")
	417	+macro("amountProjects", n(S["projects_fields"][0]), "stats.json:projects_fields[0]", "count(total_amount_usd is not null)")
	418	+macro("amountProjectsShare", f"{100S['projects_fields'][0]/P:.1f}", "stats.json", "100projects_fields[0]/projects")
	419	+macro("amountP25Musd", f"{q[1]/1e6:,.0f}".replace(",", "{,}"), "data/amount_dist.csv", "q[1]/1e6")
	420	+macro("amountP75Musd", f"{q[3]/1e6:,.0f}".replace(",", "{,}"), "data/amount_dist.csv", "q[3]/1e6")
	421	+macro("amountP99Busd", f"{q[5]/1e9:,.1f}", "data/amount_dist.csv", "q[5]/1e9")
	422	+macro("amountSumTusd", f"{float(ad['sum_gusd'])/1e3:,.1f}", "data/amount_dist.csv", "sum_gusd/1e3")
	423	+amt_note = ("\\item Amounts are the largest USD figure cited across the mentions of a project; they mix transaction values, budgets, contract values "
	424	+ "and estimates and are never summed in the text. ")
	425	+if S.get("amount_max") is not None:
	426	+ macro("amountMaxBusd", f"{S['amount_max']/1e9:,.1f}".replace(",", "{,}"), "stats.json:amount_max", "max(total_amount_usd)/1e9")
	427	+ amt_note += f"The maximum is {S['amount_max']/1e9:,.1f}~B USD. ".replace(",", "{,}")
	428	+if S.get("amount_ge_50b") is not None:
	429	+ macro("amountGeFiftyB", n(S["amount_ge_50b"]), "stats.json:amount_ge_50b", "count(total_amount_usd >= 50e9)")
	430	+ amt_note += f"{n(S['amount_ge_50b'])} projects carry an amount of 50~B USD or more. "
	431	+if S.get("amount_le_zero") is not None:
	432	+ macro("amountLeZero", n(S["amount_le_zero"]), "stats.json:amount_le_zero", "count(total_amount_usd <= 0)")
	433	+w("tab_amounts_note.tex", amt_note + "\n")
141	434
142		−# ---- Table: knowledge graph ----
	435	+# ---- knowledge graph --------------------------------------------------------------------
143	436	kg = rows("kg")
144	437	body = "\\begin{tabular}{llr}\n\\toprule\n & Type & Count \\\\\n\\midrule\n"
145		−for r in kg: body += f"{r['k'].capitalize()} & \\texttt{{{r['node_type'].replace('_','\\_')}}} & {n(r['n'])} \\\\\n"
	438	+for r in kg: body += f"{r['k'].capitalize()} & \\texttt{{{r['node_type'].replace('_', '\\_')}}} & {n(r['n'])} \\\\\n"
146	439	body += "\\bottomrule\n\\end{tabular}"
147	440	w("tab_graph.tex", body)
	441	+macro("kgNodes", n(sum(int(r["n"]) for r in kg if r["k"] == "nodes")), "data/kg.csv", "sum(n) where k=nodes")
	442	+macro("kgEdges", n(sum(int(r["n"]) for r in kg if r["k"] == "edges")), "data/kg.csv", "sum(n) where k=edges")
	443	+for r in kg:
	444	+ if r["k"] == "nodes": macro("kgNodes" + r["node_type"].capitalize(), n(r["n"]), "data/kg.csv", f"n where node_type={r['node_type']}")
148	445
149		−# ---- Table: top issuers ----
	446	+# ---- top issuers ---------------------------------------------------------------------------
150	447	body = "\\begin{tabular}{llr}\n\\toprule\nTicker & Issuer & Resolved projects \\\\\n\\midrule\n"
151		−for r in rows("top_issuers")[:12]: body += f"{r['ticker']} & {r['company_name'].title().replace('&','\\&')} & {n(r['projects'])} \\\\\n"
	448	+for r in rows("top_issuers")[:12]: body += f"{r['ticker']} & {r['company_name'].title().replace('&', '\\&')} & {n(r['projects'])} \\\\\n"
152	449	body += "\\bottomrule\n\\end{tabular}"
153	450	w("tab_top_issuers.tex", body)
154	451
155		−# ---- Table: provenance example (Cheniere Corpus Christi) ----
	452	+# ---- Table 9: provenance example (Cheniere Corpus Christi) ------------------------------------
156	453	ex = [r for r in rows("example_provenance") if r["ticker"] == "LNG"]
157	454	body = "\\begin{tabular}{llllp{6.2cm}}\n\\toprule\nAccession & Filed & Form & Status / amount & Evidence snippet (model-generated description grounded in the section) \\\\\n\\midrule\n"
158	455	for r in ex[:8]:
159	456	amt = f"{float(r['amount_usd'])/1e9:.1f} B USD" if r["amount_usd"] else "--"
160		− snip = r["snippet"].replace("&", "\\&").replace("%", "\\%").replace("$", "\\$")[:170]
161		− body += f"\\texttt{{{r['accession_number']}}} & {r['filing_date']} & {r['form_type']} & {r['m_status'].replace('_','\\_')} / {amt} & {snip} \\\\\n"
	457	+ snip = r["snippet"].replace("&", "\\&").replace("%", "\\%").replace("$", "\\$")[:DI["snippet_chars"]["value"]]
	458	+ body += f"\\texttt{{{r['accession_number']}}} & {r['filing_date']} & {r['form_type']} & {r['m_status'].replace('_', '\\_')} / {amt} & {snip} \\\\\n"
162	459	body += "\\bottomrule\n\\end{tabular}"
163	460	w("tab_provenance.tex", body)
164		−S["example_project"] = {k: ex[0][k] for k in ("project_id", "ticker", "project_name", "project_type", "status", "total_amount_usd", "n_mentions", "first_seen", "last_seen")} if ex else {}
	461	+if ex:
	462	+ forms = sorted({r["form_type"] for r in ex[:8]})
	463	+ macro("provenanceForms", " and ".join(forms), "data/example_provenance.csv", "distinct form_type of the printed rows")
	464	+ macro("provenanceN", str(len(ex[:8])), "data/example_provenance.csv", "rows printed")
	465	+ macro("provenanceFirst", ex[0]["filing_date"], "data/example_provenance.csv", "min filing_date")
	466	+ macro("provenanceLast", ex[:8][-1]["filing_date"], "data/example_provenance.csv", "max filing_date")
	467	+ macro("provenanceMaxAmountBusd", f"{max(float(r['amount_usd']) for r in ex if r['amount_usd'])/1e9:.1f}", "data/example_provenance.csv", "max(amount_usd)/1e9")
	468	+ macro("provenanceNameYear", ex[:8][-1]["filing_date"][:4], "data/example_provenance.csv", "filing year of the last mention (representative name source)")
	469	+ json.dump({k: ex[0][k] for k in ("project_id", "ticker", "project_name", "project_type", "status", "total_amount_usd", "n_mentions", "first_seen", "last_seen")},
	470	+ open(DATA_OUT / "example_project.json", "w"), indent=2)
	471	+
	472	+# ---- Table 12: data-model audit (Appendix C) as a longtable -------------------------------------
	473	+if (D / "datamodel_audit.csv").exists():
	474	+ body = ("\\begin{longtable}{p{3.1cm}p{8.6cm}p{4.3cm}}\n\\caption{Tables required by the research design, current implementation and status}"
	475	+ "\\label{tab:datamodel}\\\\\n\\toprule\nRequired table & Current implementation (database, table, key fields) & Status \\\\\n\\midrule\n\\endfirsthead\n"
	476	+ "\\toprule\nRequired table & Current implementation (database, table, key fields) & Status \\\\\n\\midrule\n\\endhead\n\\bottomrule\n\\endfoot\n")
	477	+ for r in rows("datamodel_audit"):
	478	+ body += f"\\texttt{{{r['required_table'].replace('_', '\\_')}}} & {r['implementation']} & {r['status']} \\\\\n"
	479	+ body += "\\end{longtable}"
	480	+ w("tab_datamodel.tex", body)
	481	+
	482	+# ---- Appendix B: candidate gate regex and system prompt, read from the frozen snapshot ----------
	483	+def _snapshot(name):
	484	+ for base in (SNAP, ROOT.parent.parent / "manuscripts" / "FIRC-0001" / "pipeline_code_2324b58" / "project-db" / "spid"):
	485	+ for p in (base / name, base / "extract" / name):
	486	+ if p.exists(): return p
	487	+ return None
	488	+
	489	+rules_py = _snapshot("rules.py")
	490	+if rules_py:
	491	+ tree = ast.parse(rules_py.read_text())
	492	+ pieces, flags = None, ""
	493	+ for node in ast.walk(tree):
	494	+ if isinstance(node, ast.Assign) and any(isinstance(t, ast.Name) and t.id == "_PROJECT_GATE" for t in node.targets):
	495	+ call = node.value; arg = call.args[0]
	496	+ # the pattern is written as adjacent raw-string literals; keep the author's line breaks
	497	+ seg = rules_py.read_text().splitlines()[arg.lineno - 1: arg.end_lineno]
	498	+ pieces = [re.match(r'\sr"(.)"\s,?\s$', s).group(1) for s in seg]
	499	+ flags = ", ".join(ast.unparse(a) for a in call.args[1:])
	500	+ if pieces:
	501	+ full = "".join(pieces)
	502	+ lines = "\n".join(pieces)
	503	+ w("gate_regex.tex", "\\begin{verbatim}\n" + lines + "\n\\end{verbatim}\n")
	504	+ macro("gateRegexFlags", esc(flags), str(rules_py.relative_to(ROOT)) if rules_py.is_relative_to(ROOT) else str(rules_py), "re.compile flags")
	505	+ macro("gateRegexLength", str(len(full)), "rules.py:_PROJECT_GATE", "len(pattern)")
	506	+ macro("gateRegexAlternatives", str(full.count("\|") + 1), "rules.py:_PROJECT_GATE", "number of alternatives")
	507	+
	508	+llm_py, tax_py = _snapshot("llm.py"), _snapshot("taxonomy.py")
	509	+if llm_py and tax_py:
	510	+ ttree = ast.parse(tax_py.read_text()); types = None
	511	+ for node in ast.walk(ttree):
	512	+ if isinstance(node, (ast.Assign, ast.AnnAssign)):
	513	+ tg = node.targets[0] if isinstance(node, ast.Assign) else node.target
	514	+ if isinstance(tg, ast.Name) and tg.id == "PROJECT_TYPES":
	515	+ types = ast.literal_eval(node.value)
	516	+ ltree = ast.parse(llm_py.read_text()); tmpl = None
	517	+ for node in ast.walk(ltree):
	518	+ if isinstance(node, ast.Assign) and any(isinstance(t, ast.Name) and t.id == "_SYSTEM" for t in node.targets):
	519	+ v = node.value
	520	+ if isinstance(v, ast.BinOp) and isinstance(v.left, ast.Constant): tmpl = v.left.value
	521	+ elif isinstance(v, ast.Constant): tmpl = v.value
	522	+ if types and tmpl and "%s" in tmpl:
	523	+ labels = "\n".join(f" - {k}: {v['label']}" for k, v in types.items())
	524	+ prompt = tmpl % labels
	525	+ w("prompt_verbatim.tex", "\\begin{verbatim}\n" + prompt + "\n\\end{verbatim}\n")
	526	+ macro("taxonomyN", str(len(types)), "taxonomy.py:PROJECT_TYPES", "len")
	527	+ body = "\\begin{tabular}{ll}\n\\toprule\nCode & Label \\\\\n\\midrule\n"
	528	+ for k, v in types.items(): body += f"\\texttt{{{k.replace('_', '\\_')}}} & {esc(v['label'])} \\\\\n"
	529	+ body += "\\bottomrule\n\\end{tabular}"
	530	+ w("tab_taxonomy.tex", body)
165	531
166		−# ---- Figures ----
	532	+# ---- Stage D audit tables from results/ (generic CSV -> tabular; skipped when absent) ---------------
	533	+def csv_table(texname, path, caption_cols=None, max_rows=60):
	534	+ if not path.exists():
	535	+ print("skip", texname, "(missing", path.relative_to(ROOT), ")"); return
	536	+ with open(path, newline="") as f:
	537	+ rd = csv.DictReader(f); cols = rd.fieldnames; data = list(rd)
	538	+ def fmt(v):
	539	+ try:
	540	+ x = float(v)
	541	+ if x.is_integer() and abs(x) >= 1e3: return n(x)
	542	+ return v if x.is_integer() else f"{x:,.3f}".rstrip("0").rstrip(".").replace(",", "{,}")
	543	+ except ValueError:
	544	+ return esc(v)
	545	+ spec = "l" + "r" * (len(cols) - 1)
	546	+ body = f"\\begin{{tabular}}{{{spec}}}\n\\toprule\n" + " & ".join(esc(c) for c in cols) + " \\\\\n\\midrule\n"
	547	+ for r in data[:max_rows]: body += " & ".join(fmt(r[c]) for c in cols) + " \\\\\n"
	548	+ if len(data) > max_rows: body += f"\\multicolumn{{{len(cols)}}}{{l}}{{\\ldots {len(data) - max_rows} more rows in \\texttt{{{esc(str(path.relative_to(ROOT)))}}}}} \\\\\n"
	549	+ body += "\\bottomrule\n\\end{tabular}"
	550	+ w(texname, body)
	551	+
	552	+csv_table("tab_spec_curve.tex", R / "resolver" / "spec_curve.csv")
	553	+csv_table("tab_grounding.tex", R / "grounding" / "grounding_by_field_form_item.csv")
	554	+csv_table("tab_focus.tex", R / "focus" / "focus_coverage_by_form_item.csv")
	555	+csv_table("tab_cohort.tex", R / "runs" / "cohort_by_run.csv" if (R / "runs" / "cohort_by_run.csv").exists() else D / "cohort_by_run.csv")
	556	+csv_table("tab_fp_classes.tex", R / "fp_classes" / "financing_regex_by_item_type.csv")
	557	+csv_table("tab_timeseries_cohort.tex", R / "timeseries" / "first_seen_fixed_cohort.csv")
	558	+csv_table("tab_benchmark_8k.tex", R / "benchmark_8k" / "item_vs_type.csv")
	559	+csv_table("tab_rules_agreement.tex", R / "rules" / "agreement_by_form_item.csv")
	560	+
	561	+# ---- macros from the Stage D audit results (results/**.json; skipped when absent) ------------------
	562	+def jload(rel):
	563	+ p = R / rel
	564	+ return json.load(open(p)) if p.exists() else {}
	565	+
	566	+def jmacro(name, obj, key, src, fmt=None):
	567	+ v = obj.get(key) if isinstance(obj, dict) else None
	568	+ if v is None or isinstance(v, (list, dict)): return
	569	+ macro(name, fmt(v) if fmt else (n(v) if isinstance(v, (int, float)) and float(v).is_integer() else str(v)), src, key)
	570	+
	571	+gt = jload("ledger/gate_pass_totals.json")
	572	+for k, mname, fmt in (("calls", "callsTotal", None), ("gate_pass", "gatePassSections", None), ("gate_rejected_zero", "gateRejectedSections", None),
	573	+ ("lt30_words", "ledgerUnderThirtyWords", None), ("productive_pct_calls", "productiveShareCalls", lambda v: f"{v:.1f}"),
	574	+ ("mentions_per_call", "mentionsPerCall", lambda v: f"{v:.2f}"), ("usd_per_call_paper_total_775", "usdPerCall", lambda v: f"{v:.4f}"),
	575	+ ("october_calls", "octoberCalls", None), ("october_rows", "octoberRows", None)):
	576	+ jmacro(mname, gt, k, "results/ledger/gate_pass_totals.json", fmt)
	577	+tp = jload("ledger/throughput.json")
	578	+for k, mname, fmt in (("wall_clock_hours_first_to_last_flush", "octoberWallClockHours", lambda v: f"{v:.1f}"), ("largest_gap_hours", "outageHours", lambda v: f"{v:.1f}"),
	579	+ ("effective_hours_excluding_largest_gap", "octoberEffectiveHours", lambda v: f"{v:.1f}"),
	580	+ ("rows_per_second_effective", "octoberRowsPerSecondEffective", lambda v: f"{v:.1f}"), ("rows_per_second_wall_clock", "octoberRowsPerSecondWallClock", lambda v: f"{v:.1f}"),
	581	+ ("calls_per_second_effective", "octoberCallsPerSecondEffective", lambda v: f"{v:.1f}"), ("october_first_flush", "octoberFirstFlush", lambda v: str(v)[:16]),
	582	+ ("october_last_flush", "octoberLastFlush", lambda v: str(v)[:16])):
	583	+ jmacro(mname, tp, k, "results/ledger/throughput.json", fmt)
	584	+bb = jload("ledger/backfill_block.json")
	585	+for k, mname in (("rows_at_min_timestamp", "backfilledRows"), ("june_log_sections", "juneLogSections"), ("block_lt30_words", "backfilledUnderThirtyWords"),
	586	+ ("block_stored_mentions", "backfilledMentions"), ("block_ciks", "backfilledCiks"), ("block_gate_fail", "backfilledGateFail"), ("rows_in_outage_window", "rowsInOutageWindow")):
	587	+ jmacro(mname, bb, k, "results/ledger/backfill_block.json")
	588	+if isinstance(bb.get("outage_window"), list) and len(bb["outage_window"]) == 2:
	589	+ macro("outageWindowStart", str(bb["outage_window"][0])[:16], "results/ledger/backfill_block.json", "outage_window[0]")
	590	+ macro("outageWindowEnd", str(bb["outage_window"][1])[:16], "results/ledger/backfill_block.json", "outage_window[1]")
	591	+ls_ = jload("ledger/log_summary.json")
	592	+oc_ = ls_.get("october", {}) if isinstance(ls_.get("october"), dict) else {}
	593	+for k, mname in (("llm_call_failed_total", "llmCallFailedTotal"), ("llm_call_failed_inside_window", "llmCallFailedInsideOutage"), ("llm_call_failed_outside_window", "llmCallFailedOutsideOutage")):
	594	+ jmacro(mname, oc_, k, "results/ledger/log_summary.json:october")
	595	+if isinstance(oc_.get("llm_call_failed_by_reason"), dict):
	596	+ for k, v in oc_["llm_call_failed_by_reason"].items(): macro("llmFailed" + "".join(p.capitalize() for p in k.split("_")), n(v), "results/ledger/log_summary.json:october.llm_call_failed_by_reason", k)
	597	+jn_ = ls_.get("june", {}) if isinstance(ls_.get("june"), dict) else {}
	598	+jmacro("juneLlmCallFailed", jn_, "llm_call_failed_total", "results/ledger/log_summary.json:june")
	599	+co = jload("ledger/collisions.json")
	600	+for k, mname in (("sections_ledger_gt_stored", "collisionSections"), ("excess_mentions", "collisionMentions")):
	601	+ jmacro(mname, co, k, "results/ledger/collisions.json")
	602	+cp = jload("resolver/composition.json")
	603	+for k, mname in (("projects_keyed_general", "projectsKeyedGeneral"), ("mentions_keyed_general", "mentionsKeyedGeneral")):
	604	+ jmacro(mname, cp, k, "results/resolver/composition.json")
	605	+if isinstance(cp.get("projects_by_key_branch"), list):
	606	+ for br, v in cp["projects_by_key_branch"]:
	607	+ macro("projectsKeyed" + "".join(p.capitalize() for p in str(br).split("_")), n(v), "results/resolver/composition.json", f"projects_by_key_branch[{br}]")
	608	+ macro("projectsKeyed" + "".join(p.capitalize() for p in str(br).split("_")) + "Pct", f"{100v/P:.1f}", "results/resolver/composition.json", f"100projects_by_key_branch[{br}]/projects")
	609	+ti = jload("resolver/ties_idempotence.json")
	610	+for k, mname in (("projects_with_tie_at_max_confidence", "projectsTieMaxConfidence"), ("projects_with_tie_and_distinct_names", "projectsTieDistinctNames"),
	611	+ ("projects_with_status_tie_on_last_seen", "projectsStatusTie"), ("mentions_at_confidence_1", "mentionsAtConfidenceOne")):
	612	+ jmacro(mname, ti, k, "results/resolver/ties_idempotence.json")
	613	+sc_path = R / "resolver" / "spec_curve.csv"
	614	+if sc_path.exists():
	615	+ sc = rows(sc_path.stem, sc_path.parent)
	616	+ thr = min(sc, key=lambda r: float(r["threshold"]))["threshold"]
	617	+ at = [r for r in sc if r["threshold"] == thr]
	618	+ pr = [int(float(r["projects"])) for r in at]
	619	+ macro("projectCountRangeKeys", f"{n(min(pr))}--{n(max(pr))}", "results/resolver/spec_curve.csv", f"min/max projects over keys at threshold {thr}")
	620	+ macro("projectCountRangeKeysN", str(len(at)), "results/resolver/spec_curve.csv", f"number of keys at threshold {thr}")
	621	+ pall = [int(float(r["projects"])) for r in sc]
	622	+ macro("projectCountRangeAll", f"{n(min(pall))}--{n(max(pall))}", "results/resolver/spec_curve.csv", "min/max projects over all keys x thresholds")
	623	+ cur = [r for r in at if "current" in r["key"].lower()]
	624	+ if cur: macro("projectCountCurrentKey", n(cur[0]["projects"]), "results/resolver/spec_curve.csv", f"key={cur[0]['key']} at {thr}")
	625	+tn_path = R / "resolver" / "top_name_tokens.csv"
	626	+if tn_path.exists():
	627	+ tn = rows(tn_path.stem, tn_path.parent)[:10]
	628	+ macro("topNameTokens", ", ".join(f"\\texttt{{{esc(r['name_tok'])}}} ({float(r['pct_of_tokenkeyed_projects']):.1f}\\%)" for r in tn), "results/resolver/top_name_tokens.csv", "top-10 tokens, pct of token-keyed projects")
	629	+ macro("topNameTokensProjectsPct", f"{sum(float(r['pct_of_tokenkeyed_projects']) for r in tn):.1f}", "results/resolver/top_name_tokens.csv", "sum of pct_of_tokenkeyed_projects over the top 10")
	630	+csv_table("tab_top_name_tokens.tex", R / "resolver" / "top_name_tokens.csv", max_rows=20)
	631	+csv_table("tab_overmerge.tex", R / "resolver" / "overmerge_by_type.csv")
	632	+csv_table("tab_june_october.tex", R / "resolver" / "june_october_reconciliation.csv")
	633	+csv_table("tab_table3_calls.tex", R / "ledger" / "table3_ledger_vs_stored.csv")
	634	+
	635	+# ---- headline macros ---------------------------------------------------------------------------------
	636	+macro("projects", n(P), "stats.json:projects", "count(projects)")
	637	+macro("mentions", n(M), "stats.json:mentions", "count(project_mentions)")
	638	+macro("issuersWithProjects", n(S["issuers_with_projects"]), "stats.json:issuers_with_projects", "count(distinct cik)")
	639	+macro("issuersWithFilings", n(S["issuers_with_filings"]), "stats.json:issuers_with_filings", "count(distinct cik) in filings")
	640	+macro("sectionsTotal", n(S["sections_total"]), "stats.json:sections_total", "count(filing_sections)")
	641	+macro("chunks", n(S["chunks"][0]), "stats.json:chunks[0]", "count(filing_chunks)")
	642	+macro("projectsWithLocation", n(S["projects_fields"][1]), "stats.json:projects_fields[1]", "count(canonical_location is not null)")
	643	+macro("projectsTokenKeyedShare", f"{100(P - S['projects_fields'][1])/P:.1f}", "stats.json:projects_fields", "100(projects - with location)/projects")
	644	+macro("projectsPerIssuerMean", f"{float(rows('projects_per_issuer')[0]['mean']):.1f}", "data/projects_per_issuer.csv", "mean")
	645	+macro("projectsPerIssuerMedian", f"{ppi[2]:.0f}", "data/projects_per_issuer.csv", "q[2]")
	646	+macro("extractedAtFirst", S["extracted_at_range"][0][:19], "stats.json:extracted_at_range[0]", "min(extracted_at)")
	647	+macro("extractedAtLast", S["extracted_at_range"][1][:19], "stats.json:extracted_at_range[1]", "max(extracted_at)")
	648	+for key, mname in (("ledger_10k_mdna_median_words", "tenKmdnaMedianWords"), ("annual_panel_firms", "annualPanelFirms"), ("sp500_ciks", "spFiveHundredCiks"),
	649	+ ("backfilled_rows", "backfilledRows"), ("backfilled_mentions", "backfilledMentions"), ("outage_rows", "outageRows"),
	650	+ ("llm_failed_outside_outage", "llmFailedOutsideOutage"), ("llm_failed_inside_outage", "llmFailedInsideOutage"), ("june_failed_calls", "juneFailedCalls")):
	651	+ if S.get(key) is not None: macro(mname, n(S[key]), f"stats.json:{key}", "export_stats.py")
	652	+if S.get("spid_runs"):
	653	+ for k, v in S["spid_runs"].items():
	654	+ if isinstance(v, dict):
	655	+ for kk, vv in v.items():
	656	+ if vv is not None: macro("run" + "".join(p.capitalize() for p in k.split("_")) + "".join(p.capitalize() for p in kk.split("_")), esc(vv), f"stats.json:spid_runs.{k}.{kk}", "export_stats.py")
	657	+if di("brief_definition"): macro("brief", di("brief_definition"), "data/documented_inputs.json:brief_definition", "documented input (author to confirm)")
	658	+
	659	+# ---- Figures ---------------------------------------------------------------------------------------------
167	660	BLUE, GOLD, GREY = "#16365c", "#c9a227", "#8a8a8a"
168	661	yrs = [int(r["yr"]) for r in iy]
169	662	fig, ax1 = plt.subplots(figsize=(7.2, 3.4))
170	663	ax1.bar(yrs, [int(r["filings"]) for r in iy], color=BLUE, alpha=.85, label="Filings (10-K, 10-Q, 8-K)")
171	664	ax1.set_ylabel("Filings per year"); ax1.set_xlabel("Filing year")
	665	+ax1.xaxis.set_major_locator(MaxNLocator(integer=True))
172	666	ax2 = ax1.twinx(); ax2.plot(yrs, [int(r["issuers"]) for r in iy], color=GOLD, marker="o", lw=2, label="Issuers with $\\geq$1 filing")
173		−ax2.set_ylabel("Issuers"); ax2.set_ylim(0, 2700)
	667	+ax2.set_ylabel("Issuers"); ax2.set_ylim(0, U["n"] * 1.05)
174	668	h1, l1 = ax1.get_legend_handles_labels(); h2, l2 = ax2.get_legend_handles_labels(); ax1.legend(h1 + h2, l1 + l2, loc="upper left", frameon=False, fontsize=8)
175	669	for a in (ax1, ax2): a.spines[["top"]].set_visible(False)
176		−fig.tight_layout(); fig.savefig(F / "fig_coverage.pdf"); plt.close(fig)
	670	+fig.tight_layout(); fig.savefig(F / "fig_coverage.pdf", metadata={"CreationDate": None}); plt.close(fig)
177	671
178	672	fig, ax = plt.subplots(figsize=(7.2, 5.2))
179	673	labs = [LAB[r["project_type"]].replace("\\&", "&") for r in pt][::-1]; vals = [int(r["n"]) for r in pt][::-1]
180	674	ax.barh(labs, vals, color=BLUE); ax.set_xlabel("Resolved projects"); ax.spines[["top", "right"]].set_visible(False)
181		−for i, v in enumerate(vals): ax.text(v + 300, i, f"{v:,}", va="center", fontsize=7)
182		−fig.tight_layout(); fig.savefig(F / "fig_types.pdf"); plt.close(fig)
	675	+for i, v in enumerate(vals): ax.text(v + max(vals) * 0.007, i, f"{v:,}", va="center", fontsize=7)
	676	+ax.xaxis.set_major_locator(MaxNLocator(integer=True))
	677	+fig.tight_layout(); fig.savefig(F / "fig_types.pdf", metadata={"CreationDate": None}); plt.close(fig)
183	678
184		−fig, ax = plt.subplots(figsize=(7.2, 3.2))
	679	+fig, (ax, axb) = plt.subplots(2, 1, figsize=(7.2, 5.6), sharex=True, gridspec_kw={"height_ratios": [3, 2]})
185	680	ax.plot(yrs, [int(my[str(y)]["mentions"]) for y in yrs], color=BLUE, marker="o", lw=2, label="Project mentions")
186	681	ax.plot(yrs, [int(py[str(y)]["n"]) for y in yrs], color=GOLD, marker="s", lw=2, label="Projects first observed")
187		−ax.set_xlabel("Filing year"); ax.set_ylabel("Count"); ax.legend(frameon=False, fontsize=8); ax.spines[["top", "right"]].set_visible(False)
188		−fig.tight_layout(); fig.savefig(F / "fig_mentions_year.pdf"); plt.close(fig)
	682	+ax.set_ylabel("Count"); ax.set_ylim(0, None); ax.legend(frameon=False, fontsize=8); ax.spines[["top", "right"]].set_visible(False)
	683	+ax.axvspan(yrs[0] - 0.5, yrs[0] + 0.5, color=GREY, alpha=.15); ax.axvspan(yrs[-1] - 0.5, yrs[-1] + 0.5, color=GREY, alpha=.15)
	684	+ax.text(yrs[0], ax.get_ylim()[1] * 0.97, "left-censored", fontsize=7, ha="center", va="top", color=GREY)
	685	+ax.text(yrs[-1], ax.get_ylim()[1] * 0.97, "partial year", fontsize=7, ha="center", va="top", color=GREY)
	686	+axb.plot(yrs, [int(my[str(y)]["mentions"]) / int(my[str(y)]["issuers"]) for y in yrs], color=BLUE, marker="o", lw=2, label="Mentions per issuer with $\\geq$1 mention")
	687	+axb.plot(yrs, [int(py[str(y)]["n"]) / int(my[str(y)]["issuers"]) for y in yrs], color=GOLD, marker="s", lw=2, label="Projects first observed per issuer with $\\geq$1 mention")
	688	+axb.set_xlabel("Filing year"); axb.set_ylabel("Per issuer"); axb.set_ylim(0, None); axb.legend(frameon=False, fontsize=8); axb.spines[["top", "right"]].set_visible(False)
	689	+axb.xaxis.set_major_locator(MaxNLocator(integer=True))
	690	+fig.tight_layout(); fig.savefig(F / "fig_mentions_year.pdf", metadata={"CreationDate": None}); plt.close(fig)
	691	+macro("newProjectsPerIssuerFirstYear", f"{int(py[str(y_first)]['n'])/int(my[str(y_first)]['issuers']):.1f}", "data/projects_by_first_seen_year.csv, mentions_by_year.csv", "first seen / issuers with mentions")
	692	+macro("newProjectsPerIssuerLastFullYear", f"{int(py[str(inner[-1])]['n'])/int(my[str(inner[-1])]['issuers']):.1f}", "data/projects_by_first_seen_year.csv, mentions_by_year.csv", "first seen / issuers with mentions")
189	693
190	694	fig, ax = plt.subplots(figsize=(7.2, 3.0))
191		−ax.bar([r["conf"] for r in cf], [int(r["n"]) for r in cf], width=0.08, color=BLUE)
	695	+ax.bar([float(r["conf"]) for r in cf], [int(r["n"]) for r in cf], width=0.08, color=BLUE)
192	696	ax.set_xlabel("Self-reported extraction confidence"); ax.set_ylabel("Mentions"); ax.spines[["top", "right"]].set_visible(False)
193		−fig.tight_layout(); fig.savefig(F / "fig_confidence.pdf"); plt.close(fig)
	697	+fig.tight_layout(); fig.savefig(F / "fig_confidence.pdf", metadata={"CreationDate": None}); plt.close(fig)
194	698	print("figures ok")
195		−json.dump(S, open(D / "stats.json", "w"), indent=2, default=str)
	699	+
	700	+# ---- inline-number macros ---------------------------------------------------------------------------------
	701	+lines = ["% Generated by code/make_tables.py — inline numbers of the paper. Do not edit; use \\SPID<name> in the text.",
	702	+ "% Source and formula of every macro: results/inline_numbers.json"]
	703	+for k, v in INLINE.items():
	704	+ lines.append(f"\\newcommand{{\\SPID{k}}}{{{v['value']}}}")
	705	+(T / "numbers.tex").write_text("\n".join(lines) + "\n")
	706	+json.dump(INLINE, open(RES_OUT / "inline_numbers.json", "w"), indent=1, ensure_ascii=False)
	707	+print(f"numbers.tex: {len(INLINE)} macros; stats.json untouched")

