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>
15 changed files +1,753 −0
added
code/audit/a03_resolver_speccurve.py
+257 −0
@@ -0,0 +1,257 @@ | ||
| 1 | +"""N3 - resolver composition, over-merge indicators, specification curve, ties, June->October | |
| 2 | +reconciliation (cluster B). Read-only; _m/_keyed rebuilt as TEMP tables from resolve.py:17-32. | |
| 3 | +""" | |
| 4 | +from __future__ import annotations | |
| 5 | +import json, sys | |
| 6 | +from pathlib import Path | |
| 7 | +sys.path.insert(0, str(Path(__file__).resolve().parent)) | |
| 8 | +from common import * | |
| 9 | +sys.path.insert(0, str(Path(__file__).resolve().parent / "spid")) | |
| 10 | +import taxonomy as tx # snapshot copy (hash-verified in N0) | |
| 11 | + | |
| 12 | +EXAMPLE_PROJECT = "3e2705ba5b2dd27408b25f0145e34250" # stats.json example_project (Cheniere Corpus Christi Stage 3) | |
| 13 | +STOP = ["project", "program", "development", "expansion", "acquisition", "phase", "initiative", "facility", "construction"] | |
| 14 | +THRESHOLDS = [0.45, 0.6, 0.7, 0.8, 0.9] | |
| 15 | + | |
| 16 | +r = Run("resolver") | |
| 17 | +con = connect(SPID_DB) | |
| 18 | +tmin = con.execute("select min(extracted_at) from extracted_sections").fetchone()[0] | |
| 19 | +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""") | |
| 20 | + | |
| 21 | +# ---- exact rebuild of _m / _keyed (resolve.py:17-32) -------------------------------------------- | |
| 22 | +con.execute(""" | |
| 23 | +CREATE TEMP TABLE _m AS | |
| 24 | +SELECT *, | |
| 25 | + lower(coalesce(try(locations[1]), '')) AS loc1, | |
| 26 | + regexp_extract(lower(regexp_replace(project_name, '[^A-Za-z ]', '', 'g')), '([a-z]{4,})', 1) AS name_tok | |
| 27 | +FROM project_mentions""") | |
| 28 | +con.execute(""" | |
| 29 | +CREATE TEMP TABLE _keyed AS | |
| 30 | +SELECT *, | |
| 31 | + cik || '|' || project_type || '|' || CASE WHEN loc1 <> '' THEN loc1 ELSE coalesce(nullif(name_tok,''),'general') END AS gkey, | |
| 32 | + md5(cik || '|' || project_type || '|' || CASE WHEN loc1 <> '' THEN loc1 ELSE coalesce(nullif(name_tok,''),'general') END) AS project_id | |
| 33 | +FROM _m""") | |
| 34 | +V = {} | |
| 35 | +V["rebuilt_projects"] = con.execute("select count(distinct project_id) from _keyed").fetchone()[0] | |
| 36 | +V["stored_projects"] = con.execute("select count(*) from projects").fetchone()[0] | |
| 37 | +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() | |
| 38 | +V["mentions"] = con.execute("select count(*) from _keyed").fetchone()[0] | |
| 39 | + | |
| 40 | +# ---- (a) key composition ---------------------------------------------------------------------- | |
| 41 | +V["mentions_by_key_branch"] = con.execute(""" | |
| 42 | + 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() | |
| 43 | +V["projects_by_key_branch"] = con.execute(""" | |
| 44 | + 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() | |
| 45 | +V["projects_keyed_general"] = con.execute("select count(distinct project_id) from _keyed where gkey like '%|general'").fetchone()[0] | |
| 46 | +V["mentions_keyed_general"] = con.execute("select count(*) from _keyed where gkey like '%|general'").fetchone()[0] | |
| 47 | +states = sorted(tx.US_STATES); countries = sorted(tx.COUNTRIES) | |
| 48 | +con.execute("CREATE TEMP TABLE geo AS SELECT unnest(?) AS loc, 'us_state' AS kind UNION ALL SELECT unnest(?), 'country'", [states, countries]) | |
| 49 | +V["location_keyed_projects_by_geo_kind"] = con.execute(""" | |
| 50 | + with p as (select project_id, any_value(loc1) loc1 from _keyed where loc1<>'' group by 1) | |
| 51 | + select coalesce(g.kind,'other_place') kind, count(*) from p left join geo g on p.loc1 = g.loc group by 1""").fetchall() | |
| 52 | +V["location_keyed_mentions_by_geo_kind"] = con.execute(""" | |
| 53 | + 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() | |
| 54 | +r.dump("top_name_tokens.csv", con, """ | |
| 55 | + 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) | |
| 56 | + select name_tok, mentions, projects, round(100.0*mentions/(select count(*) from _keyed where loc1=''),2) pct_of_tokenkeyed_mentions, | |
| 57 | + round(100.0*projects/(select count(distinct project_id) from _keyed where loc1=''),2) pct_of_tokenkeyed_projects | |
| 58 | + from t order by projects desc limit 50""") | |
| 59 | +r.dump("top_location_keys.csv", con, """ | |
| 60 | + select loc1, count(*) mentions, count(distinct project_id) projects from _keyed where loc1<>'' group by 1 order by 2 desc limit 50""") | |
| 61 | +r.dump("key_branch_by_type.csv", con, """ | |
| 62 | + select project_type, count(distinct project_id) projects, | |
| 63 | + count(distinct project_id) filter (where loc1<>'') loc_keyed, | |
| 64 | + count(distinct project_id) filter (where loc1='' and nullif(name_tok,'') is not null) token_keyed, | |
| 65 | + count(distinct project_id) filter (where loc1='' and nullif(name_tok,'') is null) general_keyed | |
| 66 | + from _keyed group by 1 order by 2 desc""") | |
| 67 | + | |
| 68 | +# ---- (b) over-merge indicators ---------------------------------------------------------------- | |
| 69 | +con.execute(""" | |
| 70 | +CREATE TEMP TABLE pstat AS | |
| 71 | +SELECT project_id, any_value(project_type) project_type, count(*) n_mentions, | |
| 72 | + count(DISTINCT lower(trim(project_name))) n_names, | |
| 73 | + count(DISTINCT lower(trim(coalesce(try(partners[1]), '')))) FILTER (WHERE len(partners)>0) n_partners, | |
| 74 | + count(DISTINCT accession_number) n_filings, count(DISTINCT cik) n_ciks, | |
| 75 | + count(DISTINCT lower(description)) n_desc | |
| 76 | +FROM _keyed GROUP BY 1""") | |
| 77 | +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" | |
| 78 | +r.dump("overmerge_by_type.csv", con, f""" | |
| 79 | + select project_type, count(*) projects, sum(n_mentions) mentions, | |
| 80 | + round(100.0*count(*) filter (where n_names>=3)/count(*),2) pct_ge3_names, | |
| 81 | + round(100.0*count(*) filter (where n_names>=2)/count(*),2) pct_ge2_names, | |
| 82 | + round(100.0*count(*) filter (where n_partners>=3)/nullif(count(*) filter (where n_partners>=1),0),2) pct_ge3_partners_among_with_partner, | |
| 83 | + count(*) filter (where n_partners>=3) n_ge3_partners, | |
| 84 | + 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 | |
| 85 | + from pstat group by 1 order by 2 desc""") | |
| 86 | +r.dump("overmerge_by_bucket.csv", con, f""" | |
| 87 | + select {bucket} bucket, count(*) projects, | |
| 88 | + round(100.0*count(*) filter (where n_names>=3)/count(*),2) pct_ge3_names, | |
| 89 | + round(100.0*count(*) filter (where n_partners>=3)/nullif(count(*) filter (where n_partners>=1),0),2) pct_ge3_partners_among_with_partner, | |
| 90 | + round(avg(n_names),2) mean_names | |
| 91 | + from pstat group by 1 order by min(n_mentions)""") | |
| 92 | +r.dump("overmerge_ma_by_bucket.csv", con, f""" | |
| 93 | + select {bucket} bucket, count(*) projects, | |
| 94 | + count(*) filter (where n_partners>=1) with_partner, | |
| 95 | + round(100.0*count(*) filter (where n_partners>=3)/nullif(count(*) filter (where n_partners>=1),0),2) pct_ge3_partners, | |
| 96 | + round(100.0*count(*) filter (where n_partners>=2)/nullif(count(*) filter (where n_partners>=1),0),2) pct_ge2_partners, | |
| 97 | + round(100.0*count(*) filter (where n_names>=3)/count(*),2) pct_ge3_names | |
| 98 | + from pstat where project_type='ma_integration' group by 1 order by min(n_mentions)""") | |
| 99 | +# amount from a mention naming a different counterparty than the representative mention | |
| 100 | +V["amount_from_other_counterparty"] = con.execute(""" | |
| 101 | + with rep as (select project_id, arg_max(lower(trim(coalesce(try(partners[1]),''))), confidence) rep_partner from _keyed group by 1), | |
| 102 | + 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) | |
| 103 | + select count(*) filter (where rep_partner<>'' and amt_partner<>'' and rep_partner<>amt_partner) differing, | |
| 104 | + count(*) filter (where rep_partner<>'' and amt_partner<>'') both_named, count(*) with_amount | |
| 105 | + from amt join rep using(project_id)""").fetchone() | |
| 106 | +V["amount_from_other_counterparty_ma"] = con.execute(""" | |
| 107 | + 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), | |
| 108 | + 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) | |
| 109 | + select count(*) filter (where rep_partner<>'' and amt_partner<>'' and rep_partner<>amt_partner) differing, | |
| 110 | + count(*) filter (where rep_partner<>'' and amt_partner<>'') both_named, count(*) with_amount | |
| 111 | + from amt join rep using(project_id) where t='ma_integration'""").fetchone() | |
| 112 | +V["amount_from_other_name"] = con.execute(""" | |
| 113 | + with rep as (select project_id, arg_max(lower(trim(project_name)), confidence) rep_name from _keyed group by 1), | |
| 114 | + 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) | |
| 115 | + select count(*) filter (where rep_name<>amt_name) differing, count(*) with_amount from amt join rep using(project_id)""").fetchone() | |
| 116 | +r.dump("example_provenance_keys.csv", con, """ | |
| 117 | + select project_id, cik, project_type, gkey, count(*) n, count(distinct lower(project_name)) n_names, list(distinct left(project_name,60)) names | |
| 118 | + from _keyed where project_id in (select project_id from projects where project_id in ( | |
| 119 | + 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')) | |
| 120 | + group by 1,2,3,4 order by n desc limit 30""") | |
| 121 | + | |
| 122 | +# ---- (c) specification curve ---------------------------------------------------------------------- | |
| 123 | +stop_sql = ",".join("'" + s + "'" for s in STOP) | |
| 124 | +con.execute(f""" | |
| 125 | +CREATE TEMP TABLE km AS | |
| 126 | +SELECT mention_id, cik, project_type, confidence, loc1, name_tok, gkey, | |
| 127 | + regexp_replace(trim(regexp_replace(lower(project_name), '[^a-z0-9 ]', '', 'g')), ' +', ' ', 'g') AS name_norm, | |
| 128 | + list_filter(string_split(regexp_replace(lower(project_name), '[^a-z ]', '', 'g'), ' '), lambda x: length(x) >= 4) AS toks, | |
| 129 | + 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, | |
| 130 | + 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 | |
| 131 | +FROM _keyed""") | |
| 132 | +con.execute(""" | |
| 133 | +CREATE TEMP TABLE keys AS | |
| 134 | +SELECT mention_id, confidence, project_type, | |
| 135 | + cik || '|' || project_type AS k_cik_type, | |
| 136 | + gkey AS k_current, | |
| 137 | + cik || '|' || project_type || '|' || CASE WHEN loc1 <> '' THEN loc1 ELSE coalesce(toks_sw[1], 'general') END AS k_current_stopwords, | |
| 138 | + 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, | |
| 139 | + cik || '|' || CASE WHEN loc1 <> '' THEN loc1 ELSE coalesce(nullif(name_tok,''), 'general') END AS k_type_dropped, | |
| 140 | + cik || '|' || project_type || '|' || CASE WHEN loc1 <> '' THEN loc1 ELSE coalesce(toks_sw[1], 'general') || '|' || coalesce(toks_sw[2], '') END AS k_two_tokens, | |
