N3: resolver composition, over-merge indicators, specification curve, ties, June->October reconciliation

Items: FIRC0001-ADVE-01 EDIT-07 THEO-01 AI_C-02 ECON-02 DATA-11 ECON-16 THEO-17 EDIT-06.
_keyed rebuilt from resolve.py:17-32 (121,099 projects, identical id set); 9 keys x 5 thresholds;
project count 21,027 (cik|type) .. 96,749 (type dropped) .. 121,099 (current) .. 198,488 (strict) .. 308,065 (mention);
token 'acquisition' absorbs 40,407 mentions; 33,820 projects tie at max confidence; June block reproduces 39,930 / 19,227.

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

Simon-Pierre Boucher committed yesterday (Nov 5, 2026) parent 1d2705d Browse files

15 changed files +1,753 −0

added code/audit/a03_resolver_speccurve.py +257 −0

++"""N3 - resolver composition, over-merge indicators, specification curve, ties, June->October
++reconciliation (cluster B). Read-only; _m/_keyed rebuilt as TEMP tables from resolve.py:17-32.
++"""
++from __future__ import annotations
++import json, sys
++from pathlib import Path
++sys.path.insert(0, str(Path(__file__).resolve().parent))
++from common import *
++sys.path.insert(0, str(Path(__file__).resolve().parent / "spid"))
++import taxonomy as tx  # snapshot copy (hash-verified in N0)
++
++EXAMPLE_PROJECT = "3e2705ba5b2dd27408b25f0145e34250"   # stats.json example_project (Cheniere Corpus Christi Stage 3)
++STOP = ["project", "program", "development", "expansion", "acquisition", "phase", "initiative", "facility", "construction"]
++THRESHOLDS = [0.45, 0.6, 0.7, 0.8, 0.9]
++
++r = Run("resolver")
++con = connect(SPID_DB)
++tmin = con.execute("select min(extracted_at) from extracted_sections").fetchone()[0]
++con.execute(f"""CREATE TEMP TABLE runmap AS SELECT section_id, CASE WHEN extracted_at = TIMESTAMP '{tmin}' THEN 'backfilled_june' ELSE 'october' END AS run FROM extracted_sections""")
++
++# ---- exact rebuild of _m / _keyed (resolve.py:17-32) --------------------------------------------
++con.execute("""
++CREATE TEMP TABLE _m AS
++SELECT *,
++   lower(coalesce(try(locations[1]), '')) AS loc1,
++   regexp_extract(lower(regexp_replace(project_name, '[^A-Za-z ]', '', 'g')), '([a-z]{4,})', 1) AS name_tok
++FROM project_mentions""")
++con.execute("""
++CREATE TEMP TABLE _keyed AS
++SELECT *,
++   cik || '|' || project_type || '|' || CASE WHEN loc1 <> '' THEN loc1 ELSE coalesce(nullif(name_tok,''),'general') END AS gkey,
++   md5(cik || '|' || project_type || '|' || CASE WHEN loc1 <> '' THEN loc1 ELSE coalesce(nullif(name_tok,''),'general') END) AS project_id
++FROM _m""")
++V = {}
++V["rebuilt_projects"] = con.execute("select count(distinct project_id) from _keyed").fetchone()[0]
++V["stored_projects"] = con.execute("select count(*) from projects").fetchone()[0]
++V["project_id_set_equal"] = con.execute("select count(*) from (select project_id from _keyed except select project_id from projects) union all select count(*) from (select project_id from projects except select distinct project_id from _keyed)").fetchall()
++V["mentions"] = con.execute("select count(*) from _keyed").fetchone()[0]
++
++# ---- (a) key composition ----------------------------------------------------------------------
++V["mentions_by_key_branch"] = con.execute("""
++  select case when loc1<>'' then 'location' when nullif(name_tok,'') is not null then 'name_token' else 'general' end b, count(*) from _keyed group by 1""").fetchall()
++V["projects_by_key_branch"] = con.execute("""
++  select case when loc1<>'' then 'location' when nullif(name_tok,'') is not null then 'name_token' else 'general' end b, count(distinct project_id) from _keyed group by 1""").fetchall()
++V["projects_keyed_general"] = con.execute("select count(distinct project_id) from _keyed where gkey like '%|general'").fetchone()[0]
++V["mentions_keyed_general"] = con.execute("select count(*) from _keyed where gkey like '%|general'").fetchone()[0]
++states = sorted(tx.US_STATES); countries = sorted(tx.COUNTRIES)
++con.execute("CREATE TEMP TABLE geo AS SELECT unnest(?) AS loc, 'us_state' AS kind UNION ALL SELECT unnest(?), 'country'", [states, countries])
++V["location_keyed_projects_by_geo_kind"] = con.execute("""
++  with p as (select project_id, any_value(loc1) loc1 from _keyed where loc1<>'' group by 1)
++  select coalesce(g.kind,'other_place') kind, count(*) from p left join geo g on p.loc1 = g.loc group by 1""").fetchall()
++V["location_keyed_mentions_by_geo_kind"] = con.execute("""
++  select coalesce(g.kind,'other_place') kind, count(*) from _keyed k left join geo g on k.loc1 = g.loc where k.loc1<>'' group by 1""").fetchall()
++r.dump("top_name_tokens.csv", con, """
++  with t as (select name_tok, count(*) mentions, count(distinct project_id) projects from _keyed where loc1='' and nullif(name_tok,'') is not null group by 1)
++  select name_tok, mentions, projects, round(100.0*mentions/(select count(*) from _keyed where loc1=''),2) pct_of_tokenkeyed_mentions,
++         round(100.0*projects/(select count(distinct project_id) from _keyed where loc1=''),2) pct_of_tokenkeyed_projects
++  from t order by projects desc limit 50""")
++r.dump("top_location_keys.csv", con, """
++  select loc1, count(*) mentions, count(distinct project_id) projects from _keyed where loc1<>'' group by 1 order by 2 desc limit 50""")
++r.dump("key_branch_by_type.csv", con, """
++  select project_type, count(distinct project_id) projects,
++         count(distinct project_id) filter (where loc1<>'') loc_keyed,
++         count(distinct project_id) filter (where loc1='' and nullif(name_tok,'') is not null) token_keyed,
++         count(distinct project_id) filter (where loc1='' and nullif(name_tok,'') is null) general_keyed
++  from _keyed group by 1 order by 2 desc""")
++
++# ---- (b) over-merge indicators ----------------------------------------------------------------
++con.execute("""
++CREATE TEMP TABLE pstat AS
++SELECT project_id, any_value(project_type) project_type, count(*) n_mentions,
++       count(DISTINCT lower(trim(project_name))) n_names,
++       count(DISTINCT lower(trim(coalesce(try(partners[1]), '')))) FILTER (WHERE len(partners)>0) n_partners,
++       count(DISTINCT accession_number) n_filings, count(DISTINCT cik) n_ciks,
++       count(DISTINCT lower(description)) n_desc
++FROM _keyed GROUP BY 1""")
++bucket = "case when n_mentions=1 then '1' when n_mentions=2 then '2' when n_mentions<=5 then '3-5' when n_mentions<=10 then '6-10' else '>10' end"
++r.dump("overmerge_by_type.csv", con, f"""
++  select project_type, count(*) projects, sum(n_mentions) mentions,
++         round(100.0*count(*) filter (where n_names>=3)/count(*),2) pct_ge3_names,
++         round(100.0*count(*) filter (where n_names>=2)/count(*),2) pct_ge2_names,
++         round(100.0*count(*) filter (where n_partners>=3)/nullif(count(*) filter (where n_partners>=1),0),2) pct_ge3_partners_among_with_partner,
++         count(*) filter (where n_partners>=3) n_ge3_partners,
++         round(100.0*count(*) filter (where n_mentions>1 and n_names = n_mentions)/nullif(count(*) filter (where n_mentions>1),0),2) pct_multi_all_names_distinct
++  from pstat group by 1 order by 2 desc""")
++r.dump("overmerge_by_bucket.csv", con, f"""
++  select {bucket} bucket, count(*) projects,
++         round(100.0*count(*) filter (where n_names>=3)/count(*),2) pct_ge3_names,
++         round(100.0*count(*) filter (where n_partners>=3)/nullif(count(*) filter (where n_partners>=1),0),2) pct_ge3_partners_among_with_partner,
++         round(avg(n_names),2) mean_names
++  from pstat group by 1 order by min(n_mentions)""")
++r.dump("overmerge_ma_by_bucket.csv", con, f"""
++  select {bucket} bucket, count(*) projects,
++         count(*) filter (where n_partners>=1) with_partner,
++         round(100.0*count(*) filter (where n_partners>=3)/nullif(count(*) filter (where n_partners>=1),0),2) pct_ge3_partners,
++         round(100.0*count(*) filter (where n_partners>=2)/nullif(count(*) filter (where n_partners>=1),0),2) pct_ge2_partners,
++         round(100.0*count(*) filter (where n_names>=3)/count(*),2) pct_ge3_names
++  from pstat where project_type='ma_integration' group by 1 order by min(n_mentions)""")
++# amount from a mention naming a different counterparty than the representative mention
++V["amount_from_other_counterparty"] = con.execute("""
++  with rep as (select project_id, arg_max(lower(trim(coalesce(try(partners[1]),''))), confidence) rep_partner from _keyed group by 1),
++       amt as (select project_id, arg_max(lower(trim(coalesce(try(partners[1]),''))), amount_usd) amt_partner, max(amount_usd) mx from _keyed where amount_usd is not null group by 1)
++  select count(*) filter (where rep_partner<>'' and amt_partner<>'' and rep_partner<>amt_partner) differing,
++         count(*) filter (where rep_partner<>'' and amt_partner<>'') both_named, count(*) with_amount
++  from amt join rep using(project_id)""").fetchone()
++V["amount_from_other_counterparty_ma"] = con.execute("""
++  with rep as (select project_id, any_value(project_type) t, arg_max(lower(trim(coalesce(try(partners[1]),''))), confidence) rep_partner from _keyed group by 1),
++       amt as (select project_id, arg_max(lower(trim(coalesce(try(partners[1]),''))), amount_usd) amt_partner from _keyed where amount_usd is not null group by 1)
++  select count(*) filter (where rep_partner<>'' and amt_partner<>'' and rep_partner<>amt_partner) differing,
++         count(*) filter (where rep_partner<>'' and amt_partner<>'') both_named, count(*) with_amount
++  from amt join rep using(project_id) where t='ma_integration'""").fetchone()
++V["amount_from_other_name"] = con.execute("""
++  with rep as (select project_id, arg_max(lower(trim(project_name)), confidence) rep_name from _keyed group by 1),
++       amt as (select project_id, arg_max(lower(trim(project_name)), amount_usd) amt_name from _keyed where amount_usd is not null group by 1)
++  select count(*) filter (where rep_name<>amt_name) differing, count(*) with_amount from amt join rep using(project_id)""").fetchone()
++r.dump("example_provenance_keys.csv", con, """
++  select project_id, cik, project_type, gkey, count(*) n, count(distinct lower(project_name)) n_names, list(distinct left(project_name,60)) names
++  from _keyed where project_id in (select project_id from projects where project_id in (
++     select project_id from project_timeline group by 1 having count(*) between 4 and 8) and total_amount_usd > 5e8 and project_type in ('plant_construction','data_center'))
++  group by 1,2,3,4 order by n desc limit 30""")
++
++# ---- (c) specification curve ----------------------------------------------------------------------
++stop_sql = ",".join("'" + s + "'" for s in STOP)
++con.execute(f"""
++CREATE TEMP TABLE km AS
++SELECT mention_id, cik, project_type, confidence, loc1, name_tok, gkey,
++  regexp_replace(trim(regexp_replace(lower(project_name), '[^a-z0-9 ]', '', 'g')), ' +', ' ', 'g') AS name_norm,
++  list_filter(string_split(regexp_replace(lower(project_name), '[^a-z ]', '', 'g'), ' '), lambda x: length(x) >= 4) AS toks,
++  list_filter(string_split(regexp_replace(lower(project_name), '[^a-z ]', '', 'g'), ' '), lambda x: length(x) >= 4 AND x NOT IN ({stop_sql})) AS toks_sw,
