SPB Git

spb/firc0001_uqo

Public
39.1 KB · 459 lines latex
1% ----------------------------------------------------------------------------2% PROVISIONAL inline-number macros for the Stage E prose (Agent 10, 2026-11-05).3% Every value below is copied from a Stage D audit output under results/ (file and4% field given on each line) and is defined with \providecommand so that the5% generated definition in tables/numbers.tex (code/make_tables.py, Agent 9) wins6% as soon as it exists. The same list, with value/source/formula, is filed for the7% generator in improvements/FIRC-0001/macro_requests_writing.json. Delete this8% file once make_tables.py emits every macro (check: grep providecommand).9% ----------------------------------------------------------------------------1011% ---- ledger, calls, outage (results/ledger/*.json, gate_pass_by_run.csv) ----12\providecommand{\SPIDoutageRowsRemoved}{149{,}352}            % log_summary.json:october.outage_rows_reconciliation.difference13\providecommand{\SPIDoutageLargestGapStart}{01:25}            % throughput.json:largest_gaps_seconds[-1] (2026-10-28)14\providecommand{\SPIDoutageLargestGapEnd}{06:40}              % throughput.json:largest_gaps_seconds[-1]15\providecommand{\SPIDoutageZeroBatchRange}{47--60}            % log_summary.json:october.anomalous_batches (batch ids with 0 mentions)16\providecommand{\SPIDoutageZeroBatchWindow}{01:44--06:05}     % log_summary.json:october.anomalous_batches (first/last timestamp)17\providecommand{\SPIDoutageSurvivingRows}{504}                % backfill_block.json:rows_in_outage_window[0]18\providecommand{\SPIDoutageSurvivingMentions}{1{,}011}        % backfill_block.json:rows_in_outage_window[1]19\providecommand{\SPIDresumeBatchSections}{5{,}198}            % log_summary.json:october.resume_batch1.log_sections20\providecommand{\SPIDresumeBatchCiks}{20}                     % log_summary.json:october.resume_batch1.ciks (length)21\providecommand{\SPIDresumeBatchCalls}{2{,}686}               % log_summary.json:october.resume_batch1.ledger_calls22\providecommand{\SPIDresumeBatchProductive}{23}               % log_summary.json:october.resume_batch1.ledger_with_mentions23\providecommand{\SPIDresumeBatchExpectedProductive}{536}      % resume_batch1_vs_expected.csv: sum(expected_with_mentions) = 536.224\providecommand{\SPIDresumeBatchMentions}{34}                 % log_summary.json:october.resume_batch1.log_mentions25\providecommand{\SPIDresumeBatchWindow}{06:38--06:40}         % log_summary.json:october.resume_batch1.window (2026-10-28)26\providecommand{\SPIDresumeBatchZeroSharePct}{99.2}           % flush_zero_groups_after_0622.csv (06:40 minute bin, 99.15)27\providecommand{\SPIDjuneCalls}{95{,}286}                     % gate_pass_by_run.csv:backfilled_june.calls28\providecommand{\SPIDjuneProductiveShareCalls}{25.6}          % gate_pass_by_run.csv:backfilled_june.productive_pct_calls29\providecommand{\SPIDoctoberProductiveShareCalls}{23.6}       % gate_pass_by_run.csv:october.productive_pct_calls30\providecommand{\SPIDlogExtractionCompleteSum}{1{,}117{,}479} % log_summary.json:october.extraction_complete_sum_sections31\providecommand{\SPIDlogPendingSecondStart}{968{,}127}        % log_summary.json:october.pending_lines[1]32\providecommand{\SPIDconfExactDefault}{3{,}278}               % code_vs_data_checks.json:confidence_exact_0600_total33\providecommand{\SPIDconfExactDefaultJune}{304}               % code_vs_data_checks.json:confidence_exact_0600_by_run34\providecommand{\SPIDconfExactDefaultOctober}{2{,}974}        % code_vs_data_checks.json:confidence_exact_0600_by_run35\providecommand{\SPIDamountRawDeviations}{584}                % code_vs_data_checks.json:amount_raw_rule_mismatch36\providecommand{\SPIDamountNegative}{24}                      % results/grounding/amount_tail.json:lt_037\providecommand{\SPIDamountZero}{584}                         % results/grounding/amount_tail.json:eq_038\providecommand{\SPIDledgerBackendValue}{llm}                 % code_vs_data_checks.json:distinct_backend_ledger3940% ---- grounding (results/grounding/grounding_by_group.csv, grounding_all_structured.csv, grounding_element_level.csv, fallback_bounds.json, amount_tail.json) ----41\providecommand{\SPIDgroundBootstrapReps}{1{,}000}            % a02_grounding.py (bootstrap replicates, clustered by section)42\providecommand{\SPIDgroundYearsPct}{99.8}                    % grounding_by_group.csv all/years 0.997643\providecommand{\SPIDgroundYearsCiLow}{99.7}                  % ci_low 0.997444\providecommand{\SPIDgroundYearsCiHigh}{99.8}                 % ci_high 0.997845\providecommand{\SPIDgroundPartnersPct}{99.4}                 % all/partners 0.994046\providecommand{\SPIDgroundAmountNumberPct}{93.7}             % all/amount_number 0.937247\providecommand{\SPIDgroundAmountCurrencyPct}{80.5}           % all/amount_with_currency 0.804748\providecommand{\SPIDgroundLocationsPct}{78.3}                % all/locations 0.783249\providecommand{\SPIDgroundLocationsTenK}{85.7}               % form/locations/10-K 0.857150\providecommand{\SPIDgroundLocationsTenQ}{82.1}               % form/locations/10-Q 0.820751\providecommand{\SPIDgroundLocationsEightK}{67.8}             % form/locations/8-K 0.678052\providecommand{\SPIDgroundTechPct}{63.6}                     % all/technologies 0.635853\providecommand{\SPIDgroundElemYears}{99.7}                   % grounding_element_level.csv years54\providecommand{\SPIDgroundElemPartners}{99.6}                % partners55\providecommand{\SPIDgroundElemLocations}{84.2}               % locations56\providecommand{\SPIDgroundElemTech}{70.6}                    % technologies57\providecommand{\SPIDgroundAllPct}{88.2}                      % grounding_all_structured.csv all 88.1758\providecommand{\SPIDgroundAllN}{276{,}168}                   % grounding_all_structured.csv all n_with_fields59\providecommand{\SPIDgroundAllTenK}{92.2}                     % 10-K 92.1560\providecommand{\SPIDgroundAllTenQ}{92.4}                     % 10-Q 92.4161\providecommand{\SPIDgroundAllEightK}{76.6}                   % 8-K 76.5762\providecommand{\SPIDgroundAllJune}{84.5}                     % backfilled_june 84.5163\providecommand{\SPIDgroundAllOctober}{88.7}                  % october 88.7464\providecommand{\SPIDgroundAllTopBin}{86.4}                   % 0.9-1.0 bin 86.4065\providecommand{\SPIDgroundAllLowerBinsRange}{90.7--94.2}     % bins 0.45-0.6 ... 0.8-0.966\providecommand{\SPIDyearsNonEmptyN}{252{,}469}               % fallback_bounds.json:years_nonempty67\providecommand{\SPIDyearsRegexEqualN}{98{,}438}              % fallback_bounds.json:years_eq_regex_desc68\providecommand{\SPIDyearsRegexEqualPct}{39}                  % 98,438 / 252,46969\providecommand{\SPIDtechNonEmptyN}{36{,}740}                 % fallback_bounds.json:techs_nonempty70\providecommand{\SPIDtechRegexEqualN}{16{,}949}               % fallback_bounds.json:techs_eq_regex_desc71\providecommand{\SPIDtechRegexEqualPct}{46}                   % 16,949 / 36,74072\providecommand{\SPIDyearsAbsentFromText}{604}                % fallback_bounds.json:years_not_subset_of_text73\providecommand{\SPIDtypeSignalMaPct}{79.8}                   % fallback_bounds.json:type_signal_in_name_desc_by_type ma_integration74\providecommand{\SPIDtypeSignalTechDeployPct}{5.4}            % technology_deployment 5.3575\providecommand{\SPIDtechDeployMentionedN}{124}               % fallback_bounds.json:tech_deploy_total[1]76\providecommand{\SPIDtechDeployMentionedNoSignal}{90}         % fallback_bounds.json:tech_deploy_mentioned_no_any_signal77\providecommand{\SPIDamountMaxSci}{1.0 \times 10^{12}}        % amount_tail.json:max_amount (math mode)78\providecommand{\SPIDamountGeFiftyBMentions}{161}             % amount_tail.json:ge_50e979\providecommand{\SPIDamountGeFiftyBProjects}{104}             % amount_tail.json:projects_max_amount_ge_50e980\providecommand{\SPIDamountTopNumberFound}{191}               % amount_tail.json:top200_grounded_number[0]81\providecommand{\SPIDamountTopCurrencyFound}{178}             % amount_tail.json:top200_grounded_number[1]82\providecommand{\SPIDamountTopN}{200}                         % amount_tail.json:top200_grounded_number[2]83\providecommand{\SPIDamountNonUsdTokenN}{1{,}837}             % amount_tail.json:nonusd_within_40_share[0]84\providecommand{\SPIDamountLocatedN}{112{,}692}               % amount_tail.json:nonusd_within_40_share[1]85\providecommand{\SPIDamountNonUsdTokenPct}{1.6}               % 1,837 / 112,6928687% ---- resolver (results/resolver/composition.json, spec_curve.csv, top_name_tokens.csv, overmerge_by_type.csv, ties_idempotence.json, june_october_reconciliation.json) ----88\providecommand{\SPIDmentionsKeyedLocation}{118{,}783}        % composition.json:mentions_by_key_branch location89\providecommand{\SPIDmentionsKeyedNameToken}{187{,}212}       % composition.json:mentions_by_key_branch name_token90\providecommand{\SPIDmentionsKeyedNameTokenPct}{60.8}         % 187,212 / 308,06591\providecommand{\SPIDtopTokenMentions}{40{,}407}              % top_name_tokens.csv acquisition92\providecommand{\SPIDtopTokenProjects}{2{,}256}               % top_name_tokens.csv acquisition93\providecommand{\SPIDtopTokenSharePct}{21.4}                  % pct_of_tokenkeyed_mentions94\providecommand{\SPIDlocationKeysCountry}{8{,}126}            % composition.json:location_keyed_projects_by_geo_kind country95\providecommand{\SPIDlocationKeysUsState}{6{,}110}            % us_state96\providecommand{\SPIDlocationKeysCountryStatePct}{26}         % (8,126 + 6,110) / 54,65897\providecommand{\SPIDlocationKeyUnitedStatesProjects}{2{,}551}% top_location_keys.csv 'united states'98\providecommand{\SPIDprojectsKeyCikType}{21{,}027}            % spec_curve.csv k_cik_type 0.4599\providecommand{\SPIDprojectsKeyTypeDropped}{96{,}749}        % k_type_dropped 0.45100\providecommand{\SPIDprojectsKeyNameOnly}{114{,}244}          % k_name_only 0.45101\providecommand{\SPIDprojectsKeyCityNorm}{123{,}246}          % k_city_normalised 0.45102\providecommand{\SPIDprojectsKeyStopwords}{130{,}101}         % k_current_stopwords 0.45103\providecommand{\SPIDprojectsKeyTwoTokens}{145{,}697}         % k_two_tokens 0.45104\providecommand{\SPIDprojectsKeyStrict}{198{,}488}            % k_strict 0.45105\providecommand{\SPIDprojectsKeyMentionLevel}{308{,}065}      % k_mention_level 0.45106\providecommand{\SPIDprojectsCurrentKeyAtNine}{83{,}483}      % k_current 0.9107\providecommand{\SPIDsingleMentionShareStrict}{75.8}          % k_strict 0.45 single_mention_pct108\providecommand{\SPIDsingleMentionShareCikType}{20.7}         % k_cik_type 0.45109\providecommand{\SPIDchenierClusterCurrent}{8}                % example_cluster_size_cheniere k_current110\providecommand{\SPIDchenierClusterStrict}{1}                 % k_strict111\providecommand{\SPIDchenierClusterNameOnly}{40}              % k_name_only112\providecommand{\SPIDchenierClusterCikType}{176}              % k_cik_type113\providecommand{\SPIDmaGeThreeNamesPct}{14.6}                 % overmerge_by_type.csv ma_integration pct_ge3_names114\providecommand{\SPIDmaGeThreeNamesOverTenPct}{86.6}          % overmerge_ma_by_bucket.csv >10 mentions115\providecommand{\SPIDmaGeThreePartnersPct}{10.9}              % overmerge_by_type.csv ma_integration pct_ge3_partners_among_with_partner116\providecommand{\SPIDmaAmountOtherCounterpartyN}{1{,}630}     % composition.json:amount_from_other_counterparty_ma[0]117\providecommand{\SPIDmaAmountOtherCounterpartyDenom}{12{,}372}% composition.json:amount_from_other_counterparty_ma[1]118\providecommand{\SPIDamountOtherCounterpartyN}{2{,}347}       % composition.json:amount_from_other_counterparty[0]119\providecommand{\SPIDamountOtherCounterpartyDenom}{21{,}908}  % composition.json:amount_from_other_counterparty[1]120\providecommand{\SPIDprojectsTieDistinctDescriptions}{29{,}954} % ties_idempotence.json121\providecommand{\SPIDrebuiltNameDiff}{394}                    % ties_idempotence.json:rebuilt_vs_stored_diff[0]122\providecommand{\SPIDrebuiltDescDiff}{600}                    % ties_idempotence.json:rebuilt_vs_stored_diff[2]123\providecommand{\SPIDtiebreakNameDiff}{11{,}484}              % ties_idempotence.json:deterministic_vs_stored_diff[0]124\providecommand{\SPIDtiebreakStatusDiff}{503}                 % [1]125\providecommand{\SPIDtiebreakDescDiff}{18{,}256}              % [2]126\providecommand{\SPIDjuneProjects}{19{,}227}                  % june_october_reconciliation.json:projects_from_backfilled_block_only127\providecommand{\SPIDspMentions}{70{,}367}                    % sp500_mentions_total128\providecommand{\SPIDspProjects}{27{,}766}                    % sp500_projects_total129\providecommand{\SPIDspProjectsJuneOnly}{15{,}910}            % sp500_projects_by_run_composition130\providecommand{\SPIDspProjectsBothRuns}{3{,}317}131\providecommand{\SPIDspProjectsOctoberOnly}{8{,}539}132\providecommand{\SPIDoctoberSpTenQSections}{116{,}231}        % sp500_october_ledger_by_form 10-Q133\providecommand{\SPIDoctoberSpTenQFilings}{19{,}399}134\providecommand{\SPIDoctoberSpTenQMentions}{28{,}963}         % sp500_mentions_by_run_form october 10-Q135\providecommand{\SPIDjuneTenQFilings}{3{,}710}                % june_10q_accessions_in_block_ledger136\providecommand{\SPIDjuneTenQSections}{23{,}873}              % ledger_block_accessions_by_form 10-Q137\providecommand{\SPIDjuneTenQMentions}{5{,}817}               % sp500_mentions_by_run_form backfilled_june 10-Q138\providecommand{\SPIDoctoberSpTenKMentions}{910}              % october 10-K139\providecommand{\SPIDoctoberSpEightKMentions}{564}            % october 8-K140141% ---- two runs / two segmenters (results/runs/git_evidence.md, segmenters.json, segmenter_item_comparison.csv, funnel_10k.json, within_*.csv, table6_cohort*.json/csv, fiscal_year_audit.json) ----142\providecommand{\SPIDrepoCommits}{six}                        % git_evidence.md: all commits dated 2026-10-27/28143\providecommand{\SPIDextractorMtimeDate}{June~17, 2026}       % git_evidence.md: llm.py, rules.py, base.py, taxonomy.py, resolve.py, ingest.py mtimes144\providecommand{\SPIDdiffStoreLines}{$+3/-1$}                 % git_diff_df7905d_2324b58.patch (store.py)145\providecommand{\SPIDdiffParserLines}{$+13/-7$}               % git_diff_0304133_2324b58.patch (filing_parser.py)146\providecommand{\SPIDlegacyTenKRows}{27{,}164}                % segmenters.json:legacy_rows147\providecommand{\SPIDlegacyTenKFilings}{7{,}368}              % segmenters.json:legacy_accessions148\providecommand{\SPIDlegacyShareTenKLedgerPct}{18.9}          % 27,164 / 143,704149\providecommand{\SPIDsegPairs}{25{,}673}                      % segmenters.json:legacy_rows_matched_by_item150\providecommand{\SPIDlegacyMdnaDollar}{141}                   % segmenter_item_comparison.csv md_and_a legacy_mean_dollar151\providecommand{\SPIDparsedMdnaDollar}{272}                   % parsed_mean_dollar152\providecommand{\SPIDlegacyMdnaWords}{9{,}921}                % legacy_median_words153\providecommand{\SPIDparsedMdnaWords}{11{,}661}               % parsed_median_words154\providecommand{\SPIDlegacyFewerMoneyPct}{92.3}               % pct_legacy_fewer_money_tokens155\providecommand{\SPIDlegacyMdnaNumeric}{596}                  % legacy_mean_numeric156\providecommand{\SPIDparsedMdnaNumeric}{1{,}177}              % parsed_mean_numeric157\providecommand{\SPIDpropertiesLtHalfPct}{19.4}               % properties pct_legacy_lt_half_words158\providecommand{\SPIDfullBodyMedianWords}{44{,}514}           % segmenters.json:full_body_rows[2]159\providecommand{\SPIDfullBodyYield}{0.67}                     % full_body_ledger_yield[3]160\providecommand{\SPIDfullBodyProductivePct}{25.7}             % full_body_ledger_yield[4]161\providecommand{\SPIDfullBodyWithParsedItems}{1{,}117}        % implemented_changes.md N4 (segmenters.json)162\providecommand{\SPIDfullBodyUnsubmittedSections}{5{,}385}    % implemented_changes.md N4 (segmenters.json)163\providecommand{\SPIDfullDocumentTenK}{86}                    % segmenters.json / funnel_10k.json164\providecommand{\SPIDfullDocumentTenKLegacy}{51}              % parsed_section_names_same_accessions full_document165\providecommand{\SPIDfullDocumentTenKInvisible}{35}           % 86 - 51166\providecommand{\SPIDfullDocumentTenQ}{243}                   % funnel_10k.json:parsed_10q_items full_document167\providecommand{\SPIDfullDocumentTenQLedgered}{241}           % funnel_10k.json:ledger_10q_items full_document168\providecommand{\SPIDtenKparsedRows}{341{,}207}               % funnel_10k.json:parsed_10k_rows_total169\providecommand{\SPIDtenKoutOfScopeRows}{188{,}518}           % parsed_10k_rows_out_of_scope_item170\providecommand{\SPIDtenKlegacyAccessionRows}{35{,}037}       % parsed_10k_in_scope_rows_of_legacy_accessions171\providecommand{\SPIDtenKunderThirtyRows}{1{,}112}            % parsed_10k_in_scope_rows_lt30_words_non_legacy172\providecommand{\SPIDtenKparsedLedgered}{116{,}540}           % parsed_10k_in_scope_rows_ge30_non_legacy173\providecommand{\SPIDwithinProductiveJune}{12.4}              % within_sp500_by_run_form.csv backfilled_june 10-Q productive_pct174\providecommand{\SPIDwithinProductiveOctober}{12.7}           % october 10-Q175\providecommand{\SPIDwithinMentionsPerRowJune}{0.244}         % mentions_per_row176\providecommand{\SPIDwithinMentionsPerRowOctober}{0.250}177\providecommand{\SPIDwithinConfJune}{0.889}                   % within_sp500_10q_mentions_by_run.csv mean_conf178\providecommand{\SPIDwithinConfOctober}{0.893}179\providecommand{\SPIDwithinMaShareJune}{49.9}                 % within_sp500_10q_type_mix_by_run.csv ma_integration180\providecommand{\SPIDwithinMaShareOctober}{45.7}181\providecommand{\SPIDpairedIssuers}{81}                       % within_issuer_paired_10q.json:issuers_paired182\providecommand{\SPIDpairedDeltaPp}{0.6}                      % mean_diff_productive_share_oct_minus_june (pp)183\providecommand{\SPIDpairedSePp}{1.3}                         % se (pp)184\providecommand{\SPIDcohortIssuersBoth}{491}                  % table6_cohort.csv both.issuers185\providecommand{\SPIDcohortIssuersRussellOnly}{1{,}992}       % russell_only.issuers186\providecommand{\SPIDcohortIssuersSpOnly}{9}                  % sp500_only.issuers187\providecommand{\SPIDcohortBothPerIssuerAll}{55.8}            % both.per_issuer_all188\providecommand{\SPIDcohortRussellOnlyPerIssuer}{46.9}        % russell_only.per_issuer_all189\providecommand{\SPIDcohortBothPerIssuerOctober}{25.1}        % both.per_issuer_october_only190\providecommand{\SPIDcohortOlsAll}{8.84}                      % table6_cohort_regression.json:projects_all_on_sp500.in_sp500.coef191\providecommand{\SPIDcohortOlsAllSe}{1.62}                    % hc1_se192\providecommand{\SPIDcohortOlsOctober}{-22.98}                % projects_october_only_on_sp500.in_sp500.coef193\providecommand{\SPIDcohortOlsOctoberSe}{1.20}194\providecommand{\SPIDcohortOlsControlled}{-0.28}              % projects_all_on_sp500_log_rows.in_sp500.coef195\providecommand{\SPIDcohortOlsControlledSe}{1.52}196\providecommand{\SPIDcohortOlsN}{2{,}499}                     % n197\providecommand{\SPIDfiscalYearNullMentions}{68{,}827}        % fiscal_year_audit.json198\providecommand{\SPIDfiscalYearNullOctTenK}{823}199\providecommand{\SPIDfiscalYearNullOctTenQ}{28{,}074}200\providecommand{\SPIDfiscalYearNullFilings}{134{,}124}        % src_filings_fiscal_year_null_by_form (sum)201\providecommand{\SPIDfiscalYearFillAccessions}{31{,}976}      % fiscal_year_fill_by_accession.csv rows202203% ---- focus windows (results/focus/stats_keys.json, focus_coverage_by_form_item.csv, shown_fraction_bins.csv, mdna_10k_short_by_year.csv; results/rules/focus_recall_loss*.csv) ----204\providecommand{\SPIDfocusOverBudgetSections}{326{,}095}      % stats_keys.json:ledger_sections_over_9000_chars205\providecommand{\SPIDfocusOverBudgetSectionsPct}{29}          % 326,095 / 1,123,098206\providecommand{\SPIDfocusOverBudgetCalls}{324{,}386}         % stats_keys.json:calls_over_9000_chars207\providecommand{\SPIDfocusOverBudgetCallsPct}{46}             % 324,386 / 703,725208\providecommand{\SPIDfocusMeanShownOverBudgetPct}{15.9}       % stats_keys.json:mean_shown_frac_over_budget209\providecommand{\SPIDmdnaN}{28{,}919}                         % stats_keys.json:ledger_10k_mdna_n210\providecommand{\SPIDmdnaMedianWords}{9{,}905}                % stats_keys.json:ledger_10k_mdna_median_words211\providecommand{\SPIDmdnaMedianChars}{64{,}194}               % ledger_10k_mdna_median_chars212\providecommand{\SPIDmdnaShownMedianPct}{9.3}                 % ledger_10k_mdna_shown_p50213\providecommand{\SPIDmdnaShownPTenPct}{4.3}                   % focus_coverage_by_form_item.csv 10-K md_and_a shown_p10214\providecommand{\SPIDmdnaShownPNinetyPct}{24}                 % shown_p90215\providecommand{\SPIDmdnaLastShownMedianPct}{16}              % ledger_10k_mdna_last_p50216\providecommand{\SPIDmdnaShownLtTwentyFivePct}{90.5}          % ledger_10k_mdna_pct_shown_lt_25217\providecommand{\SPIDmdnaHitsShownMedianPct}{15.6}            % hits_shown_p50218\providecommand{\SPIDbusinessShownMedianPct}{15.7}            % 10-K business shown_p50219\providecommand{\SPIDriskShownMedianPct}{10.1}                % 10-K risk_factors shown_p50220\providecommand{\SPIDtenQmdnaShownMedianPct}{13.2}            % 10-Q md_and_a shown_p50221\providecommand{\SPIDtenQfinShownMedianPct}{10.6}             % 10-Q financial_statements shown_p50222\providecommand{\SPIDeightKWholePct}{91}                      % 100 - 8-K pct_over_9000 (8.82)223\providecommand{\SPIDmsgTruncatedN}{0}                        % stats_keys.json:msg_truncated_14k224\providecommand{\SPIDmentionsFromLtTwentyFive}{193{,}416}     % stats_keys.json:mentions_from_sections_shown_lt_25225\providecommand{\SPIDmentionsFromLtTwentyFivePct}{62.7}       % / 308,477226\providecommand{\SPIDmentionsFromLtTwentyFiveTenK}{84}        % focus_coverage_by_form.csv 10-K pct_mentions_from_lt25227\providecommand{\SPIDmentionsFromLtTwentyFiveTenQ}{79}        % 10-Q228\providecommand{\SPIDmentionsFromLtTwentyFiveEightK}{6}       % 8-K (5.74)229\providecommand{\SPIDplateauLow}{0.4}                         % mentions_vs_length_by_item.csv 10-K md_and_a230\providecommand{\SPIDplateauHigh}{1.5}231\providecommand{\SPIDplateauRange}{1.2--1.6}232\providecommand{\SPIDplateauKchars}{20{,}000}233\providecommand{\SPIDmentionsPerTenKShownChars}{2.5}234\providecommand{\SPIDcapexVocabShownMdnaPct}{5.8}             % focus_coverage_by_form_item.csv pct_capex_vocab_shown_over_budget 10-K md_and_a235\providecommand{\SPIDcapexVocabShownBusinessPct}{10.0}236\providecommand{\SPIDcapexVocabShownTenQmdnaPct}{8.3}237\providecommand{\SPIDshortMdnaN}{169}                         % mdna_10k_short_by_year.csv sum(lt30_words)238\providecommand{\SPIDshortMdnaDenom}{29{,}088}                % sum(mdna_sections)239\providecommand{\SPIDshortMdnaPct}{0.6}240\providecommand{\SPIDshortMdnaIncorporatedN}{470}             % sum(lt300_incorporated_by_ref)241\providecommand{\SPIDrulesFocusRecovered}{84{,}841}           % focus_recall_loss_overall.csv rules_focused242\providecommand{\SPIDrulesFocusTotal}{324{,}237}              % rules_full243\providecommand{\SPIDrulesFocusRecoveredPct}{26.2}            % 100 - pct_lost244\providecommand{\SPIDrulesFocusMdnaPct}{20.8}                 % focus_recall_loss.csv 10-K md_and_a (100 - 79.18)245\providecommand{\SPIDrulesFocusBusinessPct}{36.9}             % 10-K business246\providecommand{\SPIDrulesFocusTenQmdnaPct}{25.1}             % 10-Q md_and_a247\providecommand{\SPIDrulesFocusEightKPct}{84.2}               % 8-K full_body248249% ---- rules baseline (results/rules/agreement_overall.csv, agreement_by_form.csv, agreement_by_run.csv, type_agreement.csv) ----250\providecommand{\SPIDrulesSampleProductive}{30{,}000}         % manifest.json notes.sample251\providecommand{\SPIDrulesSampleZero}{30{,}000}252\providecommand{\SPIDrulesGivenLlmPct}{85.7}                  % p_rules_given_llm253\providecommand{\SPIDrulesGivenLlmTenK}{97.4}254\providecommand{\SPIDrulesGivenLlmTenQ}{94.4}255\providecommand{\SPIDrulesGivenLlmEightK}{69.2}256\providecommand{\SPIDrulesGivenLlmJune}{79.8}257\providecommand{\SPIDrulesGivenLlmOctober}{86.7}258\providecommand{\SPIDllmGivenRulesPct}{32.5}                  % p_llm_given_rules_weighted259\providecommand{\SPIDrulesFlagPct}{39.5}                      % rules_pos_pct_weighted260\providecommand{\SPIDrulesAgreementPct}{71.2}                 % agreement_pct_w261\providecommand{\SPIDrulesLlmOnlyPct}{2.1}262\providecommand{\SPIDrulesOnlyPct}{26.6}263\providecommand{\SPIDrulesTypeOverlapPct}{84.6}               % type_overlap_pct_codetected264\providecommand{\SPIDrulesTypeMa}{96.8}                       % type_agreement.csv265\providecommand{\SPIDrulesTypeDrug}{92.5}266\providecommand{\SPIDrulesTypeCost}{76.9}267\providecommand{\SPIDrulesTypeCapex}{55.2}268\providecommand{\SPIDrulesTypePlant}{40.7}269\providecommand{\SPIDrulesTypeGeo}{36.5}270271% ---- financing / buy-back false-positive classes (results/fp_classes/summary.json, financing_regex_by_type.csv, _by_item.csv, _terms.csv, table5_restated_excl_financing.csv) ----272\providecommand{\SPIDfinMentions}{22{,}412}                   % summary.json:mentions_matched[0]273\providecommand{\SPIDfinMentionsPct}{7.3}                     % 7.28274\providecommand{\SPIDfinAmountB}{17.8}                        % matched_amount_gusd[0] / 1000275\providecommand{\SPIDfinAmountDenomB}{104.2}                  % matched_amount_gusd[1] / 1000276\providecommand{\SPIDfinUnregN}{5{,}179}                      % unregistered_sales_matched[0]277\providecommand{\SPIDfinUnregDenom}{9{,}506}278\providecommand{\SPIDfinUnregPct}{54.5}279\providecommand{\SPIDfinEightKPct}{19.2}                      % financing_regex_by_item.csv 8-K full_body280\providecommand{\SPIDfinFinStatementsPct}{2.4}                % 10-Q financial_statements281\providecommand{\SPIDfinControlsPct}{0.2}                     % 10-Q controls_and_procedures282\providecommand{\SPIDfinCapexPct}{52.6}                       % financing_regex_by_type.csv capex_program283\providecommand{\SPIDfinCostPct}{16.4}                        % cost_reduction284\providecommand{\SPIDfinMaPct}{7.0}                           % ma_integration285\providecommand{\SPIDcapexProjectsExcl}{4{,}725}              % table5_restated_excl_financing.csv capex_program286\providecommand{\SPIDcapexShareExcl}{4.3}287\providecommand{\SPIDcostProjectsExcl}{5{,}403}288\providecommand{\SPIDmaProjectsExcl}{37{,}527}289\providecommand{\SPIDfinProjectsRep}{12{,}027}                % summary.json:projects_matched_rep[0]290\providecommand{\SPIDfinProjectsRepPct}{9.9}291\providecommand{\SPIDfinProjectsAny}{13{,}139}                % projects_matched_rep[1]292\providecommand{\SPIDitemTwoPairs}{77{,}869}                  % summary.json:item2_collision pairs293\providecommand{\SPIDunregMedianWords}{602}294\providecommand{\SPIDtenQmdnaMedianWords}{7{,}573}295\providecommand{\SPIDunregGtThreeK}{1{,}001}296\providecommand{\SPIDunregGtThreeKPct}{1.3}297\providecommand{\SPIDswapCandidates}{296}298\providecommand{\SPIDunregGtThreeKMentions}{425}299\providecommand{\SPIDfinTermRepurchase}{10{,}886}             % financing_regex_terms.csv300\providecommand{\SPIDfinTermSeniorNotes}{3{,}375}301\providecommand{\SPIDfinTermTermLoan}{2{,}263}302303% ---- 8-K item-code consistency (results/benchmark_8k/summary.json, item_vs_type.csv scope=all_8k_sections) ----304\providecommand{\SPIDeightKItemCodePct}{99.7}                 % summary.json:coverage_pct 99.74305\providecommand{\SPIDbenchMaGivenTwoOhOne}{0.911}             % p_type_given_item ma_integration | Item 2.01306\providecommand{\SPIDbenchMaGivenTwoOhOneCiLow}{0.903}307\providecommand{\SPIDbenchMaGivenTwoOhOneCiHigh}{0.918}308\providecommand{\SPIDbenchTwoOhOneN}{5{,}456}                 % n_item309\providecommand{\SPIDbenchMaGivenEightOhOne}{0.199}           % Item 8.01 (control)310\providecommand{\SPIDbenchMaGivenFiveOhTwo}{0.031}            % Item 5.02 (control)311\providecommand{\SPIDbenchMaBase}{0.095}                      % base_rate_type312\providecommand{\SPIDbenchItemsGivenMa}{0.467}                % p_item_given_type, Item 2.01 or 1.01313\providecommand{\SPIDbenchCostGivenTwoOhFive}{0.709}          % cost_reduction | Item 2.05314\providecommand{\SPIDbenchCostGivenTwoOhFiveCiLow}{0.687}315\providecommand{\SPIDbenchCostGivenTwoOhFiveCiHigh}{0.730}316\providecommand{\SPIDbenchTwoOhFiveN}{1{,}700}317\providecommand{\SPIDbenchCostLift}{92}                       % lift_type_given_item 92.05318\providecommand{\SPIDbenchTwoOhFiveGivenCost}{0.392}319\providecommand{\SPIDbenchPartnershipGivenOneOhOne}{0.040}320\providecommand{\SPIDbenchPartnershipBase}{0.011}321322% ---- annotation frame (results/annotation_frame/design.json) ----323\providecommand{\SPIDannSeed}{20261105}324\providecommand{\SPIDannStrata}{192}325\providecommand{\SPIDannNProductive}{1{,}677}326\providecommand{\SPIDannNZero}{385}327\providecommand{\SPIDannZeroGatePass}{285}328\providecommand{\SPIDannZeroGateReject}{100}329\providecommand{\SPIDannCore}{510}330\providecommand{\SPIDannDev}{1{,}058}331\providecommand{\SPIDannHoldout}{1{,}004}332\providecommand{\SPIDannDeffProductive}{3.4}333\providecommand{\SPIDannDeffZero}{1.2}334\providecommand{\SPIDannHalfWidthPrecision}{4.4}              % half_width_95_precision_p0.5 (pp)335\providecommand{\SPIDannHalfWidthFn}{2.4}                     % half_width_95_zero_fn_rate 0.05 (pp)336\providecommand{\SPIDannMde}{7.8}                             % mde_gate_recall_diff_at_p0.05 (pp)337\providecommand{\SPIDannFloor}{10}338\providecommand{\SPIDannOversample}{2}339\providecommand{\SPIDannPopProductive}{168{,}230}340\providecommand{\SPIDannPopZero}{954{,}868}341342% ---- time series (results/timeseries/summary.json, first_seen_fixed_cohort.csv) ----343\providecommand{\SPIDfirstSeenLastYear}{6{,}694}              % all_issuers 2026 first_seen_current_key344\providecommand{\SPIDfixedCohortIssuers}{1{,}389}             % summary.json:cohort_issuers345\providecommand{\SPIDfixedCohortMentionsPerIssuerFirst}{9.6}  % 2011346\providecommand{\SPIDfixedCohortMentionsPerIssuerLast}{8.8}   % 2025 (8.75)347\providecommand{\SPIDfixedCohortNewPerIssuerFirst}{4.7}       % 2011348\providecommand{\SPIDfixedCohortNewPerIssuerLast}{2.8}        % 2025 (2.83)349\providecommand{\SPIDfixedCohortFirstSeenFirst}{6{,}533}      % 2011350\providecommand{\SPIDfixedCohortFirstSeenLast}{3{,}926}       % 2025351\providecommand{\SPIDepisodesKthree}{131{,}823}               % summary.json:episodes_k3_total352\providecommand{\SPIDepisodesKfive}{126{,}318}353354% ---- universe and corpus artefacts (results/universe/universe_artefacts.json, results/russell_coverage.json, data/stats.json) ----355\providecommand{\SPIDdualClassCiks}{18}                       % 2,573 - 2,555356\providecommand{\SPIDuniverseBoth}{491}                       % implemented_changes.md N10 (universe.json)357\providecommand{\SPIDuniverseSpOnly}{9}358\providecommand{\SPIDuniverseRuOnly}{2{,}064}359\providecommand{\SPIDparseErrors}{14}                         % filings_status_missing.csv parse_status = error360\providecommand{\SPIDannualPanelFirms}{2{,}499}               % stats.json:annual_panel_firms361\providecommand{\SPIDrussellGapMax}{441}                      % 2,996 - 2,555362\providecommand{\SPIDrussellGapMaxPct}{14.7}363\providecommand{\SPIDfactsheetDate}{September~30, 2026}       % russell_coverage.json:index_as_of364\providecommand{\SPIDiwvHoldingsDate}{October~23, 2026}       % stats.json:universe.russell_holdings_as_of365\providecommand{\SPIDiwvFetchDate}{October~27, 2026}          % universe_artefacts.json:russell_scalars.fetched_at366\providecommand{\SPIDiwvPageDate}{November~4, 2026}           % russell_coverage.json:fund_holdings_as_of367\providecommand{\SPIDiwvProspectusDate}{July~31, 2026}        % russell_coverage.json:replication_source_title368\providecommand{\SPIDuniverseJsonSha}{3967b29b}               % universe_artefacts.json sha256 prefix369\providecommand{\SPIDrussellJsonSha}{758cbebf}370\providecommand{\SPIDspJsonSha}{50840752}371\providecommand{\SPIDfactsheetSha}{281e9264}                  % russell_coverage.json:source_sha256 prefix372\providecommand{\SPIDmethodologySha}{26d2d051}                % methodology_document.sha256 prefix373\providecommand{\SPIDissuersWithoutFilings}{65}               % stats.json / Table 1374\providecommand{\SPIDissuersFilingsNoProject}{7}              % 2,499 - 2,492375\providecommand{\SPIDspWikipediaRows}{503}                    % universe_artefacts.json:sp500_scalars.count376\providecommand{\SPIDspWikipediaDate}{May~25, 2026}           % sp500_scalars.fetched_at377\providecommand{\SPIDtickerMapSize}{10{,}430}                 % cik_mapping_scalars.count378379% ---- run facts quoted in the text (docs/research_log.md, environment.md, reproducibility) ----380\providecommand{\SPIDtotalCostUsd}{775}                       % research_log.md 2026-10-27/28 (author-reported total)381\providecommand{\SPIDworkers}{48}                             % log_summary.json:october.workers_values382\providecommand{\SPIDrequirementsLockPackages}{88}            % requirements.lock (N12)383\providecommand{\SPIDpythonVersion}{3.12.15}                  % .python-version (N12)384\providecommand{\SPIDduckdbVersion}{2.0.0}                    % environment.md (N12)385\providecommand{\SPIDreferencesN}{42}                         % references.bib entries (L4)386\providecommand{\SPIDdoiVerifiedN}{36}                        % L4: DOIs re-resolved 2026-11-05387\providecommand{\SPIDtestsN}{22}                              % tests/test_tables.py (L6)388\providecommand{\SPIDsnapshotFilesN}{nine}                    % code/audit/spid_snapshot/SHA256SUMS389\providecommand{\SPIDjuneRunDate}{June~18, 2026}              % log_summary.json:june.first/last390\providecommand{\SPIDbackfillTimestamp}{October~27, 2026, 13:12}  % backfill_block.json:min_extracted_at391392% ---- added for Sections 3-4 (data.tex, methodology.tex) ----393\providecommand{\SPIDissuersFilingFirstYear}{1{,}392}        % results/timeseries/first_seen_fixed_cohort.csv all_issuers 2010 issuers_filing394\providecommand{\SPIDissuersFilingLastYear}{2{,}498}         % all_issuers 2026 issuers_filing395\providecommand{\SPIDfilingsNotParsedPct}{0.003}             % 16 / 527,548396\providecommand{\SPIDcorpusDbGb}{68}                         % results/*/manifest.json edgar_research.duckdb 73,500,995,584 B (= 68.5 GiB)397\providecommand{\SPIDspidDbGb}{3.2}                          % spid.duckdb 3,155,701,760 B398\providecommand{\SPIDcorpusParquetGb}{29.1}                  % results/n0_probe (N0): parquet 1,342,283 sections / 29.1 GB399\providecommand{\SPIDacqNewDocs}{about 400{,}000}            % author-reported run fact (docs/research_log.md 2026-10-27); orchestrator log not archived with the paper400\providecommand{\SPIDacqHours}{seven}                        % author-reported run fact; not archived401\providecommand{\SPIDacqReqPerSec}{17}                       % author-reported run fact; not archived402\providecommand{\SPIDacqNodes}{ten}                          % docs/research_log.md 2026-10-27 (10 cluster nodes + 1 external gateway)403\providecommand{\SPIDacqNodeRate}{0.9}                       % author-reported (requests per second per node)404\providecommand{\SPIDacqGatewayRate}{one}                    % author-reported (requests per second per shard on the gateway)405\providecommand{\SPIDacqGatewayDivisor}{nine}                % author-reported (requests per second shared behind one IP)406\providecommand{\SPIDparseFilingsPerSec}{100}                % author-reported run fact; not archived407\providecommand{\SPIDparseMinutesRange}{five to thirteen}    % author-reported run fact; not