| 141 | + cik || '|' || project_type || '|' || coalesce(toks_sw[1], 'general') AS k_name_only, | |
| 142 | + cik || '|' || project_type || '|' || name_norm || '|' || loc1 AS k_strict, | |
| 143 | + mention_id AS k_mention_level | |
| 144 | +FROM km""") | |
| 145 | +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"] | |
| 146 | +ex_mention = con.execute("select arg_max(mention_id, confidence) from _keyed where project_id = ?", [EXAMPLE_PROJECT]).fetchone()[0] | |
| 147 | +rows = []; bytype = [] | |
| 148 | +for k in KEYS: | |
| 149 | + for t in THRESHOLDS: | |
| 150 | + q = f""" | |
| 151 | + with g as (select {k} key, count(*) n, max(mention_id = '{ex_mention}')::int has_ex from keys where confidence >= {t} group by 1) | |
| 152 | + select count(*) projects, sum(n) mentions, round(100.0*count(*) filter (where n=1)/count(*),2) single_pct, | |
| 153 | + round(100.0*count(*) filter (where n>10)/count(*),2) gt10_pct, round(avg(n),3) mean_mentions, | |
| 154 | + max(n) max_cluster, coalesce(max(n) filter (where has_ex=1),0) example_cluster_size | |
| 155 | + from g""" | |
| 156 | + row = con.execute(q).fetchone() | |
| 157 | + rows.append((k, t) + tuple(row)) | |
| 158 | + bt = con.execute(f""" | |
| 159 | + with g as (select {k} key, any_value(project_type) project_type, count(*) n from keys where confidence >= {t} group by 1) | |
| 160 | + select project_type, count(*) n from g group by 1""").fetchall() | |
| 161 | + bytype += [(k, t, pt, n) for pt, n in bt] | |
| 162 | + print(k, t, row, flush=True) | |
| 163 | +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) | |
| 164 | +r.write_csv("spec_curve_by_type.csv", ["key", "threshold", "project_type", "projects"], bytype) | |
| 165 | +cur = [x for x in rows if x[0] == "k_current" and x[1] == 0.45][0] | |
| 166 | +V["project_count_current"] = cur[2] | |
| 167 | +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} | |
| 168 | +V["project_count_strict_045"] = V["project_count_range_045"]["k_strict"] | |
| 169 | +V["project_count_loose_045_cik_type"] = V["project_count_range_045"]["k_cik_type"] | |
| 170 | +V["example_mention"] = ex_mention | |
| 171 | + | |
| 172 | +# ---- (d) ties and idempotence ---------------------------------------------------------------------- | |
| 173 | +D = {} | |
| 174 | +D["projects_with_tie_at_max_confidence"] = con.execute(""" | |
| 175 | + with mx as (select project_id, max(confidence) mc from _keyed group by 1) | |
| 176 | + 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] | |
| 177 | +D["projects_with_tie_and_distinct_names"] = con.execute(""" | |
| 178 | + with mx as (select project_id, max(confidence) mc from _keyed group by 1) | |
| 179 | + 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] | |
| 180 | +D["projects_with_tie_and_distinct_descriptions"] = con.execute(""" | |
| 181 | + with mx as (select project_id, max(confidence) mc from _keyed group by 1) | |
| 182 | + 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] | |
| 183 | +D["projects_with_status_tie_on_last_seen"] = con.execute(""" | |
| 184 | + with mx as (select project_id, max(filing_date) md from _keyed group by 1) | |
| 185 | + 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] | |
| 186 | +D["mentions_at_confidence_1"] = con.execute("select count(*) from project_mentions where confidence = 1.0").fetchone()[0] | |
| 187 | +# stored projects vs rebuilt with the original (tie-ambiguous) SQL: how many representative fields differ | |
| 188 | +con.execute(""" | |
| 189 | +CREATE TEMP TABLE rebuilt AS | |
| 190 | +SELECT project_id, arg_max(project_name, confidence) project_name, arg_max(status, filing_date) status, arg_max(description, confidence) description, | |
| 191 | + max(amount_usd) total_amount_usd, count(*) n_mentions | |
| 192 | +FROM _keyed GROUP BY 1""") | |
| 193 | +D["rebuilt_vs_stored_diff"] = con.execute(""" | |
| 194 | + select count(*) filter (where r.project_name is distinct from p.project_name) name_diff, | |
| 195 | + count(*) filter (where r.status is distinct from p.status) status_diff, | |
| 196 | + count(*) filter (where r.description is distinct from p.description) desc_diff, | |
| 197 | + count(*) filter (where r.total_amount_usd is distinct from p.total_amount_usd) amount_diff, | |
| 198 | + count(*) filter (where r.n_mentions is distinct from p.n_mentions) n_diff, count(*) n | |
| 199 | + from rebuilt r join projects p using(project_id)""").fetchone() | |
| 200 | +con.execute(""" | |
| 201 | +CREATE TEMP TABLE rebuilt2 AS | |
| 202 | +SELECT project_id, arg_max(project_name, confidence) project_name, arg_max(status, filing_date) status, arg_max(description, confidence) description | |
| 203 | +FROM _keyed GROUP BY 1""") | |
| 204 | +D["original_sql_run_twice_diff"] = con.execute(""" | |
| 205 | + 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) | |
| 206 | + from rebuilt a join rebuilt2 b using(project_id)""").fetchone() | |
| 207 | +det = """ | |
| 208 | +SELECT project_id, project_name, status, description FROM ( | |
| 209 | + SELECT project_id, | |
| 210 | + first_value(project_name) OVER (PARTITION BY project_id ORDER BY confidence DESC, mention_id) project_name, | |
| 211 | + first_value(description) OVER (PARTITION BY project_id ORDER BY confidence DESC, mention_id) description, | |
| 212 | + first_value(status) OVER (PARTITION BY project_id ORDER BY filing_date DESC, mention_id) status, | |
| 213 | + row_number() OVER (PARTITION BY project_id ORDER BY mention_id) rn | |
| 214 | + FROM _keyed) WHERE rn = 1""" | |
| 215 | +con.execute(f"CREATE TEMP TABLE det1 AS {det}") | |
| 216 | +con.execute(f"CREATE TEMP TABLE det2 AS {det}") | |
| 217 | +D["deterministic_tiebreak_run_twice_diff"] = con.execute(""" | |
| 218 | + 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) | |
| 219 | + from det1 a join det2 b using(project_id)""").fetchone() | |
| 220 | +D["deterministic_vs_stored_diff"] = con.execute(""" | |
| 221 | + 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) | |
| 222 | + from det1 a join projects p using(project_id)""").fetchone() | |
| 223 | +r.write_json("ties_idempotence.json", D) | |
| 224 | + | |
| 225 | +# ---- (e) June -> October reconciliation (S&P 500 CIKs) ------------------------------------------- | |
| 226 | +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""") | |
| 227 | +R = {} | |
| 228 | +R["sp500_ciks"] = con.execute("select count(*) from src_companies where in_sp500").fetchone()[0] | |
| 229 | +R["mentions_in_backfilled_block"] = con.execute("select count(*) from kr where run='backfilled_june'").fetchone()[0] | |
| 230 | +R["projects_from_backfilled_block_only"] = con.execute("select count(distinct project_id) from kr where run='backfilled_june'").fetchone()[0] | |
| 231 | +R["expected_june"] = {"mentions": 39930, "projects": 19227, "timeline_rows": 39930} | |
| 232 | +R["sp500_mentions_total"] = con.execute("select count(*) from kr where in_sp500").fetchone()[0] | |
| 233 | +R["sp500_projects_total"] = con.execute("select count(distinct project_id) from kr where in_sp500").fetchone()[0] | |
| 234 | +R["paper_sp500_projects_october"] = 27766 | |
| 235 | +R["sp500_projects_by_run_composition"] = con.execute(""" | |
| 236 | + 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) | |
| 237 | + 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() | |
| 238 | +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() | |
| 239 | +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() | |
| 240 | +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] | |
| 241 | +R["backfilled_block_mentions_not_sp500"] = con.execute("select count(*) from kr where run='backfilled_june' and not coalesce(in_sp500,false)").fetchone()[0] | |
| 242 | +R["june_10q_accessions_in_block_ledger"] = con.execute(f""" | |
| 243 | + 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] | |
| 244 | +R["ledger_block_accessions_by_form"] = con.execute(f""" | |
| 245 | + 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() | |
| 246 | +R["sp500_october_ledger_by_form"] = con.execute(f""" | |
| 247 | + 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 | |
| 248 | + where e.extracted_at <> TIMESTAMP '{tmin}' and co.in_sp500 group by 1 order by 1""").fetchall() | |
| 249 | +R["sp500_block_ledger_by_form"] = con.execute(f""" | |
| 250 | + 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 | |
| 251 | + where e.extracted_at = TIMESTAMP '{tmin}' and co.in_sp500 group by 1 order by 1""").fetchall() | |
| 252 | +r.write_json("june_october_reconciliation.json", R) | |
| 253 | +r.dump("june_october_reconciliation.csv", con, """ | |
| 254 | + 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 | |
| 255 | + from kr group by 1,2,3 order by 1,2,3""") | |
| 256 | +r.write_json("composition.json", V) | |
| 257 | +r.finish() | |
added
results/resolver/composition.json
+100 −0
@@ -0,0 +1,100 @@ | ||
| 1 | +{ | |
| 2 | + "rebuilt_projects": 121099, | |
| 3 | + "stored_projects": 121099, | |
| 4 | + "project_id_set_equal": [ | |
| 5 | + [ | |
| 6 | + 0 | |
| 7 | + ], | |
| 8 | + [ | |
| 9 | + 0 | |
| 10 | + ] | |
| 11 | + ], | |
| 12 | + "mentions": 308065, | |
| 13 | + "mentions_by_key_branch": [ | |
| 14 | + [ | |
| 15 | + "name_token", | |
| 16 | + 187212 | |
| 17 | + ], | |
| 18 | + [ | |
| 19 | + "location", | |
| 20 | + 118783 | |
| 21 | + ], | |
| 22 | + [ | |
| 23 | + "general", | |
| 24 | + 2070 | |
| 25 | + ] | |
| 26 | + ], | |
| 27 | + "projects_by_key_branch": [ | |
| 28 | + [ | |
| 29 | + "name_token", | |
| 30 | + 66405 | |
| 31 | + ], | |
| 32 | + [ | |
| 33 | + "location", | |
| 34 | + 54658 | |
| 35 | + ], | |
| 36 | + [ | |
| 37 | + "general", | |
| 38 | + 229 | |
| 39 | + ] | |
| 40 | + ], | |
| 41 | + "projects_keyed_general": 286, | |
| 42 | + "mentions_keyed_general": 2152, | |
| 43 | + "location_keyed_projects_by_geo_kind": [ | |
| 44 | + [ | |
| 45 | + "other_place", | |
| 46 | + 40422 | |
| 47 | + ], | |
| 48 | + [ | |
| 49 | + "us_state", | |
| 50 | + 6110 | |
| 51 | + ], | |
| 52 | + [ | |
| 53 | + "country", | |
| 54 | + 8126 | |
| 55 | + ] | |
| 56 | + ], | |
| 57 | + "location_keyed_mentions_by_geo_kind": [ | |
| 58 | + [ | |
| 59 | + "other_place", | |
| 60 | + 78479 | |
| 61 | + ], | |
| 62 | + [ | |
| 63 | + "country", | |
| 64 | + 22986 | |
| 65 | + ], | |
| 66 | + [ | |
| 67 | + "us_state", | |
| 68 | + 17318 | |
| 69 | + ] | |
| 70 | + ], | |
| 71 | + "amount_from_other_counterparty": [ | |
| 72 | + 2347, | |
| 73 | + 21908, | |
| 74 | + 56500 | |
| 75 | + ], | |
| 76 | + "amount_from_other_counterparty_ma": [ | |
| 77 | + 1630, | |
| 78 | + 12372, | |
| 79 | + 28044 | |
| 80 | + ], | |
| 81 | + "amount_from_other_name": [ | |
| 82 | + 8882, | |
| 83 | + 56500 | |
| 84 | + ], | |
| 85 | + "project_count_current": 121099, | |
| 86 | + "project_count_range_045": { | |
| 87 | + "k_cik_type": 21027, | |