++  trim(regexp_replace(regexp_replace(regexp_replace(loc1, '\\b(u\\.s\\.|usa|u\\.s\\.a\\.|united states of america)\\b', 'united states', 'g'), '[^a-z, ]', '', 'g'), ' +', ' ', 'g')) AS loc_norm
++FROM _keyed""")
++con.execute("""
++CREATE TEMP TABLE keys AS
++SELECT mention_id, confidence, project_type,
++  cik || '|' || project_type AS k_cik_type,
++  gkey AS k_current,
++  cik || '|' || project_type || '|' || CASE WHEN loc1 <> '' THEN loc1 ELSE coalesce(toks_sw[1], 'general') END AS k_current_stopwords,
++  cik || '|' || project_type || '|' || CASE WHEN loc_norm <> '' THEN trim(string_split(loc_norm, ',')[1]) ELSE coalesce(toks_sw[1], 'general') END AS k_city_normalised,
++  cik || '|' || CASE WHEN loc1 <> '' THEN loc1 ELSE coalesce(nullif(name_tok,''), 'general') END AS k_type_dropped,
++  cik || '|' || project_type || '|' || CASE WHEN loc1 <> '' THEN loc1 ELSE coalesce(toks_sw[1], 'general') || '|' || coalesce(toks_sw[2], '') END AS k_two_tokens,
++  cik || '|' || project_type || '|' || coalesce(toks_sw[1], 'general') AS k_name_only,
++  cik || '|' || project_type || '|' || name_norm || '|' || loc1 AS k_strict,
++  mention_id AS k_mention_level
++FROM km""")
++KEYS = ["k_cik_type", "k_type_dropped", "k_current", "k_current_stopwords", "k_city_normalised", "k_name_only", "k_two_tokens", "k_strict", "k_mention_level"]
++ex_mention = con.execute("select arg_max(mention_id, confidence) from _keyed where project_id = ?", [EXAMPLE_PROJECT]).fetchone()[0]
++rows = []; bytype = []
++for k in KEYS:
++    for t in THRESHOLDS:
++        q = f"""
++        with g as (select {k} key, count(*) n, max(mention_id = '{ex_mention}')::int has_ex from keys where confidence >= {t} group by 1)
++        select count(*) projects, sum(n) mentions, round(100.0*count(*) filter (where n=1)/count(*),2) single_pct,
++               round(100.0*count(*) filter (where n>10)/count(*),2) gt10_pct, round(avg(n),3) mean_mentions,
++               max(n) max_cluster, coalesce(max(n) filter (where has_ex=1),0) example_cluster_size
++        from g"""
++        row = con.execute(q).fetchone()
++        rows.append((k, t) + tuple(row))
++        bt = con.execute(f"""
++        with g as (select {k} key, any_value(project_type) project_type, count(*) n from keys where confidence >= {t} group by 1)
++        select project_type, count(*) n from g group by 1""").fetchall()
++        bytype += [(k, t, pt, n) for pt, n in bt]
++        print(k, t, row, flush=True)
++r.write_csv("spec_curve.csv", ["key", "threshold", "projects", "mentions", "single_mention_pct", "gt10_mention_pct", "mean_mentions", "max_cluster", "example_cluster_size_cheniere"], rows)
++r.write_csv("spec_curve_by_type.csv", ["key", "threshold", "project_type", "projects"], bytype)
++cur = [x for x in rows if x[0] == "k_current" and x[1] == 0.45][0]
++V["project_count_current"] = cur[2]
++V["project_count_range_045"] = {k: [x[2] for x in rows if x[0] == k and x[1] == 0.45][0] for k in KEYS}
++V["project_count_strict_045"] = V["project_count_range_045"]["k_strict"]
++V["project_count_loose_045_cik_type"] = V["project_count_range_045"]["k_cik_type"]
++V["example_mention"] = ex_mention
++
++# ---- (d) ties and idempotence ----------------------------------------------------------------------
++D = {}
++D["projects_with_tie_at_max_confidence"] = con.execute("""
++  with mx as (select project_id, max(confidence) mc from _keyed group by 1)
++  select count(*) from (select k.project_id from _keyed k join mx using(project_id) where k.confidence = mx.mc group by 1 having count(*)>1)""").fetchone()[0]
++D["projects_with_tie_and_distinct_names"] = con.execute("""
++  with mx as (select project_id, max(confidence) mc from _keyed group by 1)
++  select count(*) from (select k.project_id from _keyed k join mx using(project_id) where k.confidence = mx.mc group by 1 having count(distinct project_name)>1)""").fetchone()[0]
++D["projects_with_tie_and_distinct_descriptions"] = con.execute("""
++  with mx as (select project_id, max(confidence) mc from _keyed group by 1)
++  select count(*) from (select k.project_id from _keyed k join mx using(project_id) where k.confidence = mx.mc group by 1 having count(distinct description)>1)""").fetchone()[0]
++D["projects_with_status_tie_on_last_seen"] = con.execute("""
++  with mx as (select project_id, max(filing_date) md from _keyed group by 1)
++  select count(*) from (select k.project_id from _keyed k join mx using(project_id) where k.filing_date = mx.md group by 1 having count(distinct status)>1)""").fetchone()[0]
++D["mentions_at_confidence_1"] = con.execute("select count(*) from project_mentions where confidence = 1.0").fetchone()[0]
++# stored projects vs rebuilt with the original (tie-ambiguous) SQL: how many representative fields differ
++con.execute("""
++CREATE TEMP TABLE rebuilt AS
++SELECT project_id, arg_max(project_name, confidence) project_name, arg_max(status, filing_date) status, arg_max(description, confidence) description,
++       max(amount_usd) total_amount_usd, count(*) n_mentions
++FROM _keyed GROUP BY 1""")
++D["rebuilt_vs_stored_diff"] = con.execute("""
++  select count(*) filter (where r.project_name is distinct from p.project_name) name_diff,
++         count(*) filter (where r.status is distinct from p.status) status_diff,
++         count(*) filter (where r.description is distinct from p.description) desc_diff,
++         count(*) filter (where r.total_amount_usd is distinct from p.total_amount_usd) amount_diff,
++         count(*) filter (where r.n_mentions is distinct from p.n_mentions) n_diff, count(*) n
++  from rebuilt r join projects p using(project_id)""").fetchone()
++con.execute("""
++CREATE TEMP TABLE rebuilt2 AS
++SELECT project_id, arg_max(project_name, confidence) project_name, arg_max(status, filing_date) status, arg_max(description, confidence) description
++FROM _keyed GROUP BY 1""")
++D["original_sql_run_twice_diff"] = con.execute("""
++  select count(*) filter (where a.project_name is distinct from b.project_name), count(*) filter (where a.status is distinct from b.status), count(*) filter (where a.description is distinct from b.description)
++  from rebuilt a join rebuilt2 b using(project_id)""").fetchone()
++det = """
++SELECT project_id, project_name, status, description FROM (
++  SELECT project_id,
++         first_value(project_name) OVER (PARTITION BY project_id ORDER BY confidence DESC, mention_id) project_name,
++         first_value(description) OVER (PARTITION BY project_id ORDER BY confidence DESC, mention_id) description,
++         first_value(status) OVER (PARTITION BY project_id ORDER BY filing_date DESC, mention_id) status,
++         row_number() OVER (PARTITION BY project_id ORDER BY mention_id) rn
++  FROM _keyed) WHERE rn = 1"""
++con.execute(f"CREATE TEMP TABLE det1 AS {det}")
++con.execute(f"CREATE TEMP TABLE det2 AS {det}")
++D["deterministic_tiebreak_run_twice_diff"] = con.execute("""
++  select count(*) filter (where a.project_name is distinct from b.project_name), count(*) filter (where a.status is distinct from b.status), count(*) filter (where a.description is distinct from b.description)
++  from det1 a join det2 b using(project_id)""").fetchone()
++D["deterministic_vs_stored_diff"] = con.execute("""
++  select count(*) filter (where a.project_name is distinct from p.project_name), count(*) filter (where a.status is distinct from p.status), count(*) filter (where a.description is distinct from p.description)
++  from det1 a join projects p using(project_id)""").fetchone()
++r.write_json("ties_idempotence.json", D)
++
++# ---- (e) June -> October reconciliation (S&P 500 CIKs) -------------------------------------------
++con.execute("""CREATE TEMP TABLE kr AS SELECT k.*, rm.run, co.in_sp500, co.in_russell3000 FROM _keyed k LEFT JOIN runmap rm USING (section_id) LEFT JOIN src_companies co ON k.cik = co.cik""")
++R = {}
++R["sp500_ciks"] = con.execute("select count(*) from src_companies where in_sp500").fetchone()[0]
++R["mentions_in_backfilled_block"] = con.execute("select count(*) from kr where run='backfilled_june'").fetchone()[0]
++R["projects_from_backfilled_block_only"] = con.execute("select count(distinct project_id) from kr where run='backfilled_june'").fetchone()[0]
++R["expected_june"] = {"mentions": 39930, "projects": 19227, "timeline_rows": 39930}
++R["sp500_mentions_total"] = con.execute("select count(*) from kr where in_sp500").fetchone()[0]
++R["sp500_projects_total"] = con.execute("select count(distinct project_id) from kr where in_sp500").fetchone()[0]
++R["paper_sp500_projects_october"] = 27766
++R["sp500_projects_by_run_composition"] = con.execute("""
++  with p as (select project_id, max(run='backfilled_june')::int has_june, max(run='october')::int has_oct from kr where in_sp500 group by 1)
++  select case when has_june=1 and has_oct=1 then 'both runs' when has_june=1 then 'june only' else 'october only' end c, count(*) from p group by 1""").fetchall()
++R["sp500_mentions_by_run_form"] = con.execute("select run, form_type, count(*), count(distinct accession_number) from kr where in_sp500 group by 1,2 order by 1,2").fetchall()
++R["sp500_mentions_filing_date_le_20260525_by_run"] = con.execute("select run, count(*), count(distinct project_id) from kr where in_sp500 and filing_date <= DATE '2026-05-25' group by 1").fetchall()
++R["sp500_projects_filing_date_le_20260525"] = con.execute("select count(distinct project_id) from kr where in_sp500 and filing_date <= DATE '2026-05-25'").fetchone()[0]
++R["backfilled_block_mentions_not_sp500"] = con.execute("select count(*) from kr where run='backfilled_june' and not coalesce(in_sp500,false)").fetchone()[0]
++R["june_10q_accessions_in_block_ledger"] = con.execute(f"""
++  select count(distinct e.accession_number) from extracted_sections e join src_filings f using(accession_number) where e.extracted_at = TIMESTAMP '{tmin}' and f.form_type='10-Q'""").fetchone()[0]
++R["ledger_block_accessions_by_form"] = con.execute(f"""
++  select f.form_type, count(distinct e.accession_number), count(*) from extracted_sections e join src_filings f using(accession_number) where e.extracted_at = TIMESTAMP '{tmin}' group by 1 order by 1""").fetchall()
++R["sp500_october_ledger_by_form"] = con.execute(f"""
++  select f.form_type, count(distinct e.accession_number), count(*), sum(e.n_mentions) from extracted_sections e join src_filings f using(accession_number) join src_companies co on f.cik=co.cik
++  where e.extracted_at <> TIMESTAMP '{tmin}' and co.in_sp500 group by 1 order by 1""").fetchall()
++R["sp500_block_ledger_by_form"] = con.execute(f"""
++  select f.form_type, count(distinct e.accession_number), count(*), sum(e.n_mentions) from extracted_sections e join src_filings f using(accession_number) join src_companies co on f.cik=co.cik
++  where e.extracted_at = TIMESTAMP '{tmin}' and co.in_sp500 group by 1 order by 1""").fetchall()
++r.write_json("june_october_reconciliation.json", R)
++r.dump("june_october_reconciliation.csv", con, """
++  select coalesce(in_sp500,false) in_sp500, run, form_type, count(*) mentions, count(distinct project_id) projects_touched, count(distinct accession_number) filings, count(distinct cik) issuers
++  from kr group by 1,2,3 order by 1,2,3""")
++r.write_json("composition.json", V)
++r.finish()