added data/datamodel_audit.csv +12 −0

		`@@ -0,0 +1,12 @@`
	1	+required_table,implementation,status
	2	+universe_snapshots,"\texttt{data/metadata/universe.json} + \texttt{companies} (CIK, ticker(s), name, sector, flags \texttt{in\_sp500}/\texttt{in\_russell3000}, fund weight, SIC, state, exchange, FYE, shard); snapshot date and source URL recorded","Partial: no file hash, no membership dates, no match confidence"
	3	+issuers,\texttt{companies} (one row per CIK; former names from SEC header stored in metadata JSON only),"Partial: no name history, no parent/subsidiary links"
	4	+filings,"\texttt{filings} (accession PK, CIK FK, form, filing/report dates, SEC URL, local path, size, download and parse status)","Implemented; no acceptance timestamp, no checksum"
	5	+sections,"\texttt{filing\_sections} (UUID PK, accession FK, name, item, order, text, counts)",Implemented; no character offsets into raw HTML
	6	+project_mentions,"\texttt{project\_mentions} (SHA-1 id, accession, CIK, section id, name, type, description, objective, amount, raw amount, lists, years, status, confidence, backend, issuer context)","Implemented; no evidence span, no prompt hash, no five-way label"
	7	+projects,"\texttt{projects} (MD5 of CIK$\|$type$\|$location-or-name, representative fields, max amount, counts, first/last seen and cited years)",Implemented (deterministic key)
	8	+project_mention_links,implicit in the key (every mention maps to exactly one project),"Proposed: explicit table with score, resolver version, adjudication"
	9	+project_events,"\texttt{project\_timeline} (one row per mention: date, form, status, amount, confidence, snippet)","Partial: mention rows, not typed events"
	10	+project_amounts,\texttt{amount\_usd}/\texttt{amount\_raw} on mentions; max on projects,"Proposed: type, currency, scale, basis, realization flag"
	11	+extraction_runs,"\texttt{extracted\_sections} ledger (section, accession, backend, n\_mentions, timestamp) + run logs","Partial: no prompt/schema/taxonomy hashes, no call status"
	12	+human_labels,---,Proposed

added data/documented_inputs.json +23 −0

		`@@ -0,0 +1,23 @@`
	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	+}
		\ No newline at end of file

added data/example_project.json +11 −0

		`@@ -0,0 +1,11 @@`
	1	+{
	2	+ "project_id": "3e2705ba5b2dd27408b25f0145e34250",
	3	+ "ticker": "LNG",
	4	+ "project_name": "Corpus Christi Liquefaction Stage 3 Project",
	5	+ "project_type": "plant_construction",
	6	+ "status": "in_progress",
	7	+ "total_amount_usd": "11500000000.0",
	8	+ "n_mentions": "8",
	9	+ "first_seen": "2014-04-08",
	10	+ "last_seen": "2022-03-07"
	11	+}
		\ No newline at end of file

modified paper/figures/fig_confidence.pdf +0 −0

Binary file not shown.

modified paper/figures/fig_coverage.pdf +0 −0

Binary file not shown.

modified paper/figures/fig_mentions_year.pdf +0 −0

Binary file not shown.

modified paper/figures/fig_types.pdf +0 −0

Binary file not shown.

modified paper/main.tex +2 −0

		`@@ -91,6 +91,8 @@`
91	91	\usetikzlibrary{positioning,arrows.meta,shapes.misc}
92	92	\usepackage{pdflscape}
93	93	\usepackage{adjustbox}
	94	+\usepackage{upquote} % straight quotes in verbatim (extraction contract, gate regex)
	95	+\input{tables/numbers} % generated inline-number macros (code/make_tables.py); never edit by hand
94	96
95	97	% ============================================================================
96	98	% METADATA — Edit these fields for each working paper

added paper/tables/gate_regex.tex +5 −0

		`@@ -0,0 +1,5 @@`
	1	+\begin{verbatim}
	2	+\b(project\|initiative\|program\|invest\|expan\|construct\|build\|launch\|develop\|
	3	+deploy\|implement\|acqui\|partner\|facilit\|capacity\|capital\|migrat\|transform\|
	4	+pipeline\|plant\|data ?cent\|automat\|sustainab\|renewable\|restructur)\w*
	5	+\end{verbatim}

added paper/tables/numbers.tex +209 −0

		`@@ -0,0 +1,209 @@`
	1	+% Generated by code/make_tables.py — inline numbers of the paper. Do not edit; use \SPID<name> in the text.
	2	+% Source and formula of every macro: results/inline_numbers.json
	3	+\newcommand{\SPIDiwvEquityLines}{2{,}587}
	4	+\newcommand{\SPIDuniverseN}{2{,}564}
	5	+\newcommand{\SPIDrussellDistinctCiks}{2{,}555}
	6	+\newcommand{\SPIDrussellMappedLines}{2{,}573}
	7	+\newcommand{\SPIDrussellUnmatched}{7}
	8	+\newcommand{\SPIDrussellIndexConstituents}{2{,}996}
	9	+\newcommand{\SPIDrussellProxyCoveragePct}{85.3}
	10	+\newcommand{\SPIDiwvHoldingsCount}{2{,}588}
	11	+\newcommand{\SPIDiwvReplicationMethod}{representative sampling}
	12	+\newcommand{\SPIDfilingDateFirst}{2010-01-04}
	13	+\newcommand{\SPIDfilingDateLast}{2026-10-27}
	14	+\newcommand{\SPIDfilingsTotal}{527{,}548}
	15	+\newcommand{\SPIDfilingsNotParsed}{16}
	16	+\newcommand{\SPIDfilingsMissingOnDisk}{2}
	17	+\newcommand{\SPIDrawGb}{254.5}
	18	+\newcommand{\SPIDfirstSeenYearMin}{2011}
	19	+\newcommand{\SPIDfirstSeenYearMax}{2025}
	20	+\newcommand{\SPIDfirstSeenRangeInner}{6{,}240--8{,}216}
	21	+\newcommand{\SPIDfirstSeenFirstYear}{7{,}835}
	22	+\newcommand{\SPIDfirstSeenInnerMean}{7{,}105}
	23	+\newcommand{\SPIDmentionsFirstYear}{11{,}908}
	24	+\newcommand{\SPIDmentionsLastFullYear}{23{,}220}
	25	+\newcommand{\SPIDissuersWithMentionsFirstYear}{1{,}224}
	26	+\newcommand{\SPIDissuersWithMentionsLastFullYear}{2{,}280}
	27	+\newcommand{\SPIDmentionsPerIssuerFirstYear}{9.7}
	28	+\newcommand{\SPIDmentionsPerIssuerLastFullYear}{10.2}
	29	+\newcommand{\SPIDlastYear}{2026}
	30	+\newcommand{\SPIDcallsOneZeroK}{135{,}310}
	31	+\newcommand{\SPIDcallsOneZeroQ}{363{,}973}
	32	+\newcommand{\SPIDcallsEightK}{204{,}442}
	33	+\newcommand{\SPIDledgerTotal}{1{,}123{,}098}
	34	+\newcommand{\SPIDledgerMentionsReturned}{308{,}477}
	35	+\newcommand{\SPIDledgerGap}{412}
	36	+\newcommand{\SPIDledgerGapByForm}{10-K 127, 10-Q 257, 8-K 28}
	37	+\newcommand{\SPIDmentionsStoredEightK}{74{,}566}
	38	+\newcommand{\SPIDmentionsLedgerEightK}{74{,}594}
	39	+\newcommand{\SPIDledgerSectionsEightK}{400{,}601}
	40	+\newcommand{\SPIDmentionsStoredOneZeroK}{81{,}495}
	41	+\newcommand{\SPIDmentionsLedgerOneZeroK}{81{,}622}
	42	+\newcommand{\SPIDledgerSectionsOneZeroK}{143{,}704}
	43	+\newcommand{\SPIDmentionsStoredOneZeroQ}{152{,}004}
	44	+\newcommand{\SPIDmentionsLedgerOneZeroQ}{152{,}261}
	45	+\newcommand{\SPIDledgerSectionsOneZeroQ}{578{,}793}
	46	+\newcommand{\SPIDproductiveSections}{168{,}230}
	47	+\newcommand{\SPIDproductiveShareLedger}{15.0}
	48	+\newcommand{\SPIDmentionsPerLedgerSection}{0.27}
	49	+\newcommand{\SPIDmentionsPerProductiveSection}{1.83}
	50	+\newcommand{\SPIDgatePassTotal}{703{,}725}
	51	+\newcommand{\SPIDproductiveShareCalls}{23.9}
	52	+\newcommand{\SPIDmentionsPerCall}{0.44}
	53	+\newcommand{\SPIDtenKmdnaMentions}{39{,}099}
	54	+\newcommand{\SPIDtenQmdnaMentions}{99{,}305}
	55	+\newcommand{\SPIDtenKbusinessMentions}{30{,}492}
	56	+\newcommand{\SPIDtenQfinancialStatementsMentions}{30{,}159}
	57	+\newcommand{\SPIDtenKfullBodyRows}{1{,}230}
	58	+\newcommand{\SPIDtypesPctSum}{100.1}
	59	+\newcommand{\SPIDamountMedianMusd}{128.5}
	60	+\newcommand{\SPIDsmallNThreshold}{50}
	61	+\newcommand{\SPIDsmallNCategories}{ai_initiative, automation, cloud_migration}
	62	+\newcommand{\SPIDshareDataCenter}{0.4}
	63	+\newcommand{\SPIDnDataCenter}{449}
	64	+\newcommand{\SPIDwithAmountDataCenter}{129}
	65	+\newcommand{\SPIDmedianAmountDataCenter}{166.0}
	66	+\newcommand{\SPIDshareAiInitiative}{0.3}
	67	+\newcommand{\SPIDnAiInitiative}{376}
	68	+\newcommand{\SPIDwithAmountAiInitiative}{20}
	69	+\newcommand{\SPIDmedianAmountAiInitiative}{127.5}
	70	+\newcommand{\SPIDshareCloudMigration}{0.2}
	71	+\newcommand{\SPIDnCloudMigration}{264}
	72	+\newcommand{\SPIDwithAmountCloudMigration}{35}
	73	+\newcommand{\SPIDmedianAmountCloudMigration}{50.0}
	74	+\newcommand{\SPIDshareAutomation}{0.3}
	75	+\newcommand{\SPIDnAutomation}{374}
	76	+\newcommand{\SPIDwithAmountAutomation}{25}
	77	+\newcommand{\SPIDmedianAmountAutomation}{13.7}
	78	+\newcommand{\SPIDshareMaIntegration}{34.5}
	79	+\newcommand{\SPIDnMaIntegration}{41{,}742}
	80	+\newcommand{\SPIDwithAmountMaIntegration}{28{,}044}
	81	+\newcommand{\SPIDmedianAmountMaIntegration}{155.0}
	82	+\newcommand{\SPIDshareCapexProgram}{8.9}
	83	+\newcommand{\SPIDnCapexProgram}{10{,}720}
	84	+\newcommand{\SPIDwithAmountCapexProgram}{9{,}452}
	85	+\newcommand{\SPIDmedianAmountCapexProgram}{300.0}
	86	+\newcommand{\SPIDsharePartnership}{8.2}
	87	+\newcommand{\SPIDnPartnership}{9{,}909}
	88	+\newcommand{\SPIDwithAmountPartnership}{2{,}943}
	89	+\newcommand{\SPIDmedianAmountPartnership}{75.0}
	90	+\newcommand{\SPIDshareGeographicExpansion}{6.5}
	91	+\newcommand{\SPIDnGeographicExpansion}{7{,}868}
	92	+\newcommand{\SPIDwithAmountGeographicExpansion}{1{,}431}
	93	+\newcommand{\SPIDmedianAmountGeographicExpansion}{36.7}
	94	+\newcommand{\SPIDsharePlantConstruction}{6.3}
	95	+\newcommand{\SPIDnPlantConstruction}{7{,}590}
	96	+\newcommand{\SPIDwithAmountPlantConstruction}{2{,}511}
	97	+\newcommand{\SPIDmedianAmountPlantConstruction}{56.0}
	98	+\newcommand{\SPIDtechCategoriesCountRange}{264--449}
	99	+\newcommand{\SPIDsectorTopFourPerIssuerRange}{62--75}
	100	+\newcommand{\SPIDsectorTopFourNames}{utilities, materials, energy, real estate}
	101	+\newcommand{\SPIDsectorFinancialsPerIssuer}{32}
	102	+\newcommand{\SPIDsectorProjectsHealthCare}{23{,}679}
	103	+\newcommand{\SPIDsectorIssuersHealthCare}{429}
	104	+\newcommand{\SPIDsectorProjectsIndustrials}{17{,}890}
	105	+\newcommand{\SPIDsectorIssuersIndustrials}{386}
	106	+\newcommand{\SPIDspanKnownN}{103{,}500}
	107	+\newcommand{\SPIDspanUnknownN}{17{,}599}
	108	+\newcommand{\SPIDspanUnknownShareAll}{14.5}
	109	+\newcommand{\SPIDspanZeroShareAll}{55.5}
	110	+\newcommand{\SPIDspanZeroShareKnown}{64.9}
	111	+\newcommand{\SPIDspanOverFiveShareAll}{8.5}
	112	+\newcommand{\SPIDspanOverFiveShareKnown}{10.0}
	113	+\newcommand{\SPIDstatusShareInProgress}{41.6}
	114	+\newcommand{\SPIDstatusShareCompleted}{41.0}
	115	+\newcommand{\SPIDstatusSharePlanned}{15.1}
	116	+\newcommand{\SPIDstatusShareMentioned}{2.3}
	117	+\newcommand{\SPIDsingleMentionShare}{60.2}
	118	+\newcommand{\SPIDoverTenMentionShare}{3.1}
	119	+\newcommand{\SPIDconfShareOne}{35.2}
	120	+\newcommand{\SPIDconfShareNine}{32.7}
	121	+\newcommand{\SPIDconfShareLeSix}{1.6}
	122	+\newcommand{\SPIDamountMentions}{120{,}240}
	123	+\newcommand{\SPIDamountMentionsShare}{39.0}
	124	+\newcommand{\SPIDamountProjects}{56{,}500}
	125	+\newcommand{\SPIDamountProjectsShare}{46.7}
	126	+\newcommand{\SPIDamountPTwoFiveMusd}{23}
	127	+\newcommand{\SPIDamountPSevenFiveMusd}{500}
	128	+\newcommand{\SPIDamountPNineNineBusd}{12.5}
	129	+\newcommand{\SPIDamountSumTusd}{55.9}
	130	+\newcommand{\SPIDkgNodes}{183{,}472}
	131	+\newcommand{\SPIDkgEdges}{204{,}456}
	132	+\newcommand{\SPIDkgNodesProject}{121{,}099}
	133	+\newcommand{\SPIDkgNodesPartner}{36{,}822}
	134	+\newcommand{\SPIDkgNodesLocation}{14{,}508}
	135	+\newcommand{\SPIDkgNodesTechnology}{8{,}551}
	136	+\newcommand{\SPIDkgNodesCompany}{2{,}492}
	137	+\newcommand{\SPIDprovenanceForms}{8-K}
	138	+\newcommand{\SPIDprovenanceN}{8}
	139	+\newcommand{\SPIDprovenanceFirst}{2014-04-08}
	140	+\newcommand{\SPIDprovenanceLast}{2022-03-07}
	141	+\newcommand{\SPIDprovenanceMaxAmountBusd}{11.5}
	142	+\newcommand{\SPIDprovenanceNameYear}{2022}
	143	+\newcommand{\SPIDgateRegexFlags}{re.IGNORECASE}
	144	+\newcommand{\SPIDgateRegexLength}{215}
	145	+\newcommand{\SPIDgateRegexAlternatives}{25}
	146	+\newcommand{\SPIDtaxonomyN}{21}
	147	+\newcommand{\SPIDcallsTotal}{703{,}725}
	148	+\newcommand{\SPIDgatePassSections}{703{,}737}
	149	+\newcommand{\SPIDgateRejectedSections}{419{,}361}
	150	+\newcommand{\SPIDledgerUnderThirtyWords}{1{,}070}
	151	+\newcommand{\SPIDusdPerCall}{0.0013}
	152	+\newcommand{\SPIDoctoberCalls}{608{,}439}
	153	+\newcommand{\SPIDoctoberRows}{968{,}134}
	154	+\newcommand{\SPIDoctoberWallClockHours}{13.7}
	155	+\newcommand{\SPIDoutageHours}{5.3}
	156	+\newcommand{\SPIDoctoberEffectiveHours}{8.4}
	157	+\newcommand{\SPIDoctoberRowsPerSecondEffective}{31.9}
	158	+\newcommand{\SPIDoctoberCallsPerSecondEffective}{20.1}
	159	+\newcommand{\SPIDoctoberFirstFlush}{2026-10-27 21:35}
	160	+\newcommand{\SPIDoctoberLastFlush}{2026-10-28 11:15}
	161	+\newcommand{\SPIDbackfilledRows}{154{,}964}
	162	+\newcommand{\SPIDjuneLogSections}{153{,}894}
	163	+\newcommand{\SPIDbackfilledUnderThirtyWords}{1{,}070}
	164	+\newcommand{\SPIDbackfilledMentions}{39{,}930}
	165	+\newcommand{\SPIDbackfilledCiks}{500}
	166	+\newcommand{\SPIDbackfilledGateFail}{59{,}666}
	167	+\newcommand{\SPIDoutageWindowStart}{2026-10-28 01:10}
	168	+\newcommand{\SPIDoutageWindowEnd}{2026-10-28 06:22}
	169	+\newcommand{\SPIDllmCallFailedTotal}{94{,}609}
	170	+\newcommand{\SPIDllmCallFailedInsideOutage}{94{,}467}
	171	+\newcommand{\SPIDllmCallFailedOutsideOutage}{142}
	172	+\newcommand{\SPIDllmFailedJsonDecodeError}{14}
	173	+\newcommand{\SPIDllmFailedRetryableHttpFourTwoNineFivexx}{94{,}593}
	174	+\newcommand{\SPIDllmFailedConnectionError}{2}
	175	+\newcommand{\SPIDjuneLlmCallFailed}{3}
	176	+\newcommand{\SPIDcollisionSections}{304}
	177	+\newcommand{\SPIDcollisionMentions}{412}
	178	+\newcommand{\SPIDprojectsKeyedGeneral}{229}
	179	+\newcommand{\SPIDmentionsKeyedGeneral}{2{,}152}
	180	+\newcommand{\SPIDprojectsKeyedNameToken}{66{,}405}
	181	+\newcommand{\SPIDprojectsKeyedNameTokenPct}{54.8}
	182	+\newcommand{\SPIDprojectsKeyedLocation}{54{,}658}
	183	+\newcommand{\SPIDprojectsKeyedLocationPct}{45.1}
	184	+\newcommand{\SPIDprojectsKeyedGeneralPct}{0.2}
	185	+\newcommand{\SPIDprojectsTieMaxConfidence}{33{,}820}
	186	+\newcommand{\SPIDprojectsTieDistinctNames}{20{,}118}
	187	+\newcommand{\SPIDprojectsStatusTie}{972}
	188	+\newcommand{\SPIDmentionsAtConfidenceOne}{108{,}023}
	189	+\newcommand{\SPIDprojectCountRangeKeys}{21{,}027--308{,}065}
	190	+\newcommand{\SPIDprojectCountRangeKeysN}{9}
	191	+\newcommand{\SPIDprojectCountRangeAll}{16{,}562--308{,}065}
	192	+\newcommand{\SPIDprojectCountCurrentKey}{121{,}099}
	193	+\newcommand{\SPIDtopNameTokens}{\texttt{acquisition} (3.4\%), \texttt{share} (3.1\%), \texttt{expansion} (1.8\%), \texttt{stock} (1.7\%), \texttt{investment} (1.6\%), \texttt{merger} (1.3\%), \texttt{sale} (1.3\%), \texttt{development} (1.2\%), \texttt{strategic} (0.9\%), \texttt{capital} (0.8\%)}
	194	+\newcommand{\SPIDtopNameTokensProjectsPct}{17.2}
	195	+\newcommand{\SPIDprojects}{121{,}099}
	196	+\newcommand{\SPIDmentions}{308{,}065}
	197	+\newcommand{\SPIDissuersWithProjects}{2{,}492}
	198	+\newcommand{\SPIDissuersWithFilings}{2{,}499}
	199	+\newcommand{\SPIDsectionsTotal}{1{,}342{,}283}
	200	+\newcommand{\SPIDchunks}{10{,}720{,}890}
	201	+\newcommand{\SPIDprojectsWithLocation}{54{,}583}
	202	+\newcommand{\SPIDprojectsTokenKeyedShare}{54.9}
	203	+\newcommand{\SPIDprojectsPerIssuerMean}{48.6}
	204	+\newcommand{\SPIDprojectsPerIssuerMedian}{42}
	205	+\newcommand{\SPIDextractedAtFirst}{2026-10-27 13:12:32}
	206	+\newcommand{\SPIDextractedAtLast}{2026-10-28 11:15:49}
	207	+\newcommand{\SPIDbrief}{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}
	208	+\newcommand{\SPIDnewProjectsPerIssuerFirstYear}{6.4}
	209	+\newcommand{\SPIDnewProjectsPerIssuerLastFullYear}{3.5}