| 88 | + "k_type_dropped": 96749, | |
| 89 | + "k_current": 121099, | |
| 90 | + "k_current_stopwords": 130101, | |
| 91 | + "k_city_normalised": 123246, | |
| 92 | + "k_name_only": 114244, | |
| 93 | + "k_two_tokens": 145697, | |
| 94 | + "k_strict": 198488, | |
| 95 | + "k_mention_level": 308065 | |
| 96 | + }, | |
| 97 | + "project_count_strict_045": 198488, | |
| 98 | + "project_count_loose_045_cik_type": 21027, | |
| 99 | + "example_mention": "cebf8e727e1a7f5bc821" | |
| 100 | +} | |
| \ No newline at end of file | ||
added
results/resolver/example_provenance_keys.csv
+31 −0
@@ -0,0 +1,31 @@ | ||
| 1 | +project_id,cik,project_type,gkey,n,n_names,names | |
| 2 | +dbe60cbe1feab59090d7ce4c63c0b6a1,0001001838,plant_construction,0001001838|plant_construction|peru,8,4,"['Tía María Mining Project', 'Tia Maria Greenfield Project', 'Tia Maria Project', 'Toquepala Expansion Project']" | |
| 3 | +7942bcad2b16e5c326d64ef7cc4d79f6,0000092122,plant_construction,0000092122|plant_construction|waynesboro/georgia/usa,8,1,['Plant Vogtle Units 3 and 4'] | |
| 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']" | |
| 5 | +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']" | |
| 6 | +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']" | |
| 7 | +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']" | |
| 8 | +dc8940627597a296318115e21e7ea024,0001164727,plant_construction,0001164727|plant_construction|peru,8,2,"['Conga Project', 'Conga']" | |
| 9 | +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']" | |
| 10 | +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']" | |
| 11 | +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']" | |
| 12 | +30a198e7029a4956be8327cd83da4b70,0001513761,plant_construction,0001513761|plant_construction|explorer,7,3,"['Explorer Class Newbuild Loan Agreement', 'Explorer Class Ships', 'Explorer Class Ship']" | |
| 13 | +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']" | |
| 14 | +fbfb8fca9ac08121c1681b13a9db3e38,0001051470,plant_construction,0001051470|plant_construction|construction,7,2,"['Construction of New Communications Infrastructure', 'Construction of Small Cells']" | |
| 15 | +7b5cdbd8d0e9a2a0519d7093bd3c78a9,0000884887,plant_construction,0000884887|plant_construction|project,7,4,"['Project Edge', 'Project Sunshine Ship 1', 'Project Sunshine Ship 2', 'Project Sunshine']" | |
| 16 | +28b552d43d7800a5e536b8c66bfd36fd,0000022444,plant_construction,"0000022444|plant_construction|berkeley county, west virginia",7,3,"['Fourth Micro Mill', 'Fourth Micro Mill Construction', 'Berkeley County Micro Mill']" | |
| 17 | +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']" | |
| 18 | +f2126501fc9d07f93ce25627ba093984,0000034903,plant_construction,"0000034903|plant_construction|somerville, massachusetts",7,4,"['Assembly Row', 'Assembly Row Phase II', 'Assembly Square', 'Assembly Row Phase I']" | |
| 19 | +a9a63ffa287236133e060b110818add5,0000833079,plant_construction,0000833079|plant_construction|land,7,1,['Land Development and Home Construction'] | |
| 20 | +7ba90cf2bc3e1cbbe5e26a2d8d8d7835,0001167419,data_center,0001167419|data_center|rockdale,7,3,"['Rockdale Facility', '191 Critical IT MW Data Center Project', 'Rockdale Facility Expansion']" | |
| 21 | +83b669268f21ba09eae690226d209c01,0000915912,plant_construction,0000915912|plant_construction|future,7,2,"['Future Apartment Community Developments', 'Future Apartment Communities Development']" | |
| 22 | +7473bc6fc5d414ab5ee5b287418491f1,0001795250,plant_construction,0001795250|plant_construction|las vegas/nevada/usa,7,2,"['Sphere in Las Vegas', 'MSG Sphere']" | |
| 23 | +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']" | |
| 24 | +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']" | |
| 25 | +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']" | |
| 26 | +13fec26e29e1bb20856eb321aadc6344,0000104169,plant_construction,0000104169|plant_construction|store,6,2,"['Store Remodels', 'Store and Club Remodels']" | |
| 27 | +0a57f5fcba583f08d49dfcdb13b7e654,0000726728,plant_construction,0000726728|plant_construction|properties,6,2,"['Properties under development', 'Properties Under Development or Expansion']" | |
| 28 | +4ec04c01a2e25d3816161f7f36aa936c,0001575965,plant_construction,0001575965|plant_construction|chicago,6,3,"['Bally’s Chicago', 'Bally’s Chicago Casino Resort', ""Bally's Chicago Development""]" | |
| 29 | +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']" | |
| 30 | +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']" | |
| 31 | +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
@@ -0,0 +1,10 @@ | ||
| 1 | +in_sp500,run,form_type,mentions,projects_touched,filings,issuers | |
| 2 | +False,october,10-K,64798,34658,15784,1857 | |
| 3 | +False,october,10-Q,117224,45274,40745,1954 | |
| 4 | +False,october,8-K,55676,34420,45937,1964 | |
| 5 | +True,backfilled_june,10-K,15787,8697,4193,481 | |
| 6 | +True,backfilled_june,10-Q,5817,2071,2028,84 | |
| 7 | +True,backfilled_june,8-K,18326,10023,15234,495 | |
| 8 | +True,october,10-K,910,649,222,97 | |
| 9 | +True,october,10-Q,28963,11030,10684,455 | |
| 10 | +True,october,8-K,564,432,477,203 | |
added
results/resolver/june_october_reconciliation.json
+137 −0
@@ -0,0 +1,137 @@ | ||
| 1 | +{ | |
| 2 | + "sp500_ciks": 500, | |
| 3 | + "mentions_in_backfilled_block": 39930, | |
| 4 | + "projects_from_backfilled_block_only": 19227, | |
| 5 | + "expected_june": { | |
| 6 | + "mentions": 39930, | |
| 7 | + "projects": 19227, | |
| 8 | + "timeline_rows": 39930 | |
| 9 | + }, | |
| 10 | + "sp500_mentions_total": 70367, | |
| 11 | + "sp500_projects_total": 27766, | |
| 12 | + "paper_sp500_projects_october": 27766, | |
| 13 | + "sp500_projects_by_run_composition": [ | |
| 14 | + [ | |
| 15 | + "june only", | |
| 16 | + 15910 | |
| 17 | + ], | |
| 18 | + [ | |
| 19 | + "both runs", | |
| 20 | + 3317 | |
| 21 | + ], | |
| 22 | + [ | |
| 23 | + "october only", | |
| 24 | + 8539 | |
| 25 | + ] | |
| 26 | + ], | |
| 27 | + "sp500_mentions_by_run_form": [ | |
| 28 | + [ | |
| 29 | + "backfilled_june", | |
| 30 | + "10-K", | |
| 31 | + 15787, | |
| 32 | + 4193 | |
| 33 | + ], | |
| 34 | + [ | |
| 35 | + "backfilled_june", | |
| 36 | + "10-Q", | |
| 37 | + 5817, | |
| 38 | + 2028 | |
| 39 | + ], | |
| 40 | + [ | |
| 41 | + "backfilled_june", | |
| 42 | + "8-K", | |
| 43 | + 18326, | |
| 44 | + 15234 | |
| 45 | + ], | |
| 46 | + [ | |
| 47 | + "october", | |
| 48 | + "10-K", | |
| 49 | + 910, | |
| 50 | + 222 | |
| 51 | + ], | |
| 52 | + [ | |
| 53 | + "october", | |
| 54 | + "10-Q", | |
| 55 | + 28963, | |
| 56 | + 10684 | |
| 57 | + ], | |
| 58 | + [ | |
| 59 | + "october", | |
| 60 | + "8-K", | |
| 61 | + 564, | |
| 62 | + 477 | |
| 63 | + ] | |
| 64 | + ], | |
| 65 | + "sp500_mentions_filing_date_le_20260525_by_run": [ | |
| 66 | + [ | |
| 67 | + "october", | |
| 68 | + 28995, | |
| 69 | + 11217 | |
| 70 | + ], | |
| 71 | + [ | |
| 72 | + "backfilled_june", | |
| 73 | + 39926, | |
| 74 | + 19225 | |
| 75 | + ] | |
| 76 | + ], | |
| 77 | + "sp500_projects_filing_date_le_20260525": 27360, | |
| 78 | + "backfilled_block_mentions_not_sp500": 0, | |
| 79 | + "june_10q_accessions_in_block_ledger": 3710, | |
| 80 | + "ledger_block_accessions_by_form": [ | |
| 81 | + [ | |
| 82 | + "10-K", | |
| 83 | + 7368, | |
| 84 | + 27164 | |
| 85 | + ], | |
| 86 | + [ | |
| 87 | + "10-Q", | |
| 88 | + 3710, | |
| 89 | + 23873 | |
| 90 | + ], | |
| 91 | + [ | |
| 92 | + "8-K", | |
| 93 | + 103927, | |
| 94 | + 103927 | |
| 95 | + ] | |
| 96 | + ], | |
| 97 | + "sp500_october_ledger_by_form": [ | |
| 98 | + [ | |
| 99 | + "10-K", | |
| 100 | + 377, | |
| 101 | + 1803, | |
| 102 | + 912 | |
| 103 | + ], | |
| 104 | + [ | |
| 105 | + "10-Q", | |
| 106 | + 19399, | |
| 107 | + 116231, | |
| 108 | + 28996 | |
| 109 | + ], | |
| 110 | + [ | |
| 111 | + "8-K", | |
| 112 | + 2939, | |
| 113 | + 2939, | |
| 114 | + 564 | |
| 115 | + ] | |
| 116 | + ], | |
| 117 | + "sp500_block_ledger_by_form": [ | |
| 118 | + [ | |
| 119 | + "10-K", | |
| 120 | + 7368, | |
| 121 | + 27164, | |
| 122 | + 15787 | |
| 123 | + ], | |
| 124 | + [ | |
| 125 | + "10-Q", | |
| 126 | + 3710, | |
| 127 | + 23873, | |
| 128 | + 5817 | |
| 129 | + ], | |
| 130 | + [ | |
| 131 | + "8-K", | |
| 132 | + 103927, | |
| 133 | + 103927, | |
| 134 | + 18326 | |
| 135 | + ] | |
| 136 | + ] | |
| 137 | +} | |
| \ No newline at end of file | ||
added
results/resolver/key_branch_by_type.csv
+22 −0
@@ -0,0 +1,22 @@ | ||
| 1 | +project_type,projects,loc_keyed,token_keyed,general_keyed | |
| 2 | +ma_integration,41742,22873,18922,12 | |
| 3 | +capex_program,10720,3638,7077,7 | |
| 4 | +partnership,9909,3396,6511,6 | |
| 5 | +geographic_expansion,7868,4895,2989,0 | |
| 6 | +plant_construction,7590,5773,1845,7 | |
| 7 | +cost_reduction,6481,2213,4275,2 | |
| 8 | +drug_pipeline,5360,1296,3935,130 | |
| 9 | +product_launch,5356,1130,4215,13 | |
| 10 | +rd_program,5080,954,4096,34 | |
| 11 | +infrastructure,4481,2801,1694,2 | |
| 12 | +manufacturing_expansion,4140,2614,1552,1 | |
| 13 | +technology_deployment,4128,1116,3004,8 | |
| 14 | +digital_transformation,2642,311,2329,3 | |
| 15 | +erp_implementation,1735,259,1478,0 | |
| 16 | +sustainability,1305,476,830,1 | |
| 17 | +supply_chain,684,269,416,0 | |
| 18 | +data_center,449,276,174,0 | |
| 19 | +energy_transition,415,243,177,0 | |
| 20 | +ai_initiative,376,29,345,2 | |
| 21 | +automation,374,70,304,0 | |
| 22 | +cloud_migration,264,26,237,1 | |
added
results/resolver/manifest.json
+38 −0
@@ -0,0 +1,38 @@ | ||
| 1 | +{ | |
| 2 | + "package": "resolver", | |
| 3 | + "script": "/Users/simon-pierreboucher/firc0001_review/scripts/a03_resolver_speccurve.py", | |
| 4 | + "script_sha256": "19cf2ed3aae78394a718a31caa106a20a67cb9a6450c0d30b89f6a84c7fe8ad8", | |
| 5 | + "started": "2026-11-05T14:20:38", | |
| 6 | + "ended": "2026-11-05T14:20:40", | |
| 7 | + "wall_seconds": 2.2, | |
| 8 | + "node": "m3u96b", | |
| 9 | + "python": "3.12.15", | |
| 10 | + "duckdb": "2.0.0", | |
| 11 | + "threads": 4, | |
| 12 | + "memory_limit": "24GB", | |
| 13 | + "seed": 20261105, | |
| 14 | + "databases": { | |
| 15 | + "/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/data/db/spid.duckdb": { | |
| 16 | + "bytes": 3155701760, | |
| 17 | + "mtime": "2026-10-28T12:21:11.091389" | |
| 18 | + }, | |
| 19 | + "/Users/simon-pierreboucher/UQO_RESEARCH_DB/data/duckdb/edgar_research.duckdb": { | |
| 20 | + "bytes": 73500995584, | |
| 21 | + "mtime": "2026-10-27T21:34:46.297884" | |
| 22 | + } | |
| 23 | + }, | |
| 24 | + "read_only": true, | |
| 25 | + "row_counts": { | |
| 26 | + "top_name_tokens.csv": 50, | |
| 27 | + "top_location_keys.csv": 50, | |
| 28 | + "key_branch_by_type.csv": 21, | |
| 29 | + "overmerge_by_type.csv": 21, | |
| 30 | + "overmerge_by_bucket.csv": 5, | |
| 31 | + "overmerge_ma_by_bucket.csv": 5, | |
| 32 | + "example_provenance_keys.csv": 30, | |
| 33 | + "spec_curve.csv": 45, | |