added results/resolver/composition.json +100 −0

++{
++  "rebuilt_projects": 121099,
++  "stored_projects": 121099,
++  "project_id_set_equal": [
++    [
++      0
++    ],
++    [
++      0
++    ]
++  ],
++  "mentions": 308065,
++  "mentions_by_key_branch": [
++    [
++      "name_token",
++      187212
++    ],
++    [
++      "location",
++      118783
++    ],
++    [
++      "general",
++      2070
++    ]
++  ],
++  "projects_by_key_branch": [
++    [
++      "name_token",
++      66405
++    ],
++    [
++      "location",
++      54658
++    ],
++    [
++      "general",
++      229
++    ]
++  ],
++  "projects_keyed_general": 286,
++  "mentions_keyed_general": 2152,
++  "location_keyed_projects_by_geo_kind": [
++    [
++      "other_place",
++      40422
++    ],
++    [
++      "us_state",
++      6110
++    ],
++    [
++      "country",
++      8126
++    ]
++  ],
++  "location_keyed_mentions_by_geo_kind": [
++    [
++      "other_place",
++      78479
++    ],
++    [
++      "country",
++      22986
++    ],
++    [
++      "us_state",
++      17318
++    ]
++  ],
++  "amount_from_other_counterparty": [
++    2347,
++    21908,
++    56500
++  ],
++  "amount_from_other_counterparty_ma": [
++    1630,
++    12372,
++    28044
++  ],
++  "amount_from_other_name": [
++    8882,
++    56500
++  ],
++  "project_count_current": 121099,
++  "project_count_range_045": {
++    "k_cik_type": 21027,
++    "k_type_dropped": 96749,
++    "k_current": 121099,
++    "k_current_stopwords": 130101,
++    "k_city_normalised": 123246,
++    "k_name_only": 114244,
++    "k_two_tokens": 145697,
++    "k_strict": 198488,
++    "k_mention_level": 308065
++  },
++  "project_count_strict_045": 198488,
++  "project_count_loose_045_cik_type": 21027,
++  "example_mention": "cebf8e727e1a7f5bc821"
++}
+ \ No newline at end of file

added results/resolver/example_provenance_keys.csv +31 −0

++project_id,cik,project_type,gkey,n,n_names,names
++dbe60cbe1feab59090d7ce4c63c0b6a1,0001001838,plant_construction,0001001838|plant_construction|peru,8,4,"['Tía María Mining Project', 'Tia Maria Greenfield Project', 'Tia Maria Project', 'Toquepala Expansion Project']"
++7942bcad2b16e5c326d64ef7cc4d79f6,0000092122,plant_construction,0000092122|plant_construction|waynesboro/georgia/usa,8,1,['Plant Vogtle Units 3 and 4']
++d333f4d6faa95492939e7d242761e7b5,0000753308,plant_construction,0000753308|plant_construction|california,8,7,"['507 Megawatt Natural Gas-Fired Power Generation Facility', 'McCoy Project', '20 MW Solar Facility', 'Redwood Trails Wind Generation Facilities', 'Desert Sunlight Solar Project', 'Genesis Project', 'Genesis Solar Project']"
++f58417bd7fc1be9b73fcd47a88f4a406,0001513761,plant_construction,0001513761|plant_construction|norwegian,8,6,"['Norwegian Breakaway', 'Norwegian Escape and Norwegian Bliss', 'Norwegian Joy and Breakaway Plus Class Ships', 'Norwegian Getaway', 'Norwegian Bliss', 'Norwegian Encore']"
++105ebf2e17ec61bd2bff6f3cce50a33b,0001451505,plant_construction,0001451505|plant_construction|deepwater,8,7,"['Deepwater Titan', 'Deepwater Champion', 'Deepwater Poseidon', 'Deepwater Thalassa Construction', 'Deepwater Atlas', 'Deepwater Pontus', 'Deepwater Proteus']"
++47fda6961d383537e6e3ce70adf8b064,0001324404,plant_construction,"0001324404|plant_construction|donaldsonville, louisiana",8,6,"['Green Hydrogen Project', 'Ammonia and Urea Production Units', 'New Ammonia and Urea Plants', 'Ammonia and UAN Plants Construction', 'Capacity Expansion Projects', 'Urea Plant Commissioning']"
++dc8940627597a296318115e21e7ea024,0001164727,plant_construction,0001164727|plant_construction|peru,8,2,"['Conga Project', 'Conga']"
++00461ab6a8ee44d809b436b3aaf59072,0001287865,plant_construction,0001287865|plant_construction|development,8,4,"['Development Project', 'Development Projects with First Choice Emergency Room', 'Development Projects with Adeptus Health, Inc.', 'Development Projects']"
++5317e0ee56e32e3563b0d34a8ec04442,0000025232,plant_construction,0000025232|plant_construction|development,8,5,"['Development Pipeline', 'New Development Projects', 'Development of Domain 10, Domain 12, and Avalon 10000', 'Development projects', 'Development of Office and Mixed-Use Projects', 'Development Projects']"
++3e2705ba5b2dd27408b25f0145e34250,0000003570,plant_construction,"0000003570|plant_construction|san patricio county, texas",8,7,"['Third Liquefaction Train', 'First Liquefaction Train Construction', 'Third Liquefaction Train at CCLNG', 'Corpus Christi Liquefaction Stage 3 Project', 'Second Liquefaction Train at CCLNG', 'Corpus Christi Liquefaction Project', 'Second Liquefaction Train']"
++30a198e7029a4956be8327cd83da4b70,0001513761,plant_construction,0001513761|plant_construction|explorer,7,3,"['Explorer Class Newbuild Loan Agreement', 'Explorer Class Ships', 'Explorer Class Ship']"
++14d587c2883840856f231fe3414727b5,0000831259,plant_construction,0000831259|plant_construction|grasberg,7,4,"['Grasberg Underground Development', 'Grasberg Block Cave Restart', 'Underground Development Activities at Grasberg', 'Grasberg Underground Mine Development']"
++fbfb8fca9ac08121c1681b13a9db3e38,0001051470,plant_construction,0001051470|plant_construction|construction,7,2,"['Construction of New Communications Infrastructure', 'Construction of Small Cells']"
++7b5cdbd8d0e9a2a0519d7093bd3c78a9,0000884887,plant_construction,0000884887|plant_construction|project,7,4,"['Project Edge', 'Project Sunshine Ship 1', 'Project Sunshine Ship 2', 'Project Sunshine']"
++28b552d43d7800a5e536b8c66bfd36fd,0000022444,plant_construction,"0000022444|plant_construction|berkeley county, west virginia",7,3,"['Fourth Micro Mill', 'Fourth Micro Mill Construction', 'Berkeley County Micro Mill']"
++eee28ac6c870400cb50b2119bd8e6c8e,0001040829,plant_construction,0001040829|plant_construction|aurora/colorado/usa,7,4,"['Aurora Resort and Convention Hotel', 'Gaylord Rockies expansion', 'Aurora Resort and Convention Hotel Development', 'Gaylord Rockies Resort & Convention Center']"
++f2126501fc9d07f93ce25627ba093984,0000034903,plant_construction,"0000034903|plant_construction|somerville, massachusetts",7,4,"['Assembly Row', 'Assembly Row Phase II', 'Assembly Square', 'Assembly Row Phase I']"
++a9a63ffa287236133e060b110818add5,0000833079,plant_construction,0000833079|plant_construction|land,7,1,['Land Development and Home Construction']
++7ba90cf2bc3e1cbbe5e26a2d8d8d7835,0001167419,data_center,0001167419|data_center|rockdale,7,3,"['Rockdale Facility', '191 Critical IT MW Data Center Project', 'Rockdale Facility Expansion']"
++83b669268f21ba09eae690226d209c01,0000915912,plant_construction,0000915912|plant_construction|future,7,2,"['Future Apartment Community Developments', 'Future Apartment Communities Development']"
++7473bc6fc5d414ab5ee5b287418491f1,0001795250,plant_construction,0001795250|plant_construction|las vegas/nevada/usa,7,2,"['Sphere in Las Vegas', 'MSG Sphere']"
++d2c21e2aa718297425664d398b9a4d0b,0000745732,plant_construction,0000745732|plant_construction|distribution,7,5,"['Distribution Centers Construction', 'New Distribution Centers', 'Distribution Center Expansion', 'Distribution Center Construction', 'New Distribution Center Construction']"
++6d7dca59c2d0c185240335f3a8060f25,0001653653,plant_construction,0001653653|plant_construction|las vegas/nevada/usa,7,5,"['Palace Station Upgrade and Expansion', 'Durango Casino Resort', 'New Casino Resort Construction', 'Durango Casino & Resort', 'Durango']"
++2a7deb96cd6e799cf0a00b78cddd55e6,0001653653,plant_construction,0001653653|plant_construction|las vegas/nevada,7,6,"['Palms Casino Resort Redevelopment', 'Durango Casino Resort', 'Palms Redevelopment Project', 'Palace Station Redevelopment', 'Durango Development', 'Palace Station Redevelopment Project']"
++13fec26e29e1bb20856eb321aadc6344,0000104169,plant_construction,0000104169|plant_construction|store,6,2,"['Store Remodels', 'Store and Club Remodels']"
++0a57f5fcba583f08d49dfcdb13b7e654,0000726728,plant_construction,0000726728|plant_construction|properties,6,2,"['Properties under development', 'Properties Under Development or Expansion']"
++4ec04c01a2e25d3816161f7f36aa936c,0001575965,plant_construction,0001575965|plant_construction|chicago,6,3,"['Bally’s Chicago', 'Bally’s Chicago Casino Resort', ""Bally's Chicago Development""]"
++6070161ae6a31d8613aa7e782212a253,0001612720,plant_construction,0001612720|plant_construction|grande,6,5,"['Rio Grande Natural Gas Liquefaction Facility', 'Rio Grande LNG Liquefaction and Export Project', 'Rio Grande Natural Gas Liquefaction Facility - Train 3', 'Rio Grande LNG Train 5', 'Rio Grande LNG Train 4']"
++61699e8c51c4cd75ceeef401fad61228,0001039684,plant_construction,"0001039684|plant_construction|texas city, texas",6,5,"['Texas City Liquified Petroleum Gas Export Terminal', 'Liquefied Petroleum Gas Export Terminal', 'Liquified Petroleum Gas Export Terminal and Pipeline', 'Texas City Logistics export terminal', 'Joint Ventures for LPG Export Terminal']"
++fe50af95e5803a7d904ff3430c127017,0000003570,plant_construction,0000003570|plant_construction|cameron parish,6,5,"['SPL Project', 'Liquefaction Facilities Construction', 'Fourth Liquefaction Train', 'Second LNG Liquefaction Train', 'Fifth Liquefaction Train']"

added results/resolver/june_october_reconciliation.csv +10 −0

++in_sp500,run,form_type,mentions,projects_touched,filings,issuers
++False,october,10-K,64798,34658,15784,1857
++False,october,10-Q,117224,45274,40745,1954
++False,october,8-K,55676,34420,45937,1964
++True,backfilled_june,10-K,15787,8697,4193,481
++True,backfilled_june,10-Q,5817,2071,2028,84
++True,backfilled_june,8-K,18326,10023,15234,495
++True,october,10-K,910,649,222,97
++True,october,10-Q,28963,11030,10684,455
++True,october,8-K,564,432,477,203

