securities heuristics statistics
corpus statistics · doj sdny + sec pr + sec litreleases
landing
docs 33,801
bytes 10107.9MB
triples 518,884
entities 114,589
ocr pending 12
corp-fraud docs 39,331
DB — FS —

enrichment coverage outcomes · courts · entity-kinds — top values populated across the corpus

outcomes settled 7,536 pleaded 3,207 charged 2,701 convicted 1,530 indicted 468 sentenced 331 dismissed 19 acquitted 8
courts SDNY 9,790 CDCA 1,365 SDFL 1,336 DC 1,169 DMA 1,083 EDNY 829 NDCA 799 NDIL 722 DNJ 612 NDTX 583
entity kinds person 52,255 company 27,153 organization 16,857 agency 9,578 scheme_term 5,547 location 1,829 court 976 unknown 394

enrichment coverage per-workflow populated / progress / done / skipped / pending / running / errored — live from workflow_runs + documents

fieldworkflowpopulated%progressdoneskippedpendingrunningerrored
Statute refsstatute-refs24,13271.4%100.0%20,21113,590000
Court / jurisdictioncourt-jurisdiction24,28771.9%100.0%18,09115,710000
Keywordskeywords-extract33,71999.8%100.0%33,701100000
Outcomeoutcome-detect15,80046.7%100.0%15,77418,027000
Money classesmoney-classify19,84358.7%100.0%19,79114,010000
Title formattedformat-title33,801100.0%100.0%33,6980000
Title LLMtitle-llm00.0%100.0%10,701412000
Schemescheme-classify33,68999.7%100.0%32,3290000
Link referenceslink-references17,88552.9%100.0%17,58516,216000
Summarysummarize32,70196.7%100.0%510000
Refetch PDFrefetch-pdf00.0%100.0%406517000
Entitiesentities00.0%100.0%11,12021,356000
Mentionsmentions-populate00.0%100.0%11,1572,073000
OCR recoveryocr-recover00.0%100.0%34463000
mentions: 185,309 docs with money classified: 19,843 settlement Σ: $305325.7M disgorgement Σ: $302634.4M civil penalty Σ: $2430906.2M victim loss Σ: $22416226.1M total victims: 40,061,720

documents per month by source · monthly buckets

SEC LitSEC PRDOJ SDNY

documents per year by source · stacked

SEC LitSEC PRDOJ SDNY

kinds top 12 across sources

litigation release· SEC Lit
10,453
press release· SEC PR
7,095
press release· DOJ SDNY
5,017
pdf· SEC PR
3,822
complaint· SEC Lit
3,374
pdf· SEC Lit
1,756
complaint· SEC PR
882
judgment· SEC Lit
442
pdf· DOJ SDNY
316
indictment· DOJ SDNY
267
complaint· DOJ SDNY
247
information· DOJ SDNY
92

top subjects canonicalized · top 12

no triples yet — run the processor

top objects canonicalized · top 12

no triples yet — run the processor

top verbs top 15

no triples yet — run the processor

dollar amounts 32,456 mentions · 5,000 bodies sampled

<$10K
6,012
$10K–$100K
4,478
$100K–$1M
4,992
$1M–$10M
6,445
$10M–$100M
4,672
$100M–$1B
2,836
≥$1B
3,021

$ mentions per year count + summed exposure on hover

case filings complaints · informations · indictments · superseding · judgments

filings by source & type all-time

complaint· SEC Lit · 1990–2026
3,374
complaint· SEC PR · 2001–2026
882
judgment· SEC Lit · 2003–2026
442
indictment· DOJ SDNY · 2013–2024
267
complaint· DOJ SDNY · 2013–2024
247
information· DOJ SDNY · 2013–2024
92
judgment· SEC PR · 2010–2024
22
superseding indictment· DOJ SDNY · 2013–2024
7
judgment· DOJ SDNY · 2014–2021
5
information· SEC PR · 2011–2017
3
information· SEC Lit · 2019
1

filings per year by type stacked

complaintjudgmentinformationindictmentsuperseding indictment

first overt act → indictment lag months · histogram SAMPLED

< 1 yr
227
1–2 yrs
259
2–3 yrs
259
3–5 yrs
520
5–10 yrs
452
10+ yrs
80

Backed by triples extraction once the processor parses overt-act dates from complaint narratives and aligns them against indictment published_at. Replace with real data when case_facts.first_act_date populates.