| 34 | + "spec_curve_by_type.csv": 945, | |
| 35 | + "june_october_reconciliation.csv": 9 | |
| 36 | + }, | |
| 37 | + "notes": {} | |
| 38 | +} | |
| \ No newline at end of file | ||
added
results/resolver/overmerge_by_bucket.csv
+6 −0
@@ -0,0 +1,6 @@ | ||
| 1 | +bucket,projects,pct_ge3_names,pct_ge3_partners_among_with_partner,mean_names | |
| 2 | +1,72932,0.0,0.0,1.0 | |
| 3 | +2,20544,0.0,0.0,1.53 | |
| 4 | +3-5,17681,37.44,15.12,2.2 | |
| 5 | +6-10,6173,64.09,31.18,3.56 | |
| 6 | +>10,3769,86.57,52.95,9.05 | |
added
results/resolver/overmerge_by_type.csv
+22 −0
@@ -0,0 +1,22 @@ | ||
| 1 | +project_type,projects,mentions,pct_ge3_names,pct_ge2_names,pct_ge3_partners_among_with_partner,n_ge3_partners,pct_multi_all_names_distinct | |
| 2 | +ma_integration,41742,130259,14.63,30.93,10.92,2289,30.24 | |
| 3 | +capex_program,10720,19211,6.4,19.43,4.13,189,38.86 | |
| 4 | +partnership,9909,17501,6.74,19.66,4.3,281,38.57 | |
| 5 | +geographic_expansion,7868,17713,10.18,25.23,1.88,14,35.76 | |
| 6 | +plant_construction,7590,18388,13.49,30.3,4.04,62,34.68 | |
| 7 | +cost_reduction,6481,13157,5.71,17.47,1.59,4,26.39 | |
| 8 | +drug_pipeline,5360,26755,27.85,46.19,11.97,238,28.07 | |
| 9 | +product_launch,5356,12456,12.23,27.97,3.38,23,37.89 | |
| 10 | +rd_program,5080,11758,11.44,27.52,3.59,32,30.05 | |
| 11 | +infrastructure,4481,8510,7.5,20.78,2.17,21,38.05 | |
| 12 | +manufacturing_expansion,4140,8825,11.26,27.08,2.17,11,34.79 | |
| 13 | +technology_deployment,4128,6725,4.77,15.79,1.78,17,34.48 | |
| 14 | +digital_transformation,2642,5249,6.25,19.3,0.0,0,25.92 | |
| 15 | +erp_implementation,1735,4242,3.46,17.23,1.41,1,12.86 | |
| 16 | +sustainability,1305,2607,6.13,15.17,1.06,2,26.77 | |
| 17 | +supply_chain,684,1171,3.51,15.06,1.0,1,26.96 | |
| 18 | +data_center,449,889,9.35,26.06,3.64,6,46.54 | |
| 19 | +energy_transition,415,866,10.12,24.34,1.57,2,38.41 | |
| 20 | +ai_initiative,376,632,4.79,16.22,0.0,0,27.83 | |
| 21 | +automation,374,630,2.67,13.1,4.17,1,28.04 | |
| 22 | +cloud_migration,264,521,5.68,17.05,0.0,0,21.88 | |
added
results/resolver/overmerge_ma_by_bucket.csv
+6 −0
@@ -0,0 +1,6 @@ | ||
| 1 | +bucket,projects,with_partner,pct_ge3_partners,pct_ge2_partners,pct_ge3_names | |
| 2 | +1,22606,9999,0.0,0.0,0.0 | |
| 3 | +2,7558,3781,0.0,32.35,0.0 | |
| 4 | +3-5,7070,3855,17.3,49.0,37.52 | |
| 5 | +6-10,2668,1766,36.35,63.65,66.15 | |
| 6 | +>10,1840,1564,62.66,80.82,91.74 | |
added
results/resolver/spec_curve.csv
+46 −0
@@ -0,0 +1,46 @@ | ||
| 1 | +key,threshold,projects,mentions,single_mention_pct,gt10_mention_pct,mean_mentions,max_cluster,example_cluster_size_cheniere | |
| 2 | +k_cik_type,0.45,21027,308065,20.69,29.82,14.651,399,176 | |
| 3 | +k_cik_type,0.6,21001,306454,20.74,29.76,14.592,399,176 | |
| 4 | +k_cik_type,0.7,20878,303175,20.76,29.48,14.521,399,175 | |
| 5 | +k_cik_type,0.8,20053,281241,21.63,28.19,14.025,375,171 | |
| 6 | +k_cik_type,0.9,16562,207150,25.35,24.03,12.508,343,106 | |
| 7 | +k_type_dropped,0.45,96749,308065,52.59,4.99,3.184,269,11 | |
| 8 | +k_type_dropped,0.6,96438,306454,52.61,4.96,3.178,269,11 | |
| 9 | +k_type_dropped,0.7,95580,303175,52.64,4.95,3.172,269,11 | |
| 10 | +k_type_dropped,0.8,89818,281241,53.07,4.84,3.131,269,11 | |
| 11 | +k_type_dropped,0.9,70174,207150,54.53,4.26,2.952,250,10 | |
| 12 | +k_current,0.45,121099,308065,60.23,3.11,2.544,269,8 | |
| 13 | +k_current,0.6,120621,306454,60.24,3.1,2.541,269,8 | |
| 14 | +k_current,0.7,119427,303175,60.26,3.1,2.539,269,8 | |
| 15 | +k_current,0.8,111079,281241,60.47,3.05,2.532,269,8 | |
| 16 | +k_current,0.9,83483,207150,61.35,2.91,2.481,250,7 | |
| 17 | +k_current_stopwords,0.45,130101,308065,59.05,2.49,2.368,209,8 | |
| 18 | +k_current_stopwords,0.6,129601,306454,59.06,2.48,2.365,209,8 | |
| 19 | +k_current_stopwords,0.7,128404,303175,59.09,2.47,2.361,209,8 | |
| 20 | +k_current_stopwords,0.8,119990,281241,59.21,2.4,2.344,209,8 | |
| 21 | +k_current_stopwords,0.9,91918,207150,59.72,2.08,2.254,206,7 | |
| 22 | +k_city_normalised,0.45,123246,308065,56.83,2.84,2.5,212,8 | |
| 23 | +k_city_normalised,0.6,122760,306454,56.83,2.83,2.496,212,8 | |
| 24 | +k_city_normalised,0.7,121588,303175,56.84,2.82,2.493,212,8 | |
| 25 | +k_city_normalised,0.8,113404,281241,56.88,2.75,2.48,212,8 | |
| 26 | +k_city_normalised,0.9,86347,207150,57.02,2.42,2.399,209,7 | |
| 27 | +k_name_only,0.45,114244,308065,56.41,3.74,2.697,230,40 | |
| 28 | +k_name_only,0.6,113779,306454,56.41,3.73,2.693,230,40 | |
| 29 | +k_name_only,0.7,112652,303175,56.43,3.73,2.691,230,39 | |
| 30 | +k_name_only,0.8,104680,281241,56.44,3.72,2.687,230,39 | |
| 31 | +k_name_only,0.9,78834,207150,56.48,3.57,2.628,226,25 | |
| 32 | +k_two_tokens,0.45,145697,308065,62.96,1.74,2.114,209,8 | |
| 33 | +k_two_tokens,0.6,145122,306454,62.97,1.73,2.112,209,8 | |
| 34 | +k_two_tokens,0.7,143667,303175,62.95,1.72,2.11,209,8 | |
| 35 | +k_two_tokens,0.8,133671,281241,62.92,1.69,2.104,209,8 | |
| 36 | +k_two_tokens,0.9,100490,207150,62.93,1.51,2.061,206,7 | |
| 37 | +k_strict,0.45,198488,308065,75.78,0.52,1.552,206,1 | |
| 38 | +k_strict,0.6,197673,306454,75.8,0.51,1.55,206,1 | |
| 39 | +k_strict,0.7,195703,303175,75.82,0.5,1.549,206,1 | |
| 40 | +k_strict,0.8,182052,281241,75.92,0.49,1.545,206,1 | |
| 41 | +k_strict,0.9,135411,207150,76.17,0.4,1.53,203,1 | |
| 42 | +k_mention_level,0.45,308065,308065,100.0,0.0,1.0,1,1 | |
| 43 | +k_mention_level,0.6,306454,306454,100.0,0.0,1.0,1,1 | |
| 44 | +k_mention_level,0.7,303175,303175,100.0,0.0,1.0,1,1 | |
| 45 | +k_mention_level,0.8,281241,281241,100.0,0.0,1.0,1,1 | |
| 46 | +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
@@ -0,0 +1,946 @@ | ||
| 1 | +key,threshold,project_type,projects | |
| 2 | +k_cik_type,0.45,product_launch,1100 | |
| 3 | +k_cik_type,0.45,geographic_expansion,1673 | |
| 4 | +k_cik_type,0.45,supply_chain,389 | |
| 5 | +k_cik_type,0.45,sustainability,537 | |
| 6 | +k_cik_type,0.45,ma_integration,2448 | |
| 7 | +k_cik_type,0.45,manufacturing_expansion,882 | |
| 8 | +k_cik_type,0.45,data_center,142 | |
| 9 | +k_cik_type,0.45,ai_initiative,209 | |
| 10 | +k_cik_type,0.45,drug_pipeline,301 | |
| 11 | +k_cik_type,0.45,capex_program,2303 | |
| 12 | +k_cik_type,0.45,cost_reduction,1784 | |
| 13 | +k_cik_type,0.45,technology_deployment,1376 | |
| 14 | +k_cik_type,0.45,infrastructure,1231 | |
| 15 | +k_cik_type,0.45,digital_transformation,904 | |
| 16 | +k_cik_type,0.45,automation,234 | |
| 17 | +k_cik_type,0.45,erp_implementation,872 | |
| 18 | +k_cik_type,0.45,energy_transition,116 | |
| 19 | +k_cik_type,0.45,partnership,2046 | |
| 20 | +k_cik_type,0.45,plant_construction,1292 | |
| 21 | +k_cik_type,0.45,rd_program,1022 | |
| 22 | +k_cik_type,0.45,cloud_migration,166 | |
| 23 | +k_cik_type,0.6,cost_reduction,1783 | |
| 24 | +k_cik_type,0.6,erp_implementation,872 | |
| 25 | +k_cik_type,0.6,capex_program,2303 | |
| 26 | +k_cik_type,0.6,technology_deployment,1373 | |
| 27 | +k_cik_type,0.6,digital_transformation,903 | |
| 28 | +k_cik_type,0.6,infrastructure,1229 | |
| 29 | +k_cik_type,0.6,energy_transition,114 | |
| 30 | +k_cik_type,0.6,automation,232 | |
| 31 | +k_cik_type,0.6,geographic_expansion,1668 | |
| 32 | +k_cik_type,0.6,product_launch,1099 | |
| 33 | +k_cik_type,0.6,sustainability,535 | |
| 34 | +k_cik_type,0.6,supply_chain,386 | |
| 35 | +k_cik_type,0.6,ma_integration,2447 | |
| 36 | +k_cik_type,0.6,manufacturing_expansion,880 | |
| 37 | +k_cik_type,0.6,data_center,142 | |
| 38 | +k_cik_type,0.6,drug_pipeline,301 | |
| 39 | +k_cik_type,0.6,ai_initiative,209 | |
| 40 | +k_cik_type,0.6,rd_program,1022 | |
| 41 | +k_cik_type,0.6,partnership,2045 | |
| 42 | +k_cik_type,0.6,cloud_migration,166 | |
| 43 | +k_cik_type,0.6,plant_construction,1292 | |
| 44 | +k_cik_type,0.7,geographic_expansion,1647 | |
| 45 | +k_cik_type,0.7,product_launch,1090 | |
| 46 | +k_cik_type,0.7,sustainability,522 | |
| 47 | +k_cik_type,0.7,supply_chain,381 | |
| 48 | +k_cik_type,0.7,rd_program,1014 | |
| 49 | +k_cik_type,0.7,partnership,2040 | |
| 50 | +k_cik_type,0.7,cloud_migration,166 | |
| 51 | +k_cik_type,0.7,plant_construction,1290 | |
| 52 | +k_cik_type,0.7,ma_integration,2447 | |
| 53 | +k_cik_type,0.7,manufacturing_expansion,873 | |
| 54 | +k_cik_type,0.7,data_center,142 | |
| 55 | +k_cik_type,0.7,drug_pipeline,301 | |
| 56 | +k_cik_type,0.7,ai_initiative,208 | |
| 57 | +k_cik_type,0.7,cost_reduction,1780 | |
| 58 | +k_cik_type,0.7,erp_implementation,872 | |
| 59 | +k_cik_type,0.7,capex_program,2301 | |
| 60 | +k_cik_type,0.7,technology_deployment,1360 | |
| 61 | +k_cik_type,0.7,digital_transformation,886 | |
| 62 | +k_cik_type,0.7,infrastructure,1224 | |
| 63 | +k_cik_type,0.7,energy_transition,113 | |
| 64 | +k_cik_type,0.7,automation,221 | |
| 65 | +k_cik_type,0.8,ma_integration,2442 | |
| 66 | +k_cik_type,0.8,manufacturing_expansion,829 | |
| 67 | +k_cik_type,0.8,ai_initiative,192 | |
| 68 | +k_cik_type,0.8,data_center,130 | |
| 69 | +k_cik_type,0.8,drug_pipeline,299 | |
| 70 | +k_cik_type,0.8,product_launch,1032 | |
| 71 | +k_cik_type,0.8,geographic_expansion,1556 | |
| 72 | +k_cik_type,0.8,sustainability,478 | |
| 73 | +k_cik_type,0.8,supply_chain,305 | |
| 74 | +k_cik_type,0.8,plant_construction,1271 | |
| 75 | +k_cik_type,0.8,rd_program,957 | |
| 76 | +k_cik_type,0.8,partnership,1990 | |
| 77 | +k_cik_type,0.8,cloud_migration,155 | |
| 78 | +k_cik_type,0.8,technology_deployment,1273 | |
| 79 | +k_cik_type,0.8,cost_reduction,1744 | |
| 80 | +k_cik_type,0.8,capex_program,2289 | |
| 81 | +k_cik_type,0.8,automation,171 | |
| 82 | +k_cik_type,0.8,infrastructure,1155 | |
| 83 | +k_cik_type,0.8,erp_implementation,852 | |
| 84 | +k_cik_type,0.8,energy_transition,108 | |
| 85 | +k_cik_type,0.8,digital_transformation,825 | |
| 86 | +k_cik_type,0.9,geographic_expansion,1107 | |
| 87 | +k_cik_type,0.9,product_launch,818 | |
| 88 | +k_cik_type,0.9,supply_chain,149 | |
| 89 | +k_cik_type,0.9,sustainability,302 | |
| 90 | +k_cik_type,0.9,ma_integration,2440 | |
| 91 | +k_cik_type,0.9,manufacturing_expansion,648 | |
| 92 | +k_cik_type,0.9,drug_pipeline,292 | |
| 93 | +k_cik_type,0.9,data_center,93 | |
| 94 | +k_cik_type,0.9,ai_initiative,118 | |
| 95 | +k_cik_type,0.9,rd_program,652 | |
| 96 | +k_cik_type,0.9,partnership,1737 | |
| 97 | +k_cik_type,0.9,cloud_migration,96 | |
| 98 | +k_cik_type,0.9,plant_construction,1157 | |
| 99 | +k_cik_type,0.9,cost_reduction,1566 | |
| 100 | +k_cik_type,0.9,capex_program,2227 | |
| 101 | +k_cik_type,0.9,erp_implementation,701 | |
| 102 | +k_cik_type,0.9,technology_deployment,909 | |
| 103 | +k_cik_type,0.9,digital_transformation,473 | |
| 104 | +k_cik_type,0.9,infrastructure,930 | |
| 105 | +k_cik_type,0.9,energy_transition,87 | |
| 106 | +k_cik_type,0.9,automation,60 | |
| 107 | +k_type_dropped,0.45,product_launch,4115 | |
| 108 | +k_type_dropped,0.45,geographic_expansion,5770 | |
| 109 | +k_type_dropped,0.45,sustainability,990 | |
| 110 | +k_type_dropped,0.45,supply_chain,450 | |