modified paper/tables/prompt_verbatim.tex +21 −1

		`@@ -20,7 +20,27 @@ Return STRICT JSON: {"projects": [ ... ]}. Each project object has:`
20	20	confidence : 0.0-1.0 (how clearly this is a real, concrete project)
21	21
22	22	Allowed project_type values:
23		− - <code>: <label> (the 21 taxonomy entries of Table A1)
	23	+ - manufacturing_expansion: Manufacturing / Capacity Expansion
	24	+ - plant_construction: Plant / Site Construction
	25	+ - data_center: Data Center
	26	+ - cloud_migration: Cloud Migration
	27	+ - ai_initiative: AI / ML Initiative
	28	+ - digital_transformation: Digital Transformation
	29	+ - erp_implementation: ERP / Systems Implementation
	30	+ - rd_program: R&D Program
	31	+ - product_launch: New Product / Launch
	32	+ - drug_pipeline: Drug / Clinical Pipeline
	33	+ - ma_integration: M&A / Integration
	34	+ - geographic_expansion: Geographic Expansion
	35	+ - capex_program: Capital Expenditure Program
	36	+ - supply_chain: Supply Chain Initiative
	37	+ - automation: Automation / Robotics
	38	+ - sustainability: Sustainability / ESG
	39	+ - energy_transition: Energy Transition / Renewables
	40	+ - infrastructure: Infrastructure Investment
	41	+ - cost_reduction: Cost Reduction / Restructuring
	42	+ - partnership: Strategic Partnership
	43	+ - technology_deployment: Technology Deployment
24	44
25	45	Rules:
26	46	- Extract ONLY real initiatives, not generic risk-factor boilerplate or hypotheticals.

modified paper/tables/tab_amounts.tex +1 −1

		`@@ -5,4 +5,4 @@`
5	5	Largest amount cited per project{,} M USD ($N$ = 56{{,}}500) & 3.2 & 23 & 128.5 & 500 & 1{,}503 & 12{,}501 \\
6	6	Projects per issuer ($N$ = 2{{,}}492) & 12 & 24 & 42 & 67 & 94 & 140 \\
7	7	\bottomrule
8		−\end{tabular}
		\ No newline at end of file
	8	+\end{tabular}

added paper/tables/tab_amounts_note.tex +1 −0

		`@@ -0,0 +1 @@`
	1	+\item Amounts are the largest USD figure cited across the mentions of a project; they mix transaction values, budgets, contract values and estimates and are never summed in the text.

modified paper/tables/tab_confidence.tex +1 −1

		`@@ -9,4 +9,4 @@ Self-reported confidence (rounded) & Mentions \\`
9	9	0.9 & 100{,}831 \\
10	10	1.0 & 108{,}418 \\
11	11	\bottomrule
12		−\end{tabular}
		\ No newline at end of file
	12	+\end{tabular}

modified paper/tables/tab_coverage_year.tex +20 −20

		`@@ -1,23 +1,23 @@`
1		−\begin{tabular}{lrrrrrrr}
	1	+\begin{tabular}{lrrrrrrrr}
2	2	\toprule
3		−Year & Issuers & 10-K & 10-Q & 8-K & Mentions & Issuers w/ mentions & Projects first seen \\
	3	+Year & Issuers & 10-K & 10-Q & 8-K & Mentions & Issuers w/ mentions & Mentions per issuer & Projects first seen \\
4	4	\midrule
5		−2010 & 1{,}392 & 1{,}357 & 4{,}152 & 17{,}672 & 11{,}908 & 1{,}224 & 7{,}835 \\
6		−2011 & 1{,}424 & 1{,}409 & 4{,}260 & 18{,}533 & 13{,}551 & 1{,}287 & 6{,}679 \\
7		−2012 & 1{,}472 & 1{,}436 & 4{,}363 & 19{,}437 & 14{,}302 & 1{,}333 & 6{,}444 \\
8		−2013 & 1{,}539 & 1{,}483 & 4{,}530 & 19{,}773 & 14{,}611 & 1{,}408 & 6{,}286 \\
9		−2014 & 1{,}619 & 1{,}549 & 4{,}780 & 20{,}927 & 16{,}274 & 1{,}490 & 6{,}732 \\
10		−2015 & 1{,}689 & 1{,}635 & 4{,}983 & 22{,}077 & 17{,}073 & 1{,}535 & 6{,}675 \\
11		−2016 & 1{,}744 & 1{,}692 & 5{,}146 & 22{,}447 & 16{,}429 & 1{,}579 & 6{,}240 \\
12		−2017 & 1{,}810 & 1{,}745 & 5{,}359 & 22{,}897 & 17{,}350 & 1{,}636 & 6{,}490 \\
13		−2018 & 1{,}893 & 1{,}827 & 5{,}582 & 23{,}709 & 18{,}064 & 1{,}737 & 6{,}815 \\
14		−2019 & 1{,}973 & 1{,}903 & 5{,}829 & 24{,}256 & 18{,}737 & 1{,}806 & 6{,}837 \\
15		−2020 & 2{,}089 & 1{,}985 & 6{,}095 & 27{,}424 & 17{,}970 & 1{,}919 & 7{,}212 \\
16		−2021 & 2{,}247 & 2{,}116 & 6{,}606 & 27{,}944 & 21{,}312 & 2{,}077 & 8{,}216 \\
17		−2022 & 2{,}291 & 2{,}258 & 6{,}830 & 26{,}533 & 22{,}720 & 2{,}105 & 8{,}158 \\
18		−2023 & 2{,}329 & 2{,}295 & 6{,}938 & 26{,}851 & 22{,}955 & 2{,}129 & 7{,}977 \\
19		−2024 & 2{,}387 & 2{,}341 & 7{,}092 & 27{,}438 & 22{,}503 & 2{,}204 & 7{,}819 \\
20		−2025 & 2{,}453 & 2{,}406 & 7{,}300 & 28{,}716 & 23{,}220 & 2{,}280 & 7{,}990 \\
21		−2026 & 2{,}498 & 2{,}338 & 5{,}322 & 23{,}972 & 19{,}086 & 2{,}260 & 6{,}694 \\
	5	+2010 & 1{,}392 & 1{,}357 & 4{,}152 & 17{,}672 & 11{,}908 & 1{,}224 & 9.7 & 7{,}835 \\
	6	+2011 & 1{,}424 & 1{,}409 & 4{,}260 & 18{,}533 & 13{,}551 & 1{,}287 & 10.5 & 6{,}679 \\
	7	+2012 & 1{,}472 & 1{,}436 & 4{,}363 & 19{,}437 & 14{,}302 & 1{,}333 & 10.7 & 6{,}444 \\
	8	+2013 & 1{,}539 & 1{,}483 & 4{,}530 & 19{,}773 & 14{,}611 & 1{,}408 & 10.4 & 6{,}286 \\
	9	+2014 & 1{,}619 & 1{,}549 & 4{,}780 & 20{,}927 & 16{,}274 & 1{,}490 & 10.9 & 6{,}732 \\
	10	+2015 & 1{,}689 & 1{,}635 & 4{,}983 & 22{,}077 & 17{,}073 & 1{,}535 & 11.1 & 6{,}675 \\
	11	+2016 & 1{,}744 & 1{,}692 & 5{,}146 & 22{,}447 & 16{,}429 & 1{,}579 & 10.4 & 6{,}240 \\
	12	+2017 & 1{,}810 & 1{,}745 & 5{,}359 & 22{,}897 & 17{,}350 & 1{,}636 & 10.6 & 6{,}490 \\
	13	+2018 & 1{,}893 & 1{,}827 & 5{,}582 & 23{,}709 & 18{,}064 & 1{,}737 & 10.4 & 6{,}815 \\
	14	+2019 & 1{,}973 & 1{,}903 & 5{,}829 & 24{,}256 & 18{,}737 & 1{,}806 & 10.4 & 6{,}837 \\
	15	+2020 & 2{,}089 & 1{,}985 & 6{,}095 & 27{,}424 & 17{,}970 & 1{,}919 & 9.4 & 7{,}212 \\
	16	+2021 & 2{,}247 & 2{,}116 & 6{,}606 & 27{,}944 & 21{,}312 & 2{,}077 & 10.3 & 8{,}216 \\
	17	+2022 & 2{,}291 & 2{,}258 & 6{,}830 & 26{,}533 & 22{,}720 & 2{,}105 & 10.8 & 8{,}158 \\
	18	+2023 & 2{,}329 & 2{,}295 & 6{,}938 & 26{,}851 & 22{,}955 & 2{,}129 & 10.8 & 7{,}977 \\
	19	+2024 & 2{,}387 & 2{,}341 & 7{,}092 & 27{,}438 & 22{,}503 & 2{,}204 & 10.2 & 7{,}819 \\
	20	+2025 & 2{,}453 & 2{,}406 & 7{,}300 & 28{,}716 & 23{,}220 & 2{,}280 & 10.2 & 7{,}990 \\
	21	+2026 & 2{,}498 & 2{,}338 & 5{,}322 & 23{,}972 & 19{,}086 & 2{,}260 & 8.4 & 6{,}694 \\
22	22	\bottomrule
23		−\end{tabular}
		\ No newline at end of file
	23	+\end{tabular}

added paper/tables/tab_datamodel.tex +24 −0

		`@@ -0,0 +1,24 @@`
	1	+\begin{longtable}{p{3.1cm}p{8.6cm}p{4.3cm}}
	2	+\caption{Tables required by the research design, current implementation and status}\label{tab:datamodel}\\
	3	+\toprule
	4	+Required table & Current implementation (database, table, key fields) & Status \\
	5	+\midrule
	6	+\endfirsthead
	7	+\toprule
	8	+Required table & Current implementation (database, table, key fields) & Status \\
	9	+\midrule
	10	+\endhead
	11	+\bottomrule
	12	+\endfoot
	13	+\texttt{universe\_snapshots} & \texttt{data/metadata/universe.json} + \texttt{companies} (CIK, ticker(s), name, sector, flags \texttt{in\_sp500}/\texttt{in\_russell3000}, fund weight, SIC, state, exchange, FYE, shard); snapshot date and source URL recorded & Partial: no file hash, no membership dates, no match confidence \\
	14	+\texttt{issuers} & \texttt{companies} (one row per CIK; former names from SEC header stored in metadata JSON only) & Partial: no name history, no parent/subsidiary links \\
	15	+\texttt{filings} & \texttt{filings} (accession PK, CIK FK, form, filing/report dates, SEC URL, local path, size, download and parse status) & Implemented; no acceptance timestamp, no checksum \\
	16	+\texttt{sections} & \texttt{filing\_sections} (UUID PK, accession FK, name, item, order, text, counts) & Implemented; no character offsets into raw HTML \\
	17	+\texttt{project\_mentions} & \texttt{project\_mentions} (SHA-1 id, accession, CIK, section id, name, type, description, objective, amount, raw amount, lists, years, status, confidence, backend, issuer context) & Implemented; no evidence span, no prompt hash, no five-way label \\
	18	+\texttt{projects} & \texttt{projects} (MD5 of CIK$\|$type$\|$location-or-name, representative fields, max amount, counts, first/last seen and cited years) & Implemented (deterministic key) \\
	19	+\texttt{project\_mention\_links} & implicit in the key (every mention maps to exactly one project) & Proposed: explicit table with score, resolver version, adjudication \\
	20	+\texttt{project\_events} & \texttt{project\_timeline} (one row per mention: date, form, status, amount, confidence, snippet) & Partial: mention rows, not typed events \\
	21	+\texttt{project\_amounts} & \texttt{amount\_usd}/\texttt{amount\_raw} on mentions; max on projects & Proposed: type, currency, scale, basis, realization flag \\
	22	+\texttt{extraction\_runs} & \texttt{extracted\_sections} ledger (section, accession, backend, n\_mentions, timestamp) + run logs & Partial: no prompt/schema/taxonomy hashes, no call status \\
	23	+\texttt{human\_labels} & --- & Proposed \\
	24	+\end{longtable}

modified paper/tables/tab_filings.tex +1 −1

		`@@ -8,4 +8,4 @@ Form & Filings & First filing & Last filing & Raw HTML (GB) & Not parsed \\`
8	8	\midrule
9	9	Total & 527{,}548 & 2010-01-04 & 2026-10-27 & 254.5 & 16 \\
10	10	\bottomrule
11		−\end{tabular}
		\ No newline at end of file
	11	+\end{tabular}

added paper/tables/tab_fp_classes.tex +67 −0

		`@@ -0,0 +1,67 @@`
	1	+\begin{tabular}{lrrrrrrr}
	2	+\toprule
	3	+form\_type & item & project\_type & mentions & matched & pct & matched\_amount\_gusd & total\_amount\_gusd \\
	4	+\midrule
	5	+8-K & full\_body & ma\_integration & 41{,}635 & 6{,}055 & 14.54 & 4{,}431.64 & 21{,}674.49 \\
	6	+10-Q & md\_and\_a & ma\_integration & 32{,}011 & 319 & 1.0 & 297.7 & 15{,}025.4 \\
	7	+10-Q & financial\_statements & ma\_integration & 19{,}165 & 260 & 1.36 & 158.12 & 7{,}994.15 \\
	8	+10-K & md\_and\_a & ma\_integration & 14{,}027 & 60 & 0.43 & 159.74 & 6{,}818.94 \\
	9	+10-Q & md\_and\_a & drug\_pipeline & 12{,}341 & 1 & 0.01 & & 161.52 \\
	10	+10-K & business & ma\_integration & 10{,}554 & 21 & 0.2 & 3.23 & 7{,}258.55 \\
	11	+8-K & full\_body & capex\_program & 10{,}415 & 7{,}135 & 68.51 & 5{,}436.73 & 7{,}873.23 \\
	12	+10-Q & md\_and\_a & geographic\_expansion & 7{,}602 & 2 & 0.03 & & 461.42 \\
	13	+10-Q & md\_and\_a & plant\_construction & 6{,}624 & 1 & 0.02 & 3.0 & 882.35 \\
	14	+10-Q & md\_and\_a & product\_launch & 5{,}935 & 1 & 0.02 & & 119.1 \\
	15	+10-Q & md\_and\_a & partnership & 5{,}563 & 38 & 0.68 & 16.44 & 2{,}199.1 \\
	16	+10-Q & md\_and\_a & rd\_program & 5{,}221 & 0 & 0.0 & & 169.15 \\
	17	+8-K & full\_body & partnership & 4{,}919 & 170 & 3.46 & 127.29 & 1{,}238.44 \\
	18	+10-Q & unregistered\_sales & ma\_integration & 4{,}565 & 2{,}334 & 51.13 & 1{,}995.02 & 2{,}281.79 \\
	19	+10-Q & md\_and\_a & cost\_reduction & 4{,}437 & 111 & 2.5 & 79.52 & 571.57 \\
	20	+8-K & full\_body & drug\_pipeline & 4{,}308 & 4 & 0.09 & 0.25 & 118.97 \\
	21	+10-Q & md\_and\_a & capex\_program & 4{,}088 & 856 & 20.94 & 796.27 & 2{,}998.47 \\
	22	+10-K & md\_and\_a & drug\_pipeline & 3{,}992 & 0 & 0.0 & & 28.52 \\
	23	+10-Q & md\_and\_a & manufacturing\_expansion & 3{,}870 & 3 & 0.08 & & 182.76 \\
	24	+10-Q & controls\_and\_procedures & ma\_integration & 3{,}536 & 5 & 0.14 & 0.43 & 248.21 \\
	25	+8-K & full\_body & cost\_reduction & 3{,}361 & 643 & 19.13 & 266.15 & 807.44 \\
	26	+10-K & properties & plant\_construction & 3{,}266 & 0 & 0.0 & & 132.04 \\
	27	+10-K & md\_and\_a & geographic\_expansion & 3{,}156 & 2 & 0.06 & & 363.7 \\
	28	+10-K & business & drug\_pipeline & 3{,}141 & 0 & 0.0 & & 25.43 \\
	29	+10-Q & md\_and\_a & infrastructure & 3{,}047 & 4 & 0.13 & 1.85 & 3{,}464.59 \\
	30	+10-K & business & geographic\_expansion & 2{,}833 & 0 & 0.0 & & 658.32 \\
	31	+10-Q & controls\_and\_procedures & erp\_implementation & 2{,}703 & 0 & 0.0 & & 61.61 \\
	32	+10-Q & md\_and\_a & digital\_transformation & 2{,}484 & 0 & 0.0 & & 67.68 \\
	33	+10-K & business & product\_launch & 2{,}462 & 0 & 0.0 & & 51.71 \\
	34	+10-Q & md\_and\_a & technology\_deployment & 2{,}410 & 35 & 1.45 & 16.79 & 179.42 \\
	35	+10-K & md\_and\_a & plant\_construction & 2{,}310 & 3 & 0.13 & 0.34 & 286.23 \\
	36	+10-K & md\_and\_a & product\_launch & 2{,}285 & 0 & 0.0 & & 80.96 \\
	37	+10-K & md\_and\_a & partnership & 2{,}246 & 16 & 0.71 & 7.36 & 223.79 \\
	38	+10-Q & risk\_factors & ma\_integration & 2{,}133 & 20 & 0.94 & 10.78 & 962.24 \\
	39	+10-K & md\_and\_a & rd\_program & 2{,}001 & 0 & 0.0 & & 125.19 \\
	40	+8-K & full\_body & plant\_construction & 1{,}983 & 23 & 1.16 & 4.29 & 685.84 \\
	41	+10-K & business & rd\_program & 1{,}898 & 0 & 0.0 & & 186.29 \\
	42	+10-K & business & partnership & 1{,}880 & 1 & 0.05 & 0.3 & 132.91 \\
	43	+10-Q & unregistered\_sales & capex\_program & 1{,}740 & 1{,}419 & 81.55 & 1{,}841.69 & 1{,}972.31 \\
	44	+10-Q & financial\_statements & drug\_pipeline & 1{,}735 & 0 & 0.0 & & 9.85 \\
	45	+10-K & business & plant\_construction & 1{,}671 & 1 & 0.06 & 0.51 & 104.63 \\
	46	+10-Q & financial\_statements & partnership & 1{,}664 & 56 & 3.37 & 35.31 & 185.07 \\
	47	+8-K & full\_body & infrastructure & 1{,}651 & 24 & 1.45 & 15.03 & 540.82 \\
	48	+10-K & md\_and\_a & cost\_reduction & 1{,}564 & 23 & 1.47 & 15.4 & 216.18 \\
	49	+10-K & md\_and\_a & capex\_program & 1{,}507 & 372 & 24.68 & 392.53 & 1{,}848.99 \\
	50	+10-Q & financial\_statements & cost\_reduction & 1{,}448 & 159 & 10.98 & 112.79 & 201.78 \\
	51	+10-K & md\_and\_a & manufacturing\_expansion & 1{,}392 & 3 & 0.22 & 0.02 & 107.1 \\
	52	+10-Q & financial\_statements & plant\_construction & 1{,}385 & 6 & 0.43 & 2.18 & 168.42 \\
	53	+10-Q & unregistered\_sales & cost\_reduction & 1{,}381 & 1{,}212 & 87.76 & 1{,}020.25 & 1{,}033.64 \\
	54	+8-K & full\_body & geographic\_expansion & 1{,}286 & 12 & 0.93 & 1.71 & 122.93 \\
	55	+10-K & business & technology\_deployment & 1{,}265 & 8 & 0.63 & 10.52 & 86.41 \\
	56	+10-K & properties & geographic\_expansion & 1{,}219 & 2 & 0.16 & 0.49 & 59.64 \\
	57	+8-K & full\_body & technology\_deployment & 1{,}177 & 202 & 17.16 & 126.57 & 317.1 \\
	58	+10-K & md\_and\_a & digital\_transformation & 1{,}090 & 0 & 0.0 & & 12.71 \\
	59	+10-K & md\_and\_a & infrastructure & 1{,}067 & 3 & 0.28 & 2.16 & 1{,}525.2 \\
	60	+10-K & business & digital\_transformation & 1{,}050 & 0 & 0.0 & & 84.4 \\
	61	+10-K & business & manufacturing\_expansion & 1{,}025 & 0 & 0.0 & & 62.95 \\
	62	+10-K & md\_and\_a & technology\_deployment & 978 & 27 & 2.76 & 13.61 & 52.45 \\
	63	+8-K & full\_body & rd\_program & 968 & 4 & 0.41 & 0.75 & 217.38 \\
	64	+10-K & properties & manufacturing\_expansion & 913 & 0 & 0.0 & & 11.22 \\
	65	+\multicolumn{8}{l}{\ldots 232 more rows in \texttt{results/fp\_classes/financing\_regex\_by\_item\_type.csv}} \\
	66	+\bottomrule
	67	+\end{tabular}