archived408\providecommand{\SPIDembedMinutesRange}{15--40}              % author-reported run fact; not archived409\providecommand{\SPIDmergeMinutes}{seven}                    % author-reported run fact; not archived410\providecommand{\SPIDworkersJune}{16}                        % results/ledger/log_summary.json:june.ciks_total_lines (workers=16)411\providecommand{\SPIDjuneBatchSize}{15}                      % log_summary.json:june (batch=15)412\providecommand{\SPIDoctoberBatchSize}{20}                   % log_summary.json:october.batch_values413\providecommand{\SPIDfocusWindowBefore}{220}                 % code/audit/spid_snapshot/llm.py _focus (characters before a gate hit)414\providecommand{\SPIDfocusWindowAfter}{380}                  % llm.py _focus (characters after a gate hit)415\providecommand{\SPIDfocusCollectBudget}{12{,}600}           % llm.py _focus (collection stop)416\providecommand{\SPIDfocusEmitBudget}{9{,}000}               % llm.py _focus (emitted budget)417\providecommand{\SPIDuserMessageCap}{14{,}000}               % llm.py:126 user message cut418\providecommand{\SPIDminWords}{30}                           % config.py / pipeline.py minimum section length419\providecommand{\SPIDconfThreshold}{0.45}                    % llm.py confidence threshold420\providecommand{\SPIDconfDefault}{0.6}                       % llm.py:142-146 default when confidence is missing or non-numeric421\providecommand{\SPIDcompletionTokens}{2{,}000}              % llm.py completion limit422\providecommand{\SPIDlistItemsMax}{eight}                    % llm.py list truncation423\providecommand{\SPIDlistItemChars}{120}                     % llm.py list item truncation424\providecommand{\SPIDidNameChars}{40}                        % llm.py:141 anchor = type + name[:40]425\providecommand{\SPIDretries}{three}                         % llm.py:119-120 retries before returning an empty list426\providecommand{\SPIDtimeoutSeconds}{120}                    % llm.py call timeout427\providecommand{\SPIDtenKsectionsMax}{fourteen}              % src/parsing/section_extractor.py (Items 1 to 9B)428\providecommand{\SPIDtenQsectionsN}{seven}                   % src/parsing/section_extractor.py429\providecommand{\SPIDchunkWords}{512}                        % src/parsing/chunker.py430\providecommand{\SPIDchunkOverlap}{64}                       % src/parsing/chunker.py431\providecommand{\SPIDmaxFileMb}{50}                          % src/parsing/html_parser.py432\providecommand{\SPIDembeddingDim}{384}                      % MiniLM embedding dimension (scripts/build_embeddings.py)433\providecommand{\SPIDsecRateLimit}{ten}                      % secfairaccess (requests per second)434\providecommand{\SPIDcooldownSeconds}{65}                    % src/acquisition/bulk_downloader.py435\providecommand{\SPIDfactorAnchors}{8}                       % scripts/build_factors.py (thematic anchors)436\providecommand{\SPIDembeddingsRows}{10{,}720{,}890}         % stats.json chunks437\providecommand{\SPIDannualPanelRows}{32{,}852}              % data/factor_tables.csv annual_panel rows438\providecommand{\SPIDquarterlyPanelRows}{128{,}043}          % data/factor_tables.csv quarterly_panel rows439440% ---- added for Sections 5-7 (construct.tex, resolution.tex, results.tex) ----441\providecommand{\SPIDgateRejectedPct}{37.3}                  % 419,361 / 1,123,098 (results/ledger/gate_pass_totals.json)442\providecommand{\SPIDusdPerOctoberRow}{0.0008}               % gate_pass_totals.json:usd_per_october_row_paper_total_775443\providecommand{\SPIDjsonFailBeforeOutage}{nine}             % log_summary.json:october.outside_window_list (json_decode_error before 01:10)444\providecommand{\SPIDjsonFailAfterOutage}{five}              % after 06:22445\providecommand{\SPIDmentionsKeyedLocationPct}{38.6}         % 118,783 / 308,065446\providecommand{\SPIDmentionsPerProject}{2.54}               % 308,065 / 121,099 (data/projects_by_type.csv mean)447\providecommand{\SPIDmentionsPerProjectDrug}{4.99}           % data/projects_by_type.csv drug_pipeline mean_mentions448\providecommand{\SPIDmentionsPerProjectTechDeploy}{1.63}     % technology_deployment mean_mentions449\providecommand{\SPIDtwoMentionShare}{17.0}                  % data/mentions_per_project.csv bucket 2 (20,544 / 121,099)450\providecommand{\SPIDoverFiveMentionShare}{8.2}              % data/mentions_per_project.csv buckets > 5451\providecommand{\SPIDprojectsPerIssuerMax}{240}              % data/projects_per_issuer.csv mx452\providecommand{\SPIDamountPTwentyFiveMusd}{23}              % data/amount_dist.csv q[1]453\providecommand{\SPIDkgEdgesOwns}{121{,}099}                 % data/kg.csv454\providecommand{\SPIDkgEdgesLocatedIn}{54{,}583}455\providecommand{\SPIDkgEdgesUses}{28{,}774}456\providecommand{\SPIDspanZeroN}{67{,}170}                    % data/duration.csv span 0457\providecommand{\SPIDconfShareHalf}{0.5}                     % data/confidence_dist.csv 1,611 / 308,065458\providecommand{\SPIDfinAmountSharePct}{17.1}                % 17.8 / 104.2 (results/fp_classes/summary.json)459
Files · 19ae77cf2e6d7ffbc1210fed09176349c410d28e
Menu

Theme