| 111 | +k_type_dropped,0.45,ma_integration,37495 | |
| 112 | +k_type_dropped,0.45,manufacturing_expansion,2792 | |
| 113 | +k_type_dropped,0.45,drug_pipeline,4665 | |
| 114 | +k_type_dropped,0.45,data_center,318 | |
| 115 | +k_type_dropped,0.45,ai_initiative,287 | |
| 116 | +k_type_dropped,0.45,rd_program,3684 | |
| 117 | +k_type_dropped,0.45,plant_construction,5695 | |
| 118 | +k_type_dropped,0.45,partnership,7417 | |
| 119 | +k_type_dropped,0.45,cloud_migration,189 | |
| 120 | +k_type_dropped,0.45,cost_reduction,4928 | |
| 121 | +k_type_dropped,0.45,technology_deployment,2837 | |
| 122 | +k_type_dropped,0.45,capex_program,8149 | |
| 123 | +k_type_dropped,0.45,digital_transformation,1938 | |
| 124 | +k_type_dropped,0.45,erp_implementation,1539 | |
| 125 | +k_type_dropped,0.45,infrastructure,2979 | |
| 126 | +k_type_dropped,0.45,automation,260 | |
| 127 | +k_type_dropped,0.45,energy_transition,252 | |
| 128 | +k_type_dropped,0.6,product_launch,4106 | |
| 129 | +k_type_dropped,0.6,geographic_expansion,5736 | |
| 130 | +k_type_dropped,0.6,supply_chain,447 | |
| 131 | +k_type_dropped,0.6,sustainability,981 | |
| 132 | +k_type_dropped,0.6,ma_integration,37453 | |
| 133 | +k_type_dropped,0.6,drug_pipeline,4647 | |
| 134 | +k_type_dropped,0.6,manufacturing_expansion,2785 | |
| 135 | +k_type_dropped,0.6,ai_initiative,286 | |
| 136 | +k_type_dropped,0.6,data_center,315 | |
| 137 | +k_type_dropped,0.6,erp_implementation,1539 | |
| 138 | +k_type_dropped,0.6,technology_deployment,2822 | |
| 139 | +k_type_dropped,0.6,digital_transformation,1938 | |
| 140 | +k_type_dropped,0.6,cost_reduction,4922 | |
| 141 | +k_type_dropped,0.6,capex_program,8140 | |
| 142 | +k_type_dropped,0.6,infrastructure,2937 | |
| 143 | +k_type_dropped,0.6,automation,259 | |
| 144 | +k_type_dropped,0.6,energy_transition,248 | |
| 145 | +k_type_dropped,0.6,partnership,7348 | |
| 146 | +k_type_dropped,0.6,plant_construction,5680 | |
| 147 | +k_type_dropped,0.6,rd_program,3660 | |
| 148 | +k_type_dropped,0.6,cloud_migration,189 | |
| 149 | +k_type_dropped,0.7,product_launch,4063 | |
| 150 | +k_type_dropped,0.7,geographic_expansion,5640 | |
| 151 | +k_type_dropped,0.7,sustainability,947 | |
| 152 | +k_type_dropped,0.7,supply_chain,441 | |
| 153 | +k_type_dropped,0.7,ma_integration,37370 | |
| 154 | +k_type_dropped,0.7,manufacturing_expansion,2758 | |
| 155 | +k_type_dropped,0.7,drug_pipeline,4604 | |
| 156 | +k_type_dropped,0.7,data_center,315 | |
| 157 | +k_type_dropped,0.7,ai_initiative,284 | |
| 158 | +k_type_dropped,0.7,erp_implementation,1535 | |
| 159 | +k_type_dropped,0.7,technology_deployment,2750 | |
| 160 | +k_type_dropped,0.7,capex_program,8094 | |
| 161 | +k_type_dropped,0.7,cost_reduction,4857 | |
| 162 | +k_type_dropped,0.7,digital_transformation,1890 | |
| 163 | +k_type_dropped,0.7,infrastructure,2879 | |
| 164 | +k_type_dropped,0.7,energy_transition,246 | |
| 165 | +k_type_dropped,0.7,automation,246 | |
| 166 | +k_type_dropped,0.7,plant_construction,5655 | |
| 167 | +k_type_dropped,0.7,partnership,7220 | |
| 168 | +k_type_dropped,0.7,rd_program,3597 | |
| 169 | +k_type_dropped,0.7,cloud_migration,189 | |
| 170 | +k_type_dropped,0.8,manufacturing_expansion,2548 | |
| 171 | +k_type_dropped,0.8,ma_integration,36888 | |
| 172 | +k_type_dropped,0.8,drug_pipeline,4321 | |
| 173 | +k_type_dropped,0.8,ai_initiative,255 | |
| 174 | +k_type_dropped,0.8,data_center,304 | |
| 175 | +k_type_dropped,0.8,geographic_expansion,4956 | |
| 176 | +k_type_dropped,0.8,product_launch,3707 | |
| 177 | +k_type_dropped,0.8,supply_chain,347 | |
| 178 | +k_type_dropped,0.8,sustainability,823 | |
| 179 | +k_type_dropped,0.8,rd_program,2954 | |
| 180 | +k_type_dropped,0.8,plant_construction,5416 | |
| 181 | +k_type_dropped,0.8,cloud_migration,175 | |
| 182 | +k_type_dropped,0.8,partnership,6390 | |
| 183 | +k_type_dropped,0.8,cost_reduction,4483 | |
| 184 | +k_type_dropped,0.8,capex_program,7855 | |
| 185 | +k_type_dropped,0.8,erp_implementation,1465 | |
| 186 | +k_type_dropped,0.8,infrastructure,2595 | |
| 187 | +k_type_dropped,0.8,automation,177 | |
| 188 | +k_type_dropped,0.8,digital_transformation,1579 | |
| 189 | +k_type_dropped,0.8,technology_deployment,2348 | |
| 190 | +k_type_dropped,0.8,energy_transition,232 | |
| 191 | +k_type_dropped,0.9,product_launch,2562 | |
| 192 | +k_type_dropped,0.9,geographic_expansion,2893 | |
| 193 | +k_type_dropped,0.9,sustainability,439 | |
| 194 | +k_type_dropped,0.9,supply_chain,158 | |
| 195 | +k_type_dropped,0.9,ma_integration,34295 | |
| 196 | +k_type_dropped,0.9,drug_pipeline,3214 | |
| 197 | +k_type_dropped,0.9,manufacturing_expansion,1549 | |
| 198 | +k_type_dropped,0.9,data_center,226 | |
| 199 | +k_type_dropped,0.9,ai_initiative,148 | |
| 200 | +k_type_dropped,0.9,rd_program,1284 | |
| 201 | +k_type_dropped,0.9,plant_construction,4221 | |
| 202 | +k_type_dropped,0.9,partnership,4169 | |
| 203 | +k_type_dropped,0.9,cloud_migration,99 | |
| 204 | +k_type_dropped,0.9,technology_deployment,1379 | |
| 205 | +k_type_dropped,0.9,digital_transformation,679 | |
| 206 | +k_type_dropped,0.9,erp_implementation,1031 | |
| 207 | +k_type_dropped,0.9,cost_reduction,3148 | |
| 208 | +k_type_dropped,0.9,capex_program,6770 | |
| 209 | +k_type_dropped,0.9,infrastructure,1663 | |
| 210 | +k_type_dropped,0.9,energy_transition,189 | |
| 211 | +k_type_dropped,0.9,automation,58 | |
| 212 | +k_current,0.45,geographic_expansion,7868 | |
| 213 | +k_current,0.45,product_launch,5356 | |
| 214 | +k_current,0.45,sustainability,1305 | |
| 215 | +k_current,0.45,supply_chain,684 | |
| 216 | +k_current,0.45,technology_deployment,4128 | |
| 217 | +k_current,0.45,erp_implementation,1735 | |
| 218 | +k_current,0.45,digital_transformation,2642 | |
| 219 | +k_current,0.45,capex_program,10720 | |
| 220 | +k_current,0.45,cost_reduction,6481 | |
| 221 | +k_current,0.45,infrastructure,4481 | |
| 222 | +k_current,0.45,energy_transition,415 | |
| 223 | +k_current,0.45,automation,374 | |
| 224 | +k_current,0.45,ma_integration,41742 | |
| 225 | +k_current,0.45,manufacturing_expansion,4140 | |
| 226 | +k_current,0.45,data_center,449 | |
| 227 | +k_current,0.45,ai_initiative,376 | |
| 228 | +k_current,0.45,drug_pipeline,5360 | |
| 229 | +k_current,0.45,plant_construction,7590 | |
| 230 | +k_current,0.45,partnership,9909 | |
| 231 | +k_current,0.45,rd_program,5080 | |
| 232 | +k_current,0.45,cloud_migration,264 | |
| 233 | +k_current,0.6,ma_integration,41675 | |
| 234 | +k_current,0.6,manufacturing_expansion,4119 | |
| 235 | +k_current,0.6,drug_pipeline,5340 | |
| 236 | +k_current,0.6,ai_initiative,375 | |
| 237 | +k_current,0.6,data_center,445 | |
| 238 | +k_current,0.6,plant_construction,7561 | |
| 239 | +k_current,0.6,cloud_migration,264 | |
| 240 | +k_current,0.6,partnership,9825 | |
| 241 | +k_current,0.6,rd_program,5035 | |
| 242 | +k_current,0.6,erp_implementation,1735 | |
| 243 | +k_current,0.6,capex_program,10707 | |
| 244 | +k_current,0.6,digital_transformation,2638 | |
| 245 | +k_current,0.6,cost_reduction,6473 | |
| 246 | +k_current,0.6,technology_deployment,4103 | |
| 247 | +k_current,0.6,infrastructure,4424 | |
| 248 | +k_current,0.6,automation,372 | |
| 249 | +k_current,0.6,energy_transition,407 | |
| 250 | +k_current,0.6,supply_chain,681 | |
| 251 | +k_current,0.6,product_launch,5345 | |
| 252 | +k_current,0.6,sustainability,1295 | |
| 253 | +k_current,0.6,geographic_expansion,7802 | |
| 254 | +k_current,0.7,product_launch,5286 | |
| 255 | +k_current,0.7,geographic_expansion,7670 | |
| 256 | +k_current,0.7,supply_chain,671 | |
| 257 | +k_current,0.7,sustainability,1251 | |
| 258 | +k_current,0.7,ma_integration,41564 | |
| 259 | +k_current,0.7,manufacturing_expansion,4079 | |
| 260 | +k_current,0.7,drug_pipeline,5289 | |
| 261 | +k_current,0.7,ai_initiative,372 | |
| 262 | +k_current,0.7,data_center,444 | |
| 263 | +k_current,0.7,plant_construction,7511 | |
| 264 | +k_current,0.7,rd_program,4933 | |
| 265 | +k_current,0.7,partnership,9662 | |
| 266 | +k_current,0.7,cloud_migration,264 | |
| 267 | +k_current,0.7,erp_implementation,1728 | |
| 268 | +k_current,0.7,infrastructure,4334 | |
| 269 | +k_current,0.7,technology_deployment,4001 | |
| 270 | +k_current,0.7,capex_program,10648 | |
| 271 | +k_current,0.7,digital_transformation,2567 | |
| 272 | +k_current,0.7,cost_reduction,6394 | |
| 273 | +k_current,0.7,automation,355 | |
| 274 | +k_current,0.7,energy_transition,404 | |
| 275 | +k_current,0.8,product_launch,4760 | |
| 276 | +k_current,0.8,geographic_expansion,6719 | |
| 277 | +k_current,0.8,sustainability,1082 | |
| 278 | +k_current,0.8,supply_chain,524 | |
| 279 | +k_current,0.8,erp_implementation,1645 | |
| 280 | +k_current,0.8,infrastructure,3834 | |
| 281 | +k_current,0.8,technology_deployment,3382 | |
| 282 | +k_current,0.8,capex_program,10275 | |
| 283 | +k_current,0.8,digital_transformation,2120 | |
| 284 | +k_current,0.8,cost_reduction,5896 | |
| 285 | +k_current,0.8,automation,254 | |
| 286 | +k_current,0.8,energy_transition,374 | |
| 287 | +k_current,0.8,ma_integration,40876 | |
| 288 | +k_current,0.8,manufacturing_expansion,3734 | |
| 289 | +k_current,0.8,drug_pipeline,4938 | |
| 290 | +k_current,0.8,ai_initiative,337 | |
| 291 | +k_current,0.8,data_center,416 | |
| 292 | +k_current,0.8,rd_program,4034 | |
| 293 | +k_current,0.8,partnership,8544 | |
| 294 | +k_current,0.8,plant_construction,7092 | |
| 295 | +k_current,0.8,cloud_migration,243 | |
| 296 | +k_current,0.9,product_launch,3163 | |
| 297 | +k_current,0.9,geographic_expansion,3803 | |
| 298 | +k_current,0.9,sustainability,558 | |
| 299 | +k_current,0.9,supply_chain,220 | |
| 300 | +k_current,0.9,ma_integration,37290 | |
| 301 | +k_current,0.9,manufacturing_expansion,2241 | |
| 302 | +k_current,0.9,drug_pipeline,3595 | |
| 303 | +k_current,0.9,ai_initiative,193 | |
| 304 | +k_current,0.9,data_center,299 | |
| 305 | +k_current,0.9,capex_program,8724 | |
| 306 | +k_current,0.9,technology_deployment,1875 | |
| 307 | +k_current,0.9,cost_reduction,4158 | |
| 308 | +k_current,0.9,digital_transformation,874 | |
| 309 | +k_current,0.9,erp_implementation,1124 | |
| 310 | +k_current,0.9,infrastructure,2375 | |
| 311 | +k_current,0.9,energy_transition,274 | |
| 312 | +k_current,0.9,automation,76 | |
| 313 | +k_current,0.9,rd_program,1708 | |
| 314 | +k_current,0.9,plant_construction,5330 | |
| 315 | +k_current,0.9,partnership,5473 | |
| 316 | +k_current,0.9,cloud_migration,130 | |
| 317 | +k_current_stopwords,0.45,geographic_expansion,8001 | |
| 318 | +k_current_stopwords,0.45,product_launch,5315 | |
| 319 | +k_current_stopwords,0.45,sustainability,1301 | |
| 320 | +k_current_stopwords,0.45,supply_chain,680 | |
| 321 | +k_current_stopwords,0.45,ma_integration,50614 | |
| 322 | +k_current_stopwords,0.45,manufacturing_expansion,4118 | |
| 323 | +k_current_stopwords,0.45,data_center,446 | |
| 324 | +k_current_stopwords,0.45,ai_initiative,373 | |
| 325 | +k_current_stopwords,0.45,drug_pipeline,5438 | |