modified paper/tables/tab_graph.tex +1 −1

		`@@ -11,4 +11,4 @@ Nodes & \texttt{Location} & 14{,}508 \\`
11	11	Nodes & \texttt{Technology} & 8{,}551 \\
12	12	Nodes & \texttt{Company} & 2{,}492 \\
13	13	\bottomrule
14		−\end{tabular}
		\ No newline at end of file
	14	+\end{tabular}

added paper/tables/tab_grounding.tex +67 −0

		`@@ -0,0 +1,67 @@`
	1	+\begin{tabular}{lrrrrrrrr}
	2	+\toprule
	3	+form & item & field & n\_mentions & n\_sections & n\_grounded & grounded\_share & ci\_low & ci\_high \\
	4	+\midrule
	5	+10-Q & financial\_statements & years & 27{,}098 & 18{,}213 & 27{,}085 & 1 & 0.999 & 1 \\
	6	+10-K & md\_and\_a & years & 30{,}493 & 13{,}345 & 30{,}433 & 0.998 & 0.997 & 0.999 \\
	7	+10-Q & md\_and\_a & years & 76{,}041 & 36{,}503 & 75{,}894 & 0.998 & 0.998 & 0.998 \\
	8	+8-K & full\_body & years & 69{,}075 & 59{,}295 & 68{,}920 & 0.998 & 0.997 & 0.998 \\
	9	+10-Q & risk\_factors & years & 2{,}905 & 2{,}288 & 2{,}891 & 0.995 & 0.992 & 0.997 \\
	10	+10-Q & unregistered\_sales & years & 9{,}009 & 6{,}923 & 8{,}999 & 0.999 & 0.998 & 1 \\
	11	+10-K & properties & years & 6{,}061 & 3{,}401 & 6{,}009 & 0.991 & 0.988 & 0.994 \\
	12	+10-K & business & years & 20{,}877 & 9{,}200 & 20{,}776 & 0.995 & 0.994 & 0.996 \\
	13	+10-K & quantitative\_disclosures & years & 460 & 330 & 460 & 1.0 & 1.0 & 1.0 \\
	14	+10-Q & controls\_and\_procedures & years & 6{,}606 & 5{,}434 & 6{,}571 & 0.995 & 0.993 & 0.996 \\
	15	+10-Q & legal\_proceedings & years & 679 & 558 & 677 & 0.997 & 0.993 & 1.0 \\
	16	+10-Q & quantitative\_disclosures & years & 697 & 531 & 693 & 0.994 & 0.984 & 1.0 \\
	17	+10-K & risk\_factors & years & 1{,}704 & 1{,}034 & 1{,}695 & 0.995 & 0.991 & 0.998 \\
	18	+10-Q & full\_document & years & 93 & 34 & 93 & 1.0 & 1.0 & 1.0 \\
	19	+10-K & full\_body & years & 671 & 301 & 669 & 0.997 & 0.993 & 1.0 \\
	20	+8-K & full\_body & locations & 39{,}399 & 36{,}198 & 26{,}714 & 0.678 & 0.673 & 0.683 \\
	21	+10-Q & md\_and\_a & locations & 32{,}007 & 19{,}345 & 27{,}070 & 0.846 & 0.841 & 0.851 \\
	22	+10-K & md\_and\_a & locations & 12{,}521 & 7{,}249 & 10{,}572 & 0.844 & 0.836 & 0.852 \\
	23	+10-Q & financial\_statements & locations & 11{,}964 & 9{,}096 & 9{,}225 & 0.771 & 0.762 & 0.78 \\
	24	+10-Q & controls\_and\_procedures & locations & 691 & 618 & 485 & 0.702 & 0.665 & 0.735 \\
	25	+10-K & properties & locations & 6{,}769 & 3{,}524 & 5{,}818 & 0.86 & 0.847 & 0.872 \\
	26	+10-K & risk\_factors & locations & 863 & 578 & 744 & 0.862 & 0.832 & 0.892 \\
	27	+10-K & business & locations & 11{,}424 & 6{,}107 & 9{,}918 & 0.868 & 0.86 & 0.876 \\
	28	+10-Q & risk\_factors & locations & 1{,}063 & 828 & 917 & 0.863 & 0.838 & 0.886 \\
	29	+10-Q & quantitative\_disclosures & locations & 166 & 136 & 133 & 0.801 & 0.732 & 0.861 \\
	30	+10-Q & unregistered\_sales & locations & 723 & 595 & 533 & 0.737 & 0.701 & 0.774 \\
	31	+10-K & quantitative\_disclosures & locations & 165 & 124 & 138 & 0.836 & 0.764 & 0.899 \\
	32	+10-Q & legal\_proceedings & locations & 595 & 463 & 375 & 0.63 & 0.584 & 0.674 \\
	33	+10-Q & full\_document & locations & 86 & 31 & 76 & 0.884 & 0.811 & 0.951 \\
	34	+10-K & full\_body & locations & 347 & 184 & 314 & 0.905 & 0.864 & 0.939 \\
	35	+10-K & md\_and\_a & partners & 6{,}268 & 4{,}289 & 6{,}223 & 0.993 & 0.99 & 0.995 \\
	36	+10-Q & financial\_statements & partners & 5{,}933 & 4{,}753 & 5{,}902 & 0.995 & 0.993 & 0.997 \\
	37	+8-K & full\_body & partners & 42{,}167 & 37{,}852 & 41{,}998 & 0.996 & 0.995 & 0.997 \\
	38	+10-Q & md\_and\_a & partners & 16{,}157 & 11{,}346 & 15{,}993 & 0.99 & 0.988 & 0.992 \\
	39	+10-Q & risk\_factors & partners & 1{,}359 & 1{,}189 & 1{,}352 & 0.995 & 0.991 & 0.998 \\
	40	+10-Q & controls\_and\_procedures & partners & 488 & 453 & 487 & 0.998 & 0.994 & 1.0 \\
	41	+10-Q & unregistered\_sales & partners & 1{,}964 & 1{,}599 & 1{,}939 & 0.987 & 0.981 & 0.993 \\
	42	+10-K & business & partners & 5{,}164 & 3{,}484 & 5{,}132 & 0.994 & 0.991 & 0.996 \\
	43	+10-K & properties & partners & 799 & 531 & 792 & 0.991 & 0.985 & 0.997 \\
	44	+10-Q & legal\_proceedings & partners & 313 & 282 & 308 & 0.984 & 0.968 & 0.997 \\
	45	+10-K & risk\_factors & partners & 403 & 326 & 399 & 0.99 & 0.979 & 0.998 \\
	46	+10-Q & quantitative\_disclosures & partners & 98 & 91 & 97 & 0.99 & 0.965 & 1.0 \\
	47	+10-K & quantitative\_disclosures & partners & 64 & 54 & 64 & 1.0 & 1.0 & 1.0 \\
	48	+10-K & full\_body & partners & 127 & 89 & 127 & 1.0 & 1.0 & 1.0 \\
	49	+10-Q & full\_document & partners & 16 & 10 & 16 & 1.0 & 1.0 & 1.0 \\
	50	+10-K & md\_and\_a & technologies & 5{,}311 & 3{,}624 & 3{,}252 & 0.612 & 0.596 & 0.627 \\
	51	+10-Q & controls\_and\_procedures & technologies & 2{,}014 & 1{,}957 & 1{,}820 & 0.904 & 0.89 & 0.917 \\
	52	+10-Q & financial\_statements & technologies & 3{,}218 & 2{,}625 & 1{,}968 & 0.612 & 0.591 & 0.632 \\
	53	+10-Q & unregistered\_sales & technologies & 232 & 188 & 116 & 0.5 & 0.429 & 0.574 \\
	54	+10-K & business & technologies & 5{,}448 & 3{,}379 & 3{,}654 & 0.671 & 0.655 & 0.686 \\
	55	+8-K & full\_body & technologies & 5{,}116 & 4{,}613 & 2{,}977 & 0.582 & 0.567 & 0.596 \\
	56	+10-Q & md\_and\_a & technologies & 13{,}596 & 9{,}327 & 8{,}492 & 0.625 & 0.615 & 0.635 \\
	57	+10-Q & risk\_factors & technologies & 549 & 483 & 328 & 0.597 & 0.552 & 0.645 \\
	58	+10-K & properties & technologies & 616 & 416 & 367 & 0.596 & 0.545 & 0.647 \\
	59	+10-Q & quantitative\_disclosures & technologies & 51 & 46 & 23 & 0.451 & 0.302 & 0.591 \\
	60	+10-K & risk\_factors & technologies & 367 & 297 & 223 & 0.608 & 0.549 & 0.665 \\
	61	+10-Q & legal\_proceedings & technologies & 63 & 60 & 47 & 0.746 & 0.63 & 0.854 \\
	62	+10-K & quantitative\_disclosures & technologies & 47 & 39 & 32 & 0.681 & 0.535 & 0.814 \\
	63	+10-Q & full\_document & technologies & 6 & 6 & 1 & 0.167 & 0.0 & 0.5 \\
	64	+10-K & full\_body & technologies & 106 & 71 & 61 & 0.576 & 0.462 & 0.68 \\
	65	+\multicolumn{9}{l}{\ldots 30 more rows in \texttt{results/grounding/grounding\_by\_field\_form\_item.csv}} \\
	66	+\bottomrule
	67	+\end{tabular}

modified paper/tables/tab_items.tex +17 −17

		`@@ -1,21 +1,21 @@`
1		−\begin{tabular}{llrr}
	1	+\begin{tabular}{llrrr}
2	2	\toprule
3		−Form & Section (item) & Sections extracted & Mentions \\
	3	+Form & Section (item) & Ledgered sections & Mentions & Gate passed (calls) \\
4	4	\midrule
5		−10-K & \texttt{business} & 29{,}285 & 30{,}492 \\
6		−10-K & \texttt{risk\_factors} & 29{,}158 & 2{,}797 \\
7		−10-K & \texttt{md\_and\_a} & 28{,}919 & 39{,}099 \\
8		−10-K & \texttt{properties} & 28{,}236 & 7{,}879 \\
9		−10-K & \texttt{quantitative\_disclosures} & 26{,}876 & 531 \\
10		−10-K & \texttt{full\_body} & 1{,}230 & 824 \\
	5	+10-K & \texttt{business} & 29{,}285 & 30{,}492 & 29{,}118 \\
	6	+10-K & \texttt{risk\_factors} & 29{,}158 & 2{,}797 & 28{,}941 \\
	7	+10-K & \texttt{md\_and\_a} & 28{,}919 & 39{,}099 & 28{,}050 \\
	8	+10-K & \texttt{properties} & 28{,}236 & 7{,}879 & 25{,}940 \\
	9	+10-K & \texttt{quantitative\_disclosures} & 26{,}876 & 531 & 22{,}032 \\
	10	+10-K & \texttt{full\_body} & 1{,}230 & 824 & 1{,}229 \\
11	11	\midrule
12		−10-Q & \texttt{controls\_and\_procedures} & 92{,}393 & 7{,}082 \\
13		−10-Q & \texttt{financial\_statements} & 91{,}882 & 30{,}159 \\
14		−10-Q & \texttt{md\_and\_a} & 91{,}371 & 99{,}305 \\
15		−10-Q & \texttt{quantitative\_disclosures} & 83{,}138 & 808 \\
16		−10-Q & \texttt{unregistered\_sales} & 80{,}210 & 9{,}535 \\
17		−10-Q & \texttt{risk\_factors} & 72{,}560 & 4{,}420 \\
18		−10-Q & \texttt{legal\_proceedings} & 66{,}998 & 845 \\
19		−10-Q & \texttt{full\_document} & 241 & 107 \\
	12	+10-Q & \texttt{controls\_and\_procedures} & 92{,}393 & 7{,}082 & 20{,}913 \\
	13	+10-Q & \texttt{financial\_statements} & 91{,}882 & 30{,}159 & 90{,}106 \\
	14	+10-Q & \texttt{md\_and\_a} & 91{,}371 & 99{,}305 & 90{,}269 \\
	15	+10-Q & \texttt{quantitative\_disclosures} & 83{,}138 & 808 & 46{,}720 \\
	16	+10-Q & \texttt{unregistered\_sales} & 80{,}210 & 9{,}535 & 61{,}867 \\
	17	+10-Q & \texttt{risk\_factors} & 72{,}560 & 4{,}420 & 33{,}826 \\
	18	+10-Q & \texttt{legal\_proceedings} & 66{,}998 & 845 & 20{,}031 \\
	19	+10-Q & \texttt{full\_document} & 241 & 107 & 241 \\
20	20	\bottomrule
21		−\end{tabular}
		\ No newline at end of file
	21	+\end{tabular}

added paper/tables/tab_june_october.tex +15 −0

		`@@ -0,0 +1,15 @@`
	1	+\begin{tabular}{lrrrrrr}
	2	+\toprule
	3	+in\_sp500 & run & form\_type & mentions & projects\_touched & filings & issuers \\
	4	+\midrule
	5	+False & october & 10-K & 64{,}798 & 34{,}658 & 15{,}784 & 1{,}857 \\
	6	+False & october & 10-Q & 117{,}224 & 45{,}274 & 40{,}745 & 1{,}954 \\
	7	+False & october & 8-K & 55{,}676 & 34{,}420 & 45{,}937 & 1{,}964 \\
	8	+True & backfilled\_june & 10-K & 15{,}787 & 8{,}697 & 4{,}193 & 481 \\
	9	+True & backfilled\_june & 10-Q & 5{,}817 & 2{,}071 & 2{,}028 & 84 \\
	10	+True & backfilled\_june & 8-K & 18{,}326 & 10{,}023 & 15{,}234 & 495 \\
	11	+True & october & 10-K & 910 & 649 & 222 & 97 \\
	12	+True & october & 10-Q & 28{,}963 & 11{,}030 & 10{,}684 & 455 \\
	13	+True & october & 8-K & 564 & 432 & 477 & 203 \\
	14	+\bottomrule
	15	+\end{tabular}

added paper/tables/tab_overmerge.tex +27 −0

		`@@ -0,0 +1,27 @@`
	1	+\begin{tabular}{lrrrrrrr}
	2	+\toprule
	3	+project\_type & projects & mentions & pct\_ge3\_names & pct\_ge2\_names & pct\_ge3\_partners\_among\_with\_partner & n\_ge3\_partners & pct\_multi\_all\_names\_distinct \\
	4	+\midrule
	5	+ma\_integration & 41{,}742 & 130{,}259 & 14.63 & 30.93 & 10.92 & 2{,}289 & 30.24 \\
	6	+capex\_program & 10{,}720 & 19{,}211 & 6.4 & 19.43 & 4.13 & 189 & 38.86 \\
	7	+partnership & 9{,}909 & 17{,}501 & 6.74 & 19.66 & 4.3 & 281 & 38.57 \\
	8	+geographic\_expansion & 7{,}868 & 17{,}713 & 10.18 & 25.23 & 1.88 & 14 & 35.76 \\
	9	+plant\_construction & 7{,}590 & 18{,}388 & 13.49 & 30.3 & 4.04 & 62 & 34.68 \\
	10	+cost\_reduction & 6{,}481 & 13{,}157 & 5.71 & 17.47 & 1.59 & 4 & 26.39 \\
	11	+drug\_pipeline & 5{,}360 & 26{,}755 & 27.85 & 46.19 & 11.97 & 238 & 28.07 \\
	12	+product\_launch & 5{,}356 & 12{,}456 & 12.23 & 27.97 & 3.38 & 23 & 37.89 \\
	13	+rd\_program & 5{,}080 & 11{,}758 & 11.44 & 27.52 & 3.59 & 32 & 30.05 \\
	14	+infrastructure & 4{,}481 & 8{,}510 & 7.5 & 20.78 & 2.17 & 21 & 38.05 \\
	15	+manufacturing\_expansion & 4{,}140 & 8{,}825 & 11.26 & 27.08 & 2.17 & 11 & 34.79 \\
	16	+technology\_deployment & 4{,}128 & 6{,}725 & 4.77 & 15.79 & 1.78 & 17 & 34.48 \\
	17	+digital\_transformation & 2{,}642 & 5{,}249 & 6.25 & 19.3 & 0.0 & 0 & 25.92 \\
	18	+erp\_implementation & 1{,}735 & 4{,}242 & 3.46 & 17.23 & 1.41 & 1 & 12.86 \\
	19	+sustainability & 1{,}305 & 2{,}607 & 6.13 & 15.17 & 1.06 & 2 & 26.77 \\
	20	+supply\_chain & 684 & 1{,}171 & 3.51 & 15.06 & 1.0 & 1 & 26.96 \\
	21	+data\_center & 449 & 889 & 9.35 & 26.06 & 3.64 & 6 & 46.54 \\
	22	+energy\_transition & 415 & 866 & 10.12 & 24.34 & 1.57 & 2 & 38.41 \\
	23	+ai\_initiative & 376 & 632 & 4.79 & 16.22 & 0.0 & 0 & 27.83 \\
	24	+automation & 374 & 630 & 2.67 & 13.1 & 4.17 & 1 & 28.04 \\
	25	+cloud\_migration & 264 & 521 & 5.68 & 17.05 & 0.0 & 0 & 21.88 \\
	26	+\bottomrule
	27	+\end{tabular}

modified paper/tables/tab_provenance.tex +1 −1

		`@@ -11,4 +11,4 @@ Accession & Filed & Form & Status / amount & Evidence snippet (model-generated d`
11	11	\texttt{0001193125-15-186045} & 2015-05-13 & 8-K & in\_progress / 11.5 B USD & The project involves the development, construction, operation, and maintenance of a natural gas liquefaction and export facility and related infrastructure in San Patrici \\
12	12	\texttt{0000003570-22-000029} & 2022-03-07 & 8-K & in\_progress / 5.5 B USD & The project involves the engineering, procurement, construction, pre-commissioning, commissioning, start-up, and testing of a mid-scale natural gas liquefaction facility \\
13	13	\bottomrule
14		−\end{tabular}
		\ No newline at end of file
	14	+\end{tabular}

modified paper/tables/tab_reconciliation.tex +2 −2

		`@@ -2,7 +2,7 @@`
2	2	\toprule
3	3	Step & Count \\
4	4	\midrule
5		−iShares IWV holdings file, equity lines with a ticker (as of Oct 23, 2026) & 2{,}587 \\
	5	+iShares IWV holdings file, equity lines with a ticker (as of Oct 23, 2026); count reported by the build log, source file not archived & 2{,}587 \\
6	6	\quad of which mapped to an SEC CIK (CVRs, escrow lines and FDIC-only banks excluded) & 2{,}573 \\
7	7	\quad distinct CIKs (share classes collapsed) & 2{,}555 \\
8	8	S\&P~500 constituents, cached snapshot of 2026-05-25 (500 CIKs) & 503 \\
		`@@ -16,4 +16,4 @@ Issuers with at least one 10-K, 10-Q or 8-K since 2010 & 2{,}499 \\`
16	16	Issuers without any such filing (foreign private issuers filing 20-F/40-F, FDIC-only banks) & 65 \\
17	17	Issuers with at least one resolved project & 2{,}492 \\
18	18	\bottomrule
19		−\end{tabular}
		\ No newline at end of file
	19	+\end{tabular}

modified paper/tables/tab_sections.tex +7 −7

		`@@ -1,11 +1,11 @@`
1		−\begin{tabular}{lrrrrrr}
	1	+\begin{tabular}{lrrrrrrrr}
2	2	\toprule
3		−Form & Parsed sections & Median words & Sections sent to the extractor & Sections with $\geq 1$ mention & Mentions & Issuers \\
	3	+Form & Parsed sections & Median words & Ledgered sections ($\geq$ 30 words) & Gate-passing calls & Sections with $\geq 1$ mention & Mentions returned by the model (ledger) & Mentions stored & Issuers \\
4	4	\midrule
5		−10-K & 341{,}207 & 875 & 143{,}704 & 30{,}877 & 81{,}622 & 2{,}464 \\
6		−10-Q & 600{,}471 & 500 & 578{,}793 & 75{,}705 & 152{,}261 & 2{,}494 \\
7		−8-K & 400{,}605 & 575 & 400{,}601 & 61{,}648 & 74{,}594 & 2{,}499 \\
	5	+10-K & 341{,}207 & 875 & 143{,}704 & 135{,}310 & 30{,}877 & 81{,}622 & 81{,}495 & 2{,}464 \\
	6	+10-Q & 600{,}471 & 500 & 578{,}793 & 363{,}973 & 75{,}705 & 152{,}261 & 152{,}004 & 2{,}494 \\
	7	+8-K & 400{,}605 & 575 & 400{,}601 & 204{,}442 & 61{,}648 & 74{,}594 & 74{,}566 & 2{,}499 \\
8	8	\midrule
9		−Total & 1{,}342{,}283 & & 1{,}123{,}098 & 168{,}230 & 308{,}477 & 2{,}499 \\
	9	+Total & 1{,}342{,}283 & & 1{,}123{,}098 & 703{,}725 & 168{,}230 & 308{,}477 & 308{,}065 & 2{,}499$^{\dagger}$ \\
10	10	\bottomrule
11		−\end{tabular}
		\ No newline at end of file
	11	+\end{tabular}

added paper/tables/tab_sections_note.tex +1 −0

		`@@ -0,0 +1 @@`
	1	+\item ``Ledgered sections'' counts rows of the \texttt{extracted\_sections} ledger (sections with at least 30 words; for 10-Ks restricted to the items of Table~\ref{tab:items}); the ledger does not record whether the candidate gate passed or whether the API call succeeded, so this is not a count of calls; ``Gate-passing calls'' recomputes the candidate gate of Appendix~\ref{app:prompt} over the ledgered text (703{,}725 sections reached the model). ``Mentions returned by the model'' is $\sum$\texttt{n\_mentions} over the ledger (308{,}477); ``Mentions stored'' is the row count of \texttt{project\_mentions} (308{,}065). The difference of 412 (10-K 127, 10-Q 257, 8-K 28), spread over 304 sections, is the number of mentions overwritten by mention-identifier collisions before storage (Section~\ref{sec:construct}). $^{\dagger}$Issuers with at least one filing of any form, not a column sum.