added results/resolver/june_october_reconciliation.json +137 −0

++{
++  "sp500_ciks": 500,
++  "mentions_in_backfilled_block": 39930,
++  "projects_from_backfilled_block_only": 19227,
++  "expected_june": {
++    "mentions": 39930,
++    "projects": 19227,
++    "timeline_rows": 39930
++  },
++  "sp500_mentions_total": 70367,
++  "sp500_projects_total": 27766,
++  "paper_sp500_projects_october": 27766,
++  "sp500_projects_by_run_composition": [
++    [
++      "june only",
++      15910
++    ],
++    [
++      "both runs",
++      3317
++    ],
++    [
++      "october only",
++      8539
++    ]
++  ],
++  "sp500_mentions_by_run_form": [
++    [
++      "backfilled_june",
++      "10-K",
++      15787,
++      4193
++    ],
++    [
++      "backfilled_june",
++      "10-Q",
++      5817,
++      2028
++    ],
++    [
++      "backfilled_june",
++      "8-K",
++      18326,
++      15234
++    ],
++    [
++      "october",
++      "10-K",
++      910,
++      222
++    ],
++    [
++      "october",
++      "10-Q",
++      28963,
++      10684
++    ],
++    [
++      "october",
++      "8-K",
++      564,
++      477
++    ]
++  ],
++  "sp500_mentions_filing_date_le_20260525_by_run": [
++    [
++      "october",
++      28995,
++      11217
++    ],
++    [
++      "backfilled_june",
++      39926,
++      19225
++    ]
++  ],
++  "sp500_projects_filing_date_le_20260525": 27360,
++  "backfilled_block_mentions_not_sp500": 0,
++  "june_10q_accessions_in_block_ledger": 3710,
++  "ledger_block_accessions_by_form": [
++    [
++      "10-K",
++      7368,
++      27164
++    ],
++    [
++      "10-Q",
++      3710,
++      23873
++    ],
++    [
++      "8-K",
++      103927,
++      103927
++    ]
++  ],
++  "sp500_october_ledger_by_form": [
++    [
++      "10-K",
++      377,
++      1803,
++      912
++    ],
++    [
++      "10-Q",
++      19399,
++      116231,
++      28996
++    ],
++    [
++      "8-K",
++      2939,
++      2939,
++      564
++    ]
++  ],
++  "sp500_block_ledger_by_form": [
++    [
++      "10-K",
++      7368,
++      27164,
++      15787
++    ],
++    [
++      "10-Q",
++      3710,
++      23873,
++      5817
++    ],
++    [
++      "8-K",
++      103927,
++      103927,
++      18326
++    ]
++  ]
++}
+ \ No newline at end of file

added results/resolver/key_branch_by_type.csv +22 −0

++project_type,projects,loc_keyed,token_keyed,general_keyed
++ma_integration,41742,22873,18922,12
++capex_program,10720,3638,7077,7
++partnership,9909,3396,6511,6
++geographic_expansion,7868,4895,2989,0
++plant_construction,7590,5773,1845,7
++cost_reduction,6481,2213,4275,2
++drug_pipeline,5360,1296,3935,130
++product_launch,5356,1130,4215,13
++rd_program,5080,954,4096,34
++infrastructure,4481,2801,1694,2
++manufacturing_expansion,4140,2614,1552,1
++technology_deployment,4128,1116,3004,8
++digital_transformation,2642,311,2329,3
++erp_implementation,1735,259,1478,0
++sustainability,1305,476,830,1
++supply_chain,684,269,416,0
++data_center,449,276,174,0
++energy_transition,415,243,177,0
++ai_initiative,376,29,345,2
++automation,374,70,304,0
++cloud_migration,264,26,237,1

added results/resolver/manifest.json +38 −0

++{
++  "package": "resolver",
++  "script": "/Users/simon-pierreboucher/firc0001_review/scripts/a03_resolver_speccurve.py",
++  "script_sha256": "19cf2ed3aae78394a718a31caa106a20a67cb9a6450c0d30b89f6a84c7fe8ad8",
++  "started": "2026-11-05T14:20:38",
++  "ended": "2026-11-05T14:20:40",
++  "wall_seconds": 2.2,
++  "node": "m3u96b",
++  "python": "3.12.15",
++  "duckdb": "2.0.0",
++  "threads": 4,
++  "memory_limit": "24GB",
++  "seed": 20261105,
++  "databases": {
++    "/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/data/db/spid.duckdb": {
++      "bytes": 3155701760,
++      "mtime": "2026-10-28T12:21:11.091389"
++    },
++    "/Users/simon-pierreboucher/UQO_RESEARCH_DB/data/duckdb/edgar_research.duckdb": {
++      "bytes": 73500995584,
++      "mtime": "2026-10-27T21:34:46.297884"
++    }
++  },
++  "read_only": true,
++  "row_counts": {
++    "top_name_tokens.csv": 50,
++    "top_location_keys.csv": 50,
++    "key_branch_by_type.csv": 21,
++    "overmerge_by_type.csv": 21,
++    "overmerge_by_bucket.csv": 5,
++    "overmerge_ma_by_bucket.csv": 5,
++    "example_provenance_keys.csv": 30,
++    "spec_curve.csv": 45,
++    "spec_curve_by_type.csv": 945,
++    "june_october_reconciliation.csv": 9
++  },
++  "notes": {}
++}
+ \ No newline at end of file

added results/resolver/overmerge_by_bucket.csv +6 −0

++bucket,projects,pct_ge3_names,pct_ge3_partners_among_with_partner,mean_names
++1,72932,0.0,0.0,1.0
++2,20544,0.0,0.0,1.53
++3-5,17681,37.44,15.12,2.2
++6-10,6173,64.09,31.18,3.56
++>10,3769,86.57,52.95,9.05

added results/resolver/overmerge_by_type.csv +22 −0

++project_type,projects,mentions,pct_ge3_names,pct_ge2_names,pct_ge3_partners_among_with_partner,n_ge3_partners,pct_multi_all_names_distinct
++ma_integration,41742,130259,14.63,30.93,10.92,2289,30.24
++capex_program,10720,19211,6.4,19.43,4.13,189,38.86
++partnership,9909,17501,6.74,19.66,4.3,281,38.57
++geographic_expansion,7868,17713,10.18,25.23,1.88,14,35.76
++plant_construction,7590,18388,13.49,30.3,4.04,62,34.68
++cost_reduction,6481,13157,5.71,17.47,1.59,4,26.39
++drug_pipeline,5360,26755,27.85,46.19,11.97,238,28.07
++product_launch,5356,12456,12.23,27.97,3.38,23,37.89
++rd_program,5080,11758,11.44,27.52,3.59,32,30.05
++infrastructure,4481,8510,7.5,20.78,2.17,21,38.05
++manufacturing_expansion,4140,8825,11.26,27.08,2.17,11,34.79
++technology_deployment,4128,6725,4.77,15.79,1.78,17,34.48
++digital_transformation,2642,5249,6.25,19.3,0.0,0,25.92
++erp_implementation,1735,4242,3.46,17.23,1.41,1,12.86
++sustainability,1305,2607,6.13,15.17,1.06,2,26.77
++supply_chain,684,1171,3.51,15.06,1.0,1,26.96
++data_center,449,889,9.35,26.06,3.64,6,46.54
++energy_transition,415,866,10.12,24.34,1.57,2,38.41
++ai_initiative,376,632,4.79,16.22,0.0,0,27.83
++automation,374,630,2.67,13.1,4.17,1,28.04
++cloud_migration,264,521,5.68,17.05,0.0,0,21.88

added results/resolver/overmerge_ma_by_bucket.csv +6 −0

++bucket,projects,with_partner,pct_ge3_partners,pct_ge2_partners,pct_ge3_names
++1,22606,9999,0.0,0.0,0.0
++2,7558,3781,0.0,32.35,0.0
++3-5,7070,3855,17.3,49.0,37.52
++6-10,2668,1766,36.35,63.65,66.15
++>10,1840,1564,62.66,80.82,91.74

added results/resolver/spec_curve.csv +46 −0

++key,threshold,projects,mentions,single_mention_pct,gt10_mention_pct,mean_mentions,max_cluster,example_cluster_size_cheniere
++k_cik_type,0.45,21027,308065,20.69,29.82,14.651,399,176
++k_cik_type,0.6,21001,306454,20.74,29.76,14.592,399,176
++k_cik_type,0.7,20878,303175,20.76,29.48,14.521,399,175
++k_cik_type,0.8,20053,281241,21.63,28.19,14.025,375,171
++k_cik_type,0.9,16562,207150,25.35,24.03,12.508,343,106
++k_type_dropped,0.45,96749,308065,52.59,4.99,3.184,269,11
++k_type_dropped,0.6,96438,306454,52.61,4.96,3.178,269,11
++k_type_dropped,0.7,95580,303175,52.64,4.95,3.172,269,11
++k_type_dropped,0.8,89818,281241,53.07,4.84,3.131,269,11
++k_type_dropped,0.9,70174,207150,54.53,4.26,2.952,250,10
++k_current,0.45,121099,308065,60.23,3.11,2.544,269,8
++k_current,0.6,120621,306454,60.24,3.1,2.541,269,8
++k_current,0.7,119427,303175,60.26,3.1,2.539,269,8
++k_current,0.8,111079,281241,60.47,3.05,2.532,269,8
++k_current,0.9,83483,207150,61.35,2.91,2.481,250,7
++k_current_stopwords,0.45,130101,308065,59.05,2.49,2.368,209,8
++k_current_stopwords,0.6,129601,306454,59.06,2.48,2.365,209,8
++k_current_stopwords,0.7,128404,303175,59.09,2.47,2.361,209,8
++k_current_stopwords,0.8,119990,281241,59.21,2.4,2.344,209,8
++k_current_stopwords,0.9,91918,207150,59.72,2.08,2.254,206,7
++k_city_normalised,0.45,123246,308065,56.83,2.84,2.5,212,8
++k_city_normalised,0.6,122760,306454,56.83,2.83,2.496,212,8
++k_city_normalised,0.7,121588,303175,56.84,2.82,2.493,212,8
++k_city_normalised,0.8,113404,281241,56.88,2.75,2.48,212,8
++k_city_normalised,0.9,86347,207150,57.02,2.42,2.399,209,7
++k_name_only,0.45,114244,308065,56.41,3.74,2.697,230,40
++k_name_only,0.6,113779,306454,56.41,3.73,2.693,230,40
++k_name_only,0.7,112652,303175,56.43,3.73,2.691,230,39
++k_name_only,0.8,104680,281241,56.44,3.72,2.687,230,39
++k_name_only,0.9,78834,207150,56.48,3.57,2.628,226,25
++k_two_tokens,0.45,145697,308065,62.96,1.74,2.114,209,8
++k_two_tokens,0.6,145122,306454,62.97,1.73,2.112,209,8
++k_two_tokens,0.7,143667,303175,62.95,1.72,2.11,209,8
++k_two_tokens,0.8,133671,281241,62.92,1.69,2.104,209,8
++k_two_tokens,0.9,100490,207150,62.93,1.51,2.061,206,7
++k_strict,0.45,198488,308065,75.78,0.52,1.552,206,1
++k_strict,0.6,197673,306454,75.8,0.51,1.55,206,1
++k_strict,0.7,195703,303175,75.82,0.5,1.549,206,1
++k_strict,0.8,182052,281241,75.92,0.49,1.545,206,1
++k_strict,0.9,135411,207150,76.17,0.4,1.53,203,1
++k_mention_level,0.45,308065,308065,100.0,0.0,1.0,1,1
++k_mention_level,0.6,306454,306454,100.0,0.0,1.0,1,1
++k_mention_level,0.7,303175,303175,100.0,0.0,1.0,1,1
++k_mention_level,0.8,281241,281241,100.0,0.0,1.0,1,1
++k_mention_level,0.9,207150,207150,100.0,0.0,1.0,1,1