| 326 | +k_current_stopwords,0.45,plant_construction,7609 | |
| 327 | +k_current_stopwords,0.45,partnership,9896 | |
| 328 | +k_current_stopwords,0.45,rd_program,5122 | |
| 329 | +k_current_stopwords,0.45,cloud_migration,261 | |
| 330 | +k_current_stopwords,0.45,technology_deployment,4122 | |
| 331 | +k_current_stopwords,0.45,erp_implementation,1733 | |
| 332 | +k_current_stopwords,0.45,digital_transformation,2617 | |
| 333 | +k_current_stopwords,0.45,capex_program,10712 | |
| 334 | +k_current_stopwords,0.45,cost_reduction,6484 | |
| 335 | +k_current_stopwords,0.45,infrastructure,4473 | |
| 336 | +k_current_stopwords,0.45,energy_transition,415 | |
| 337 | +k_current_stopwords,0.45,automation,371 | |
| 338 | +k_current_stopwords,0.6,ma_integration,50526 | |
| 339 | +k_current_stopwords,0.6,manufacturing_expansion,4097 | |
| 340 | +k_current_stopwords,0.6,drug_pipeline,5419 | |
| 341 | +k_current_stopwords,0.6,ai_initiative,372 | |
| 342 | +k_current_stopwords,0.6,data_center,442 | |
| 343 | +k_current_stopwords,0.6,product_launch,5304 | |
| 344 | +k_current_stopwords,0.6,geographic_expansion,7934 | |
| 345 | +k_current_stopwords,0.6,supply_chain,677 | |
| 346 | +k_current_stopwords,0.6,sustainability,1291 | |
| 347 | +k_current_stopwords,0.6,erp_implementation,1733 | |
| 348 | +k_current_stopwords,0.6,infrastructure,4417 | |
| 349 | +k_current_stopwords,0.6,technology_deployment,4097 | |
| 350 | +k_current_stopwords,0.6,capex_program,10699 | |
| 351 | +k_current_stopwords,0.6,digital_transformation,2613 | |
| 352 | +k_current_stopwords,0.6,cost_reduction,6475 | |
| 353 | +k_current_stopwords,0.6,automation,369 | |
| 354 | +k_current_stopwords,0.6,energy_transition,407 | |
| 355 | +k_current_stopwords,0.6,plant_construction,7581 | |
| 356 | +k_current_stopwords,0.6,rd_program,5077 | |
| 357 | +k_current_stopwords,0.6,partnership,9810 | |
| 358 | +k_current_stopwords,0.6,cloud_migration,261 | |
| 359 | +k_current_stopwords,0.7,product_launch,5246 | |
| 360 | +k_current_stopwords,0.7,geographic_expansion,7799 | |
| 361 | +k_current_stopwords,0.7,supply_chain,667 | |
| 362 | +k_current_stopwords,0.7,sustainability,1247 | |
| 363 | +k_current_stopwords,0.7,erp_implementation,1726 | |
| 364 | +k_current_stopwords,0.7,infrastructure,4329 | |
| 365 | +k_current_stopwords,0.7,technology_deployment,3994 | |
| 366 | +k_current_stopwords,0.7,capex_program,10639 | |
| 367 | +k_current_stopwords,0.7,digital_transformation,2544 | |
| 368 | +k_current_stopwords,0.7,cost_reduction,6397 | |
| 369 | +k_current_stopwords,0.7,automation,353 | |
| 370 | +k_current_stopwords,0.7,energy_transition,404 | |
| 371 | +k_current_stopwords,0.7,ma_integration,50396 | |
| 372 | +k_current_stopwords,0.7,manufacturing_expansion,4058 | |
| 373 | +k_current_stopwords,0.7,drug_pipeline,5376 | |
| 374 | +k_current_stopwords,0.7,ai_initiative,369 | |
| 375 | +k_current_stopwords,0.7,data_center,441 | |
| 376 | +k_current_stopwords,0.7,plant_construction,7534 | |
| 377 | +k_current_stopwords,0.7,rd_program,4976 | |
| 378 | +k_current_stopwords,0.7,partnership,9648 | |
| 379 | +k_current_stopwords,0.7,cloud_migration,261 | |
| 380 | +k_current_stopwords,0.8,product_launch,4733 | |
| 381 | +k_current_stopwords,0.8,geographic_expansion,6822 | |
| 382 | +k_current_stopwords,0.8,sustainability,1079 | |
| 383 | +k_current_stopwords,0.8,supply_chain,520 | |
| 384 | +k_current_stopwords,0.8,erp_implementation,1644 | |
| 385 | +k_current_stopwords,0.8,infrastructure,3831 | |
| 386 | +k_current_stopwords,0.8,technology_deployment,3377 | |
| 387 | +k_current_stopwords,0.8,capex_program,10268 | |
| 388 | +k_current_stopwords,0.8,digital_transformation,2104 | |
| 389 | +k_current_stopwords,0.8,cost_reduction,5897 | |
| 390 | +k_current_stopwords,0.8,automation,254 | |
| 391 | +k_current_stopwords,0.8,energy_transition,374 | |
| 392 | +k_current_stopwords,0.8,ma_integration,49641 | |
| 393 | +k_current_stopwords,0.8,manufacturing_expansion,3712 | |
| 394 | +k_current_stopwords,0.8,drug_pipeline,5017 | |
| 395 | +k_current_stopwords,0.8,ai_initiative,334 | |
| 396 | +k_current_stopwords,0.8,data_center,415 | |
| 397 | +k_current_stopwords,0.8,rd_program,4077 | |
| 398 | +k_current_stopwords,0.8,partnership,8535 | |
| 399 | +k_current_stopwords,0.8,plant_construction,7115 | |
| 400 | +k_current_stopwords,0.8,cloud_migration,241 | |
| 401 | +k_current_stopwords,0.9,product_launch,3153 | |
| 402 | +k_current_stopwords,0.9,sustainability,557 | |
| 403 | +k_current_stopwords,0.9,geographic_expansion,3843 | |
| 404 | +k_current_stopwords,0.9,supply_chain,219 | |
| 405 | +k_current_stopwords,0.9,ma_integration,45679 | |
| 406 | +k_current_stopwords,0.9,manufacturing_expansion,2233 | |
| 407 | +k_current_stopwords,0.9,drug_pipeline,3619 | |
| 408 | +k_current_stopwords,0.9,data_center,300 | |
| 409 | +k_current_stopwords,0.9,ai_initiative,190 | |
| 410 | +k_current_stopwords,0.9,cost_reduction,4161 | |
| 411 | +k_current_stopwords,0.9,erp_implementation,1124 | |
| 412 | +k_current_stopwords,0.9,infrastructure,2375 | |
| 413 | +k_current_stopwords,0.9,technology_deployment,1873 | |
| 414 | +k_current_stopwords,0.9,capex_program,8715 | |
| 415 | +k_current_stopwords,0.9,energy_transition,274 | |
| 416 | +k_current_stopwords,0.9,automation,76 | |
| 417 | +k_current_stopwords,0.9,digital_transformation,871 | |
| 418 | +k_current_stopwords,0.9,plant_construction,5344 | |
| 419 | +k_current_stopwords,0.9,rd_program,1709 | |
| 420 | +k_current_stopwords,0.9,partnership,5473 | |
| 421 | +k_current_stopwords,0.9,cloud_migration,130 | |
| 422 | +k_city_normalised,0.45,plant_construction,6635 | |
| 423 | +k_city_normalised,0.45,rd_program,5021 | |
| 424 | +k_city_normalised,0.45,partnership,9701 | |
| 425 | +k_city_normalised,0.45,cloud_migration,261 | |
| 426 | +k_city_normalised,0.45,ma_integration,47448 | |
| 427 | +k_city_normalised,0.45,manufacturing_expansion,3730 | |
| 428 | +k_city_normalised,0.45,drug_pipeline,5329 | |
| 429 | +k_city_normalised,0.45,ai_initiative,370 | |
| 430 | +k_city_normalised,0.45,data_center,394 | |
| 431 | +k_city_normalised,0.45,infrastructure,4187 | |
| 432 | +k_city_normalised,0.45,capex_program,9862 | |
| 433 | +k_city_normalised,0.45,digital_transformation,2608 | |
| 434 | +k_city_normalised,0.45,cost_reduction,6307 | |
| 435 | +k_city_normalised,0.45,erp_implementation,1728 | |
| 436 | +k_city_normalised,0.45,technology_deployment,4065 | |
| 437 | +k_city_normalised,0.45,automation,367 | |
| 438 | +k_city_normalised,0.45,energy_transition,394 | |
| 439 | +k_city_normalised,0.45,product_launch,5269 | |
| 440 | +k_city_normalised,0.45,geographic_expansion,7629 | |
| 441 | +k_city_normalised,0.45,supply_chain,669 | |
| 442 | +k_city_normalised,0.45,sustainability,1272 | |
| 443 | +k_city_normalised,0.6,ma_integration,47361 | |
| 444 | +k_city_normalised,0.6,manufacturing_expansion,3710 | |
| 445 | +k_city_normalised,0.6,drug_pipeline,5310 | |
| 446 | +k_city_normalised,0.6,data_center,390 | |
| 447 | +k_city_normalised,0.6,ai_initiative,369 | |
| 448 | +k_city_normalised,0.6,product_launch,5258 | |
| 449 | +k_city_normalised,0.6,geographic_expansion,7566 | |
| 450 | +k_city_normalised,0.6,sustainability,1262 | |
| 451 | +k_city_normalised,0.6,supply_chain,666 | |
| 452 | +k_city_normalised,0.6,plant_construction,6610 | |
| 453 | +k_city_normalised,0.6,partnership,9616 | |
| 454 | +k_city_normalised,0.6,rd_program,4976 | |
| 455 | +k_city_normalised,0.6,cloud_migration,261 | |
| 456 | +k_city_normalised,0.6,cost_reduction,6298 | |
| 457 | +k_city_normalised,0.6,capex_program,9850 | |
| 458 | +k_city_normalised,0.6,erp_implementation,1728 | |
| 459 | +k_city_normalised,0.6,automation,365 | |
| 460 | +k_city_normalised,0.6,digital_transformation,2604 | |
| 461 | +k_city_normalised,0.6,infrastructure,4134 | |
| 462 | +k_city_normalised,0.6,energy_transition,386 | |
| 463 | +k_city_normalised,0.6,technology_deployment,4040 | |
| 464 | +k_city_normalised,0.7,product_launch,5200 | |
| 465 | +k_city_normalised,0.7,geographic_expansion,7437 | |
| 466 | +k_city_normalised,0.7,sustainability,1219 | |
| 467 | +k_city_normalised,0.7,supply_chain,656 | |
| 468 | +k_city_normalised,0.7,ma_integration,47233 | |
| 469 | +k_city_normalised,0.7,manufacturing_expansion,3677 | |
| 470 | +k_city_normalised,0.7,drug_pipeline,5269 | |
| 471 | +k_city_normalised,0.7,data_center,389 | |
| 472 | +k_city_normalised,0.7,ai_initiative,366 | |
| 473 | +k_city_normalised,0.7,plant_construction,6566 | |
| 474 | +k_city_normalised,0.7,partnership,9455 | |
| 475 | +k_city_normalised,0.7,rd_program,4876 | |
| 476 | +k_city_normalised,0.7,cloud_migration,261 | |
| 477 | +k_city_normalised,0.7,cost_reduction,6220 | |
| 478 | +k_city_normalised,0.7,capex_program,9790 | |
| 479 | +k_city_normalised,0.7,erp_implementation,1721 | |
| 480 | +k_city_normalised,0.7,automation,349 | |
| 481 | +k_city_normalised,0.7,digital_transformation,2535 | |
| 482 | +k_city_normalised,0.7,infrastructure,4048 | |
| 483 | +k_city_normalised,0.7,energy_transition,383 | |
| 484 | +k_city_normalised,0.7,technology_deployment,3938 | |
| 485 | +k_city_normalised,0.8,product_launch,4692 | |
| 486 | +k_city_normalised,0.8,geographic_expansion,6500 | |
| 487 | +k_city_normalised,0.8,sustainability,1057 | |
| 488 | +k_city_normalised,0.8,supply_chain,511 | |
| 489 | +k_city_normalised,0.8,cost_reduction,5733 | |
| 490 | +k_city_normalised,0.8,capex_program,9422 | |
| 491 | +k_city_normalised,0.8,erp_implementation,1639 | |
| 492 | +k_city_normalised,0.8,digital_transformation,2097 | |
| 493 | +k_city_normalised,0.8,infrastructure,3574 | |
| 494 | +k_city_normalised,0.8,energy_transition,354 | |
| 495 | +k_city_normalised,0.8,technology_deployment,3325 | |
| 496 | +k_city_normalised,0.8,automation,251 | |
| 497 | +k_city_normalised,0.8,ma_integration,46499 | |
| 498 | +k_city_normalised,0.8,manufacturing_expansion,3352 | |
| 499 | +k_city_normalised,0.8,drug_pipeline,4910 | |
| 500 | +k_city_normalised,0.8,data_center,366 | |
| 501 | +k_city_normalised,0.8,ai_initiative,331 | |
| 502 | +k_city_normalised,0.8,plant_construction,6204 | |
| 503 | +k_city_normalised,0.8,partnership,8356 | |
| 504 | +k_city_normalised,0.8,rd_program,3990 | |
| 505 | +k_city_normalised,0.8,cloud_migration,241 | |
| 506 | +k_city_normalised,0.9,plant_construction,4671 | |
| 507 | +k_city_normalised,0.9,rd_program,1660 | |
| 508 | +k_city_normalised,0.9,partnership,5342 | |
| 509 | +k_city_normalised,0.9,cloud_migration,130 | |
| 510 | +k_city_normalised,0.9,product_launch,3123 | |
| 511 | +k_city_normalised,0.9,geographic_expansion,3645 | |
| 512 | +k_city_normalised,0.9,sustainability,546 | |
| 513 | +k_city_normalised,0.9,supply_chain,213 | |
| 514 | +k_city_normalised,0.9,cost_reduction,4051 | |
| 515 | +k_city_normalised,0.9,erp_implementation,1120 | |
| 516 | +k_city_normalised,0.9,infrastructure,2214 | |
| 517 | +k_city_normalised,0.9,technology_deployment,1837 | |