modified paper/tables/tab_sectors.tex +1 −1

		`@@ -14,4 +14,4 @@ Consumer Staples & 103 & 36 & 103 & 5{,}921 & 57.5 \\`
14	14	Utilities & 68 & 31 & 66 & 4{,}920 & 74.5 \\
15	15	Communication Services & 105 & 20 & 101 & 4{,}520 & 44.8 \\
16	16	\bottomrule
17		−\end{tabular}
		\ No newline at end of file
	17	+\end{tabular}

added paper/tables/tab_spec_curve.tex +51 −0

		`@@ -0,0 +1,51 @@`
	1	+\begin{tabular}{lrrrrrrrr}
	2	+\toprule
	3	+key & threshold & projects & mentions & single\_mention\_pct & gt10\_mention\_pct & mean\_mentions & max\_cluster & example\_cluster\_size\_cheniere \\
	4	+\midrule
	5	+k\_cik\_type & 0.45 & 21{,}027 & 308{,}065 & 20.69 & 29.82 & 14.651 & 399 & 176 \\
	6	+k\_cik\_type & 0.6 & 21{,}001 & 306{,}454 & 20.74 & 29.76 & 14.592 & 399 & 176 \\
	7	+k\_cik\_type & 0.7 & 20{,}878 & 303{,}175 & 20.76 & 29.48 & 14.521 & 399 & 175 \\
	8	+k\_cik\_type & 0.8 & 20{,}053 & 281{,}241 & 21.63 & 28.19 & 14.025 & 375 & 171 \\
	9	+k\_cik\_type & 0.9 & 16{,}562 & 207{,}150 & 25.35 & 24.03 & 12.508 & 343 & 106 \\
	10	+k\_type\_dropped & 0.45 & 96{,}749 & 308{,}065 & 52.59 & 4.99 & 3.184 & 269 & 11 \\
	11	+k\_type\_dropped & 0.6 & 96{,}438 & 306{,}454 & 52.61 & 4.96 & 3.178 & 269 & 11 \\
	12	+k\_type\_dropped & 0.7 & 95{,}580 & 303{,}175 & 52.64 & 4.95 & 3.172 & 269 & 11 \\
	13	+k\_type\_dropped & 0.8 & 89{,}818 & 281{,}241 & 53.07 & 4.84 & 3.131 & 269 & 11 \\
	14	+k\_type\_dropped & 0.9 & 70{,}174 & 207{,}150 & 54.53 & 4.26 & 2.952 & 250 & 10 \\
	15	+k\_current & 0.45 & 121{,}099 & 308{,}065 & 60.23 & 3.11 & 2.544 & 269 & 8 \\
	16	+k\_current & 0.6 & 120{,}621 & 306{,}454 & 60.24 & 3.1 & 2.541 & 269 & 8 \\
	17	+k\_current & 0.7 & 119{,}427 & 303{,}175 & 60.26 & 3.1 & 2.539 & 269 & 8 \\
	18	+k\_current & 0.8 & 111{,}079 & 281{,}241 & 60.47 & 3.05 & 2.532 & 269 & 8 \\
	19	+k\_current & 0.9 & 83{,}483 & 207{,}150 & 61.35 & 2.91 & 2.481 & 250 & 7 \\
	20	+k\_current\_stopwords & 0.45 & 130{,}101 & 308{,}065 & 59.05 & 2.49 & 2.368 & 209 & 8 \\
	21	+k\_current\_stopwords & 0.6 & 129{,}601 & 306{,}454 & 59.06 & 2.48 & 2.365 & 209 & 8 \\
	22	+k\_current\_stopwords & 0.7 & 128{,}404 & 303{,}175 & 59.09 & 2.47 & 2.361 & 209 & 8 \\
	23	+k\_current\_stopwords & 0.8 & 119{,}990 & 281{,}241 & 59.21 & 2.4 & 2.344 & 209 & 8 \\
	24	+k\_current\_stopwords & 0.9 & 91{,}918 & 207{,}150 & 59.72 & 2.08 & 2.254 & 206 & 7 \\
	25	+k\_city\_normalised & 0.45 & 123{,}246 & 308{,}065 & 56.83 & 2.84 & 2.5 & 212 & 8 \\
	26	+k\_city\_normalised & 0.6 & 122{,}760 & 306{,}454 & 56.83 & 2.83 & 2.496 & 212 & 8 \\
	27	+k\_city\_normalised & 0.7 & 121{,}588 & 303{,}175 & 56.84 & 2.82 & 2.493 & 212 & 8 \\
	28	+k\_city\_normalised & 0.8 & 113{,}404 & 281{,}241 & 56.88 & 2.75 & 2.48 & 212 & 8 \\
	29	+k\_city\_normalised & 0.9 & 86{,}347 & 207{,}150 & 57.02 & 2.42 & 2.399 & 209 & 7 \\
	30	+k\_name\_only & 0.45 & 114{,}244 & 308{,}065 & 56.41 & 3.74 & 2.697 & 230 & 40 \\
	31	+k\_name\_only & 0.6 & 113{,}779 & 306{,}454 & 56.41 & 3.73 & 2.693 & 230 & 40 \\
	32	+k\_name\_only & 0.7 & 112{,}652 & 303{,}175 & 56.43 & 3.73 & 2.691 & 230 & 39 \\
	33	+k\_name\_only & 0.8 & 104{,}680 & 281{,}241 & 56.44 & 3.72 & 2.687 & 230 & 39 \\
	34	+k\_name\_only & 0.9 & 78{,}834 & 207{,}150 & 56.48 & 3.57 & 2.628 & 226 & 25 \\
	35	+k\_two\_tokens & 0.45 & 145{,}697 & 308{,}065 & 62.96 & 1.74 & 2.114 & 209 & 8 \\
	36	+k\_two\_tokens & 0.6 & 145{,}122 & 306{,}454 & 62.97 & 1.73 & 2.112 & 209 & 8 \\
	37	+k\_two\_tokens & 0.7 & 143{,}667 & 303{,}175 & 62.95 & 1.72 & 2.11 & 209 & 8 \\
	38	+k\_two\_tokens & 0.8 & 133{,}671 & 281{,}241 & 62.92 & 1.69 & 2.104 & 209 & 8 \\
	39	+k\_two\_tokens & 0.9 & 100{,}490 & 207{,}150 & 62.93 & 1.51 & 2.061 & 206 & 7 \\
	40	+k\_strict & 0.45 & 198{,}488 & 308{,}065 & 75.78 & 0.52 & 1.552 & 206 & 1 \\
	41	+k\_strict & 0.6 & 197{,}673 & 306{,}454 & 75.8 & 0.51 & 1.55 & 206 & 1 \\
	42	+k\_strict & 0.7 & 195{,}703 & 303{,}175 & 75.82 & 0.5 & 1.549 & 206 & 1 \\
	43	+k\_strict & 0.8 & 182{,}052 & 281{,}241 & 75.92 & 0.49 & 1.545 & 206 & 1 \\
	44	+k\_strict & 0.9 & 135{,}411 & 207{,}150 & 76.17 & 0.4 & 1.53 & 203 & 1 \\
	45	+k\_mention\_level & 0.45 & 308{,}065 & 308{,}065 & 100.0 & 0.0 & 1.0 & 1 & 1 \\
	46	+k\_mention\_level & 0.6 & 306{,}454 & 306{,}454 & 100.0 & 0.0 & 1.0 & 1 & 1 \\
	47	+k\_mention\_level & 0.7 & 303{,}175 & 303{,}175 & 100.0 & 0.0 & 1.0 & 1 & 1 \\
	48	+k\_mention\_level & 0.8 & 281{,}241 & 281{,}241 & 100.0 & 0.0 & 1.0 & 1 & 1 \\
	49	+k\_mention\_level & 0.9 & 207{,}150 & 207{,}150 & 100.0 & 0.0 & 1.0 & 1 & 1 \\
	50	+\bottomrule
	51	+\end{tabular}

modified paper/tables/tab_status.tex +1 −1

		`@@ -8,4 +8,4 @@ Latest status & Projects & Mentions per project & Projects & Span of cited years`
8	8	\texttt{mentioned} & 2{,}745 & 6-10 & 6{,}173 & $>$5 years & 10{,}326 \\
9	9	& & >10 & 3{,}769 & unknown years & 17{,}599 \\
10	10	\bottomrule
11		−\end{tabular}
		\ No newline at end of file
	11	+\end{tabular}

added paper/tables/tab_table3_calls.tex +9 −0

		`@@ -0,0 +1,9 @@`
	1	+\begin{tabular}{lrrrrrrr}
	2	+\toprule
	3	+form\_type & ledger\_rows & calls & with\_mentions & returned\_by\_model\_before\_dedup & stored\_mentions & issuers & issuers\_with\_mentions \\
	4	+\midrule
	5	+10-K & 143{,}704 & 135{,}310 & 30{,}877 & 81{,}622 & 81{,}495 & 2{,}464 & 2{,}344 \\
	6	+10-Q & 578{,}793 & 363{,}973 & 75{,}705 & 152{,}261 & 152{,}004 & 2{,}494 & 2{,}446 \\
	7	+8-K & 400{,}601 & 204{,}442 & 61{,}648 & 74{,}594 & 74{,}566 & 2{,}499 & 2{,}462 \\
	8	+\bottomrule
	9	+\end{tabular}

added paper/tables/tab_timeseries_cohort.tex +40 −0

		`@@ -0,0 +1,40 @@`
	1	+\begin{tabular}{lrrrrrrrrrr}
	2	+\toprule
	3	+series & year & issuers\_filing & mentions & issuers\_with\_mentions & mentions\_per\_issuer\_filing & first\_seen\_current\_key & first\_seen\_per\_issuer & first\_seen\_k3 & first\_seen\_k5 & flag \\
	4	+\midrule
	5	+all\_issuers & 2{,}010 & 1{,}392 & 11{,}908 & 1{,}224 & 8.55 & 7{,}835 & 5.63 & 7{,}835 & 7{,}835 & left-censored \\
	6	+all\_issuers & 2{,}011 & 1{,}424 & 13{,}551 & 1{,}287 & 9.52 & 6{,}679 & 4.69 & 6{,}679 & 6{,}679 & \\
	7	+all\_issuers & 2{,}012 & 1{,}472 & 14{,}302 & 1{,}333 & 9.72 & 6{,}444 & 4.38 & 6{,}444 & 6{,}444 & \\
	8	+all\_issuers & 2{,}013 & 1{,}539 & 14{,}611 & 1{,}408 & 9.49 & 6{,}286 & 4.08 & 6{,}385 & 6{,}286 & \\
	9	+all\_issuers & 2{,}014 & 1{,}619 & 16{,}274 & 1{,}490 & 10.05 & 6{,}732 & 4.16 & 7{,}004 & 6{,}732 & \\
	10	+all\_issuers & 2{,}015 & 1{,}689 & 17{,}073 & 1{,}535 & 10.11 & 6{,}675 & 3.95 & 7{,}092 & 6{,}734 & \\
	11	+all\_issuers & 2{,}016 & 1{,}744 & 16{,}429 & 1{,}579 & 9.42 & 6{,}240 & 3.58 & 6{,}710 & 6{,}372 & \\
	12	+all\_issuers & 2{,}017 & 1{,}810 & 17{,}350 & 1{,}636 & 9.59 & 6{,}490 & 3.59 & 7{,}120 & 6{,}725 & \\
	13	+all\_issuers & 2{,}018 & 1{,}893 & 18{,}064 & 1{,}737 & 9.54 & 6{,}815 & 3.6 & 7{,}529 & 7{,}115 & \\
	14	+all\_issuers & 2{,}019 & 1{,}973 & 18{,}737 & 1{,}806 & 9.5 & 6{,}837 & 3.47 & 7{,}644 & 7{,}208 & \\
	15	+all\_issuers & 2{,}020 & 2{,}089 & 17{,}970 & 1{,}919 & 8.6 & 7{,}212 & 3.45 & 8{,}010 & 7{,}649 & \\
	16	+all\_issuers & 2{,}021 & 2{,}247 & 21{,}312 & 2{,}077 & 9.48 & 8{,}216 & 3.66 & 9{,}191 & 8{,}732 & \\
	17	+all\_issuers & 2{,}022 & 2{,}291 & 22{,}720 & 2{,}105 & 9.92 & 8{,}158 & 3.56 & 9{,}135 & 8{,}689 & \\
	18	+all\_issuers & 2{,}023 & 2{,}329 & 22{,}955 & 2{,}129 & 9.86 & 7{,}977 & 3.43 & 9{,}061 & 8{,}557 & \\
	19	+all\_issuers & 2{,}024 & 2{,}387 & 22{,}503 & 2{,}204 & 9.43 & 7{,}819 & 3.28 & 8{,}954 & 8{,}500 & \\
	20	+all\_issuers & 2{,}025 & 2{,}453 & 23{,}220 & 2{,}280 & 9.47 & 7{,}990 & 3.26 & 9{,}252 & 8{,}719 & \\
	21	+all\_issuers & 2{,}026 & 2{,}498 & 19{,}086 & 2{,}260 & 7.64 & 6{,}694 & 2.68 & 7{,}778 & 7{,}342 & partial year \\
	22	+fixed\_2010\_cohort & 2{,}010 & 1{,}389 & 11{,}889 & 1{,}221 & 8.56 & 7{,}819 & 5.63 & 7{,}819 & 7{,}819 & left-censored \\
	23	+fixed\_2010\_cohort & 2{,}011 & 1{,}389 & 13{,}333 & 1{,}255 & 9.6 & 6{,}533 & 4.7 & 6{,}533 & 6{,}533 & \\
	24	+fixed\_2010\_cohort & 2{,}012 & 1{,}389 & 13{,}775 & 1{,}262 & 9.92 & 6{,}125 & 4.41 & 6{,}125 & 6{,}125 & \\
	25	+fixed\_2010\_cohort & 2{,}013 & 1{,}389 & 13{,}411 & 1{,}276 & 9.66 & 5{,}602 & 4.03 & 5{,}701 & 5{,}602 & \\
	26	+fixed\_2010\_cohort & 2{,}014 & 1{,}389 & 13{,}999 & 1{,}285 & 10.08 & 5{,}583 & 4.02 & 5{,}852 & 5{,}583 & \\
	27	+fixed\_2010\_cohort & 2{,}015 & 1{,}389 & 14{,}038 & 1{,}270 & 10.11 & 5{,}288 & 3.81 & 5{,}700 & 5{,}347 & \\
	28	+fixed\_2010\_cohort & 2{,}016 & 1{,}389 & 13{,}093 & 1{,}275 & 9.43 & 4{,}810 & 3.46 & 5{,}260 & 4{,}941 & \\
	29	+fixed\_2010\_cohort & 2{,}017 & 1{,}389 & 13{,}088 & 1{,}258 & 9.42 & 4{,}674 & 3.37 & 5{,}274 & 4{,}907 & \\
	30	+fixed\_2010\_cohort & 2{,}018 & 1{,}389 & 13{,}035 & 1{,}271 & 9.38 & 4{,}719 & 3.4 & 5{,}373 & 5{,}009 & \\
	31	+fixed\_2010\_cohort & 2{,}019 & 1{,}389 & 12{,}937 & 1{,}277 & 9.31 & 4{,}496 & 3.24 & 5{,}235 & 4{,}852 & \\
	32	+fixed\_2010\_cohort & 2{,}020 & 1{,}389 & 11{,}371 & 1{,}294 & 8.19 & 4{,}380 & 3.15 & 5{,}069 & 4{,}779 & \\
	33	+fixed\_2010\_cohort & 2{,}021 & 1{,}389 & 12{,}376 & 1{,}284 & 8.91 & 4{,}505 & 3.24 & 5{,}327 & 4{,}972 & \\
	34	+fixed\_2010\_cohort & 2{,}022 & 1{,}389 & 12{,}870 & 1{,}273 & 9.27 & 4{,}447 & 3.2 & 5{,}224 & 4{,}902 & \\
	35	+fixed\_2010\_cohort & 2{,}023 & 1{,}389 & 12{,}649 & 1{,}254 & 9.11 & 4{,}251 & 3.06 & 5{,}098 & 4{,}752 & \\
	36	+fixed\_2010\_cohort & 2{,}024 & 1{,}389 & 12{,}170 & 1{,}277 & 8.76 & 4{,}085 & 2.94 & 4{,}953 & 4{,}663 & \\
	37	+fixed\_2010\_cohort & 2{,}025 & 1{,}389 & 12{,}156 & 1{,}285 & 8.75 & 3{,}926 & 2.83 & 4{,}858 & 4{,}518 & \\
	38	+fixed\_2010\_cohort & 2{,}026 & 1{,}389 & 9{,}792 & 1{,}244 & 7.05 & 3{,}192 & 2.3 & 3{,}958 & 3{,}697 & partial year \\
	39	+\bottomrule
	40	+\end{tabular}

modified paper/tables/tab_top_issuers.tex +1 −1

		`@@ -15,4 +15,4 @@ CLSK & Cleanspark & 170 \\`
15	15	CWEN & Clearway Energy Inc Class C & 168 \\
16	16	ALK & Alaska Air Group Inc & 168 \\
17	17	\bottomrule
18		−\end{tabular}
		\ No newline at end of file
	18	+\end{tabular}

added paper/tables/tab_top_name_tokens.tex +27 −0

		`@@ -0,0 +1,27 @@`
	1	+\begin{tabular}{lrrrr}
	2	+\toprule
	3	+name\_tok & mentions & projects & pct\_of\_tokenkeyed\_mentions & pct\_of\_tokenkeyed\_projects \\
	4	+\midrule
	5	+acquisition & 40{,}407 & 2{,}256 & 21.35 & 3.39 \\
	6	+share & 5{,}106 & 2{,}060 & 2.7 & 3.09 \\
	7	+expansion & 2{,}645 & 1{,}171 & 1.4 & 1.76 \\
	8	+stock & 2{,}624 & 1{,}146 & 1.39 & 1.72 \\
	9	+investment & 2{,}054 & 1{,}086 & 1.09 & 1.63 \\
	10	+merger & 3{,}357 & 895 & 1.77 & 1.34 \\
	11	+sale & 2{,}694 & 842 & 1.42 & 1.26 \\
	12	+development & 4{,}514 & 805 & 2.38 & 1.21 \\
	13	+strategic & 1{,}358 & 629 & 0.72 & 0.94 \\
	14	+capital & 2{,}295 & 562 & 1.21 & 0.84 \\
	15	+integration & 1{,}436 & 558 & 0.76 & 0.84 \\
	16	+credit & 635 & 473 & 0.34 & 0.71 \\
	17	+restructuring & 1{,}650 & 468 & 0.87 & 0.7 \\
	18	+research & 1{,}160 & 416 & 0.61 & 0.62 \\
	19	+product & 1{,}004 & 386 & 0.53 & 0.58 \\
	20	+private & 528 & 385 & 0.28 & 0.58 \\
	21	+global & 1{,}096 & 375 & 0.58 & 0.56 \\
	22	+business & 893 & 372 & 0.47 & 0.56 \\
	23	+senior & 506 & 357 & 0.27 & 0.54 \\
	24	+acquisitions & 935 & 354 & 0.49 & 0.53 \\
	25	+\multicolumn{5}{l}{\ldots 30 more rows in \texttt{results/resolver/top\_name\_tokens.csv}} \\
	26	+\bottomrule
	27	+\end{tabular}

modified paper/tables/tab_types.tex +25 −25

		`@@ -1,29 +1,29 @@`
1		−\begin{tabular}{llrrrrr}
	1	+\begin{tabular}{llrrrrrrr}
2	2	\toprule
3		−Code & Category & Projects & Share (\%) & With amount & Median amount (M USD) & Mentions / project \\
	3	+Code & Category & Projects & Share (\%) & With amount ($N$) & Median amount (M USD) & 95\% CI of the median & Mentions / project & $\geq 3$ distinct names (\%) \\
4	4	\midrule
5		−\texttt{ma\_integration} & M\&A / integration & 41{,}742 & 34.5 & 28{,}044 & 155.0 & 3.12 \\
6		−\texttt{capex\_program} & Capital expenditure program & 10{,}720 & 8.9 & 9{,}452 & 300.0 & 1.79 \\
7		−\texttt{partnership} & Strategic partnership & 9{,}909 & 8.2 & 2{,}943 & 75.0 & 1.77 \\
8		−\texttt{geographic\_expansion} & Geographic expansion & 7{,}868 & 6.5 & 1{,}431 & 36.7 & 2.25 \\
9		−\texttt{plant\_construction} & Plant / site construction & 7{,}590 & 6.3 & 2{,}511 & 56.0 & 2.42 \\
10		−\texttt{cost\_reduction} & Cost reduction / restructuring & 6{,}481 & 5.4 & 4{,}378 & 50.0 & 2.03 \\
11		−\texttt{drug\_pipeline} & Drug / clinical pipeline & 5{,}360 & 4.4 & 778 & 46.1 & 4.99 \\
12		−\texttt{product\_launch} & New product / launch & 5{,}356 & 4.4 & 447 & 26.7 & 2.33 \\
13		−\texttt{rd\_program} & R\&D program & 5{,}080 & 4.2 & 1{,}272 & 20.0 & 2.31 \\
14		−\texttt{infrastructure} & Infrastructure investment & 4{,}481 & 3.7 & 1{,}694 & 48.0 & 1.90 \\
15		−\texttt{manufacturing\_expansion} & Manufacturing / capacity expansion & 4{,}140 & 3.4 & 1{,}040 & 45.0 & 2.13 \\
16		−\texttt{technology\_deployment} & Technology deployment & 4{,}128 & 3.4 & 1{,}219 & 135.0 & 1.63 \\
17		−\texttt{digital\_transformation} & Digital transformation & 2{,}642 & 2.2 & 240 & 34.2 & 1.99 \\
18		−\texttt{erp\_implementation} & ERP / systems implementation & 1{,}735 & 1.4 & 184 & 15.0 & 2.44 \\
19		−\texttt{sustainability} & Sustainability / ESG & 1{,}305 & 1.1 & 410 & 34.4 & 2.00 \\
20		−\texttt{supply\_chain} & Supply-chain initiative & 684 & 0.6 & 139 & 38.0 & 1.71 \\
21		−\texttt{data\_center} & Data center & 449 & 0.4 & 129 & 166.0 & 1.98 \\
22		−\texttt{energy\_transition} & Energy transition / renewables & 415 & 0.3 & 109 & 109.0 & 2.09 \\
23		−\texttt{ai\_initiative} & AI / ML initiative & 376 & 0.3 & 20 & 127.5 & 1.68 \\
24		−\texttt{automation} & Automation / robotics & 374 & 0.3 & 25 & 13.7 & 1.68 \\
25		−\texttt{cloud\_migration} & Cloud migration & 264 & 0.2 & 35 & 50.0 & 1.97 \\
	5	+\texttt{ma\_integration} & M\&A / integration & 41{,}742 & 34.5 & 28{,}044 & 155.0 & -- & 3.12 & 14.6 \\
	6	+\texttt{capex\_program} & Capital expenditure program & 10{,}720 & 8.9 & 9{,}452 & 300.0 & -- & 1.79 & 6.4 \\
	7	+\texttt{partnership} & Strategic partnership & 9{,}909 & 8.2 & 2{,}943 & 75.0 & -- & 1.77 & 6.7 \\
	8	+\texttt{geographic\_expansion} & Geographic expansion & 7{,}868 & 6.5 & 1{,}431 & 36.7 & -- & 2.25 & 10.2 \\
	9	+\texttt{plant\_construction} & Plant / site construction & 7{,}590 & 6.3 & 2{,}511 & 56.0 & -- & 2.42 & 13.5 \\
	10	+\texttt{cost\_reduction} & Cost reduction / restructuring & 6{,}481 & 5.4 & 4{,}378 & 50.0 & -- & 2.03 & 5.7 \\
	11	+\texttt{drug\_pipeline} & Drug / clinical pipeline & 5{,}360 & 4.4 & 778 & 46.1 & -- & 4.99 & 27.9 \\
	12	+\texttt{product\_launch} & New product / launch & 5{,}356 & 4.4 & 447 & 26.7 & -- & 2.33 & 12.2 \\
	13	+\texttt{rd\_program} & R\&D program & 5{,}080 & 4.2 & 1{,}272 & 20.0 & -- & 2.31 & 11.4 \\
	14	+\texttt{infrastructure} & Infrastructure investment & 4{,}481 & 3.7 & 1{,}694 & 48.0 & -- & 1.90 & 7.5 \\
	15	+\texttt{manufacturing\_expansion} & Manufacturing / capacity expansion & 4{,}140 & 3.4 & 1{,}040 & 45.0 & -- & 2.13 & 11.3 \\
	16	+\texttt{technology\_deployment} & Technology deployment & 4{,}128 & 3.4 & 1{,}219 & 135.0 & -- & 1.63 & 4.8 \\
	17	+\texttt{digital\_transformation} & Digital transformation & 2{,}642 & 2.2 & 240 & 34.2 & -- & 1.99 & 6.2 \\
	18	+\texttt{erp\_implementation} & ERP / systems implementation & 1{,}735 & 1.4 & 184 & 15.0 & -- & 2.44 & 3.5 \\
	19	+\texttt{sustainability} & Sustainability / ESG & 1{,}305 & 1.1 & 410 & 34.4 & -- & 2.00 & 6.1 \\
	20	+\texttt{supply\_chain} & Supply-chain initiative & 684 & 0.6 & 139 & 38.0 & -- & 1.71 & 3.5 \\
	21	+\texttt{data\_center} & Data center & 449 & 0.4 & 129 & 166.0 & -- & 1.98 & 9.3 \\
	22	+\texttt{energy\_transition} & Energy transition / renewables & 415 & 0.3 & 109 & 109.0 & -- & 2.09 & 10.1 \\
	23	+\texttt{ai\_initiative} & AI / ML initiative & 376 & 0.3 & 20 & \textcolor{gray}{127.5} & -- & 1.68 & 4.8 \\
	24	+\texttt{automation} & Automation / robotics & 374 & 0.3 & 25 & \textcolor{gray}{13.7} & -- & 1.68 & 2.7 \\
	25	+\texttt{cloud\_migration} & Cloud migration & 264 & 0.2 & 35 & \textcolor{gray}{50.0} & -- & 1.97 & 5.7 \\
26	26	\midrule
27		− & Total & 121{,}099 & 100.0 & 56{,}500 & 128.5 & 2.54 \\
	27	+ & Total & 121{,}099 & 100.1 & 56{,}500 & 128.5 & -- & 2.54 & \\
28	28	\bottomrule
29		−\end{tabular}
		\ No newline at end of file
	29	+\end{tabular}

added paper/tables/tab_types_note.tex +1 −0

		`@@ -0,0 +1 @@`
	1	+\item Shares are rounded to one decimal and sum to 100.1. ``With amount'' counts projects for which at least one mention carries a USD figure; ``median amount'' is the median across those projects of the largest amount cited (Section~\ref{sec:amounts} on why amounts are never summed). Medians printed in grey rest on fewer than 50 projects with an amount (\texttt{ai\_initiative}, \texttt{automation}, \texttt{cloud\_migration}) and should not be quoted without their $N$. The 95\% interval column is filled when \texttt{data/projects\_by\_type\_ci.csv} (bootstrap on the node) is present. ``$\geq 3$ distinct names'' is the share of projects of the category whose mentions carry three or more distinct project names (over-merge indicator of the resolution key, \texttt{results/resolver/overmerge\_by\_type.csv}).