added results/resolver/spec_curve_by_type.csv +946 −0

++key,threshold,project_type,projects
++k_cik_type,0.45,product_launch,1100
++k_cik_type,0.45,geographic_expansion,1673
++k_cik_type,0.45,supply_chain,389
++k_cik_type,0.45,sustainability,537
++k_cik_type,0.45,ma_integration,2448
++k_cik_type,0.45,manufacturing_expansion,882
++k_cik_type,0.45,data_center,142
++k_cik_type,0.45,ai_initiative,209
++k_cik_type,0.45,drug_pipeline,301
++k_cik_type,0.45,capex_program,2303
++k_cik_type,0.45,cost_reduction,1784
++k_cik_type,0.45,technology_deployment,1376
++k_cik_type,0.45,infrastructure,1231
++k_cik_type,0.45,digital_transformation,904
++k_cik_type,0.45,automation,234
++k_cik_type,0.45,erp_implementation,872
++k_cik_type,0.45,energy_transition,116
++k_cik_type,0.45,partnership,2046
++k_cik_type,0.45,plant_construction,1292
++k_cik_type,0.45,rd_program,1022
++k_cik_type,0.45,cloud_migration,166
++k_cik_type,0.6,cost_reduction,1783
++k_cik_type,0.6,erp_implementation,872
++k_cik_type,0.6,capex_program,2303
++k_cik_type,0.6,technology_deployment,1373
++k_cik_type,0.6,digital_transformation,903
++k_cik_type,0.6,infrastructure,1229
++k_cik_type,0.6,energy_transition,114
++k_cik_type,0.6,automation,232
++k_cik_type,0.6,geographic_expansion,1668
++k_cik_type,0.6,product_launch,1099
++k_cik_type,0.6,sustainability,535
++k_cik_type,0.6,supply_chain,386
++k_cik_type,0.6,ma_integration,2447
++k_cik_type,0.6,manufacturing_expansion,880
++k_cik_type,0.6,data_center,142
++k_cik_type,0.6,drug_pipeline,301
++k_cik_type,0.6,ai_initiative,209
++k_cik_type,0.6,rd_program,1022
++k_cik_type,0.6,partnership,2045
++k_cik_type,0.6,cloud_migration,166
++k_cik_type,0.6,plant_construction,1292
++k_cik_type,0.7,geographic_expansion,1647
++k_cik_type,0.7,product_launch,1090
++k_cik_type,0.7,sustainability,522
++k_cik_type,0.7,supply_chain,381
++k_cik_type,0.7,rd_program,1014
++k_cik_type,0.7,partnership,2040
++k_cik_type,0.7,cloud_migration,166
++k_cik_type,0.7,plant_construction,1290
++k_cik_type,0.7,ma_integration,2447
++k_cik_type,0.7,manufacturing_expansion,873
++k_cik_type,0.7,data_center,142
++k_cik_type,0.7,drug_pipeline,301
++k_cik_type,0.7,ai_initiative,208
++k_cik_type,0.7,cost_reduction,1780
++k_cik_type,0.7,erp_implementation,872
++k_cik_type,0.7,capex_program,2301
++k_cik_type,0.7,technology_deployment,1360
++k_cik_type,0.7,digital_transformation,886
++k_cik_type,0.7,infrastructure,1224
++k_cik_type,0.7,energy_transition,113
++k_cik_type,0.7,automation,221
++k_cik_type,0.8,ma_integration,2442
++k_cik_type,0.8,manufacturing_expansion,829
++k_cik_type,0.8,ai_initiative,192
++k_cik_type,0.8,data_center,130
++k_cik_type,0.8,drug_pipeline,299
++k_cik_type,0.8,product_launch,1032
++k_cik_type,0.8,geographic_expansion,1556
++k_cik_type,0.8,sustainability,478
++k_cik_type,0.8,supply_chain,305
++k_cik_type,0.8,plant_construction,1271
++k_cik_type,0.8,rd_program,957
++k_cik_type,0.8,partnership,1990
++k_cik_type,0.8,cloud_migration,155
++k_cik_type,0.8,technology_deployment,1273
++k_cik_type,0.8,cost_reduction,1744
++k_cik_type,0.8,capex_program,2289
++k_cik_type,0.8,automation,171
++k_cik_type,0.8,infrastructure,1155
++k_cik_type,0.8,erp_implementation,852
++k_cik_type,0.8,energy_transition,108
++k_cik_type,0.8,digital_transformation,825
++k_cik_type,0.9,geographic_expansion,1107
++k_cik_type,0.9,product_launch,818
++k_cik_type,0.9,supply_chain,149
++k_cik_type,0.9,sustainability,302
++k_cik_type,0.9,ma_integration,2440
++k_cik_type,0.9,manufacturing_expansion,648
++k_cik_type,0.9,drug_pipeline,292
++k_cik_type,0.9,data_center,93
++k_cik_type,0.9,ai_initiative,118
++k_cik_type,0.9,rd_program,652
++k_cik_type,0.9,partnership,1737
++k_cik_type,0.9,cloud_migration,96
++k_cik_type,0.9,plant_construction,1157
++k_cik_type,0.9,cost_reduction,1566
++k_cik_type,0.9,capex_program,2227
++k_cik_type,0.9,erp_implementation,701
++k_cik_type,0.9,technology_deployment,909
++k_cik_type,0.9,digital_transformation,473
++k_cik_type,0.9,infrastructure,930
++k_cik_type,0.9,energy_transition,87
++k_cik_type,0.9,automation,60
++k_type_dropped,0.45,product_launch,4115
++k_type_dropped,0.45,geographic_expansion,5770
++k_type_dropped,0.45,sustainability,990
++k_type_dropped,0.45,supply_chain,450
++k_type_dropped,0.45,ma_integration,37495
++k_type_dropped,0.45,manufacturing_expansion,2792
++k_type_dropped,0.45,drug_pipeline,4665
++k_type_dropped,0.45,data_center,318
++k_type_dropped,0.45,ai_initiative,287
++k_type_dropped,0.45,rd_program,3684
++k_type_dropped,0.45,plant_construction,5695
++k_type_dropped,0.45,partnership,7417
++k_type_dropped,0.45,cloud_migration,189
++k_type_dropped,0.45,cost_reduction,4928
++k_type_dropped,0.45,technology_deployment,2837
++k_type_dropped,0.45,capex_program,8149
++k_type_dropped,0.45,digital_transformation,1938
++k_type_dropped,0.45,erp_implementation,1539
++k_type_dropped,0.45,infrastructure,2979
++k_type_dropped,0.45,automation,260
++k_type_dropped,0.45,energy_transition,252
++k_type_dropped,0.6,product_launch,4106
++k_type_dropped,0.6,geographic_expansion,5736
++k_type_dropped,0.6,supply_chain,447
++k_type_dropped,0.6,sustainability,981
++k_type_dropped,0.6,ma_integration,37453
++k_type_dropped,0.6,drug_pipeline,4647
++k_type_dropped,0.6,manufacturing_expansion,2785
++k_type_dropped,0.6,ai_initiative,286
++k_type_dropped,0.6,data_center,315
++k_type_dropped,0.6,erp_implementation,1539
++k_type_dropped,0.6,technology_deployment,2822
++k_type_dropped,0.6,digital_transformation,1938
++k_type_dropped,0.6,cost_reduction,4922
++k_type_dropped,0.6,capex_program,8140
++k_type_dropped,0.6,infrastructure,2937
++k_type_dropped,0.6,automation,259
++k_type_dropped,0.6,energy_transition,248
++k_type_dropped,0.6,partnership,7348
++k_type_dropped,0.6,plant_construction,5680
++k_type_dropped,0.6,rd_program,3660
++k_type_dropped,0.6,cloud_migration,189
++k_type_dropped,0.7,product_launch,4063
++k_type_dropped,0.7,geographic_expansion,5640
++k_type_dropped,0.7,sustainability,947
++k_type_dropped,0.7,supply_chain,441
++k_type_dropped,0.7,ma_integration,37370
++k_type_dropped,0.7,manufacturing_expansion,2758
++k_type_dropped,0.7,drug_pipeline,4604
++k_type_dropped,0.7,data_center,315
++k_type_dropped,0.7,ai_initiative,284
++k_type_dropped,0.7,erp_implementation,1535
++k_type_dropped,0.7,technology_deployment,2750
++k_type_dropped,0.7,capex_program,8094
++k_type_dropped,0.7,cost_reduction,4857
++k_type_dropped,0.7,digital_transformation,1890
++k_type_dropped,0.7,infrastructure,2879
++k_type_dropped,0.7,energy_transition,246
++k_type_dropped,0.7,automation,246
++k_type_dropped,0.7,plant_construction,5655
++k_type_dropped,0.7,partnership,7220
++k_type_dropped,0.7,rd_program,3597
++k_type_dropped,0.7,cloud_migration,189
++k_type_dropped,0.8,manufacturing_expansion,2548
++k_type_dropped,0.8,ma_integration,36888
++k_type_dropped,0.8,drug_pipeline,4321
++k_type_dropped,0.8,ai_initiative,255
++k_type_dropped,0.8,data_center,304
++k_type_dropped,0.8,geographic_expansion,4956
++k_type_dropped,0.8,product_launch,3707
++k_type_dropped,0.8,supply_chain,347
++k_type_dropped,0.8,sustainability,823
++k_type_dropped,0.8,rd_program,2954
++k_type_dropped,0.8,plant_construction,5416
++k_type_dropped,0.8,cloud_migration,175
++k_type_dropped,0.8,partnership,6390
++k_type_dropped,0.8,cost_reduction,4483
++k_type_dropped,0.8,capex_program,7855
++k_type_dropped,0.8,erp_implementation,1465
++k_type_dropped,0.8,infrastructure,2595
++k_type_dropped,0.8,automation,177
++k_type_dropped,0.8,digital_transformation,1579
++k_type_dropped,0.8,technology_deployment,2348
++k_type_dropped,0.8,energy_transition,232
++k_type_dropped,0.9,product_launch,2562
++k_type_dropped,0.9,geographic_expansion,2893
++k_type_dropped,0.9,sustainability,439
++k_type_dropped,0.9,supply_chain,158
++k_type_dropped,0.9,ma_integration,34295
++k_type_dropped,0.9,drug_pipeline,3214
++k_type_dropped,0.9,manufacturing_expansion,1549
++k_type_dropped,0.9,data_center,226
++k_type_dropped,0.9,ai_initiative,148
++k_type_dropped,0.9,rd_program,1284
++k_type_dropped,0.9,plant_construction,4221
++k_type_dropped,0.9,partnership,4169
++k_type_dropped,0.9,cloud_migration,99
++k_type_dropped,0.9,technology_deployment,1379
++k_type_dropped,0.9,digital_transformation,679
++k_type_dropped,0.9,erp_implementation,1031
++k_type_dropped,0.9,cost_reduction,3148
++k_type_dropped,0.9,capex_program,6770
++k_type_dropped,0.9,infrastructure,1663
++k_type_dropped,0.9,energy_transition,189
++k_type_dropped,0.9,automation,58
++k_current,0.45,geographic_expansion,7868
++k_current,0.45,product_launch,5356
++k_current,0.45,sustainability,1305
++k_current,0.45,supply_chain,684
++k_current,0.45,technology_deployment,4128
++k_current,0.45,erp_implementation,1735
++k_current,0.45,digital_transformation,2642
++k_current,0.45,capex_program,10720
++k_current,0.45,cost_reduction,6481
++k_current,0.45,infrastructure,4481
++k_current,0.45,energy_transition,415
++k_current,0.45,automation,374
++k_current,0.45,ma_integration,41742
++k_current,0.45,manufacturing_expansion,4140
++k_current,0.45,data_center,449
++k_current,0.45,ai_initiative,376
++k_current,0.45,drug_pipeline,5360
++k_current,0.45,plant_construction,7590
++k_current,0.45,partnership,9909
++k_current,0.45,rd_program,5080
++k_current,0.45,cloud_migration,264
++k_current,0.6,ma_integration,41675
++k_current,0.6,manufacturing_expansion,4119
++k_current,0.6,drug_pipeline,5340
++k_current,0.6,ai_initiative,375
++k_current,0.6,data_center,445
++k_current,0.6,plant_construction,7561
++k_current,0.6,cloud_migration,264
++k_current,0.6,partnership,9825
++k_current,0.6,rd_program,5035
++k_current,0.6,erp_implementation,1735
++k_current,0.6,capex_program,10707
++k_current,0.6,digital_transformation,2638
++k_current,0.6,cost_reduction,6473
++k_current,0.6,technology_deployment,4103
++k_current,0.6,infrastructure,4424
