SPB Git

Repository Public Research preview

corpus_counts.json 14.1 KB 765 lines json

1{2 "targets": {3  "chunks": 10720890,4  "sections": 1342283,5  "filings": 5275486 },7 "filings_total": 527548,8 "filings_distinct_accession": 527548,9 "issuers_cik": 2499,10 "issuers_ticker": 2501,11 "companies_rows": 2564,12 "filings_by_form": [13  {14   "form_type": "10-K",15   "n": 31775,16   "issuers": 2468,17   "parsed": 31772.0,18   "dmin": "2010-01-08",19   "dmax": "2026-10-27"20  },21  {22   "form_type": "10-Q",23   "n": 95167,24   "issuers": 2494,25   "parsed": 95155.0,26   "dmin": "2010-01-05",27   "dmax": "2026-10-27"28  },29  {30   "form_type": "8-K",31   "n": 400606,32   "issuers": 2499,33   "parsed": 400605.0,34   "dmin": "2010-01-04",35   "dmax": "2026-10-27"36  }37 ],38 "parse_status": [39  {40   "form_type": "10-K",41   "parse_status": "complete",42   "n": 3177243  },44  {45   "form_type": "10-K",46   "parse_status": "error",47   "n": 248  },49  {50   "form_type": "10-K",51   "parse_status": "missing",52   "n": 153  },54  {55   "form_type": "10-Q",56   "parse_status": "complete",57   "n": 9515558  },59  {60   "form_type": "10-Q",61   "parse_status": "error",62   "n": 1163  },64  {65   "form_type": "10-Q",66   "parse_status": "missing",67   "n": 168  },69  {70   "form_type": "8-K",71   "parse_status": "complete",72   "n": 40060573  },74  {75   "form_type": "8-K",76   "parse_status": "error",77   "n": 178  }79 ],80 "download_status": [81  {82   "download_status": "complete",83   "n": 52754884  }85 ],86 "sections_total": 1342283,87 "sections_distinct_id": 1342283,88 "sections_filings_with_section": 527532,89 "sections_by_form_name": [90  {91   "form_type": "10-K",92   "section_name": "business",93   "n": 30738,94   "med_words": 5346.0,95   "mean_words": 6975.906337432494,96   "words": 214425409.097  },98  {99   "form_type": "10-K",100   "section_name": "changes_in_accounting",101   "n": 12628,102   "med_words": 2841.5,103   "mean_words": 8412.70066518847,104   "words": 106235584.0105  },106  {107   "form_type": "10-K",108   "section_name": "controls_and_procedures",109   "n": 30917,110   "med_words": 597.0,111   "mean_words": 1042.0516867742665,112   "words": 32217112.0113  },114  {115   "form_type": "10-K",116   "section_name": "financial_statements",117   "n": 30096,118   "med_words": 16451.5,119   "mean_words": 15643.91812865497,120   "words": 470819360.0121  },122  {123   "form_type": "10-K",124   "section_name": "full_document",125   "n": 86,126   "med_words": 72520.5,127   "mean_words": 89592.12790697675,128   "words": 7704923.0129  },130  {131   "form_type": "10-K",132   "section_name": "legal_proceedings",133   "n": 29051,134   "med_words": 84.0,135   "mean_words": 340.8722591304946,136   "words": 9902680.0137  },138  {139   "form_type": "10-K",140   "section_name": "market_for_equity",141   "n": 31094,142   "med_words": 568.0,143   "mean_words": 733.467389206921,144   "words": 22806435.0145  },146  {147   "form_type": "10-K",148   "section_name": "md_and_a",149   "n": 31000,150   "med_words": 10138.0,151   "mean_words": 11266.152322580645,152   "words": 349250722.0153  },154  {155   "form_type": "10-K",156   "section_name": "mine_safety",157   "n": 6240,158   "med_words": 532.5,159   "mean_words": 755.2865384615385,160   "words": 4712988.0161  },162  {163   "form_type": "10-K",164   "section_name": "other_information",165   "n": 26506,166   "med_words": 2731.0,167   "mean_words": 8393.148079680072,168   "words": 222468783.0169  },170  {171   "form_type": "10-K",172   "section_name": "properties",173   "n": 30241,174   "med_words": 200.0,175   "mean_words": 584.5251149102212,176   "words": 17676624.0177  },178  {179   "form_type": "10-K",180   "section_name": "quantitative_disclosures",181   "n": 30025,182   "med_words": 502.0,183   "mean_words": 1555.9927060782682,184   "words": 46718681.0185  },186  {187   "form_type": "10-K",188   "section_name": "risk_factors",189   "n": 30685,190   "med_words": 