defendants per case caption parse SAMPLED

1 defendants
967
2 defendants
1,115
3 defendants
852
4 defendants
548
5 defendants
358
6-10 defendants
682
11+ defendants
193

top statutes charged U.S.C. citations SAMPLED

15 U.S.C. § 78
281
15 U.S.C. § 77
183
44 U.S.C. § 3501
106
15 U.S.C. § 80
100
44 U.S.C. § 3507
80
5 U.S.C. § 603
80
18 U.S.C. § 1350
77
5 U.S.C. § 601
60
31 U.S.C. § 3717
53
44 U.S.C. § 3506
43
5 U.S.C. § 552
40
5 U.S.C. § 605
39

scheme classification high-level SAMPLED

non-corporate
6,686
unregistered-securities
4,092
insider-trading
3,027
accounting
2,956
ponzi
2,744
investment-adviser
2,602
financial
1,758
market-manipulation
1,550
broker-dealer
1,271
pump-and-dump
1,225
corporate
604
public-corruption
592
fcpa
578
health-care
475
pre-ipo
442
crypto-securities
415
racketeering
390
cyber
260
affinity
237
advance-fee
211
obstruction
199
boiler-room
197
other
50
delinquent-filer
4
money-laundering
1

case dispositions outcomes SAMPLED

consent_judgment
1,318
settlement
500
default_judgment
475
guilty_plea
410
final_judgment
322
dismissed
292
pending
201
jury_verdict
125
summary_judgment
34
dpa
4
npa
1

sentence length distribution sentenced defendants SAMPLED

corporate fraud focus sub-type breakdown · defendants · tickers

fraud type distributioncorporate-fraud sub-typeslive

Insider trading
8,522
Investment adviser fraud
7,356
Market manipulation
6,573
Offering / securities fraud — general
5,171
Unregistered securities
4,641
Pump-and-dump
3,276
Microcap / shell-company scheme
2,346
Accounting fraud / false financials
1,446

fraud types per yeartrend by sub-typelive

Pump-and-dumpUnregistered securitiesInsider tradingMarket manipulationAccounting fraud / false financialsInvestment adviser fraudOffering / securities fraud — generalMicrocap / shell-company scheme

fraud type by sourcestacked by sourcelive

source src-1source src-3source src-2

top defendants — corporateby case countlive

1205
828
777
738
692
320
307
302
281
279
276
225
211
189
185
183
177
171
171
168
165
145
139
138
137
135
127
125
114
111

top target companiesnamed in filingslive

553
302
229
104
88
67
67
65
64
58
56
47
44
41
41
40
39
37
36
35
35
35
34
33
31
30
30
29
28
28

top tickersmentioned in filingslive

69
30
30
27
27
25
24
23
23
22
22
21
21
21
20
20
19
19
19
19
18
17
17
17
16
15
12
8
8
8

securities fraud — detail view statutes · money · sub-type trends

securities statutesU.S.C. citationslive

10,928
7,775
6,350
5,126
4,121
3,856
3,148
2,438
2,316
2,239
2,133
1,939
1,738
1,596
1,542
1,214
1,192
1,054
1,036
987
940
855
851
834
813
800
793
771
754
747

securities money bucketsalleged exposure by sizelive

< $10K
102,584
$10K–$100K
47,291
$100K–$1M
65,342
$1M–$10M
69,714
$10M–$100M
46,146
$100M–$1B
23,226
≥ $1B
21,281

pump-and-dump trendannuallive

unregistered securities trendannuallive

insider trading trendannuallive

market manipulation trendannuallive

microcap + shell-company schemes flag rates · sub-types · promoters · target heatmap

microcap flag rateD2preview

34.0%

shell flag rateD3preview

21.0%

microcap/shell overlapD4preview

12.0%

microcap by fraud sub-typeD5live

Pump-and-dump
3,115
Microcap / shell-company scheme
1,802
Market manipulation
1,445
Insider trading
1,312
Unregistered securities
1,293
Offering / securities fraud — general
931
Investment adviser fraud
801
Accounting fraud / false financials
155

shell-co by fraud sub-typeD6live

Microcap / shell-company scheme
1,157
Market manipulation
617
Insider trading
595
Pump-and-dump
584
Unregistered securities
509
Offering / securities fraud — general
464
Investment adviser fraud
307
Accounting fraud / false financials
93

microcap/shell promotersD7 · top promoters by mention countlive

boiler room
1,410
stock promoter
1,320
stock promotion
969
cold call
243
paid promotion
118
cold calling
42
promotional newsletter
15