++k_current,0.6,automation,372
++k_current,0.6,energy_transition,407
++k_current,0.6,supply_chain,681
++k_current,0.6,product_launch,5345
++k_current,0.6,sustainability,1295
++k_current,0.6,geographic_expansion,7802
++k_current,0.7,product_launch,5286
++k_current,0.7,geographic_expansion,7670
++k_current,0.7,supply_chain,671
++k_current,0.7,sustainability,1251
++k_current,0.7,ma_integration,41564
++k_current,0.7,manufacturing_expansion,4079
++k_current,0.7,drug_pipeline,5289
++k_current,0.7,ai_initiative,372
++k_current,0.7,data_center,444
++k_current,0.7,plant_construction,7511
++k_current,0.7,rd_program,4933
++k_current,0.7,partnership,9662
++k_current,0.7,cloud_migration,264
++k_current,0.7,erp_implementation,1728
++k_current,0.7,infrastructure,4334
++k_current,0.7,technology_deployment,4001
++k_current,0.7,capex_program,10648
++k_current,0.7,digital_transformation,2567
++k_current,0.7,cost_reduction,6394
++k_current,0.7,automation,355
++k_current,0.7,energy_transition,404
++k_current,0.8,product_launch,4760
++k_current,0.8,geographic_expansion,6719
++k_current,0.8,sustainability,1082
++k_current,0.8,supply_chain,524
++k_current,0.8,erp_implementation,1645
++k_current,0.8,infrastructure,3834
++k_current,0.8,technology_deployment,3382
++k_current,0.8,capex_program,10275
++k_current,0.8,digital_transformation,2120
++k_current,0.8,cost_reduction,5896
++k_current,0.8,automation,254
++k_current,0.8,energy_transition,374
++k_current,0.8,ma_integration,40876
++k_current,0.8,manufacturing_expansion,3734
++k_current,0.8,drug_pipeline,4938
++k_current,0.8,ai_initiative,337
++k_current,0.8,data_center,416
++k_current,0.8,rd_program,4034
++k_current,0.8,partnership,8544
++k_current,0.8,plant_construction,7092
++k_current,0.8,cloud_migration,243
++k_current,0.9,product_launch,3163
++k_current,0.9,geographic_expansion,3803
++k_current,0.9,sustainability,558
++k_current,0.9,supply_chain,220
++k_current,0.9,ma_integration,37290
++k_current,0.9,manufacturing_expansion,2241
++k_current,0.9,drug_pipeline,3595
++k_current,0.9,ai_initiative,193
++k_current,0.9,data_center,299
++k_current,0.9,capex_program,8724
++k_current,0.9,technology_deployment,1875
++k_current,0.9,cost_reduction,4158
++k_current,0.9,digital_transformation,874
++k_current,0.9,erp_implementation,1124
++k_current,0.9,infrastructure,2375
++k_current,0.9,energy_transition,274
++k_current,0.9,automation,76
++k_current,0.9,rd_program,1708
++k_current,0.9,plant_construction,5330
++k_current,0.9,partnership,5473
++k_current,0.9,cloud_migration,130
++k_current_stopwords,0.45,geographic_expansion,8001
++k_current_stopwords,0.45,product_launch,5315
++k_current_stopwords,0.45,sustainability,1301
++k_current_stopwords,0.45,supply_chain,680
++k_current_stopwords,0.45,ma_integration,50614
++k_current_stopwords,0.45,manufacturing_expansion,4118
++k_current_stopwords,0.45,data_center,446
++k_current_stopwords,0.45,ai_initiative,373
++k_current_stopwords,0.45,drug_pipeline,5438
++k_current_stopwords,0.45,plant_construction,7609
++k_current_stopwords,0.45,partnership,9896
++k_current_stopwords,0.45,rd_program,5122
++k_current_stopwords,0.45,cloud_migration,261
++k_current_stopwords,0.45,technology_deployment,4122
++k_current_stopwords,0.45,erp_implementation,1733
++k_current_stopwords,0.45,digital_transformation,2617
++k_current_stopwords,0.45,capex_program,10712
++k_current_stopwords,0.45,cost_reduction,6484
++k_current_stopwords,0.45,infrastructure,4473
++k_current_stopwords,0.45,energy_transition,415
++k_current_stopwords,0.45,automation,371
++k_current_stopwords,0.6,ma_integration,50526
++k_current_stopwords,0.6,manufacturing_expansion,4097
++k_current_stopwords,0.6,drug_pipeline,5419
++k_current_stopwords,0.6,ai_initiative,372
++k_current_stopwords,0.6,data_center,442
++k_current_stopwords,0.6,product_launch,5304
++k_current_stopwords,0.6,geographic_expansion,7934
++k_current_stopwords,0.6,supply_chain,677
++k_current_stopwords,0.6,sustainability,1291
++k_current_stopwords,0.6,erp_implementation,1733
++k_current_stopwords,0.6,infrastructure,4417
++k_current_stopwords,0.6,technology_deployment,4097
++k_current_stopwords,0.6,capex_program,10699
++k_current_stopwords,0.6,digital_transformation,2613
++k_current_stopwords,0.6,cost_reduction,6475
++k_current_stopwords,0.6,automation,369
++k_current_stopwords,0.6,energy_transition,407
++k_current_stopwords,0.6,plant_construction,7581
++k_current_stopwords,0.6,rd_program,5077
++k_current_stopwords,0.6,partnership,9810
++k_current_stopwords,0.6,cloud_migration,261
++k_current_stopwords,0.7,product_launch,5246
++k_current_stopwords,0.7,geographic_expansion,7799
++k_current_stopwords,0.7,supply_chain,667
++k_current_stopwords,0.7,sustainability,1247
++k_current_stopwords,0.7,erp_implementation,1726
++k_current_stopwords,0.7,infrastructure,4329
++k_current_stopwords,0.7,technology_deployment,3994
++k_current_stopwords,0.7,capex_program,10639
++k_current_stopwords,0.7,digital_transformation,2544
++k_current_stopwords,0.7,cost_reduction,6397
++k_current_stopwords,0.7,automation,353
++k_current_stopwords,0.7,energy_transition,404
++k_current_stopwords,0.7,ma_integration,50396
++k_current_stopwords,0.7,manufacturing_expansion,4058
++k_current_stopwords,0.7,drug_pipeline,5376
++k_current_stopwords,0.7,ai_initiative,369
++k_current_stopwords,0.7,data_center,441
++k_current_stopwords,0.7,plant_construction,7534
++k_current_stopwords,0.7,rd_program,4976
++k_current_stopwords,0.7,partnership,9648
++k_current_stopwords,0.7,cloud_migration,261
++k_current_stopwords,0.8,product_launch,4733
++k_current_stopwords,0.8,geographic_expansion,6822
++k_current_stopwords,0.8,sustainability,1079
++k_current_stopwords,0.8,supply_chain,520
++k_current_stopwords,0.8,erp_implementation,1644
++k_current_stopwords,0.8,infrastructure,3831
++k_current_stopwords,0.8,technology_deployment,3377
++k_current_stopwords,0.8,capex_program,10268
++k_current_stopwords,0.8,digital_transformation,2104
++k_current_stopwords,0.8,cost_reduction,5897
++k_current_stopwords,0.8,automation,254
++k_current_stopwords,0.8,energy_transition,374
++k_current_stopwords,0.8,ma_integration,49641
++k_current_stopwords,0.8,manufacturing_expansion,3712
++k_current_stopwords,0.8,drug_pipeline,5017
++k_current_stopwords,0.8,ai_initiative,334
++k_current_stopwords,0.8,data_center,415
++k_current_stopwords,0.8,rd_program,4077
++k_current_stopwords,0.8,partnership,8535
++k_current_stopwords,0.8,plant_construction,7115
++k_current_stopwords,0.8,cloud_migration,241
++k_current_stopwords,0.9,product_launch,3153
++k_current_stopwords,0.9,sustainability,557
++k_current_stopwords,0.9,geographic_expansion,3843
++k_current_stopwords,0.9,supply_chain,219
++k_current_stopwords,0.9,ma_integration,45679
++k_current_stopwords,0.9,manufacturing_expansion,2233
++k_current_stopwords,0.9,drug_pipeline,3619
++k_current_stopwords,0.9,data_center,300
++k_current_stopwords,0.9,ai_initiative,190
++k_current_stopwords,0.9,cost_reduction,4161
++k_current_stopwords,0.9,erp_implementation,1124
++k_current_stopwords,0.9,infrastructure,2375
++k_current_stopwords,0.9,technology_deployment,1873
++k_current_stopwords,0.9,capex_program,8715
++k_current_stopwords,0.9,energy_transition,274
++k_current_stopwords,0.9,automation,76
++k_current_stopwords,0.9,digital_transformation,871
++k_current_stopwords,0.9,plant_construction,5344
++k_current_stopwords,0.9,rd_program,1709
++k_current_stopwords,0.9,partnership,5473
++k_current_stopwords,0.9,cloud_migration,130
++k_city_normalised,0.45,plant_construction,6635
++k_city_normalised,0.45,rd_program,5021
++k_city_normalised,0.45,partnership,9701
++k_city_normalised,0.45,cloud_migration,261
++k_city_normalised,0.45,ma_integration,47448
++k_city_normalised,0.45,manufacturing_expansion,3730
++k_city_normalised,0.45,drug_pipeline,5329
++k_city_normalised,0.45,ai_initiative,370
++k_city_normalised,0.45,data_center,394
++k_city_normalised,0.45,infrastructure,4187
++k_city_normalised,0.45,capex_program,9862
++k_city_normalised,0.45,digital_transformation,2608
++k_city_normalised,0.45,cost_reduction,6307
++k_city_normalised,0.45,erp_implementation,1728
++k_city_normalised,0.45,technology_deployment,4065
++k_city_normalised,0.45,automation,367
++k_city_normalised,0.45,energy_transition,394
++k_city_normalised,0.45,product_launch,5269
++k_city_normalised,0.45,geographic_expansion,7629
++k_city_normalised,0.45,supply_chain,669
++k_city_normalised,0.45,sustainability,1272
++k_city_normalised,0.6,ma_integration,47361
++k_city_normalised,0.6,manufacturing_expansion,3710
++k_city_normalised,0.6,drug_pipeline,5310
++k_city_normalised,0.6,data_center,390
++k_city_normalised,0.6,ai_initiative,369
++k_city_normalised,0.6,product_launch,5258
++k_city_normalised,0.6,geographic_expansion,7566
++k_city_normalised,0.6,sustainability,1262
++k_city_normalised,0.6,supply_chain,666
++k_city_normalised,0.6,plant_construction,6610
++k_city_normalised,0.6,partnership,9616
++k_city_normalised,0.6,rd_program,4976
++k_city_normalised,0.6,cloud_migration,261
++k_city_normalised,0.6,cost_reduction,6298
++k_city_normalised,0.6,capex_program,9850
++k_city_normalised,0.6,erp_implementation,1728
++k_city_normalised,0.6,automation,365
++k_city_normalised,0.6,digital_transformation,2604
++k_city_normalised,0.6,infrastructure,4134
++k_city_normalised,0.6,energy_transition,386
++k_city_normalised,0.6,technology_deployment,4040
++k_city_normalised,0.7,product_launch,5200
++k_city_normalised,0.7,geographic_expansion,7437
++k_city_normalised,0.7,sustainability,1219
++k_city_normalised,0.7,supply_chain,656
++k_city_normalised,0.7,ma_integration,47233
++k_city_normalised,0.7,manufacturing_expansion,3677
++k_city_normalised,0.7,drug_pipeline,5269
++k_city_normalised,0.7,data_center,389
++k_city_normalised,0.7,ai_initiative,366