9353.0,191   "mean_words": 11558.247482483299,192   "words": 354664824.0193  },194  {195   "form_type": "10-K",196   "section_name": "selected_financial_data",197   "n": 19509,198   "med_words": 524.0,199   "mean_words": 1640.0496693833616,200   "words": 31995729.0201  },202  {203   "form_type": "10-K",204   "section_name": "unresolved_staff_comments",205   "n": 2391,206   "med_words": 53.0,207   "mean_words": 1082.4550397323296,208   "words": 2588150.0209  },210  {211   "form_type": "10-Q",212   "section_name": "controls_and_procedures",213   "n": 92520,214   "med_words": 253.0,215   "mean_words": 537.4949200172936,216   "words": 49729030.0217  },218  {219   "form_type": "10-Q",220   "section_name": "financial_statements",221   "n": 92025,222   "med_words": 10060.0,223   "mean_words": 11470.74547133931,224   "words": 1055595352.0225  },226  {227   "form_type": "10-Q",228   "section_name": "full_document",229   "n": 243,230   "med_words": 49797.0,231   "mean_words": 54927.83950617284,232   "words": 13347465.0233  },234  {235   "form_type": "10-Q",236   "section_name": "legal_proceedings",237   "n": 76253,238   "med_words": 69.0,239   "mean_words": 293.8554679815876,240   "words": 22407361.0241  },242  {243   "form_type": "10-Q",244   "section_name": "md_and_a",245   "n": 91624,246   "med_words": 7392.0,247   "mean_words": 8633.759593556273,248   "words": 791059589.0249  },250  {251   "form_type": "10-Q",252   "section_name": "quantitative_disclosures",253   "n": 87110,254   "med_words": 213.0,255   "mean_words": 418.6373665480427,256   "words": 36467501.0257  },258  {259   "form_type": "10-Q",260   "section_name": "risk_factors",261   "n": 80445,262   "med_words": 117.0,263   "mean_words": 3330.6629747032134,264   "words": 267935183.0265  },266  {267   "form_type": "10-Q",268   "section_name": "unregistered_sales",269   "n": 80251,270   "med_words": 602.0,271   "mean_words": 886.5637686757798,272   "words": 71147629.0273  },274  {275   "form_type": "8-K",276   "section_name": "full_body",277   "n": 400605,278   "med_words": 575.0,279   "mean_words": 769.3125472722508,280   "words": 308190453.0281  }282 ],283 "sections_words_total": 4510067567,284 "sections_orphan_no_filing": 0,285 "chunks_total": 10720890,286 "chunks_distinct_id": 10720890,287 "chunks_filings": 527531,288 "chunks_null_section": 0,289 "chunks_orphan_no_section": 0,290 "chunk_word_count": {291  "n": 10720890.0,292  "mn": 1.0,293  "p05": 197.0,294  "p25": 512.0,295  "med": 512.0,296  "mean": 479.6619028830629,297  "p75": 512.0,298  "p95": 512.0,299  "mx": 18498.0,300  "share_eq512": 0.8420088257598016,301  "share_gt512": 0.003957040880001567,302  "share_lt512": 0.15403413336019678,303  "mean_chars": 3091.1050013571635,304  "med_chars": 3280.0,305  "words": 5142402498.0306 },307 "chunks_per_filing": [308  {309   "form_type": "10-K",310   "filings": 31772,311   "mean_chunks": 137.86019136346468,312   "med_chunks": 131.0,313   "mn": 1,314   "mx": 982,315   "chunks": 4380094.0316  },317  {318   "form_type": "10-Q",319   "filings": 95155,320   "mean_chunks": 57.723461720351004,321   "med_chunks": 50.0,322   "mn": 1,323   "mx": 532,324   "chunks": 5492676.0325  },326  {327   "form_type": "8-K",328   "filings": 400604,329   "mean_chunks": 2.1171031742069477,330   "med_chunks": 2.0,331   "mn": 1,332   "mx": 541,333   "chunks": 848120.0334  }335 ],336 "chunks_by_form": [337  {338   "form_type": "10-K",339   "chunks": 4380094,340   "filings": 31772,341   "words": 2152676772.0342  },343  {344   "form_type": "10-Q",345   "chunks": 5492676,346   "filings": 95155,347   "words": 2642064535.0348  },349  {350   "form_type": "8-K",351   "chunks": 848120,352   "filings": 400604,353   "words": 347661191.0354  }355 ],356 "chunks_by_year": [357  {358   "year": 2010,359   "chunks": 394127,360   "filings": 23181361  },362  {363   "year": 2011,364   "chunks": 421290,365   "filings": 24202366  },367  {368   "year": 2012,369   "chunks": 442965,370   "filings": 25235371  },372  {373   "year": 2013,374   "chunks": 469360,375   "filings": 25786376  },377  {378   "year": 2014,379   "chunks": 501935,380   "filings": 27255381  },382  {383   "year": 2015,384   "chunks": 534891,385   "filings": 28695386  },387  {388   "year": 2016,389   "chunks": 560511,390   "filings": 29282391  },392  {393   "year": 2017,394   "chunks": 592519,395   "filings": 29997396  },397  {398   "year": 2018,399   "chunks": 642769,400   "filings": 31115401  },402  {403   "year": 2019,404   "chunks": 679706,405   "filings": 31987406  },407  {408   "year": 2020,409   "chunks": 751203,410   "filings": 35503411  },412  {413   "year": 2021,414   "chunks": 798035,415   "filings": 36666416  },417  {418   "year": 2022,419   "chunks": 814289,420   "filings": 35619421  },422  {423   "year": 2023,424   "chunks": 813309,425   "filings": 36083426  },427  {428   "year": 2024,429   "chunks": 792466,430   "filings": 36871431  },432  {433   "year": 2025,434   "chunks": 829198,435   "filings": 38422436  },437  {438   "year": 2026,439   "chunks": 682317,440   "filings": 31632441  }442 ],443 "chunk_scores_total": 10720890,444 "chunk_scores_by_form": [445  {446   "form_type": "10-K",447   "n": 4380094,448   "filings": 31772,449   "issuers": 2468450  },451  {452   "form_type": "10-Q",453   "n": 5492676,454   "filings": 95155,455   "issuers": 2494456  },457  {458   "form_type": "8-K",459   "n": 848120,460   "filings": 400604,461   "issuers": 2499462  }463 ],464 "chunk_scores_by_section": [465  {466   "form_type": "10-K",467   "section_name": "business",468   "n": 489791,469   "mean_adopt": 0.12368709554513263,470   "mean_infra": 0.08599793253854457471  },472  {473   "form_type": "10-K",474   "section_name": "changes_in_accounting",475   "n": 242308,476   "mean_adopt": 0.07968649244536928,477   "mean_infra": 0.051765400592117115478  },479  {480   "form_type": "10-K",481   "section_name": "controls_and_procedures",482   "n": 83404,483   "mean_adopt": 0.07301698636742508,484   "mean_infra": -0.032470850736706844485  },486  {487   "form_type": "10-K",488   "section_name": "financial_statements",489   "n": 1066434,490   "mean_adopt": 0.06954534036513288,491   "mean_infra": 0.06329838411741626492  },493  {494   "form_type": "10-K",495   "section_name": "full_document",496   "n": 17233,497   "mean_adopt": 0.08201288691293951,498   "mean_infra": 0.07178964389691253499  },500  {501   "form_type": "10-K",502   "section_name": "legal_proceedings",503   "n": 42449,504   "mean_adopt": 0.06779023665847575,505   "mean_infra": 0.03542287793507819506  },507  {508   "form_type": "10-K",509   "section_name": "market_for_equity",510   "n": 62108,511   "mean_adopt": 0.05147512931310972,512   "mean_infra": 0.05011089547913074513  },514  {515   "form_type": "10-K",516   "section_name": "md_and_a",517   "n": 791442,518   "mean_adopt": 0.09247743881212221,519   "mean_infra": 0.08983561456945592520  },521  {522   "form_type": "10-K",523   "section_name": "mine_safety",524   "n": 13525,525   "mean_adopt": 0.12917606499746725,526   "mean_infra": 0.04712945714689471527  },528  {529   "form_type": "10-K",530   "section_name": "other_information",531   "n": 508501,532   "mean_adopt": 0.07491645444015085,533   "mean_infra": 0.04711681337199872534  },535  {536   "form_type": "10-K",537   "section_name": "properties",538   "n": 55917,539   "mean_adopt": 0.11838388677203159,540   "mean_infra": 0.11029761023599514541  },542  {543   "form_type": "10-K",544   "section_name": "quantitative_disclosures",545   "n": 117727,546   "mean_adopt": 0.06632884976276136,547   "mean_infra": 0.05060997765769921548  },549  {550   "form_type": "10-K",551   "section_name": "risk_factors",552   "n": 802770,553   "mean_adopt": 0.11045867079129247,554   "mean_infra": 0.07599452447636197555  },556  {557   "form_type": "10-K",558   "section_name": "selected_financial_data",559   "n": 79063,560   "mean_adopt": 0.09641463910141433,561   "mean_infra": 0.07861255831137565562  },563  {564   "form_type": "10-K",565   "section_name": "unresolved_staff_comments",566   "n": 7422,567   "mean_adopt": 0.10291811815281066,568   "mean_infra": 0.06505893812945229569  },570  {571   "form_type": "10-Q",572   "section_name": "controls_and_procedures",573   "n": 152080,574   "mean_adopt": 0.061414188567595875,575   "mean_infra": -0.025818235090903544576  },577  {578   "form_type": "10-Q",579   "section_name": "financial_statements",580   "n": 2416864,581   "mean_adopt": 0.07520625547114947,582   "mean_infra": 0.06836083244324583  },584  {585   "form_type": "10-Q",586   "section_name": "full_document",587   "n": 29877,588   "mean_adopt": 0.07537414329879337,589   "mean_infra": 0.07610664376619439590  },591  {592   "form_type": "10-Q",593   "section_name": "legal_proceedings",594   "n": 105238,595   "mean_adopt": 0.07280548647526451,596   "mean_infra": 0.03655486306949872597  },598  {599   "form_type": "10-Q",600   "section_name": "md_and_a",601   "n": 1818702,602   "mean_adopt": 0.10134849380215029,603   "mean_infra": 0.09288822326471928604  },605  {606   "form_type": "10-Q",607   "section_name": "quantitative_disclosures",608   "n": 131488,609   "mean_adopt": 0.06631231685052688,610   "mean_infra": 0.03276769384453286611  },612  {613   "form_type": "10-Q",614   "section_name": "risk_factors",615   "n": 650290,616   "mean_adopt": 0.11807213023775247,617   "mean_infra": 0.07999691672280011618  },619  {620   "form_type": "10-Q",621   "section_name": "unregistered_sales",622   "n": 188137,623   "mean_adopt": 0.061328818041107735,624   "mean_infra": 0.027080230087483597625  },626  {627   "form_type": "8-K",628   "section_name": "full_body",629   "n": 848120,630   "mean_adopt": 0.044406480044369166,631   "mean_infra": -0.01476883249606206632  }633 ],634 "chunks_without_score": 0,635 "scores_without_chunk": 0,636 "embeddings_total": 10721045,637 "embeddings_files": 1175,638 "embeddings_rows_per_file": {639  "min": 9,640  "max": 50000,641  "mean": 9124.293617021276642 },643 "embeddings_by_model": [644  {645   "model_name": "all-MiniLM-L6-v2",646   "n": 10721045647  }648 ],649 "filing_scores_total": 527531,650 "filing_scores_by_form": [651  {652   "form_type": "10-K",653   "n": 31772,654   "chunks": 4380094.0655  },656  {657   "form_type": "10-Q",658   "n": 95155,659   "chunks": 5492676.0660  },661  {662   "form_type": "8-K",663   "n": 400604,664   "chunks": 848120.0665  }666 ],667 "annual_final_rows": 32870,668 "annual_final_years": [669  {670   "fiscal_year": 2010,671   "n": 1393,672   "ciks": 1392673  },674  {675   "fiscal_year": 2011,676   "n": 1425,677   "ciks": 1424678  },679  {680   "fiscal_year": 2012,681   "n": 1473,682   "ciks": 1472683  },684  {685   "fiscal_year": 2013,686   "n": 1540,687   "ciks": 1539688  },689  {690   "fiscal_year": 2014,691   "n": 1620,692   "ciks": 1619693  },694  {695   "fiscal_year": 2015,696   "n": 1690,697   "ciks": 1689698  },699  {700   "fiscal_year": 2016,701   "n": 1745,702   "ciks": 1744703  },704  {705   "fiscal_year": 2017,706   "n": 1811,707   "ciks": 1810708  },709  {710   "fiscal_year": 2018,711   "n": 1894,712   "ciks": 1893713  },714  {715   "fiscal_year": 2019,716   "n": 1974,717   "ciks": 1973718  },719  {720   "fiscal_year": 2020,721   "n": 2090,722   "ciks": 2089723  },724  {725   "fiscal_year": 2021,726   "n": 2248,727   "ciks": 2247728  },729  {730   "fiscal_year": 2022,731   "n": 2292,732   "ciks": 2291733  },734  {735   "fiscal_year": 2023,736   "n": 2330,737   "ciks": 2329738  },739  {740   "fiscal_year": 2024,741   "n": 2388,742   "ciks": 2387743  },744  {745   "fiscal_year": 2025,746   "n": 2454,747   "ciks": 2453748  },749  {750   "fiscal_year": 2026,751   "n": 2503,752   "ciks": 2498753  }754 ],755 "acceptance": {756  "chunks_match": true,757  "chunks_diff": 0,758  "sections_match": true,759  "sections_diff": 0,760  "filings_match": true,761  "filings_diff": 0,762  "embeddings_vs_chunks_diff": 155,763  "chunk_scores_vs_chunks_diff": 0764 }765}
Files main
Menu

Theme