federal crime distribution top-level crime buckets · trend

federal crime distributionE1 · by charge bucketlive

Corporate fraud
22,678
Other fraud
9,720
Perjury / false statements
2,573
Wire fraud
2,240
Money laundering
1,584
Mail fraud
969
Obstruction
604
Tax fraud / evasion
331
Crypto / digital-asset fraud
216

crime bucket trendE2 · annual by bucketlive

Corporate fraudWire fraudMail fraudMoney launderingObstructionPerjury / false statementsTax fraud / evasionCrypto / digital-asset fraudOther fraud

case-no cardinalityF4 · unique case numberslive

0

caption parse coverageF5 · % captions parsedlive

0.0%

litigators AUSAs · SEC counsel · judges · fraud-type mix

top AUSAsG2 · by case countlive

44
17
12
11
8
8
7
7
6
6
6
6
5
5
5
5
5
4
4
4
4
4
4
4
4
4
4
4
4
4

top SEC counselG3 · by case countlive

256
145
18
17
17
15
13
12
12
12
12
8
7
7
7
6
6
6
6
6
6
6
5
5
5
4
4
4
4
4

top judgesG4 · by case countlive

108
107
98
94
86
83
75
69
69
69
66
63
57
44
41
35
25
24
22
16
16
15
15
11
11
11
9
8
7
6

litigator fraud-type mixG5 · stacked by charge typelive

Pump-and-dumpUnregistered securitiesInsider tradingMarket manipulationAccounting fraud / false financialsInvestment adviser fraudOffering / securities fraud — generalMicrocap / shell-company scheme

civil penalty distributionH5 · by size bucketlive

< $100K
1,206
$100K–$1M
1,210
$1M–$10M
331
$10M–$100M
115
≥ $100M
25

disgorgement distributionH6 · by size bucketlive

< $100K
932
$100K–$1M
1,215
$1M–$10M
752
$10M–$100M
308
≥ $100M
46

signal & anomaly benford's law · quality pulses · body-length distribution

benford leading digitI1 · observed vs expectedlive

0
0
0
0
0
0
0
0
0

benford deviation by yearI2 · chi-sq trendlive

summary quality pulseI3 · avg scorelive

0.0%

OCR quality pulseI4 · avg scorelive

0.0%

body length distributionI5 · by char bucketlive

426
2330
1414
15495
10686
3437

filing calendar one cell per day · faceted by source · colour = log(count)

filings per dayall sources

loading…

scheme calendar one cell per day · faceted by scheme · colour = log(count)

schemes per dayall classified schemes

loading…

entity co-occurrence graph top-200 entities · edge = co-occurs in same doc (weight ≥ 2)

entity networkdrag nodes · hover for detail

loading…

scheme → outcome flow triples-derived scheme · plea / sentence / pending

scheme → outcomeSankey · Phase E will improve scheme labels

loading…

scheme dollar packing agency → scheme → case · size = monetary amount

scheme & amount packinghierarchy: source → scheme → case

loading…

cross-corpus: fraud entities × EDGAR filings fraud-heuristics defendants matched against edgar-indexer

cross-corpus networkred = fraud entity · blue = EDGAR match · run script to populate

Loading cross-corpus data...

top 10 classified schemesLLM taxonomy — all →

non-corporate 6,686
unregistered-securities 4,092
insider-trading 3,027
accounting-fraud 2,956
ponzi 2,744
investment-adviser-fraud 2,602
financial-fraud 1,758
market-manipulation 1,550
broker-dealer-fraud 1,271
pump-and-dump 1,225

all classified schemes10 total — strict mono

non-corporate 6,686
unregistered-securities 4,092
insider-trading 3,027
accounting-fraud 2,956
ponzi 2,744
investment-adviser-fraud 2,602
financial-fraud 1,758
market-manipulation 1,550
broker-dealer-fraud 1,271
pump-and-dump 1,225

coverage summary progress per workflow — full table on architecture

Statute refs 71.4%
Court / jurisdiction 71.9%
Keywords 99.8%
Outcome 46.7%
Money classes 58.7%
Title formatted 100.0%
Title LLM 0.0%
Scheme 99.7%
Link references 52.9%
Summary 96.7%
Refetch PDF 0.0%
Entities 0.0%
Mentions 0.0%
OCR recovery 0.0%

sources color legend

SEC Lit SEC PR DOJ SDNY
sqlite fts5 · doj-sdny + sec-pr + sec-litreleases read-only public corpus dollar bucket scan limited to 2000 most recent bodies
build b23a6a8 · corpus snapshot pinned to this build