++k_city_normalised,0.7,plant_construction,6566
++k_city_normalised,0.7,partnership,9455
++k_city_normalised,0.7,rd_program,4876
++k_city_normalised,0.7,cloud_migration,261
++k_city_normalised,0.7,cost_reduction,6220
++k_city_normalised,0.7,capex_program,9790
++k_city_normalised,0.7,erp_implementation,1721
++k_city_normalised,0.7,automation,349
++k_city_normalised,0.7,digital_transformation,2535
++k_city_normalised,0.7,infrastructure,4048
++k_city_normalised,0.7,energy_transition,383
++k_city_normalised,0.7,technology_deployment,3938
++k_city_normalised,0.8,product_launch,4692
++k_city_normalised,0.8,geographic_expansion,6500
++k_city_normalised,0.8,sustainability,1057
++k_city_normalised,0.8,supply_chain,511
++k_city_normalised,0.8,cost_reduction,5733
++k_city_normalised,0.8,capex_program,9422
++k_city_normalised,0.8,erp_implementation,1639
++k_city_normalised,0.8,digital_transformation,2097
++k_city_normalised,0.8,infrastructure,3574
++k_city_normalised,0.8,energy_transition,354
++k_city_normalised,0.8,technology_deployment,3325
++k_city_normalised,0.8,automation,251
++k_city_normalised,0.8,ma_integration,46499
++k_city_normalised,0.8,manufacturing_expansion,3352
++k_city_normalised,0.8,drug_pipeline,4910
++k_city_normalised,0.8,data_center,366
++k_city_normalised,0.8,ai_initiative,331
++k_city_normalised,0.8,plant_construction,6204
++k_city_normalised,0.8,partnership,8356
++k_city_normalised,0.8,rd_program,3990
++k_city_normalised,0.8,cloud_migration,241
++k_city_normalised,0.9,plant_construction,4671
++k_city_normalised,0.9,rd_program,1660
++k_city_normalised,0.9,partnership,5342
++k_city_normalised,0.9,cloud_migration,130
++k_city_normalised,0.9,product_launch,3123
++k_city_normalised,0.9,geographic_expansion,3645
++k_city_normalised,0.9,sustainability,546
++k_city_normalised,0.9,supply_chain,213
++k_city_normalised,0.9,cost_reduction,4051
++k_city_normalised,0.9,erp_implementation,1120
++k_city_normalised,0.9,infrastructure,2214
++k_city_normalised,0.9,technology_deployment,1837
++k_city_normalised,0.9,capex_program,7903
++k_city_normalised,0.9,energy_transition,261
++k_city_normalised,0.9,automation,75
++k_city_normalised,0.9,digital_transformation,867
++k_city_normalised,0.9,ma_integration,42702
++k_city_normalised,0.9,manufacturing_expansion,2014
++k_city_normalised,0.9,drug_pipeline,3523
++k_city_normalised,0.9,data_center,262
++k_city_normalised,0.9,ai_initiative,188
++k_name_only,0.45,product_launch,4890
++k_name_only,0.45,geographic_expansion,6903
++k_name_only,0.45,sustainability,1296
++k_name_only,0.45,supply_chain,654
++k_name_only,0.45,ma_integration,41205
++k_name_only,0.45,manufacturing_expansion,3607
++k_name_only,0.45,data_center,357
++k_name_only,0.45,ai_initiative,365
++k_name_only,0.45,drug_pipeline,4599
++k_name_only,0.45,technology_deployment,4041
++k_name_only,0.45,digital_transformation,2502
++k_name_only,0.45,capex_program,10258
++k_name_only,0.45,cost_reduction,5896
++k_name_only,0.45,erp_implementation,1614
++k_name_only,0.45,infrastructure,4253
++k_name_only,0.45,automation,356
++k_name_only,0.45,energy_transition,425
++k_name_only,0.45,plant_construction,6511
++k_name_only,0.45,partnership,9428
++k_name_only,0.45,cloud_migration,251
++k_name_only,0.45,rd_program,4833
++k_name_only,0.6,ma_integration,41128
++k_name_only,0.6,manufacturing_expansion,3593
++k_name_only,0.6,data_center,353
++k_name_only,0.6,ai_initiative,364
++k_name_only,0.6,drug_pipeline,4580
++k_name_only,0.6,product_launch,4878
++k_name_only,0.6,geographic_expansion,6844
++k_name_only,0.6,sustainability,1286
++k_name_only,0.6,supply_chain,650
++k_name_only,0.6,technology_deployment,4015
++k_name_only,0.6,digital_transformation,2498
++k_name_only,0.6,capex_program,10245
++k_name_only,0.6,cost_reduction,5888
++k_name_only,0.6,erp_implementation,1614
++k_name_only,0.6,infrastructure,4199
++k_name_only,0.6,automation,354
++k_name_only,0.6,energy_transition,417
++k_name_only,0.6,plant_construction,6485
++k_name_only,0.6,partnership,9344
++k_name_only,0.6,cloud_migration,251
++k_name_only,0.6,rd_program,4793
++k_name_only,0.7,product_launch,4822
++k_name_only,0.7,geographic_expansion,6720
++k_name_only,0.7,supply_chain,641
++k_name_only,0.7,sustainability,1241
++k_name_only,0.7,partnership,9185
++k_name_only,0.7,plant_construction,6445
++k_name_only,0.7,rd_program,4700
++k_name_only,0.7,cloud_migration,251
++k_name_only,0.7,digital_transformation,2431
++k_name_only,0.7,cost_reduction,5815
++k_name_only,0.7,capex_program,10191
++k_name_only,0.7,infrastructure,4120
++k_name_only,0.7,erp_implementation,1608
++k_name_only,0.7,technology_deployment,3910
++k_name_only,0.7,automation,338
++k_name_only,0.7,energy_transition,415
++k_name_only,0.7,ma_integration,41011
++k_name_only,0.7,manufacturing_expansion,3561
++k_name_only,0.7,drug_pipeline,4535
++k_name_only,0.7,ai_initiative,361
++k_name_only,0.7,data_center,351
++k_name_only,0.8,product_launch,4317
++k_name_only,0.8,geographic_expansion,5837
++k_name_only,0.8,sustainability,1072
++k_name_only,0.8,supply_chain,502
++k_name_only,0.8,digital_transformation,2007
++k_name_only,0.8,capex_program,9833
++k_name_only,0.8,technology_deployment,3308
++k_name_only,0.8,cost_reduction,5356
++k_name_only,0.8,erp_implementation,1532
++k_name_only,0.8,infrastructure,3648
++k_name_only,0.8,automation,243
++k_name_only,0.8,energy_transition,386
++k_name_only,0.8,plant_construction,6077
++k_name_only,0.8,partnership,8110
++k_name_only,0.8,cloud_migration,232
++k_name_only,0.8,rd_program,3824
++k_name_only,0.8,ma_integration,40304
++k_name_only,0.8,manufacturing_expansion,3248
++k_name_only,0.8,data_center,328
++k_name_only,0.8,ai_initiative,327
++k_name_only,0.8,drug_pipeline,4189
++k_name_only,0.9,partnership,5215
++k_name_only,0.9,plant_construction,4533
++k_name_only,0.9,rd_program,1586
++k_name_only,0.9,cloud_migration,126
++k_name_only,0.9,product_launch,2836
++k_name_only,0.9,geographic_expansion,3211
++k_name_only,0.9,sustainability,567
++k_name_only,0.9,supply_chain,214
++k_name_only,0.9,cost_reduction,3763
++k_name_only,0.9,capex_program,8367
++k_name_only,0.9,technology_deployment,1815
++k_name_only,0.9,erp_implementation,1043
++k_name_only,0.9,infrastructure,2267
++k_name_only,0.9,automation,74
++k_name_only,0.9,digital_transformation,822
++k_name_only,0.9,energy_transition,278
++k_name_only,0.9,ma_integration,36838
++k_name_only,0.9,manufacturing_expansion,1940
++k_name_only,0.9,drug_pipeline,2923
++k_name_only,0.9,data_center,230
++k_name_only,0.9,ai_initiative,186
++k_two_tokens,0.45,product_launch,6735
++k_two_tokens,0.45,geographic_expansion,8710
++k_two_tokens,0.45,sustainability,1358
++k_two_tokens,0.45,supply_chain,705
++k_two_tokens,0.45,plant_construction,8060
++k_two_tokens,0.45,partnership,10556
++k_two_tokens,0.45,rd_program,6124
++k_two_tokens,0.45,cloud_migration,292
++k_two_tokens,0.45,erp_implementation,1867
++k_two_tokens,0.45,infrastructure,4663
++k_two_tokens,0.45,technology_deployment,4390
++k_two_tokens,0.45,cost_reduction,6926
++k_two_tokens,0.45,capex_program,11342
++k_two_tokens,0.45,digital_transformation,3011
++k_two_tokens,0.45,automation,394
++k_two_tokens,0.45,energy_transition,454
++k_two_tokens,0.45,ma_integration,56961
++k_two_tokens,0.45,manufacturing_expansion,4419
++k_two_tokens,0.45,drug_pipeline,7851
++k_two_tokens,0.45,data_center,465
++k_two_tokens,0.45,ai_initiative,414
++k_two_tokens,0.6,erp_implementation,1866
++k_two_tokens,0.6,technology_deployment,4365
++k_two_tokens,0.6,automation,392
++k_two_tokens,0.6,cost_reduction,6913
++k_two_tokens,0.6,capex_program,11327
++k_two_tokens,0.6,digital_transformation,3006
++k_two_tokens,0.6,infrastructure,4605
++k_two_tokens,0.6,energy_transition,445
++k_two_tokens,0.6,geographic_expansion,8636
++k_two_tokens,0.6,product_launch,6722
++k_two_tokens,0.6,sustainability,1348
++k_two_tokens,0.6,supply_chain,702
++k_two_tokens,0.6,ma_integration,56860
++k_two_tokens,0.6,drug_pipeline,7820
++k_two_tokens,0.6,manufacturing_expansion,4398
++k_two_tokens,0.6,data_center,461
++k_two_tokens,0.6,ai_initiative,413
++k_two_tokens,0.6,plant_construction,8026
++k_two_tokens,0.6,partnership,10459
++k_two_tokens,0.6,rd_program,6066
++k_two_tokens,0.6,cloud_migration,292
++k_two_tokens,0.7,plant_construction,7967
++k_two_tokens,0.7,rd_program,5923
++k_two_tokens,0.7,cloud_migration,292
++k_two_tokens,0.7,partnership,10270
++k_two_tokens,0.7,product_launch,6647
++k_two_tokens,0.7,geographic_expansion,8483
++k_two_tokens,0.7,supply_chain,692
++k_two_tokens,0.7,sustainability,1304
++k_two_tokens,0.7,ma_integration,56698
++k_two_tokens,0.7,manufacturing_expansion,4353
++k_two_tokens,0.7,drug_pipeline,7741
++k_two_tokens,0.7,data_center,460
++k_two_tokens,0.7,ai_initiative,410
++k_two_tokens,0.7,technology_deployment,4253
++k_two_tokens,0.7,capex_program,11256
++k_two_tokens,0.7,infrastructure,4509
++k_two_tokens,0.7,cost_reduction,6821
++k_two_tokens,0.7,digital_transformation,2917
++k_two_tokens,0.7,erp_implementation,1854
++k_two_tokens,0.7,energy_transition,442
++k_two_tokens,0.7,automation,375
++k_two_tokens,0.8,geographic_expansion,7359
++k_two_tokens,0.8,product_launch,6006
++k_two_tokens,0.8,sustainability,1123
++k_two_tokens,0.8,supply_chain,533
++k_two_tokens,0.8,ma_integration,55748
++k_two_tokens,0.8,manufacturing_expansion,3956
++k_two_tokens,0.8,drug_pipeline,7134
++k_two_tokens,0.8,data_center,431
++k_two_tokens,0.8,ai_initiative,367
++k_two_tokens,0.8,plant_construction,7483
++k_two_tokens,0.8,partnership,9041
++k_two_tokens,0.8,rd_program,4764
++k_two_tokens,0.8,cloud_migration,269
++k_two_tokens,0.8,erp_implementation,1755
++k_two_tokens,0.8,technology_deployment,3565
++k_two_tokens,0.8,automation,268
++k_two_tokens,0.8,cost_reduction,6263
++k_two_tokens,0.8,capex_program,10835
++k_two_tokens,0.8,digital_transformation,2391