| 518 | +k_city_normalised,0.9,capex_program,7903 | |
| 519 | +k_city_normalised,0.9,energy_transition,261 | |
| 520 | +k_city_normalised,0.9,automation,75 | |
| 521 | +k_city_normalised,0.9,digital_transformation,867 | |
| 522 | +k_city_normalised,0.9,ma_integration,42702 | |
| 523 | +k_city_normalised,0.9,manufacturing_expansion,2014 | |
| 524 | +k_city_normalised,0.9,drug_pipeline,3523 | |
| 525 | +k_city_normalised,0.9,data_center,262 | |
| 526 | +k_city_normalised,0.9,ai_initiative,188 | |
| 527 | +k_name_only,0.45,product_launch,4890 | |
| 528 | +k_name_only,0.45,geographic_expansion,6903 | |
| 529 | +k_name_only,0.45,sustainability,1296 | |
| 530 | +k_name_only,0.45,supply_chain,654 | |
| 531 | +k_name_only,0.45,ma_integration,41205 | |
| 532 | +k_name_only,0.45,manufacturing_expansion,3607 | |
| 533 | +k_name_only,0.45,data_center,357 | |
| 534 | +k_name_only,0.45,ai_initiative,365 | |
| 535 | +k_name_only,0.45,drug_pipeline,4599 | |
| 536 | +k_name_only,0.45,technology_deployment,4041 | |
| 537 | +k_name_only,0.45,digital_transformation,2502 | |
| 538 | +k_name_only,0.45,capex_program,10258 | |
| 539 | +k_name_only,0.45,cost_reduction,5896 | |
| 540 | +k_name_only,0.45,erp_implementation,1614 | |
| 541 | +k_name_only,0.45,infrastructure,4253 | |
| 542 | +k_name_only,0.45,automation,356 | |
| 543 | +k_name_only,0.45,energy_transition,425 | |
| 544 | +k_name_only,0.45,plant_construction,6511 | |
| 545 | +k_name_only,0.45,partnership,9428 | |
| 546 | +k_name_only,0.45,cloud_migration,251 | |
| 547 | +k_name_only,0.45,rd_program,4833 | |
| 548 | +k_name_only,0.6,ma_integration,41128 | |
| 549 | +k_name_only,0.6,manufacturing_expansion,3593 | |
| 550 | +k_name_only,0.6,data_center,353 | |
| 551 | +k_name_only,0.6,ai_initiative,364 | |
| 552 | +k_name_only,0.6,drug_pipeline,4580 | |
| 553 | +k_name_only,0.6,product_launch,4878 | |
| 554 | +k_name_only,0.6,geographic_expansion,6844 | |
| 555 | +k_name_only,0.6,sustainability,1286 | |
| 556 | +k_name_only,0.6,supply_chain,650 | |
| 557 | +k_name_only,0.6,technology_deployment,4015 | |
| 558 | +k_name_only,0.6,digital_transformation,2498 | |
| 559 | +k_name_only,0.6,capex_program,10245 | |
| 560 | +k_name_only,0.6,cost_reduction,5888 | |
| 561 | +k_name_only,0.6,erp_implementation,1614 | |
| 562 | +k_name_only,0.6,infrastructure,4199 | |
| 563 | +k_name_only,0.6,automation,354 | |
| 564 | +k_name_only,0.6,energy_transition,417 | |
| 565 | +k_name_only,0.6,plant_construction,6485 | |
| 566 | +k_name_only,0.6,partnership,9344 | |
| 567 | +k_name_only,0.6,cloud_migration,251 | |
| 568 | +k_name_only,0.6,rd_program,4793 | |
| 569 | +k_name_only,0.7,product_launch,4822 | |
| 570 | +k_name_only,0.7,geographic_expansion,6720 | |
| 571 | +k_name_only,0.7,supply_chain,641 | |
| 572 | +k_name_only,0.7,sustainability,1241 | |
| 573 | +k_name_only,0.7,partnership,9185 | |
| 574 | +k_name_only,0.7,plant_construction,6445 | |
| 575 | +k_name_only,0.7,rd_program,4700 | |
| 576 | +k_name_only,0.7,cloud_migration,251 | |
| 577 | +k_name_only,0.7,digital_transformation,2431 | |
| 578 | +k_name_only,0.7,cost_reduction,5815 | |
| 579 | +k_name_only,0.7,capex_program,10191 | |
| 580 | +k_name_only,0.7,infrastructure,4120 | |
| 581 | +k_name_only,0.7,erp_implementation,1608 | |
| 582 | +k_name_only,0.7,technology_deployment,3910 | |
| 583 | +k_name_only,0.7,automation,338 | |
| 584 | +k_name_only,0.7,energy_transition,415 | |
| 585 | +k_name_only,0.7,ma_integration,41011 | |
| 586 | +k_name_only,0.7,manufacturing_expansion,3561 | |
| 587 | +k_name_only,0.7,drug_pipeline,4535 | |
| 588 | +k_name_only,0.7,ai_initiative,361 | |
| 589 | +k_name_only,0.7,data_center,351 | |
| 590 | +k_name_only,0.8,product_launch,4317 | |
| 591 | +k_name_only,0.8,geographic_expansion,5837 | |
| 592 | +k_name_only,0.8,sustainability,1072 | |
| 593 | +k_name_only,0.8,supply_chain,502 | |
| 594 | +k_name_only,0.8,digital_transformation,2007 | |
| 595 | +k_name_only,0.8,capex_program,9833 | |
| 596 | +k_name_only,0.8,technology_deployment,3308 | |
| 597 | +k_name_only,0.8,cost_reduction,5356 | |
| 598 | +k_name_only,0.8,erp_implementation,1532 | |
| 599 | +k_name_only,0.8,infrastructure,3648 | |
| 600 | +k_name_only,0.8,automation,243 | |
| 601 | +k_name_only,0.8,energy_transition,386 | |
| 602 | +k_name_only,0.8,plant_construction,6077 | |
| 603 | +k_name_only,0.8,partnership,8110 | |
| 604 | +k_name_only,0.8,cloud_migration,232 | |
| 605 | +k_name_only,0.8,rd_program,3824 | |
| 606 | +k_name_only,0.8,ma_integration,40304 | |
| 607 | +k_name_only,0.8,manufacturing_expansion,3248 | |
| 608 | +k_name_only,0.8,data_center,328 | |
| 609 | +k_name_only,0.8,ai_initiative,327 | |
| 610 | +k_name_only,0.8,drug_pipeline,4189 | |
| 611 | +k_name_only,0.9,partnership,5215 | |
| 612 | +k_name_only,0.9,plant_construction,4533 | |
| 613 | +k_name_only,0.9,rd_program,1586 | |
| 614 | +k_name_only,0.9,cloud_migration,126 | |
| 615 | +k_name_only,0.9,product_launch,2836 | |
| 616 | +k_name_only,0.9,geographic_expansion,3211 | |
| 617 | +k_name_only,0.9,sustainability,567 | |
| 618 | +k_name_only,0.9,supply_chain,214 | |
| 619 | +k_name_only,0.9,cost_reduction,3763 | |
| 620 | +k_name_only,0.9,capex_program,8367 | |
| 621 | +k_name_only,0.9,technology_deployment,1815 | |
| 622 | +k_name_only,0.9,erp_implementation,1043 | |
| 623 | +k_name_only,0.9,infrastructure,2267 | |
| 624 | +k_name_only,0.9,automation,74 | |
| 625 | +k_name_only,0.9,digital_transformation,822 | |
| 626 | +k_name_only,0.9,energy_transition,278 | |
| 627 | +k_name_only,0.9,ma_integration,36838 | |
| 628 | +k_name_only,0.9,manufacturing_expansion,1940 | |
| 629 | +k_name_only,0.9,drug_pipeline,2923 | |
| 630 | +k_name_only,0.9,data_center,230 | |
| 631 | +k_name_only,0.9,ai_initiative,186 | |
| 632 | +k_two_tokens,0.45,product_launch,6735 | |
| 633 | +k_two_tokens,0.45,geographic_expansion,8710 | |
| 634 | +k_two_tokens,0.45,sustainability,1358 | |
| 635 | +k_two_tokens,0.45,supply_chain,705 | |
| 636 | +k_two_tokens,0.45,plant_construction,8060 | |
| 637 | +k_two_tokens,0.45,partnership,10556 | |
| 638 | +k_two_tokens,0.45,rd_program,6124 | |
| 639 | +k_two_tokens,0.45,cloud_migration,292 | |
| 640 | +k_two_tokens,0.45,erp_implementation,1867 | |
| 641 | +k_two_tokens,0.45,infrastructure,4663 | |
| 642 | +k_two_tokens,0.45,technology_deployment,4390 | |
| 643 | +k_two_tokens,0.45,cost_reduction,6926 | |
| 644 | +k_two_tokens,0.45,capex_program,11342 | |
| 645 | +k_two_tokens,0.45,digital_transformation,3011 | |
| 646 | +k_two_tokens,0.45,automation,394 | |
| 647 | +k_two_tokens,0.45,energy_transition,454 | |
| 648 | +k_two_tokens,0.45,ma_integration,56961 | |
| 649 | +k_two_tokens,0.45,manufacturing_expansion,4419 | |
| 650 | +k_two_tokens,0.45,drug_pipeline,7851 | |
| 651 | +k_two_tokens,0.45,data_center,465 | |
| 652 | +k_two_tokens,0.45,ai_initiative,414 | |
| 653 | +k_two_tokens,0.6,erp_implementation,1866 | |
| 654 | +k_two_tokens,0.6,technology_deployment,4365 | |
| 655 | +k_two_tokens,0.6,automation,392 | |
| 656 | +k_two_tokens,0.6,cost_reduction,6913 | |
| 657 | +k_two_tokens,0.6,capex_program,11327 | |
| 658 | +k_two_tokens,0.6,digital_transformation,3006 | |
| 659 | +k_two_tokens,0.6,infrastructure,4605 | |
| 660 | +k_two_tokens,0.6,energy_transition,445 | |
| 661 | +k_two_tokens,0.6,geographic_expansion,8636 | |
| 662 | +k_two_tokens,0.6,product_launch,6722 | |
| 663 | +k_two_tokens,0.6,sustainability,1348 | |
| 664 | +k_two_tokens,0.6,supply_chain,702 | |
| 665 | +k_two_tokens,0.6,ma_integration,56860 | |
| 666 | +k_two_tokens,0.6,drug_pipeline,7820 | |
| 667 | +k_two_tokens,0.6,manufacturing_expansion,4398 | |
| 668 | +k_two_tokens,0.6,data_center,461 | |
| 669 | +k_two_tokens,0.6,ai_initiative,413 | |
| 670 | +k_two_tokens,0.6,plant_construction,8026 | |
| 671 | +k_two_tokens,0.6,partnership,10459 | |
| 672 | +k_two_tokens,0.6,rd_program,6066 | |
| 673 | +k_two_tokens,0.6,cloud_migration,292 | |
| 674 | +k_two_tokens,0.7,plant_construction,7967 | |
| 675 | +k_two_tokens,0.7,rd_program,5923 | |
| 676 | +k_two_tokens,0.7,cloud_migration,292 | |
| 677 | +k_two_tokens,0.7,partnership,10270 | |
| 678 | +k_two_tokens,0.7,product_launch,6647 | |
| 679 | +k_two_tokens,0.7,geographic_expansion,8483 | |
| 680 | +k_two_tokens,0.7,supply_chain,692 | |
| 681 | +k_two_tokens,0.7,sustainability,1304 | |
| 682 | +k_two_tokens,0.7,ma_integration,56698 | |
| 683 | +k_two_tokens,0.7,manufacturing_expansion,4353 | |
| 684 | +k_two_tokens,0.7,drug_pipeline,7741 | |
| 685 | +k_two_tokens,0.7,data_center,460 | |
| 686 | +k_two_tokens,0.7,ai_initiative,410 | |
| 687 | +k_two_tokens,0.7,technology_deployment,4253 | |
| 688 | +k_two_tokens,0.7,capex_program,11256 | |
| 689 | +k_two_tokens,0.7,infrastructure,4509 | |
| 690 | +k_two_tokens,0.7,cost_reduction,6821 | |
| 691 | +k_two_tokens,0.7,digital_transformation,2917 | |
| 692 | +k_two_tokens,0.7,erp_implementation,1854 | |
| 693 | +k_two_tokens,0.7,energy_transition,442 | |
| 694 | +k_two_tokens,0.7,automation,375 | |
| 695 | +k_two_tokens,0.8,geographic_expansion,7359 | |
| 696 | +k_two_tokens,0.8,product_launch,6006 | |
| 697 | +k_two_tokens,0.8,sustainability,1123 | |
| 698 | +k_two_tokens,0.8,supply_chain,533 | |
| 699 | +k_two_tokens,0.8,ma_integration,55748 | |
| 700 | +k_two_tokens,0.8,manufacturing_expansion,3956 | |
| 701 | +k_two_tokens,0.8,drug_pipeline,7134 | |
| 702 | +k_two_tokens,0.8,data_center,431 | |
| 703 | +k_two_tokens,0.8,ai_initiative,367 | |
| 704 | +k_two_tokens,0.8,plant_construction,7483 | |
| 705 | +k_two_tokens,0.8,partnership,9041 | |
| 706 | +k_two_tokens,0.8,rd_program,4764 | |
| 707 | +k_two_tokens,0.8,cloud_migration,269 | |
| 708 | +k_two_tokens,0.8,erp_implementation,1755 | |
| 709 | +k_two_tokens,0.8,technology_deployment,3565 | |
| 710 | +k_two_tokens,0.8,automation,268 | |
| 711 | +k_two_tokens,0.8,cost_reduction,6263 | |
| 712 | +k_two_tokens,0.8,capex_program,10835 | |
| 713 | +k_two_tokens,0.8,digital_transformation,2391 | |
| 714 | +k_two_tokens,0.8,infrastructure,3969 | |
| 715 | +k_two_tokens,0.8,energy_transition,411 | |
| 716 | +k_two_tokens,0.9,sustainability,565 | |
| 717 | +k_two_tokens,0.9,product_launch,3951 | |
| 718 | +k_two_tokens,0.9,geographic_expansion,4047 | |
| 719 | +k_two_tokens,0.9,supply_chain,220 | |
| 720 | +k_two_tokens,0.9,ma_integration,50615 | |
| 721 | +k_two_tokens,0.9,manufacturing_expansion,2320 | |
| 722 | +k_two_tokens,0.9,drug_pipeline,4766 | |
| 723 | +k_two_tokens,0.9,data_center,311 | |
| 724 | +k_two_tokens,0.9,ai_initiative,204 | |
| 725 | +k_two_tokens,0.9,erp_implementation,1176 | |
| 726 | +k_two_tokens,0.9,technology_deployment,1935 | |
| 727 | +k_two_tokens,0.9,cost_reduction,4340 | |
| 728 | +k_two_tokens,0.9,capex_program,9074 | |
| 729 | +k_two_tokens,0.9,digital_transformation,950 | |
| 730 | +k_two_tokens,0.9,infrastructure,2422 | |
| 731 | +k_two_tokens,0.9,energy_transition,298 | |