added results/inline_numbers.json +1037 −0

		`@@ -0,0 +1,1037 @@`
	1	+{
	2	+ "iwvEquityLines": {
	3	+ "value": "2{,}587",
	4	+ "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",
	5	+ "formula": "documented input or stats.json"
	6	+ },
	7	+ "universeN": {
	8	+ "value": "2{,}564",
	9	+ "source": "stats.json:universe.n",
	10	+ "formula": "count"
	11	+ },
	12	+ "russellDistinctCiks": {
	13	+ "value": "2{,}555",
	14	+ "source": "stats.json:universe.russell_distinct_ciks",
	15	+ "formula": "count"
	16	+ },
	17	+ "russellMappedLines": {
	18	+ "value": "2{,}573",
	19	+ "source": "stats.json:universe.russell_equity_lines_mapped",
	20	+ "formula": "count"
	21	+ },
	22	+ "russellUnmatched": {
	23	+ "value": "7",
	24	+ "source": "stats.json:universe.russell_unmatched",
	25	+ "formula": "len(unmatched)"
	26	+ },
	27	+ "russellIndexConstituents": {
	28	+ "value": "2{,}996",
	29	+ "source": "results/russell_coverage.json:index_constituents",
	30	+ "formula": "https://research.ftserussell.com/Analytics/FactSheets/Home/DownloadSingleIssue?issueName=US3000USD&isManual=True"
	31	+ },
	32	+ "russellProxyCoveragePct": {
	33	+ "value": "85.3",
	34	+ "source": "results/russell_coverage.json",
	35	+ "formula": "100 * russell_distinct_ciks / index_constituents"
	36	+ },
	37	+ "iwvHoldingsCount": {
	38	+ "value": "2{,}588",
	39	+ "source": "results/russell_coverage.json:fund_holdings_count",
	40	+ "formula": "https://www.ishares.com/us/products/239714/ishares-russell-3000-etf"
	41	+ },
	42	+ "iwvReplicationMethod": {
	43	+ "value": "representative sampling",
	44	+ "source": "results/russell_coverage.json:replication_method",
	45	+ "formula": "https://www.ishares.com/us/products/239714/ishares-russell-3000-etf"
	46	+ },
	47	+ "filingDateFirst": {
	48	+ "value": "2010-01-04",
	49	+ "source": "stats.json:filing_date_range or min(filings_by_form.first)",
	50	+ "formula": "min"
	51	+ },
	52	+ "filingDateLast": {
	53	+ "value": "2026-10-27",
	54	+ "source": "stats.json:filing_date_range or max(filings_by_form.last)",
	55	+ "formula": "max"
	56	+ },
	57	+ "filingsTotal": {
	58	+ "value": "527{,}548",
	59	+ "source": "stats.json:filings_total",
	60	+ "formula": "count"
	61	+ },
	62	+ "filingsNotParsed": {
	63	+ "value": "16",
	64	+ "source": "data/parse_status.csv",
	65	+ "formula": "sum(error)+sum(missing)"
	66	+ },
	67	+ "filingsMissingOnDisk": {
	68	+ "value": "2",
	69	+ "source": "data/parse_status.csv",
	70	+ "formula": "sum(missing)"
	71	+ },
	72	+ "rawGb": {
	73	+ "value": "254.5",
	74	+ "source": "stats.json:raw_gb",
	75	+ "formula": "sum(file_size_bytes)/1e9"
	76	+ },
	77	+ "firstSeenYearMin": {
	78	+ "value": "2011",
	79	+ "source": "data/projects_by_first_seen_year.csv",
	80	+ "formula": "first full year after the left-censored start"
	81	+ },
	82	+ "firstSeenYearMax": {
	83	+ "value": "2025",
	84	+ "source": "data/projects_by_first_seen_year.csv",
	85	+ "formula": "last full year before the partial final year"
	86	+ },
	87	+ "firstSeenRangeInner": {
	88	+ "value": "6{,}240--8{,}216",
	89	+ "source": "data/projects_by_first_seen_year.csv",
	90	+ "formula": "min/max of projects first seen, 2011--2025"
	91	+ },
	92	+ "firstSeenFirstYear": {
	93	+ "value": "7{,}835",
	94	+ "source": "data/projects_by_first_seen_year.csv",
	95	+ "formula": "projects first seen in 2010 (left-censored)"
	96	+ },
	97	+ "firstSeenInnerMean": {
	98	+ "value": "7{,}105",
	99	+ "source": "data/projects_by_first_seen_year.csv",
	100	+ "formula": "mean 2011--2025"
	101	+ },
	102	+ "mentionsFirstYear": {
	103	+ "value": "11{,}908",
	104	+ "source": "data/mentions_by_year.csv",
	105	+ "formula": "mentions in 2010"
	106	+ },
	107	+ "mentionsLastFullYear": {
	108	+ "value": "23{,}220",
	109	+ "source": "data/mentions_by_year.csv",
	110	+ "formula": "mentions in 2025"
	111	+ },
	112	+ "issuersWithMentionsFirstYear": {
	113	+ "value": "1{,}224",
	114	+ "source": "data/mentions_by_year.csv",
	115	+ "formula": "issuers with mentions in 2010"
	116	+ },
	117	+ "issuersWithMentionsLastFullYear": {
	118	+ "value": "2{,}280",
	119	+ "source": "data/mentions_by_year.csv",
	120	+ "formula": "issuers with mentions in 2025"
	121	+ },
	122	+ "mentionsPerIssuerFirstYear": {
	123	+ "value": "9.7",
	124	+ "source": "data/mentions_by_year.csv",
	125	+ "formula": "mentions/issuers"
	126	+ },
	127	+ "mentionsPerIssuerLastFullYear": {
	128	+ "value": "10.2",
	129	+ "source": "data/mentions_by_year.csv",
	130	+ "formula": "mentions/issuers"
	131	+ },
	132	+ "lastYear": {
	133	+ "value": "2026",
	134	+ "source": "data/issuers_by_year.csv",
	135	+ "formula": "max year (partial)"
	136	+ },
	137	+ "callsOneZeroK": {
	138	+ "value": "135{,}310",
	139	+ "source": "results/ledger/table3_ledger_vs_stored.csv",
	140	+ "formula": "calls where form_type=10-K"
	141	+ },
	142	+ "callsOneZeroQ": {
	143	+ "value": "363{,}973",
	144	+ "source": "results/ledger/table3_ledger_vs_stored.csv",
	145	+ "formula": "calls where form_type=10-Q"
	146	+ },
	147	+ "callsEightK": {
	148	+ "value": "204{,}442",
	149	+ "source": "results/ledger/table3_ledger_vs_stored.csv",
	150	+ "formula": "calls where form_type=8-K"
	151	+ },
	152	+ "ledgerTotal": {
	153	+ "value": "1{,}123{,}098",
	154	+ "source": "stats.json:ledger_total",
	155	+ "formula": "count(extracted_sections)"
	156	+ },
	157	+ "ledgerMentionsReturned": {
	158	+ "value": "308{,}477",
	159	+ "source": "data/ledger_by_form.csv",
	160	+ "formula": "sum(mentions)"
	161	+ },
	162	+ "ledgerGap": {
	163	+ "value": "412",
	164	+ "source": "data/ledger_by_form.csv, data/mentions_by_form.csv",
	165	+ "formula": "sum(ledger mentions) - sum(stored mentions)"
	166	+ },
	167	+ "ledgerGapByForm": {
	168	+ "value": "10-K 127, 10-Q 257, 8-K 28",
	169	+ "source": "data/ledger_by_form.csv, data/mentions_by_form.csv",
	170	+ "formula": "per form"
	171	+ },
	172	+ "mentionsStoredEightK": {
	173	+ "value": "74{,}566",
	174	+ "source": "data/mentions_by_form.csv",
	175	+ "formula": "n where form_type=8-K"
	176	+ },
	177	+ "mentionsLedgerEightK": {
	178	+ "value": "74{,}594",
	179	+ "source": "data/ledger_by_form.csv",
	180	+ "formula": "mentions where form_type=8-K"
	181	+ },
	182	+ "ledgerSectionsEightK": {
	183	+ "value": "400{,}601",
	184	+ "source": "data/ledger_by_form.csv",
	185	+ "formula": "sections where form_type=8-K"
	186	+ },
	187	+ "mentionsStoredOneZeroK": {
	188	+ "value": "81{,}495",
	189	+ "source": "data/mentions_by_form.csv",
	190	+ "formula": "n where form_type=10-K"
	191	+ },
	192	+ "mentionsLedgerOneZeroK": {
	193	+ "value": "81{,}622",
	194	+ "source": "data/ledger_by_form.csv",
	195	+ "formula": "mentions where form_type=10-K"
	196	+ },
	197	+ "ledgerSectionsOneZeroK": {
	198	+ "value": "143{,}704",
	199	+ "source": "data/ledger_by_form.csv",
	200	+ "formula": "sections where form_type=10-K"
	201	+ },
	202	+ "mentionsStoredOneZeroQ": {
	203	+ "value": "152{,}004",
	204	+ "source": "data/mentions_by_form.csv",
	205	+ "formula": "n where form_type=10-Q"
	206	+ },
	207	+ "mentionsLedgerOneZeroQ": {
	208	+ "value": "152{,}261",
	209	+ "source": "data/ledger_by_form.csv",
	210	+ "formula": "mentions where form_type=10-Q"
	211	+ },
	212	+ "ledgerSectionsOneZeroQ": {
	213	+ "value": "578{,}793",
	214	+ "source": "data/ledger_by_form.csv",
	215	+ "formula": "sections where form_type=10-Q"
	216	+ },
	217	+ "productiveSections": {
	218	+ "value": "168{,}230",
	219	+ "source": "data/ledger_by_form.csv",
	220	+ "formula": "sum(with_mentions)"
	221	+ },
	222	+ "productiveShareLedger": {
	223	+ "value": "15.0",
	224	+ "source": "data/ledger_by_form.csv, stats.json",
	225	+ "formula": "100*productive/ledger_total"
	226	+ },
	227	+ "mentionsPerLedgerSection": {
	228	+ "value": "0.27",
	229	+ "source": "stats.json",
	230	+ "formula": "mentions/ledger_total"
	231	+ },
	232	+ "mentionsPerProductiveSection": {
	233	+ "value": "1.83",
	234	+ "source": "stats.json, data/ledger_by_form.csv",
	235	+ "formula": "mentions/productive"
	236	+ },
	237	+ "gatePassTotal": {
	238	+ "value": "703{,}725",
	239	+ "source": "stats.json:gate_pass_total",
	240	+ "formula": "regexp_matches(_PROJECT_GATE) over the ledger"
	241	+ },
	242	+ "productiveShareCalls": {
	243	+ "value": "23.9",
	244	+ "source": "results/ledger/gate_pass_totals.json",
	245	+ "formula": "productive_pct_calls"
	246	+ },
	247	+ "mentionsPerCall": {
	248	+ "value": "0.44",
	249	+ "source": "results/ledger/gate_pass_totals.json",
	250	+ "formula": "mentions_per_call"
	251	+ },
	252	+ "tenKmdnaMentions": {
	253	+ "value": "39{,}099",
	254	+ "source": "data/ledger_10k_items.csv / ledger_10q_items.csv",
	255	+ "formula": "mentions by item"
	256	+ },
	257	+ "tenQmdnaMentions": {
	258	+ "value": "99{,}305",
	259	+ "source": "data/ledger_10k_items.csv / ledger_10q_items.csv",
	260	+ "formula": "mentions by item"
	261	+ },
	262	+ "tenKbusinessMentions": {
	263	+ "value": "30{,}492",
	264	+ "source": "data/ledger_10k_items.csv / ledger_10q_items.csv",
	265	+ "formula": "mentions by item"
	266	+ },
	267	+ "tenQfinancialStatementsMentions": {
	268	+ "value": "30{,}159",
	269	+ "source": "data/ledger_10k_items.csv / ledger_10q_items.csv",
	270	+ "formula": "mentions by item"
	271	+ },
	272	+ "tenKfullBodyRows": {
	273	+ "value": "1{,}230",
	274	+ "source": "data/ledger_10k_items.csv",
	275	+ "formula": "n where section_name=full_body"
	276	+ },
	277	+ "typesPctSum": {
	278	+ "value": "100.1",
	279	+ "source": "data/projects_by_type.csv",
	280	+ "formula": "sum(pct)"
	281	+ },
	282	+ "amountMedianMusd": {
	283	+ "value": "128.5",
	284	+ "source": "stats.json:amount_total_median_musd or data/amount_dist.csv",
	285	+ "formula": "median(total_amount_usd)/1e6"
	286	+ },
	287	+ "smallNThreshold": {
	288	+ "value": "50",
	289	+ "source": "data/documented_inputs.json:small_n_threshold",
	290	+ "formula": "presentation rule"
	291	+ },
	292	+ "smallNCategories": {
	293	+ "value": "ai_initiative, automation, cloud_migration",
	294	+ "source": "data/projects_by_type.csv",
	295	+ "formula": "with_amount < 50"
	296	+ },
	297	+ "shareDataCenter": {
	298	+ "value": "0.4",
	299	+ "source": "data/projects_by_type.csv",
	300	+ "formula": "pct where project_type=data_center"
	301	+ },
	302	+ "nDataCenter": {
	303	+ "value": "449",
	304	+ "source": "data/projects_by_type.csv",
	305	+ "formula": "n where project_type=data_center"
	306	+ },
	307	+ "withAmountDataCenter": {
	308	+ "value": "129",
	309	+ "source": "data/projects_by_type.csv",
	310	+ "formula": "with_amount where project_type=data_center"
	311	+ },
	312	+ "medianAmountDataCenter": {
	313	+ "value": "166.0",
	314	+ "source": "data/projects_by_type.csv",
	315	+ "formula": "median_amount_musd where project_type=data_center"
	316	+ },
	317	+ "shareAiInitiative": {
	318	+ "value": "0.3",
	319	+ "source": "data/projects_by_type.csv",
	320	+ "formula": "pct where project_type=ai_initiative"
	321	+ },
	322	+ "nAiInitiative": {
	323	+ "value": "376",
	324	+ "source": "data/projects_by_type.csv",
	325	+ "formula": "n where project_type=ai_initiative"
	326	+ },
	327	+ "withAmountAiInitiative": {
	328	+ "value": "20",
	329	+ "source": "data/projects_by_type.csv",
	330	+ "formula": "with_amount where project_type=ai_initiative"
	331	+ },
	332	+ "medianAmountAiInitiative": {
	333	+ "value": "127.5",
	334	+ "source": "data/projects_by_type.csv",
	335	+ "formula": "median_amount_musd where project_type=ai_initiative"
	336	+ },
	337	+ "shareCloudMigration": {
	338	+ "value": "0.2",
	339	+ "source": "data/projects_by_type.csv",
	340	+ "formula": "pct where project_type=cloud_migration"
	341	+ },
	342	+ "nCloudMigration": {
	343	+ "value": "264",
	344	+ "source": "data/projects_by_type.csv",
	345	+ "formula": "n where project_type=cloud_migration"
	346	+ },
	347	+ "withAmountCloudMigration": {
	348	+ "value": "35",
	349	+ "source": "data/projects_by_type.csv",
	350	+ "formula": "with_amount where project_type=cloud_migration"
	351	+ },
	352	+ "medianAmountCloudMigration": {
	353	+ "value": "50.0",
	354	+ "source": "data/projects_by_type.csv",
	355	+ "formula": "median_amount_musd where project_type=cloud_migration"
	356	+ },
	357	+ "shareAutomation": {
	358	+ "value": "0.3",
	359	+ "source": "data/projects_by_type.csv",
	360	+ "formula": "pct where project_type=automation"
	361	+ },
	362	+ "nAutomation": {
	363	+ "value": "374",
	364	+ "source": "data/projects_by_type.csv",
	365	+ "formula": "n where project_type=automation"
	366	+ },
	367	+ "withAmountAutomation": {
	368	+ "value": "25",
	369	+ "source": "data/projects_by_type.csv",
	370	+ "formula": "with_amount where project_type=automation"
	371	+ },
	372	+ "medianAmountAutomation": {
	373	+ "value": "13.7",
	374	+ "source": "data/projects_by_type.csv",
	375	+ "formula": "median_amount_musd where project_type=automation"
	376	+ },
	377	+ "shareMaIntegration": {
	378	+ "value": "34.5",
	379	+ "source": "data/projects_by_type.csv",
	380	+ "formula": "pct where project_type=ma_integration"
	381	+ },
	382	+ "nMaIntegration": {
	383	+ "value": "41{,}742",
	384	+ "source": "data/projects_by_type.csv",
	385	+ "formula": "n where project_type=ma_integration"
	386	+ },
	387	+ "withAmountMaIntegration": {
	388	+ "value": "28{,}044",
	389	+ "source": "data/projects_by_type.csv",
	390	+ "formula": "with_amount where project_type=ma_integration"
	391	+ },
	392	+ "medianAmountMaIntegration": {
	393	+ "value": "155.0",
	394	+ "source": "data/projects_by_type.csv",
	395	+ "formula": "median_amount_musd where project_type=ma_integration"
	396	+ },
	397	+ "shareCapexProgram": {
	398	+ "value": "8.9",
	399	+ "source": "data/projects_by_type.csv",
	400	+ "formula": "pct where project_type=capex_program"
	401	+ },
	402	+ "nCapexProgram": {
	403	+ "value": "10{,}720",
	404	+ "source": "data/projects_by_type.csv",
	405	+ "formula": "n where project_type=capex_program"
	406	+ },
	407	+ "withAmountCapexProgram": {
	408	+ "value": "9{,}452",
	409	+ "source": "data/projects_by_type.csv",
	410	+ "formula": "with_amount where project_type=capex_program"
	411	+ },
	412	+ "medianAmountCapexProgram": {
	413	+ "value": "300.0",
	414	+ "source": "data/projects_by_type.csv",
	415	+ "formula": "median_amount_musd where project_type=capex_program"
	416	+ },
	417	+ "sharePartnership": {
	418	+ "value": "8.2",
	419	+ "source": "data/projects_by_type.csv",
	420	+ "formula": "pct where project_type=partnership"
	421	+ },
	422	+ "nPartnership": {
	423	+ "value": "9{,}909",
	424	+ "source": "data/projects_by_type.csv",
	425	+ "formula": "n where project_type=partnership"
	426	+ },
	427	+ "withAmountPartnership": {
	428	+ "value": "2{,}943",
	429	+ "source": "data/projects_by_type.csv",
	430	+ "formula": "with_amount where project_type=partnership"
	431	+ },
	432	+ "medianAmountPartnership": {
	433	+ "value": "75.0",
	434	+ "source": "data/projects_by_type.csv",
	435	+ "formula": "median_amount_musd where project_type=partnership"
	436	+ },
	437	+ "shareGeographicExpansion": {
	438	+ "value": "6.5",
	439	+ "source": "data/projects_by_type.csv",
	440	+ "formula": "pct where project_type=geographic_expansion"
	441	+ },
	442	+ "nGeographicExpansion": {
	443	+ "value": "7{,}868",
	444	+ "source": "data/projects_by_type.csv",
	445	+ "formula": "n where project_type=geographic_expansion"
	446	+ },
	447	+ "withAmountGeographicExpansion": {
	448	+ "value": "1{,}431",
	449	+ "source": "data/projects_by_type.csv",
	450	+ "formula": "with_amount where project_type=geographic_expansion"
	451	+ },
	452	+ "medianAmountGeographicExpansion": {
	453	+ "value": "36.7",
	454	+ "source": "data/projects_by_type.csv",
	455	+ "formula": "median_amount_musd where project_type=geographic_expansion"
	456	+ },
	457	+ "sharePlantConstruction": {
	458	+ "value": "6.3",
	459	+ "source": "data/projects_by_type.csv",
	460	+ "formula": "pct where project_type=plant_construction"
	461	+ },
	462	+ "nPlantConstruction": {
	463	+ "value": "7{,}590",
	464	+ "source": "data/projects_by_type.csv",
	465	+ "formula": "n where project_type=plant_construction"
	466	+ },
	467	+ "withAmountPlantConstruction": {
	468	+ "value": "2{,}511",
	469	+ "source": "data/projects_by_type.csv",
	470	+ "formula": "with_amount where project_type=plant_construction"
	471	+ },
	472	+ "medianAmountPlantConstruction": {
	473	+ "value": "56.0",
	474	+ "source": "data/projects_by_type.csv",
	475	+ "formula": "median_amount_musd where project_type=plant_construction"
	476	+ },
	477	+ "techCategoriesCountRange": {
	478	+ "value": "264--449",
	479	+ "source": "data/projects_by_type.csv",
	480	+ "formula": "min/max n over data_center, ai_initiative, cloud_migration, automation"
	481	+ },
	482	+ "sectorTopFourPerIssuerRange": {
	483	+ "value": "62--75",
	484	+ "source": "data/projects_by_sector.csv",
	485	+ "formula": "floor(min)/ceil(max) of per_issuer over the four highest sectors: Utilities, Materials, Energy, Real Estate"
	486	+ },
	487	+ "sectorTopFourNames": {
	488	+ "value": "utilities, materials, energy, real estate",
	489	+ "source": "data/projects_by_sector.csv",
	490	+ "formula": "four highest per_issuer"
	491	+ },
	492	+ "sectorFinancialsPerIssuer": {
	493	+ "value": "32",
	494	+ "source": "data/projects_by_sector.csv",
	495	+ "formula": "round(per_issuer) for Financials"
	496	+ },
	497	+ "sectorProjectsHealthCare": {
	498	+ "value": "23{,}679",
	499	+ "source": "data/projects_by_sector.csv",
	500	+ "formula": "n for Health Care"
	501	+ },
	502	+ "sectorIssuersHealthCare": {
	503	+ "value": "429",
	504	+ "source": "data/projects_by_sector.csv",
	505	+ "formula": "issuers for Health Care"
	506	+ },
	507	+ "sectorProjectsIndustrials": {
	508	+ "value": "17{,}890",