++k_two_tokens,0.8,infrastructure,3969
++k_two_tokens,0.8,energy_transition,411
++k_two_tokens,0.9,sustainability,565
++k_two_tokens,0.9,product_launch,3951
++k_two_tokens,0.9,geographic_expansion,4047
++k_two_tokens,0.9,supply_chain,220
++k_two_tokens,0.9,ma_integration,50615
++k_two_tokens,0.9,manufacturing_expansion,2320
++k_two_tokens,0.9,drug_pipeline,4766
++k_two_tokens,0.9,data_center,311
++k_two_tokens,0.9,ai_initiative,204
++k_two_tokens,0.9,erp_implementation,1176
++k_two_tokens,0.9,technology_deployment,1935
++k_two_tokens,0.9,cost_reduction,4340
++k_two_tokens,0.9,capex_program,9074
++k_two_tokens,0.9,digital_transformation,950
++k_two_tokens,0.9,infrastructure,2422
++k_two_tokens,0.9,energy_transition,298
++k_two_tokens,0.9,automation,82
++k_two_tokens,0.9,plant_construction,5520
++k_two_tokens,0.9,partnership,5701
++k_two_tokens,0.9,rd_program,1853
++k_two_tokens,0.9,cloud_migration,140
++k_strict,0.45,product_launch,8649
++k_strict,0.45,geographic_expansion,11713
++k_strict,0.45,supply_chain,822
++k_strict,0.45,sustainability,1716
++k_strict,0.45,erp_implementation,2129
++k_strict,0.45,technology_deployment,5135
++k_strict,0.45,cost_reduction,8400
++k_strict,0.45,digital_transformation,3411
++k_strict,0.45,automation,436
++k_strict,0.45,capex_program,14407
++k_strict,0.45,infrastructure,6258
++k_strict,0.45,energy_transition,656
++k_strict,0.45,ma_integration,79531
++k_strict,0.45,manufacturing_expansion,6360
++k_strict,0.45,drug_pipeline,13930
++k_strict,0.45,ai_initiative,459
++k_strict,0.45,data_center,670
++k_strict,0.45,plant_construction,12527
++k_strict,0.45,partnership,13266
++k_strict,0.45,rd_program,7674
++k_strict,0.45,cloud_migration,339
++k_strict,0.6,product_launch,8634
++k_strict,0.6,sustainability,1702
++k_strict,0.6,geographic_expansion,11604
++k_strict,0.6,supply_chain,818
++k_strict,0.6,infrastructure,6178
++k_strict,0.6,cost_reduction,8384
++k_strict,0.6,erp_implementation,2127
++k_strict,0.6,digital_transformation,3405
++k_strict,0.6,capex_program,14385
++k_strict,0.6,technology_deployment,5099
++k_strict,0.6,energy_transition,647
++k_strict,0.6,automation,433
++k_strict,0.6,partnership,13140
++k_strict,0.6,plant_construction,12461
++k_strict,0.6,rd_program,7585
++k_strict,0.6,cloud_migration,339
++k_strict,0.6,ma_integration,79405
++k_strict,0.6,manufacturing_expansion,6335
++k_strict,0.6,drug_pipeline,13868
++k_strict,0.6,data_center,666
++k_strict,0.6,ai_initiative,458
++k_strict,0.7,infrastructure,6048
++k_strict,0.7,digital_transformation,3306
++k_strict,0.7,technology_deployment,4964
++k_strict,0.7,cost_reduction,8278
++k_strict,0.7,automation,413
++k_strict,0.7,erp_implementation,2114
++k_strict,0.7,capex_program,14301
++k_strict,0.7,energy_transition,643
++k_strict,0.7,product_launch,8538
++k_strict,0.7,geographic_expansion,11387
++k_strict,0.7,sustainability,1648
++k_strict,0.7,supply_chain,807
++k_strict,0.7,ma_integration,79211
++k_strict,0.7,drug_pipeline,13700
++k_strict,0.7,manufacturing_expansion,6275
++k_strict,0.7,data_center,663
++k_strict,0.7,ai_initiative,455
++k_strict,0.7,plant_construction,12341
++k_strict,0.7,rd_program,7382
++k_strict,0.7,partnership,12890
++k_strict,0.7,cloud_migration,339
++k_strict,0.8,ma_integration,77954
++k_strict,0.8,manufacturing_expansion,5681
++k_strict,0.8,drug_pipeline,12499
++k_strict,0.8,data_center,616
++k_strict,0.8,ai_initiative,407
++k_strict,0.8,product_launch,7733
++k_strict,0.8,geographic_expansion,9828
++k_strict,0.8,supply_chain,622
++k_strict,0.8,sustainability,1419
++k_strict,0.8,technology_deployment,4142
++k_strict,0.8,capex_program,13785
++k_strict,0.8,cost_reduction,7584
++k_strict,0.8,digital_transformation,2698
++k_strict,0.8,erp_implementation,1990
++k_strict,0.8,infrastructure,5314
++k_strict,0.8,energy_transition,597
++k_strict,0.8,automation,292
++k_strict,0.8,partnership,11275
++k_strict,0.8,plant_construction,11475
++k_strict,0.8,rd_program,5830
++k_strict,0.8,cloud_migration,311
++k_strict,0.9,product_launch,5066
++k_strict,0.9,sustainability,699
++k_strict,0.9,geographic_expansion,5180
++k_strict,0.9,supply_chain,256
++k_strict,0.9,digital_transformation,1041
++k_strict,0.9,technology_deployment,2210
++k_strict,0.9,cost_reduction,5158
++k_strict,0.9,erp_implementation,1278
++k_strict,0.9,capex_program,11518
++k_strict,0.9,energy_transition,417
++k_strict,0.9,infrastructure,3084
++k_strict,0.9,automation,88
++k_strict,0.9,ma_integration,70579
++k_strict,0.9,drug_pipeline,7712
++k_strict,0.9,manufacturing_expansion,3181
++k_strict,0.9,data_center,430
++k_strict,0.9,ai_initiative,229
++k_strict,0.9,rd_program,2173
++k_strict,0.9,plant_construction,8089
++k_strict,0.9,partnership,6870
++k_strict,0.9,cloud_migration,153
++k_mention_level,0.45,cost_reduction,13157
++k_mention_level,0.45,capex_program,19211
++k_mention_level,0.45,erp_implementation,4242
++k_mention_level,0.45,automation,630
++k_mention_level,0.45,technology_deployment,6725
++k_mention_level,0.45,digital_transformation,5249
++k_mention_level,0.45,infrastructure,8510
++k_mention_level,0.45,energy_transition,866
++k_mention_level,0.45,geographic_expansion,17713
++k_mention_level,0.45,product_launch,12456
++k_mention_level,0.45,sustainability,2607
++k_mention_level,0.45,supply_chain,1171
++k_mention_level,0.45,ma_integration,130259
++k_mention_level,0.45,manufacturing_expansion,8825
++k_mention_level,0.45,drug_pipeline,26755
++k_mention_level,0.45,ai_initiative,632
++k_mention_level,0.45,data_center,889
++k_mention_level,0.45,plant_construction,18388
++k_mention_level,0.45,partnership,17501
++k_mention_level,0.45,rd_program,11758
++k_mention_level,0.45,cloud_migration,521
++k_mention_level,0.6,product_launch,12426
++k_mention_level,0.6,geographic_expansion,17424
++k_mention_level,0.6,sustainability,2582
++k_mention_level,0.6,supply_chain,1165
++k_mention_level,0.6,plant_construction,18271
++k_mention_level,0.6,rd_program,11587
++k_mention_level,0.6,partnership,17318
++k_mention_level,0.6,cloud_migration,521
++k_mention_level,0.6,ma_integration,130004
++k_mention_level,0.6,drug_pipeline,26523
++k_mention_level,0.6,manufacturing_expansion,8786
++k_mention_level,0.6,data_center,884
++k_mention_level,0.6,ai_initiative,631
++k_mention_level,0.6,erp_implementation,4240
++k_mention_level,0.6,cost_reduction,13124
++k_mention_level,0.6,capex_program,19182
++k_mention_level,0.6,automation,627
++k_mention_level,0.6,technology_deployment,6677
++k_mention_level,0.6,digital_transformation,5231
++k_mention_level,0.6,infrastructure,8396
++k_mention_level,0.6,energy_transition,855
++k_mention_level,0.7,geographic_expansion,17050
++k_mention_level,0.7,product_launch,12265
++k_mention_level,0.7,sustainability,2503
++k_mention_level,0.7,supply_chain,1142
++k_mention_level,0.7,erp_implementation,4214
++k_mention_level,0.7,cost_reduction,12973
++k_mention_level,0.7,automation,605
++k_mention_level,0.7,technology_deployment,6502
++k_mention_level,0.7,digital_transformation,5092
++k_mention_level,0.7,infrastructure,8205
++k_mention_level,0.7,capex_program,19064
++k_mention_level,0.7,energy_transition,850
++k_mention_level,0.7,plant_construction,18092
++k_mention_level,0.7,partnership,16928
++k_mention_level,0.7,rd_program,11214
++k_mention_level,0.7,cloud_migration,521
++k_mention_level,0.7,ma_integration,129674
++k_mention_level,0.7,manufacturing_expansion,8671
++k_mention_level,0.7,drug_pipeline,26107
++k_mention_level,0.7,ai_initiative,627
++k_mention_level,0.7,data_center,876
++k_mention_level,0.8,plant_construction,16758
++k_mention_level,0.8,cloud_migration,478
++k_mention_level,0.8,rd_program,8651
++k_mention_level,0.8,partnership,14523
++k_mention_level,0.8,geographic_expansion,14501
++k_mention_level,0.8,product_launch,11102
++k_mention_level,0.8,sustainability,2124
++k_mention_level,0.8,supply_chain,880
++k_mention_level,0.8,technology_deployment,5330
++k_mention_level,0.8,capex_program,18260
++k_mention_level,0.8,erp_implementation,3979
++k_mention_level,0.8,cost_reduction,11876
++k_mention_level,0.8,digital_transformation,4182
++k_mention_level,0.8,infrastructure,7146
++k_mention_level,0.8,automation,415
++k_mention_level,0.8,energy_transition,785
++k_mention_level,0.8,ma_integration,127709
++k_mention_level,0.8,drug_pipeline,23441
++k_mention_level,0.8,manufacturing_expansion,7737
++k_mention_level,0.8,data_center,801
++k_mention_level,0.8,ai_initiative,563
++k_mention_level,0.9,ma_integration,115621
++k_mention_level,0.9,manufacturing_expansion,4220
++k_mention_level,0.9,drug_pipeline,13708
++k_mention_level,0.9,ai_initiative,319
++k_mention_level,0.9,data_center,534
++k_mention_level,0.9,product_launch,7283
++k_mention_level,0.9,geographic_expansion,7146
++k_mention_level,0.9,sustainability,1005
++k_mention_level,0.9,supply_chain,351
++k_mention_level,0.9,erp_implementation,2204
++k_mention_level,0.9,capex_program,14939
++k_mention_level,0.9,digital_transformation,1494
++k_mention_level,0.9,technology_deployment,2723
++k_mention_level,0.9,cost_reduction,7814
++k_mention_level,0.9,infrastructure,3987
++k_mention_level,0.9,energy_transition,517
++k_mention_level,0.9,automation,110
++k_mention_level,0.9,plant_construction,11519
++k_mention_level,0.9,partnership,8390
++k_mention_level,0.9,rd_program,3050
++k_mention_level,0.9,cloud_migration,216

added results/resolver/ties_idempotence.json +30 −0

Large diff (31 lines) is not loaded by default to keep the page fast.Load diff

added results/resolver/top_location_keys.csv +51 −0

Large diff (51 lines) is not loaded by default to keep the page fast.Load diff

added results/resolver/top_name_tokens.csv +51 −0

Large diff (52 lines) is not loaded by default to keep the page fast.Load diff

spb/firc0001_uqo

N3: resolver composition, over-merge indicators, specification curve, ties, June->October reconciliation

Theme