| 732 | +k_two_tokens,0.9,automation,82 | |
| 733 | +k_two_tokens,0.9,plant_construction,5520 | |
| 734 | +k_two_tokens,0.9,partnership,5701 | |
| 735 | +k_two_tokens,0.9,rd_program,1853 | |
| 736 | +k_two_tokens,0.9,cloud_migration,140 | |
| 737 | +k_strict,0.45,product_launch,8649 | |
| 738 | +k_strict,0.45,geographic_expansion,11713 | |
| 739 | +k_strict,0.45,supply_chain,822 | |
| 740 | +k_strict,0.45,sustainability,1716 | |
| 741 | +k_strict,0.45,erp_implementation,2129 | |
| 742 | +k_strict,0.45,technology_deployment,5135 | |
| 743 | +k_strict,0.45,cost_reduction,8400 | |
| 744 | +k_strict,0.45,digital_transformation,3411 | |
| 745 | +k_strict,0.45,automation,436 | |
| 746 | +k_strict,0.45,capex_program,14407 | |
| 747 | +k_strict,0.45,infrastructure,6258 | |
| 748 | +k_strict,0.45,energy_transition,656 | |
| 749 | +k_strict,0.45,ma_integration,79531 | |
| 750 | +k_strict,0.45,manufacturing_expansion,6360 | |
| 751 | +k_strict,0.45,drug_pipeline,13930 | |
| 752 | +k_strict,0.45,ai_initiative,459 | |
| 753 | +k_strict,0.45,data_center,670 | |
| 754 | +k_strict,0.45,plant_construction,12527 | |
| 755 | +k_strict,0.45,partnership,13266 | |
| 756 | +k_strict,0.45,rd_program,7674 | |
| 757 | +k_strict,0.45,cloud_migration,339 | |
| 758 | +k_strict,0.6,product_launch,8634 | |
| 759 | +k_strict,0.6,sustainability,1702 | |
| 760 | +k_strict,0.6,geographic_expansion,11604 | |
| 761 | +k_strict,0.6,supply_chain,818 | |
| 762 | +k_strict,0.6,infrastructure,6178 | |
| 763 | +k_strict,0.6,cost_reduction,8384 | |
| 764 | +k_strict,0.6,erp_implementation,2127 | |
| 765 | +k_strict,0.6,digital_transformation,3405 | |
| 766 | +k_strict,0.6,capex_program,14385 | |
| 767 | +k_strict,0.6,technology_deployment,5099 | |
| 768 | +k_strict,0.6,energy_transition,647 | |
| 769 | +k_strict,0.6,automation,433 | |
| 770 | +k_strict,0.6,partnership,13140 | |
| 771 | +k_strict,0.6,plant_construction,12461 | |
| 772 | +k_strict,0.6,rd_program,7585 | |
| 773 | +k_strict,0.6,cloud_migration,339 | |
| 774 | +k_strict,0.6,ma_integration,79405 | |
| 775 | +k_strict,0.6,manufacturing_expansion,6335 | |
| 776 | +k_strict,0.6,drug_pipeline,13868 | |
| 777 | +k_strict,0.6,data_center,666 | |
| 778 | +k_strict,0.6,ai_initiative,458 | |
| 779 | +k_strict,0.7,infrastructure,6048 | |
| 780 | +k_strict,0.7,digital_transformation,3306 | |
| 781 | +k_strict,0.7,technology_deployment,4964 | |
| 782 | +k_strict,0.7,cost_reduction,8278 | |
| 783 | +k_strict,0.7,automation,413 | |
| 784 | +k_strict,0.7,erp_implementation,2114 | |
| 785 | +k_strict,0.7,capex_program,14301 | |
| 786 | +k_strict,0.7,energy_transition,643 | |
| 787 | +k_strict,0.7,product_launch,8538 | |
| 788 | +k_strict,0.7,geographic_expansion,11387 | |
| 789 | +k_strict,0.7,sustainability,1648 | |
| 790 | +k_strict,0.7,supply_chain,807 | |
| 791 | +k_strict,0.7,ma_integration,79211 | |
| 792 | +k_strict,0.7,drug_pipeline,13700 | |
| 793 | +k_strict,0.7,manufacturing_expansion,6275 | |
| 794 | +k_strict,0.7,data_center,663 | |
| 795 | +k_strict,0.7,ai_initiative,455 | |
| 796 | +k_strict,0.7,plant_construction,12341 | |
| 797 | +k_strict,0.7,rd_program,7382 | |
| 798 | +k_strict,0.7,partnership,12890 | |
| 799 | +k_strict,0.7,cloud_migration,339 | |
| 800 | +k_strict,0.8,ma_integration,77954 | |
| 801 | +k_strict,0.8,manufacturing_expansion,5681 | |
| 802 | +k_strict,0.8,drug_pipeline,12499 | |
| 803 | +k_strict,0.8,data_center,616 | |
| 804 | +k_strict,0.8,ai_initiative,407 | |
| 805 | +k_strict,0.8,product_launch,7733 | |
| 806 | +k_strict,0.8,geographic_expansion,9828 | |
| 807 | +k_strict,0.8,supply_chain,622 | |
| 808 | +k_strict,0.8,sustainability,1419 | |
| 809 | +k_strict,0.8,technology_deployment,4142 | |
| 810 | +k_strict,0.8,capex_program,13785 | |
| 811 | +k_strict,0.8,cost_reduction,7584 | |
| 812 | +k_strict,0.8,digital_transformation,2698 | |
| 813 | +k_strict,0.8,erp_implementation,1990 | |
| 814 | +k_strict,0.8,infrastructure,5314 | |
| 815 | +k_strict,0.8,energy_transition,597 | |
| 816 | +k_strict,0.8,automation,292 | |
| 817 | +k_strict,0.8,partnership,11275 | |
| 818 | +k_strict,0.8,plant_construction,11475 | |
| 819 | +k_strict,0.8,rd_program,5830 | |
| 820 | +k_strict,0.8,cloud_migration,311 | |
| 821 | +k_strict,0.9,product_launch,5066 | |
| 822 | +k_strict,0.9,sustainability,699 | |
| 823 | +k_strict,0.9,geographic_expansion,5180 | |
| 824 | +k_strict,0.9,supply_chain,256 | |
| 825 | +k_strict,0.9,digital_transformation,1041 | |
| 826 | +k_strict,0.9,technology_deployment,2210 | |
| 827 | +k_strict,0.9,cost_reduction,5158 | |
| 828 | +k_strict,0.9,erp_implementation,1278 | |
| 829 | +k_strict,0.9,capex_program,11518 | |
| 830 | +k_strict,0.9,energy_transition,417 | |
| 831 | +k_strict,0.9,infrastructure,3084 | |
| 832 | +k_strict,0.9,automation,88 | |
| 833 | +k_strict,0.9,ma_integration,70579 | |
| 834 | +k_strict,0.9,drug_pipeline,7712 | |
| 835 | +k_strict,0.9,manufacturing_expansion,3181 | |
| 836 | +k_strict,0.9,data_center,430 | |
| 837 | +k_strict,0.9,ai_initiative,229 | |
| 838 | +k_strict,0.9,rd_program,2173 | |
| 839 | +k_strict,0.9,plant_construction,8089 | |
| 840 | +k_strict,0.9,partnership,6870 | |
| 841 | +k_strict,0.9,cloud_migration,153 | |
| 842 | +k_mention_level,0.45,cost_reduction,13157 | |
| 843 | +k_mention_level,0.45,capex_program,19211 | |
| 844 | +k_mention_level,0.45,erp_implementation,4242 | |
| 845 | +k_mention_level,0.45,automation,630 | |
| 846 | +k_mention_level,0.45,technology_deployment,6725 | |
| 847 | +k_mention_level,0.45,digital_transformation,5249 | |
| 848 | +k_mention_level,0.45,infrastructure,8510 | |
| 849 | +k_mention_level,0.45,energy_transition,866 | |
| 850 | +k_mention_level,0.45,geographic_expansion,17713 | |
| 851 | +k_mention_level,0.45,product_launch,12456 | |
| 852 | +k_mention_level,0.45,sustainability,2607 | |
| 853 | +k_mention_level,0.45,supply_chain,1171 | |
| 854 | +k_mention_level,0.45,ma_integration,130259 | |
| 855 | +k_mention_level,0.45,manufacturing_expansion,8825 | |
| 856 | +k_mention_level,0.45,drug_pipeline,26755 | |
| 857 | +k_mention_level,0.45,ai_initiative,632 | |
| 858 | +k_mention_level,0.45,data_center,889 | |
| 859 | +k_mention_level,0.45,plant_construction,18388 | |
| 860 | +k_mention_level,0.45,partnership,17501 | |
| 861 | +k_mention_level,0.45,rd_program,11758 | |
| 862 | +k_mention_level,0.45,cloud_migration,521 | |
| 863 | +k_mention_level,0.6,product_launch,12426 | |
| 864 | +k_mention_level,0.6,geographic_expansion,17424 | |
| 865 | +k_mention_level,0.6,sustainability,2582 | |
| 866 | +k_mention_level,0.6,supply_chain,1165 | |
| 867 | +k_mention_level,0.6,plant_construction,18271 | |
| 868 | +k_mention_level,0.6,rd_program,11587 | |
| 869 | +k_mention_level,0.6,partnership,17318 | |
| 870 | +k_mention_level,0.6,cloud_migration,521 | |
| 871 | +k_mention_level,0.6,ma_integration,130004 | |
| 872 | +k_mention_level,0.6,drug_pipeline,26523 | |
| 873 | +k_mention_level,0.6,manufacturing_expansion,8786 | |
| 874 | +k_mention_level,0.6,data_center,884 | |
| 875 | +k_mention_level,0.6,ai_initiative,631 | |
| 876 | +k_mention_level,0.6,erp_implementation,4240 | |
| 877 | +k_mention_level,0.6,cost_reduction,13124 | |
| 878 | +k_mention_level,0.6,capex_program,19182 | |
| 879 | +k_mention_level,0.6,automation,627 | |
| 880 | +k_mention_level,0.6,technology_deployment,6677 | |
| 881 | +k_mention_level,0.6,digital_transformation,5231 | |
| 882 | +k_mention_level,0.6,infrastructure,8396 | |
| 883 | +k_mention_level,0.6,energy_transition,855 | |
| 884 | +k_mention_level,0.7,geographic_expansion,17050 | |
| 885 | +k_mention_level,0.7,product_launch,12265 | |
| 886 | +k_mention_level,0.7,sustainability,2503 | |
| 887 | +k_mention_level,0.7,supply_chain,1142 | |
| 888 | +k_mention_level,0.7,erp_implementation,4214 | |
| 889 | +k_mention_level,0.7,cost_reduction,12973 | |
| 890 | +k_mention_level,0.7,automation,605 | |
| 891 | +k_mention_level,0.7,technology_deployment,6502 | |
| 892 | +k_mention_level,0.7,digital_transformation,5092 | |
| 893 | +k_mention_level,0.7,infrastructure,8205 | |
| 894 | +k_mention_level,0.7,capex_program,19064 | |
| 895 | +k_mention_level,0.7,energy_transition,850 | |
| 896 | +k_mention_level,0.7,plant_construction,18092 | |
| 897 | +k_mention_level,0.7,partnership,16928 | |
| 898 | +k_mention_level,0.7,rd_program,11214 | |
| 899 | +k_mention_level,0.7,cloud_migration,521 | |
| 900 | +k_mention_level,0.7,ma_integration,129674 | |
| 901 | +k_mention_level,0.7,manufacturing_expansion,8671 | |
| 902 | +k_mention_level,0.7,drug_pipeline,26107 | |
| 903 | +k_mention_level,0.7,ai_initiative,627 | |
| 904 | +k_mention_level,0.7,data_center,876 | |
| 905 | +k_mention_level,0.8,plant_construction,16758 | |
| 906 | +k_mention_level,0.8,cloud_migration,478 | |
| 907 | +k_mention_level,0.8,rd_program,8651 | |
| 908 | +k_mention_level,0.8,partnership,14523 | |
| 909 | +k_mention_level,0.8,geographic_expansion,14501 | |
| 910 | +k_mention_level,0.8,product_launch,11102 | |
| 911 | +k_mention_level,0.8,sustainability,2124 | |
| 912 | +k_mention_level,0.8,supply_chain,880 | |
| 913 | +k_mention_level,0.8,technology_deployment,5330 | |
| 914 | +k_mention_level,0.8,capex_program,18260 | |
| 915 | +k_mention_level,0.8,erp_implementation,3979 | |
| 916 | +k_mention_level,0.8,cost_reduction,11876 | |
| 917 | +k_mention_level,0.8,digital_transformation,4182 | |
| 918 | +k_mention_level,0.8,infrastructure,7146 | |
| 919 | +k_mention_level,0.8,automation,415 | |
| 920 | +k_mention_level,0.8,energy_transition,785 | |
| 921 | +k_mention_level,0.8,ma_integration,127709 | |
| 922 | +k_mention_level,0.8,drug_pipeline,23441 | |
| 923 | +k_mention_level,0.8,manufacturing_expansion,7737 | |
| 924 | +k_mention_level,0.8,data_center,801 | |
| 925 | +k_mention_level,0.8,ai_initiative,563 | |
| 926 | +k_mention_level,0.9,ma_integration,115621 | |
| 927 | +k_mention_level,0.9,manufacturing_expansion,4220 | |
| 928 | +k_mention_level,0.9,drug_pipeline,13708 | |
| 929 | +k_mention_level,0.9,ai_initiative,319 | |
| 930 | +k_mention_level,0.9,data_center,534 | |
| 931 | +k_mention_level,0.9,product_launch,7283 | |
| 932 | +k_mention_level,0.9,geographic_expansion,7146 | |
| 933 | +k_mention_level,0.9,sustainability,1005 | |
| 934 | +k_mention_level,0.9,supply_chain,351 | |
| 935 | +k_mention_level,0.9,erp_implementation,2204 | |
| 936 | +k_mention_level,0.9,capex_program,14939 | |
| 937 | +k_mention_level,0.9,digital_transformation,1494 | |
| 938 | +k_mention_level,0.9,technology_deployment,2723 | |
| 939 | +k_mention_level,0.9,cost_reduction,7814 | |
| 940 | +k_mention_level,0.9,infrastructure,3987 | |
| 941 | +k_mention_level,0.9,energy_transition,517 | |
| 942 | +k_mention_level,0.9,automation,110 | |
| 943 | +k_mention_level,0.9,plant_construction,11519 | |
| 944 | +k_mention_level,0.9,partnership,8390 | |
| 945 | +k_mention_level,0.9,rd_program,3050 | |
| 946 | +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