	509	+ "source": "data/projects_by_sector.csv",
	510	+ "formula": "n for Industrials"
	511	+ },
	512	+ "sectorIssuersIndustrials": {
	513	+ "value": "386",
	514	+ "source": "data/projects_by_sector.csv",
	515	+ "formula": "issuers for Industrials"
	516	+ },
	517	+ "spanKnownN": {
	518	+ "value": "103{,}500",
	519	+ "source": "data/duration.csv",
	520	+ "formula": "projects - unknown"
	521	+ },
	522	+ "spanUnknownN": {
	523	+ "value": "17{,}599",
	524	+ "source": "data/duration.csv",
	525	+ "formula": "n where span_years=unknown"
	526	+ },
	527	+ "spanUnknownShareAll": {
	528	+ "value": "14.5",
	529	+ "source": "data/duration.csv",
	530	+ "formula": "100*unknown/projects"
	531	+ },
	532	+ "spanZeroShareAll": {
	533	+ "value": "55.5",
	534	+ "source": "data/duration.csv",
	535	+ "formula": "100*n(0)/projects"
	536	+ },
	537	+ "spanZeroShareKnown": {
	538	+ "value": "64.9",
	539	+ "source": "data/duration.csv",
	540	+ "formula": "100*n(0)/(projects-unknown)"
	541	+ },
	542	+ "spanOverFiveShareAll": {
	543	+ "value": "8.5",
	544	+ "source": "data/duration.csv",
	545	+ "formula": "100*n(>5)/projects"
	546	+ },
	547	+ "spanOverFiveShareKnown": {
	548	+ "value": "10.0",
	549	+ "source": "data/duration.csv",
	550	+ "formula": "100*n(>5)/(projects-unknown)"
	551	+ },
	552	+ "statusShareInProgress": {
	553	+ "value": "41.6",
	554	+ "source": "data/projects_by_status.csv",
	555	+ "formula": "pct where status=in_progress"
	556	+ },
	557	+ "statusShareCompleted": {
	558	+ "value": "41.0",
	559	+ "source": "data/projects_by_status.csv",
	560	+ "formula": "pct where status=completed"
	561	+ },
	562	+ "statusSharePlanned": {
	563	+ "value": "15.1",
	564	+ "source": "data/projects_by_status.csv",
	565	+ "formula": "pct where status=planned"
	566	+ },
	567	+ "statusShareMentioned": {
	568	+ "value": "2.3",
	569	+ "source": "data/projects_by_status.csv",
	570	+ "formula": "pct where status=mentioned"
	571	+ },
	572	+ "singleMentionShare": {
	573	+ "value": "60.2",
	574	+ "source": "data/mentions_per_project.csv",
	575	+ "formula": "100*n(bucket=1)/projects"
	576	+ },
	577	+ "overTenMentionShare": {
	578	+ "value": "3.1",
	579	+ "source": "data/mentions_per_project.csv",
	580	+ "formula": "100*n(bucket=>10)/projects"
	581	+ },
	582	+ "confShareOne": {
	583	+ "value": "35.2",
	584	+ "source": "data/confidence_dist.csv",
	585	+ "formula": "100*n(conf=1.0)/mentions"
	586	+ },
	587	+ "confShareNine": {
	588	+ "value": "32.7",
	589	+ "source": "data/confidence_dist.csv",
	590	+ "formula": "100*n(conf=0.9)/mentions"
	591	+ },
	592	+ "confShareLeSix": {
	593	+ "value": "1.6",
	594	+ "source": "data/confidence_dist.csv",
	595	+ "formula": "100*n(conf<=0.6)/mentions"
	596	+ },
	597	+ "amountMentions": {
	598	+ "value": "120{,}240",
	599	+ "source": "stats.json:mentions_fields[0]",
	600	+ "formula": "count(amount_usd is not null)"
	601	+ },
	602	+ "amountMentionsShare": {
	603	+ "value": "39.0",
	604	+ "source": "stats.json",
	605	+ "formula": "100*mentions_fields[0]/mentions"
	606	+ },
	607	+ "amountProjects": {
	608	+ "value": "56{,}500",
	609	+ "source": "stats.json:projects_fields[0]",
	610	+ "formula": "count(total_amount_usd is not null)"
	611	+ },
	612	+ "amountProjectsShare": {
	613	+ "value": "46.7",
	614	+ "source": "stats.json",
	615	+ "formula": "100*projects_fields[0]/projects"
	616	+ },
	617	+ "amountPTwoFiveMusd": {
	618	+ "value": "23",
	619	+ "source": "data/amount_dist.csv",
	620	+ "formula": "q[1]/1e6"
	621	+ },
	622	+ "amountPSevenFiveMusd": {
	623	+ "value": "500",
	624	+ "source": "data/amount_dist.csv",
	625	+ "formula": "q[3]/1e6"
	626	+ },
	627	+ "amountPNineNineBusd": {
	628	+ "value": "12.5",
	629	+ "source": "data/amount_dist.csv",
	630	+ "formula": "q[5]/1e9"
	631	+ },
	632	+ "amountSumTusd": {
	633	+ "value": "55.9",
	634	+ "source": "data/amount_dist.csv",
	635	+ "formula": "sum_gusd/1e3"
	636	+ },
	637	+ "kgNodes": {
	638	+ "value": "183{,}472",
	639	+ "source": "data/kg.csv",
	640	+ "formula": "sum(n) where k=nodes"
	641	+ },
	642	+ "kgEdges": {
	643	+ "value": "204{,}456",
	644	+ "source": "data/kg.csv",
	645	+ "formula": "sum(n) where k=edges"
	646	+ },
	647	+ "kgNodesProject": {
	648	+ "value": "121{,}099",
	649	+ "source": "data/kg.csv",
	650	+ "formula": "n where node_type=Project"
	651	+ },
	652	+ "kgNodesPartner": {
	653	+ "value": "36{,}822",
	654	+ "source": "data/kg.csv",
	655	+ "formula": "n where node_type=Partner"
	656	+ },
	657	+ "kgNodesLocation": {
	658	+ "value": "14{,}508",
	659	+ "source": "data/kg.csv",
	660	+ "formula": "n where node_type=Location"
	661	+ },
	662	+ "kgNodesTechnology": {
	663	+ "value": "8{,}551",
	664	+ "source": "data/kg.csv",
	665	+ "formula": "n where node_type=Technology"
	666	+ },
	667	+ "kgNodesCompany": {
	668	+ "value": "2{,}492",
	669	+ "source": "data/kg.csv",
	670	+ "formula": "n where node_type=Company"
	671	+ },
	672	+ "provenanceForms": {
	673	+ "value": "8-K",
	674	+ "source": "data/example_provenance.csv",
	675	+ "formula": "distinct form_type of the printed rows"
	676	+ },
	677	+ "provenanceN": {
	678	+ "value": "8",
	679	+ "source": "data/example_provenance.csv",
	680	+ "formula": "rows printed"
	681	+ },
	682	+ "provenanceFirst": {
	683	+ "value": "2014-04-08",
	684	+ "source": "data/example_provenance.csv",
	685	+ "formula": "min filing_date"
	686	+ },
	687	+ "provenanceLast": {
	688	+ "value": "2022-03-07",
	689	+ "source": "data/example_provenance.csv",
	690	+ "formula": "max filing_date"
	691	+ },
	692	+ "provenanceMaxAmountBusd": {
	693	+ "value": "11.5",
	694	+ "source": "data/example_provenance.csv",
	695	+ "formula": "max(amount_usd)/1e9"
	696	+ },
	697	+ "provenanceNameYear": {
	698	+ "value": "2022",
	699	+ "source": "data/example_provenance.csv",
	700	+ "formula": "filing year of the last mention (representative name source)"
	701	+ },
	702	+ "gateRegexFlags": {
	703	+ "value": "re.IGNORECASE",
	704	+ "source": "code/audit/spid_snapshot/rules.py",
	705	+ "formula": "re.compile flags"
	706	+ },
	707	+ "gateRegexLength": {
	708	+ "value": "215",
	709	+ "source": "rules.py:_PROJECT_GATE",
	710	+ "formula": "len(pattern)"
	711	+ },
	712	+ "gateRegexAlternatives": {
	713	+ "value": "25",
	714	+ "source": "rules.py:_PROJECT_GATE",
	715	+ "formula": "number of alternatives"
	716	+ },
	717	+ "taxonomyN": {
	718	+ "value": "21",
	719	+ "source": "taxonomy.py:PROJECT_TYPES",
	720	+ "formula": "len"
	721	+ },
	722	+ "callsTotal": {
	723	+ "value": "703{,}725",
	724	+ "source": "results/ledger/gate_pass_totals.json",
	725	+ "formula": "calls"
	726	+ },
	727	+ "gatePassSections": {
	728	+ "value": "703{,}737",
	729	+ "source": "results/ledger/gate_pass_totals.json",
	730	+ "formula": "gate_pass"
	731	+ },
	732	+ "gateRejectedSections": {
	733	+ "value": "419{,}361",
	734	+ "source": "results/ledger/gate_pass_totals.json",
	735	+ "formula": "gate_rejected_zero"
	736	+ },
	737	+ "ledgerUnderThirtyWords": {
	738	+ "value": "1{,}070",
	739	+ "source": "results/ledger/gate_pass_totals.json",
	740	+ "formula": "lt30_words"
	741	+ },
	742	+ "usdPerCall": {
	743	+ "value": "0.0013",
	744	+ "source": "results/ledger/gate_pass_totals.json",
	745	+ "formula": "usd_per_call_paper_total_775"
	746	+ },
	747	+ "octoberCalls": {
	748	+ "value": "608{,}439",
	749	+ "source": "results/ledger/gate_pass_totals.json",
	750	+ "formula": "october_calls"
	751	+ },
	752	+ "octoberRows": {
	753	+ "value": "968{,}134",
	754	+ "source": "results/ledger/gate_pass_totals.json",
	755	+ "formula": "october_rows"
	756	+ },
	757	+ "octoberWallClockHours": {
	758	+ "value": "13.7",
	759	+ "source": "results/ledger/throughput.json",
	760	+ "formula": "wall_clock_hours_first_to_last_flush"
	761	+ },
	762	+ "outageHours": {
	763	+ "value": "5.3",
	764	+ "source": "results/ledger/throughput.json",
	765	+ "formula": "largest_gap_hours"
	766	+ },
	767	+ "octoberEffectiveHours": {
	768	+ "value": "8.4",
	769	+ "source": "results/ledger/throughput.json",
	770	+ "formula": "effective_hours_excluding_largest_gap"
	771	+ },
	772	+ "octoberRowsPerSecondEffective": {
	773	+ "value": "31.9",
	774	+ "source": "results/ledger/throughput.json",
	775	+ "formula": "rows_per_second_effective"
	776	+ },
	777	+ "octoberCallsPerSecondEffective": {
	778	+ "value": "20.1",
	779	+ "source": "results/ledger/throughput.json",
	780	+ "formula": "calls_per_second_effective"
	781	+ },
	782	+ "octoberFirstFlush": {
	783	+ "value": "2026-10-27 21:35",
	784	+ "source": "results/ledger/throughput.json",
	785	+ "formula": "october_first_flush"
	786	+ },
	787	+ "octoberLastFlush": {
	788	+ "value": "2026-10-28 11:15",
	789	+ "source": "results/ledger/throughput.json",
	790	+ "formula": "october_last_flush"
	791	+ },
	792	+ "backfilledRows": {
	793	+ "value": "154{,}964",
	794	+ "source": "results/ledger/backfill_block.json",
	795	+ "formula": "rows_at_min_timestamp"
	796	+ },
	797	+ "juneLogSections": {
	798	+ "value": "153{,}894",
	799	+ "source": "results/ledger/backfill_block.json",
	800	+ "formula": "june_log_sections"
	801	+ },
	802	+ "backfilledUnderThirtyWords": {
	803	+ "value": "1{,}070",
	804	+ "source": "results/ledger/backfill_block.json",
	805	+ "formula": "block_lt30_words"
	806	+ },
	807	+ "backfilledMentions": {
	808	+ "value": "39{,}930",
	809	+ "source": "results/ledger/backfill_block.json",
	810	+ "formula": "block_stored_mentions"
	811	+ },
	812	+ "backfilledCiks": {
	813	+ "value": "500",
	814	+ "source": "results/ledger/backfill_block.json",
	815	+ "formula": "block_ciks"
	816	+ },
	817	+ "backfilledGateFail": {
	818	+ "value": "59{,}666",
	819	+ "source": "results/ledger/backfill_block.json",
	820	+ "formula": "block_gate_fail"
	821	+ },
	822	+ "outageWindowStart": {
	823	+ "value": "2026-10-28 01:10",
	824	+ "source": "results/ledger/backfill_block.json",
	825	+ "formula": "outage_window[0]"
	826	+ },
	827	+ "outageWindowEnd": {
	828	+ "value": "2026-10-28 06:22",
	829	+ "source": "results/ledger/backfill_block.json",
	830	+ "formula": "outage_window[1]"
	831	+ },
	832	+ "llmCallFailedTotal": {
	833	+ "value": "94{,}609",
	834	+ "source": "results/ledger/log_summary.json:october",
	835	+ "formula": "llm_call_failed_total"
	836	+ },
	837	+ "llmCallFailedInsideOutage": {
	838	+ "value": "94{,}467",
	839	+ "source": "results/ledger/log_summary.json:october",
	840	+ "formula": "llm_call_failed_inside_window"
	841	+ },
	842	+ "llmCallFailedOutsideOutage": {
	843	+ "value": "142",
	844	+ "source": "results/ledger/log_summary.json:october",
	845	+ "formula": "llm_call_failed_outside_window"
	846	+ },
	847	+ "llmFailedJsonDecodeError": {
	848	+ "value": "14",
	849	+ "source": "results/ledger/log_summary.json:october.llm_call_failed_by_reason",
	850	+ "formula": "json_decode_error"
	851	+ },
	852	+ "llmFailedRetryableHttpFourTwoNineFivexx": {
	853	+ "value": "94{,}593",
	854	+ "source": "results/ledger/log_summary.json:october.llm_call_failed_by_reason",
	855	+ "formula": "retryable_http_429_5xx"
	856	+ },
	857	+ "llmFailedConnectionError": {
	858	+ "value": "2",
	859	+ "source": "results/ledger/log_summary.json:october.llm_call_failed_by_reason",
	860	+ "formula": "connection_error"
	861	+ },
	862	+ "juneLlmCallFailed": {
	863	+ "value": "3",
	864	+ "source": "results/ledger/log_summary.json:june",
	865	+ "formula": "llm_call_failed_total"
	866	+ },
	867	+ "collisionSections": {
	868	+ "value": "304",
	869	+ "source": "results/ledger/collisions.json",
	870	+ "formula": "sections_ledger_gt_stored"
	871	+ },
	872	+ "collisionMentions": {
	873	+ "value": "412",
	874	+ "source": "results/ledger/collisions.json",
	875	+ "formula": "excess_mentions"
	876	+ },
	877	+ "projectsKeyedGeneral": {
	878	+ "value": "229",
	879	+ "source": "results/resolver/composition.json",
	880	+ "formula": "projects_by_key_branch[general]"
	881	+ },
	882	+ "mentionsKeyedGeneral": {
	883	+ "value": "2{,}152",
	884	+ "source": "results/resolver/composition.json",
	885	+ "formula": "mentions_keyed_general"
	886	+ },
	887	+ "projectsKeyedNameToken": {
	888	+ "value": "66{,}405",
	889	+ "source": "results/resolver/composition.json",
	890	+ "formula": "projects_by_key_branch[name_token]"
	891	+ },
	892	+ "projectsKeyedNameTokenPct": {
	893	+ "value": "54.8",
	894	+ "source": "results/resolver/composition.json",
	895	+ "formula": "100*projects_by_key_branch[name_token]/projects"
	896	+ },
	897	+ "projectsKeyedLocation": {
	898	+ "value": "54{,}658",
	899	+ "source": "results/resolver/composition.json",
	900	+ "formula": "projects_by_key_branch[location]"
	901	+ },
	902	+ "projectsKeyedLocationPct": {
	903	+ "value": "45.1",
	904	+ "source": "results/resolver/composition.json",
	905	+ "formula": "100*projects_by_key_branch[location]/projects"
	906	+ },
	907	+ "projectsKeyedGeneralPct": {
	908	+ "value": "0.2",
	909	+ "source": "results/resolver/composition.json",
	910	+ "formula": "100*projects_by_key_branch[general]/projects"
	911	+ },
	912	+ "projectsTieMaxConfidence": {
	913	+ "value": "33{,}820",
	914	+ "source": "results/resolver/ties_idempotence.json",
	915	+ "formula": "projects_with_tie_at_max_confidence"
	916	+ },
	917	+ "projectsTieDistinctNames": {
	918	+ "value": "20{,}118",
	919	+ "source": "results/resolver/ties_idempotence.json",
	920	+ "formula": "projects_with_tie_and_distinct_names"
	921	+ },
	922	+ "projectsStatusTie": {
	923	+ "value": "972",
	924	+ "source": "results/resolver/ties_idempotence.json",
	925	+ "formula": "projects_with_status_tie_on_last_seen"
	926	+ },
	927	+ "mentionsAtConfidenceOne": {
	928	+ "value": "108{,}023",
	929	+ "source": "results/resolver/ties_idempotence.json",
	930	+ "formula": "mentions_at_confidence_1"
	931	+ },
	932	+ "projectCountRangeKeys": {
	933	+ "value": "21{,}027--308{,}065",
	934	+ "source": "results/resolver/spec_curve.csv",
	935	+ "formula": "min/max projects over keys at threshold 0.45"
	936	+ },
	937	+ "projectCountRangeKeysN": {
	938	+ "value": "9",
	939	+ "source": "results/resolver/spec_curve.csv",
	940	+ "formula": "number of keys at threshold 0.45"
	941	+ },
	942	+ "projectCountRangeAll": {
	943	+ "value": "16{,}562--308{,}065",
	944	+ "source": "results/resolver/spec_curve.csv",
	945	+ "formula": "min/max projects over all keys x thresholds"
	946	+ },
	947	+ "projectCountCurrentKey": {
	948	+ "value": "121{,}099",
	949	+ "source": "results/resolver/spec_curve.csv",
	950	+ "formula": "key=k_current at 0.45"
	951	+ },
	952	+ "topNameTokens": {
	953	+ "value": "\\texttt{acquisition} (3.4\\%), \\texttt{share} (3.1\\%), \\texttt{expansion} (1.8\\%), \\texttt{stock} (1.7\\%), \\texttt{investment} (1.6\\%), \\texttt{merger} (1.3\\%), \\texttt{sale} (1.3\\%), \\texttt{development} (1.2\\%), \\texttt{strategic} (0.9\\%), \\texttt{capital} (0.8\\%)",
	954	+ "source": "results/resolver/top_name_tokens.csv",
	955	+ "formula": "top-10 tokens, pct of token-keyed projects"
	956	+ },
	957	+ "topNameTokensProjectsPct": {
	958	+ "value": "17.2",
	959	+ "source": "results/resolver/top_name_tokens.csv",
	960	+ "formula": "sum of pct_of_tokenkeyed_projects over the top 10"
	961	+ },
	962	+ "projects": {
	963	+ "value": "121{,}099",
	964	+ "source": "stats.json:projects",
	965	+ "formula": "count(projects)"
	966	+ },
	967	+ "mentions": {
	968	+ "value": "308{,}065",
	969	+ "source": "stats.json:mentions",
	970	+ "formula": "count(project_mentions)"
	971	+ },
	972	+ "issuersWithProjects": {
	973	+ "value": "2{,}492",
	974	+ "source": "stats.json:issuers_with_projects",
	975	+ "formula": "count(distinct cik)"
	976	+ },
	977	+ "issuersWithFilings": {
	978	+ "value": "2{,}499",
	979	+ "source": "stats.json:issuers_with_filings",
	980	+ "formula": "count(distinct cik) in filings"
	981	+ },
	982	+ "sectionsTotal": {
	983	+ "value": "1{,}342{,}283",
	984	+ "source": "stats.json:sections_total",
	985	+ "formula": "count(filing_sections)"
	986	+ },
	987	+ "chunks": {
	988	+ "value": "10{,}720{,}890",
	989	+ "source": "stats.json:chunks[0]",
	990	+ "formula": "count(filing_chunks)"
	991	+ },
	992	+ "projectsWithLocation": {
	993	+ "value": "54{,}583",
	994	+ "source": "stats.json:projects_fields[1]",
	995	+ "formula": "count(canonical_location is not null)"
	996	+ },
	997	+ "projectsTokenKeyedShare": {
	998	+ "value": "54.9",
	999	+ "source": "stats.json:projects_fields",
	1000	+ "formula": "100*(projects - with location)/projects"
	1001	+ },
	1002	+ "projectsPerIssuerMean": {
	1003	+ "value": "48.6",
	1004	+ "source": "data/projects_per_issuer.csv",
	1005	+ "formula": "mean"
	1006	+ },
	1007	+ "projectsPerIssuerMedian": {
	1008	+ "value": "42",
	1009	+ "source": "data/projects_per_issuer.csv",
	1010	+ "formula": "q[2]"
	1011	+ },
	1012	+ "extractedAtFirst": {
	1013	+ "value": "2026-10-27 13:12:32",
	1014	+ "source": "stats.json:extracted_at_range[0]",
	1015	+ "formula": "min(extracted_at)"
	1016	+ },
	1017	+ "extractedAtLast": {
	1018	+ "value": "2026-10-28 11:15:49",
	1019	+ "source": "stats.json:extracted_at_range[1]",
	1020	+ "formula": "max(extracted_at)"
	1021	+ },
	1022	+ "brief": {
	1023	+ "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",
	1024	+ "source": "data/documented_inputs.json:brief_definition",
	1025	+ "formula": "documented input (author to confirm)"
	1026	+ },
	1027	+ "newProjectsPerIssuerFirstYear": {
	1028	+ "value": "6.4",
	1029	+ "source": "data/projects_by_first_seen_year.csv, mentions_by_year.csv",
	1030	+ "formula": "first seen / issuers with mentions"
	1031	+ },
	1032	+ "newProjectsPerIssuerLastFullYear": {
	1033	+ "value": "3.5",
	1034	+ "source": "data/projects_by_first_seen_year.csv, mentions_by_year.csv",
	1035	+ "formula": "first seen / issuers with mentions"
	1036	+ }
	1037	+}
		\ No newline at end of file

added results/tables_diff.txt +318 −0

		`@@ -0,0 +1,318 @@`
	1	+diff --git a/paper/tables/prompt_verbatim.tex b/paper/tables/prompt_verbatim.tex
	2	+index 60359fa..78d298e 100644
	3	+--- a/paper/tables/prompt_verbatim.tex
	4	++++ b/paper/tables/prompt_verbatim.tex
	5	+@@ -20,7 +20,27 @@ Return STRICT JSON: {"projects": [ ... ]}. Each project object has:
	6	+ confidence : 0.0-1.0 (how clearly this is a real, concrete project)
	7	+
	8	+ Allowed project_type values:
	9	+- - <code>: <label> (the 21 taxonomy entries of Table A1)
	10	++ - manufacturing_expansion: Manufacturing / Capacity Expansion
	11	++ - plant_construction: Plant / Site Construction
	12	++ - data_center: Data Center
	13	++ - cloud_migration: Cloud Migration
	14	++ - ai_initiative: AI / ML Initiative
	15	++ - digital_transformation: Digital Transformation
	16	++ - erp_implementation: ERP / Systems Implementation
	17	++ - rd_program: R&D Program
	18	++ - product_launch: New Product / Launch
	19	++ - drug_pipeline: Drug / Clinical Pipeline
	20	++ - ma_integration: M&A / Integration
	21	++ - geographic_expansion: Geographic Expansion
	22	++ - capex_program: Capital Expenditure Program
	23	++ - supply_chain: Supply Chain Initiative
	24	++ - automation: Automation / Robotics
	25	++ - sustainability: Sustainability / ESG
	26	++ - energy_transition: Energy Transition / Renewables
	27	++ - infrastructure: Infrastructure Investment
	28	++ - cost_reduction: Cost Reduction / Restructuring
	29	++ - partnership: Strategic Partnership
	30	++ - technology_deployment: Technology Deployment
	31	+
	32	+ Rules:
	33	+ - Extract ONLY real initiatives, not generic risk-factor boilerplate or hypotheticals.
	34	+diff --git a/paper/tables/tab_amounts.tex b/paper/tables/tab_amounts.tex
	35	+index 0576150..0551234 100644
	36	+--- a/paper/tables/tab_amounts.tex
	37	++++ b/paper/tables/tab_amounts.tex
	38	+@@ -5,4 +5,4 @@
	39	+ Largest amount cited per project{,} M USD ($N$ = 56{{,}}500) & 3.2 & 23 & 128.5 & 500 & 1{,}503 & 12{,}501 \\
	40	+ Projects per issuer ($N$ = 2{{,}}492) & 12 & 24 & 42 & 67 & 94 & 140 \\
	41	+ \bottomrule
	42	+-\end{tabular}
	43	+\ No newline at end of file
	44	++\end{tabular}
	45	+diff --git a/paper/tables/tab_confidence.tex b/paper/tables/tab_confidence.tex
	46	+index 7b5bc9c..808aff6 100644
	47	+--- a/paper/tables/tab_confidence.tex
	48	++++ b/paper/tables/tab_confidence.tex
	49	+@@ -9,4 +9,4 @@ Self-reported confidence (rounded) & Mentions \\
	50	+ 0.9 & 100{,}831 \\
	51	+ 1.0 & 108{,}418 \\
	52	+ \bottomrule
	53	+-\end{tabular}
	54	+\ No newline at end of file
	55	++\end{tabular}
	56	+diff --git a/paper/tables/tab_coverage_year.tex b/paper/tables/tab_coverage_year.tex
	57	+index 04d5edd..093ed79 100644
	58	+--- a/paper/tables/tab_coverage_year.tex
	59	++++ b/paper/tables/tab_coverage_year.tex
	60	+@@ -1,23 +1,23 @@
	61	+-\begin{tabular}{lrrrrrrr}
	62	++\begin{tabular}{lrrrrrrrr}
	63	+ \toprule
	64	+-Year & Issuers & 10-K & 10-Q & 8-K & Mentions & Issuers w/ mentions & Projects first seen \\
	65	++Year & Issuers & 10-K & 10-Q & 8-K & Mentions & Issuers w/ mentions & Mentions per issuer & Projects first seen \\
	66	+ \midrule
	67	+-2010 & 1{,}392 & 1{,}357 & 4{,}152 & 17{,}672 & 11{,}908 & 1{,}224 & 7{,}835 \\
	68	+-2011 & 1{,}424 & 1{,}409 & 4{,}260 & 18{,}533 & 13{,}551 & 1{,}287 & 6{,}679 \\
	69	+-2012 & 1{,}472 & 1{,}436 & 4{,}363 & 19{,}437 & 14{,}302 & 1{,}333 & 6{,}444 \\
	70	+-2013 & 1{,}539 & 1{,}483 & 4{,}530 & 19{,}773 & 14{,}611 & 1{,}408 & 6{,}286 \\
	71	+-2014 & 1{,}619 & 1{,}549 & 4{,}780 & 20{,}927 & 16{,}274 & 1{,}490 & 6{,}732 \\
	72	+-2015 & 1{,}689 & 1{,}635 & 4{,}983 & 22{,}077 & 17{,}073 & 1{,}535 & 6{,}675 \\
	73	+-2016 & 1{,}744 & 1{,}692 & 5{,}146 & 22{,}447 & 16{,}429 & 1{,}579 & 6{,}240 \\
	74	+-2017 & 1{,}810 & 1{,}745 & 5{,}359 & 22{,}897 & 17{,}350 & 1{,}636 & 6{,}490 \\
	75	+-2018 & 1{,}893 & 1{,}827 & 5{,}582 & 23{,}709 & 18{,}064 & 1{,}737 & 6{,}815 \\
	76	+-2019 & 1{,}973 & 1{,}903 & 5{,}829 & 24{,}256 & 18{,}737 & 1{,}806 & 6{,}837 \\
	77	+-2020 & 2{,}089 & 1{,}985 & 6{,}095 & 27{,}424 & 17{,}970 & 1{,}919 & 7{,}212 \\
	78	+-2021 & 2{,}247 & 2{,}116 & 6{,}606 & 27{,}944 & 21{,}312 & 2{,}077 & 8{,}216 \\
	79	+-2022 & 2{,}291 & 2{,}258 & 6{,}830 & 26{,}533 & 22{,}720 & 2{,}105 & 8{,}158 \\
	80	+-2023 & 2{,}329 & 2{,}295 & 6{,}938 & 26{,}851 & 22{,}955 & 2{,}129 & 7{,}977 \\
	81	+-2024 & 2{,}387 & 2{,}341 & 7{,}092 & 27{,}438 & 22{,}503 & 2{,}204 & 7{,}819 \\
	82	+-2025 & 2{,}453 & 2{,}406 & 7{,}300 & 28{,}716 & 23{,}220 & 2{,}280 & 7{,}990 \\
	83	+-2026 & 2{,}498 & 2{,}338 & 5{,}322 & 23{,}972 & 19{,}086 & 2{,}260 & 6{,}694 \\
	84	++2010 & 1{,}392 & 1{,}357 & 4{,}152 & 17{,}672 & 11{,}908 & 1{,}224 & 9.7 & 7{,}835 \\
	85	++2011 & 1{,}424 & 1{,}409 & 4{,}260 & 18{,}533 & 13{,}551 & 1{,}287 & 10.5 & 6{,}679 \\
	86	++2012 & 1{,}472 & 1{,}436 & 4{,}363 & 19{,}437 & 14{,}302 & 1{,}333 & 10.7 & 6{,}444 \\
	87	++2013 & 1{,}539 & 1{,}483 & 4{,}530 & 19{,}773 & 14{,}611 & 1{,}408 & 10.4 & 6{,}286 \\
	88	++2014 & 1{,}619 & 1{,}549 & 4{,}780 & 20{,}927 & 16{,}274 & 1{,}490 & 10.9 & 6{,}732 \\
	89	++2015 & 1{,}689 & 1{,}635 & 4{,}983 & 22{,}077 & 17{,}073 & 1{,}535 & 11.1 & 6{,}675 \\
	90	++2016 & 1{,}744 & 1{,}692 & 5{,}146 & 22{,}447 & 16{,}429 & 1{,}579 & 10.4 & 6{,}240 \\
	91	++2017 & 1{,}810 & 1{,}745 & 5{,}359 & 22{,}897 & 17{,}350 & 1{,}636 & 10.6 & 6{,}490 \\
	92	++2018 & 1{,}893 & 1{,}827 & 5{,}582 & 23{,}709 & 18{,}064 & 1{,}737 & 10.4 & 6{,}815 \\
	93	++2019 & 1{,}973 & 1{,}903 & 5{,}829 & 24{,}256 & 18{,}737 & 1{,}806 & 10.4 & 6{,}837 \\
	94	++2020 & 2{,}089 & 1{,}985 & 6{,}095 & 27{,}424 & 17{,}970 & 1{,}919 & 9.4 & 7{,}212 \\
	95	++2021 & 2{,}247 & 2{,}116 & 6{,}606 & 27{,}944 & 21{,}312 & 2{,}077 & 10.3 & 8{,}216 \\
	96	++2022 & 2{,}291 & 2{,}258 & 6{,}830 & 26{,}533 & 22{,}720 & 2{,}105 & 10.8 & 8{,}158 \\
	97	++2023 & 2{,}329 & 2{,}295 & 6{,}938 & 26{,}851 & 22{,}955 & 2{,}129 & 10.8 & 7{,}977 \\
	98	++2024 & 2{,}387 & 2{,}341 & 7{,}092 & 27{,}438 & 22{,}503 & 2{,}204 & 10.2 & 7{,}819 \\
	99	++2025 & 2{,}453 & 2{,}406 & 7{,}300 & 28{,}716 & 23{,}220 & 2{,}280 & 10.2 & 7{,}990 \\
	100	++2026 & 2{,}498 & 2{,}338 & 5{,}322 & 23{,}972 & 19{,}086 & 2{,}260 & 8.4 & 6{,}694 \\
	101	+ \bottomrule
	102	+-\end{tabular}
	103	+\ No newline at end of file
	104	++\end{tabular}
	105	+diff --git a/paper/tables/tab_filings.tex b/paper/tables/tab_filings.tex
	106	+index 625a1f0..0e3f777 100644
	107	+--- a/paper/tables/tab_filings.tex
	108	++++ b/paper/tables/tab_filings.tex
	109	+@@ -8,4 +8,4 @@ Form & Filings & First filing & Last filing & Raw HTML (GB) & Not parsed \\
	110	+ \midrule
	111	+ Total & 527{,}548 & 2010-01-04 & 2026-10-27 & 254.5 & 16 \\
	112	+ \bottomrule
	113	+-\end{tabular}
	114	+\ No newline at end of file
	115	++\end{tabular}
	116	+diff --git a/paper/tables/tab_graph.tex b/paper/tables/tab_graph.tex
	117	+index 7dd3c7e..4444a61 100644
	118	+--- a/paper/tables/tab_graph.tex
	119	++++ b/paper/tables/tab_graph.tex
	120	+@@ -11,4 +11,4 @@ Nodes & \texttt{Location} & 14{,}508 \\
	121	+ Nodes & \texttt{Technology} & 8{,}551 \\
	122	+ Nodes & \texttt{Company} & 2{,}492 \\
	123	+ \bottomrule
	124	+-\end{tabular}
	125	+\ No newline at end of file
	126	++\end{tabular}
	127	+diff --git a/paper/tables/tab_items.tex b/paper/tables/tab_items.tex
	128	+index 8b4f50f..6411493 100644
	129	+--- a/paper/tables/tab_items.tex
	130	++++ b/paper/tables/tab_items.tex
	131	+@@ -1,21 +1,21 @@
	132	+-\begin{tabular}{llrr}
	133	++\begin{tabular}{llrrr}
	134	+ \toprule
	135	+-Form & Section (item) & Sections extracted & Mentions \\
	136	++Form & Section (item) & Ledgered sections & Mentions & Gate passed (calls) \\
	137	+ \midrule
	138	+-10-K & \texttt{business} & 29{,}285 & 30{,}492 \\
	139	+-10-K & \texttt{risk\_factors} & 29{,}158 & 2{,}797 \\
	140	+-10-K & \texttt{md\_and\_a} & 28{,}919 & 39{,}099 \\
	141	+-10-K & \texttt{properties} & 28{,}236 & 7{,}879 \\
	142	+-10-K & \texttt{quantitative\_disclosures} & 26{,}876 & 531 \\
	143	+-10-K & \texttt{full\_body} & 1{,}230 & 824 \\
	144	++10-K & \texttt{business} & 29{,}285 & 30{,}492 & 29{,}118 \\
	145	++10-K & \texttt{risk\_factors} & 29{,}158 & 2{,}797 & 28{,}941 \\
	146	++10-K & \texttt{md\_and\_a} & 28{,}919 & 39{,}099 & 28{,}050 \\
	147	++10-K & \texttt{properties} & 28{,}236 & 7{,}879 & 25{,}940 \\
	148	++10-K & \texttt{quantitative\_disclosures} & 26{,}876 & 531 & 22{,}032 \\
	149	++10-K & \texttt{full\_body} & 1{,}230 & 824 & 1{,}229 \\
	150	+ \midrule
	151	+-10-Q & \texttt{controls\_and\_procedures} & 92{,}393 & 7{,}082 \\
	152	+-10-Q & \texttt{financial\_statements} & 91{,}882 & 30{,}159 \\
	153	+-10-Q & \texttt{md\_and\_a} & 91{,}371 & 99{,}305 \\
	154	+-10-Q & \texttt{quantitative\_disclosures} & 83{,}138 & 808 \\
	155	+-10-Q & \texttt{unregistered\_sales} & 80{,}210 & 9{,}535 \\
	156	+-10-Q & \texttt{risk\_factors} & 72{,}560 & 4{,}420 \\
	157	+-10-Q & \texttt{legal\_proceedings} & 66{,}998 & 845 \\
	158	+-10-Q & \texttt{full\_document} & 241 & 107 \\
	159	++10-Q & \texttt{controls\_and\_procedures} & 92{,}393 & 7{,}082 & 20{,}913 \\
	160	++10-Q & \texttt{financial\_statements} & 91{,}882 & 30{,}159 & 90{,}106 \\
	161	++10-Q & \texttt{md\_and\_a} & 91{,}371 & 99{,}305 & 90{,}269 \\
	162	++10-Q & \texttt{quantitative\_disclosures} & 83{,}138 & 808 & 46{,}720 \\
	163	++10-Q & \texttt{unregistered\_sales} & 80{,}210 & 9{,}535 & 61{,}867 \\
	164	++10-Q & \texttt{risk\_factors} & 72{,}560 & 4{,}420 & 33{,}826 \\
	165	++10-Q & \texttt{legal\_proceedings} & 66{,}998 & 845 & 20{,}031 \\
	166	++10-Q & \texttt{full\_document} & 241 & 107 & 241 \\
	167	+ \bottomrule
	168	+-\end{tabular}
	169	+\ No newline at end of file
	170	++\end{tabular}
	171	+diff --git a/paper/tables/tab_provenance.tex b/paper/tables/tab_provenance.tex
	172	+index 153ace1..65c772a 100644
	173	+--- a/paper/tables/tab_provenance.tex
	174	++++ b/paper/tables/tab_provenance.tex
	175	+@@ -11,4 +11,4 @@ Accession & Filed & Form & Status / amount & Evidence snippet (model-generated d
	176	+ \texttt{0001193125-15-186045} & 2015-05-13 & 8-K & in\_progress / 11.5 B USD & The project involves the development, construction, operation, and maintenance of a natural gas liquefaction and export facility and related infrastructure in San Patrici \\
	177	+ \texttt{0000003570-22-000029} & 2022-03-07 & 8-K & in\_progress / 5.5 B USD & The project involves the engineering, procurement, construction, pre-commissioning, commissioning, start-up, and testing of a mid-scale natural gas liquefaction facility \\
	178	+ \bottomrule
	179	+-\end{tabular}
	180	+\ No newline at end of file
	181	++\end{tabular}
	182	+diff --git a/paper/tables/tab_reconciliation.tex b/paper/tables/tab_reconciliation.tex
	183	+index a1f0a84..aa41007 100644
	184	+--- a/paper/tables/tab_reconciliation.tex
	185	++++ b/paper/tables/tab_reconciliation.tex
	186	+@@ -2,7 +2,7 @@
	187	+ \toprule
	188	+ Step & Count \\
	189	+ \midrule
	190	+-iShares IWV holdings file, equity lines with a ticker (as of Oct 23, 2026) & 2{,}587 \\
	191	++iShares IWV holdings file, equity lines with a ticker (as of Oct 23, 2026); count reported by the build log, source file not archived & 2{,}587 \\
	192	+ \quad of which mapped to an SEC CIK (CVRs, escrow lines and FDIC-only banks excluded) & 2{,}573 \\
	193	+ \quad distinct CIKs (share classes collapsed) & 2{,}555 \\
	194	+ S\&P~500 constituents, cached snapshot of 2026-05-25 (500 CIKs) & 503 \\
	195	+@@ -16,4 +16,4 @@ Issuers with at least one 10-K, 10-Q or 8-K since 2010 & 2{,}499 \\
	196	+ Issuers without any such filing (foreign private issuers filing 20-F/40-F, FDIC-only banks) & 65 \\
	197	+ Issuers with at least one resolved project & 2{,}492 \\
	198	+ \bottomrule
	199	+-\end{tabular}
	200	+\ No newline at end of file
	201	++\end{tabular}
	202	+diff --git a/paper/tables/tab_sections.tex b/paper/tables/tab_sections.tex
	203	+index 57983ae..1c741a2 100644
	204	+--- a/paper/tables/tab_sections.tex
	205	++++ b/paper/tables/tab_sections.tex
	206	+@@ -1,11 +1,11 @@
	207	+-\begin{tabular}{lrrrrrr}
	208	++\begin{tabular}{lrrrrrrrr}
	209	+ \toprule
	210	+-Form & Parsed sections & Median words & Sections sent to the extractor & Sections with $\geq 1$ mention & Mentions & Issuers \\
	211	++Form & Parsed sections & Median words & Ledgered sections ($\geq$ 30 words) & Gate-passing calls & Sections with $\geq 1$ mention & Mentions returned by the model (ledger) & Mentions stored & Issuers \\
	212	+ \midrule
	213	+-10-K & 341{,}207 & 875 & 143{,}704 & 30{,}877 & 81{,}622 & 2{,}464 \\
	214	+-10-Q & 600{,}471 & 500 & 578{,}793 & 75{,}705 & 152{,}261 & 2{,}494 \\
	215	+-8-K & 400{,}605 & 575 & 400{,}601 & 61{,}648 & 74{,}594 & 2{,}499 \\
	216	++10-K & 341{,}207 & 875 & 143{,}704 & 135{,}310 & 30{,}877 & 81{,}622 & 81{,}495 & 2{,}464 \\
	217	++10-Q & 600{,}471 & 500 & 578{,}793 & 363{,}973 & 75{,}705 & 152{,}261 & 152{,}004 & 2{,}494 \\
	218	++8-K & 400{,}605 & 575 & 400{,}601 & 204{,}442 & 61{,}648 & 74{,}594 & 74{,}566 & 2{,}499 \\
	219	+ \midrule
	220	+-Total & 1{,}342{,}283 & & 1{,}123{,}098 & 168{,}230 & 308{,}477 & 2{,}499 \\
	221	++Total & 1{,}342{,}283 & & 1{,}123{,}098 & 703{,}725 & 168{,}230 & 308{,}477 & 308{,}065 & 2{,}499$^{\dagger}$ \\
	222	+ \bottomrule
	223	+-\end{tabular}
	224	+\ No newline at end of file
	225	++\end{tabular}
	226	+diff --git a/paper/tables/tab_sectors.tex b/paper/tables/tab_sectors.tex
	227	+index 34a1b08..a35431e 100644
	228	+--- a/paper/tables/tab_sectors.tex
	229	++++ b/paper/tables/tab_sectors.tex
	230	+@@ -14,4 +14,4 @@ Consumer Staples & 103 & 36 & 103 & 5{,}921 & 57.5 \\
	231	+ Utilities & 68 & 31 & 66 & 4{,}920 & 74.5 \\
	232	+ Communication Services & 105 & 20 & 101 & 4{,}520 & 44.8 \\
	233	+ \bottomrule
	234	+-\end{tabular}
	235	+\ No newline at end of file
	236	++\end{tabular}
	237	+diff --git a/paper/tables/tab_status.tex b/paper/tables/tab_status.tex
	238	+index 2b94374..dc3cc93 100644
	239	+--- a/paper/tables/tab_status.tex
	240	++++ b/paper/tables/tab_status.tex
	241	+@@ -8,4 +8,4 @@ Latest status & Projects & Mentions per project & Projects & Span of cited years
	242	+ \texttt{mentioned} & 2{,}745 & 6-10 & 6{,}173 & $>$5 years & 10{,}326 \\
	243	+ & & >10 & 3{,}769 & unknown years & 17{,}599 \\
	244	+ \bottomrule
	245	+-\end{tabular}
	246	+\ No newline at end of file
	247	++\end{tabular}
	248	+diff --git a/paper/tables/tab_top_issuers.tex b/paper/tables/tab_top_issuers.tex
	249	+index 03aae51..918e7b9 100644
	250	+--- a/paper/tables/tab_top_issuers.tex
	251	++++ b/paper/tables/tab_top_issuers.tex
	252	+@@ -15,4 +15,4 @@ CLSK & Cleanspark & 170 \\
	253	+ CWEN & Clearway Energy Inc Class C & 168 \\
	254	+ ALK & Alaska Air Group Inc & 168 \\
	255	+ \bottomrule
	256	+-\end{tabular}
	257	+\ No newline at end of file
	258	++\end{tabular}
	259	+diff --git a/paper/tables/tab_types.tex b/paper/tables/tab_types.tex
	260	+index 78f685e..e2c2ff8 100644
	261	+--- a/paper/tables/tab_types.tex
	262	++++ b/paper/tables/tab_types.tex
	263	+@@ -1,29 +1,29 @@
	264	+-\begin{tabular}{llrrrrr}
	265	++\begin{tabular}{llrrrrrrr}
	266	+ \toprule
	267	+-Code & Category & Projects & Share (\%) & With amount & Median amount (M USD) & Mentions / project \\
	268	++Code & Category & Projects & Share (\%) & With amount ($N$) & Median amount (M USD) & 95\% CI of the median & Mentions / project & $\geq 3$ distinct names (\%) \\
	269	+ \midrule
	270	+-\texttt{ma\_integration} & M\&A / integration & 41{,}742 & 34.5 & 28{,}044 & 155.0 & 3.12 \\
	271	+-\texttt{capex\_program} & Capital expenditure program & 10{,}720 & 8.9 & 9{,}452 & 300.0 & 1.79 \\
	272	+-\texttt{partnership} & Strategic partnership & 9{,}909 & 8.2 & 2{,}943 & 75.0 & 1.77 \\
	273	+-\texttt{geographic\_expansion} & Geographic expansion & 7{,}868 & 6.5 & 1{,}431 & 36.7 & 2.25 \\
	274	+-\texttt{plant\_construction} & Plant / site construction & 7{,}590 & 6.3 & 2{,}511 & 56.0 & 2.42 \\
	275	+-\texttt{cost\_reduction} & Cost reduction / restructuring & 6{,}481 & 5.4 & 4{,}378 & 50.0 & 2.03 \\
	276	+-\texttt{drug\_pipeline} & Drug / clinical pipeline & 5{,}360 & 4.4 & 778 & 46.1 & 4.99 \\
	277	+-\texttt{product\_launch} & New product / launch & 5{,}356 & 4.4 & 447 & 26.7 & 2.33 \\
	278	+-\texttt{rd\_program} & R\&D program & 5{,}080 & 4.2 & 1{,}272 & 20.0 & 2.31 \\
	279	+-\texttt{infrastructure} & Infrastructure investment & 4{,}481 & 3.7 & 1{,}694 & 48.0 & 1.90 \\
	280	+-\texttt{manufacturing\_expansion} & Manufacturing / capacity expansion & 4{,}140 & 3.4 & 1{,}040 & 45.0 & 2.13 \\
	281	+-\texttt{technology\_deployment} & Technology deployment & 4{,}128 & 3.4 & 1{,}219 & 135.0 & 1.63 \\
	282	+-\texttt{digital\_transformation} & Digital transformation & 2{,}642 & 2.2 & 240 & 34.2 & 1.99 \\
	283	+-\texttt{erp\_implementation} & ERP / systems implementation & 1{,}735 & 1.4 & 184 & 15.0 & 2.44 \\
	284	+-\texttt{sustainability} & Sustainability / ESG & 1{,}305 & 1.1 & 410 & 34.4 & 2.00 \\
	285	+-\texttt{supply\_chain} & Supply-chain initiative & 684 & 0.6 & 139 & 38.0 & 1.71 \\
	286	+-\texttt{data\_center} & Data center & 449 & 0.4 & 129 & 166.0 & 1.98 \\
	287	+-\texttt{energy\_transition} & Energy transition / renewables & 415 & 0.3 & 109 & 109.0 & 2.09 \\
	288	+-\texttt{ai\_initiative} & AI / ML initiative & 376 & 0.3 & 20 & 127.5 & 1.68 \\
	289	+-\texttt{automation} & Automation / robotics & 374 & 0.3 & 25 & 13.7 & 1.68 \\
	290	+-\texttt{cloud\_migration} & Cloud migration & 264 & 0.2 & 35 & 50.0 & 1.97 \\
	291	++\texttt{ma\_integration} & M\&A / integration & 41{,}742 & 34.5 & 28{,}044 & 155.0 & -- & 3.12 & 14.6 \\
	292	++\texttt{capex\_program} & Capital expenditure program & 10{,}720 & 8.9 & 9{,}452 & 300.0 & -- & 1.79 & 6.4 \\
	293	++\texttt{partnership} & Strategic partnership & 9{,}909 & 8.2 & 2{,}943 & 75.0 & -- & 1.77 & 6.7 \\
	294	++\texttt{geographic\_expansion} & Geographic expansion & 7{,}868 & 6.5 & 1{,}431 & 36.7 & -- & 2.25 & 10.2 \\
	295	++\texttt{plant\_construction} & Plant / site construction & 7{,}590 & 6.3 & 2{,}511 & 56.0 & -- & 2.42 & 13.5 \\
	296	++\texttt{cost\_reduction} & Cost reduction / restructuring & 6{,}481 & 5.4 & 4{,}378 & 50.0 & -- & 2.03 & 5.7 \\
	297	++\texttt{drug\_pipeline} & Drug / clinical pipeline & 5{,}360 & 4.4 & 778 & 46.1 & -- & 4.99 & 27.9 \\
	298	++\texttt{product\_launch} & New product / launch & 5{,}356 & 4.4 & 447 & 26.7 & -- & 2.33 & 12.2 \\
	299	++\texttt{rd\_program} & R\&D program & 5{,}080 & 4.2 & 1{,}272 & 20.0 & -- & 2.31 & 11.4 \\
	300	++\texttt{infrastructure} & Infrastructure investment & 4{,}481 & 3.7 & 1{,}694 & 48.0 & -- & 1.90 & 7.5 \\
	301	++\texttt{manufacturing\_expansion} & Manufacturing / capacity expansion & 4{,}140 & 3.4 & 1{,}040 & 45.0 & -- & 2.13 & 11.3 \\
	302	++\texttt{technology\_deployment} & Technology deployment & 4{,}128 & 3.4 & 1{,}219 & 135.0 & -- & 1.63 & 4.8 \\
	303	++\texttt{digital\_transformation} & Digital transformation & 2{,}642 & 2.2 & 240 & 34.2 & -- & 1.99 & 6.2 \\
	304	++\texttt{erp\_implementation} & ERP / systems implementation & 1{,}735 & 1.4 & 184 & 15.0 & -- & 2.44 & 3.5 \\
	305	++\texttt{sustainability} & Sustainability / ESG & 1{,}305 & 1.1 & 410 & 34.4 & -- & 2.00 & 6.1 \\
	306	++\texttt{supply\_chain} & Supply-chain initiative & 684 & 0.6 & 139 & 38.0 & -- & 1.71 & 3.5 \\
	307	++\texttt{data\_center} & Data center & 449 & 0.4 & 129 & 166.0 & -- & 1.98 & 9.3 \\
	308	++\texttt{energy\_transition} & Energy transition / renewables & 415 & 0.3 & 109 & 109.0 & -- & 2.09 & 10.1 \\
	309	++\texttt{ai\_initiative} & AI / ML initiative & 376 & 0.3 & 20 & \textcolor{gray}{127.5} & -- & 1.68 & 4.8 \\
	310	++\texttt{automation} & Automation / robotics & 374 & 0.3 & 25 & \textcolor{gray}{13.7} & -- & 1.68 & 2.7 \\
	311	++\texttt{cloud\_migration} & Cloud migration & 264 & 0.2 & 35 & \textcolor{gray}{50.0} & -- & 1.97 & 5.7 \\
	312	+ \midrule
	313	+- & Total & 121{,}099 & 100.0 & 56{,}500 & 128.5 & 2.54 \\
	314	++ & Total & 121{,}099 & 100.1 & 56{,}500 & 128.5 & -- & 2.54 & \\
	315	+ \bottomrule
	316	+-\end{tabular}
	317	+\ No newline at end of file
	318	++\end{tabular}
	319

spb/firc0001_uqo

L1: de-literalise make_tables.py/export_stats.py; generated notes, macros (numbers.tex), prompt/regex from the snapshot, Table 12 longtable, figures (integer ticks, y from 0, per-issuer panel); stats.json never rewritten

Theme