Back to products
Case study

SEC / EDGAR Financial Grounding

Groundtruth Data found a repeatable weakness in period-specific SEC financial fact grounding. The strongest failures were numerical financial facts, fiscal dates, temporal comparisons, and YoY calculations.

Request SEC packageDownload public sample
What Was Tested

The proof evaluation asked period-specific questions about SEC financial facts from companyfacts, companyconcept, submissions metadata, and 10-K and 10-Q filing metadata. Tasks covered revenue, net income, operating income, cash flow, cash and equivalents, assets, liabilities, acquisition values, fiscal year dates, period comparisons, and YoY calculations.

CapabilitySEC financial fact grounding
Designationmixed
Version2026-08-30
Updated2026-08-30
SourcesSEC EDGAR companyfacts, SEC EDGAR companyconcept, SEC EDGAR submissions metadata, 10-K and 10-Q filing metadata
FormatsJSON, JSONL eval, JSONL remediation, JSONL SFT, JSONL observed-failure DPO
Product typeproduct family
Pricing modelcomponent pricing
Source Of Truth

Every answer traces to SEC EDGAR structured data or a deterministic calculation from SEC values. Numeric rows preserve CIK, company, accession, form, filing date, fiscal period, XBRL concept, raw SEC value, unit, normalized verified answer, and source URL.

Proof Result
500Proof rows
27.2%Accuracy
72.8%Observed error
364Incorrect responses
0Refusals

The observed error rate has a 95% Wilson confidence interval of 68.7% to 76.5%. This result is specific to the completed chatgpt-web proof run and deterministic SEC-source grading.

Main Failure Modes
wrong numeric value

327 rows

temporal confusion

65 rows

wrong date

37 rows

calculation error

30 rows

Identity tasks performed strongly and are not the focus of the remediation package.

What Remediation Was Built

Groundtruth Data built 10,000 validated remediation rows targeting the observed SEC failure modes. The remediation data is designed to help teams train against period-specific numeric grounding, date grounding, temporal comparisons, and deterministic financial calculations.

No claim is made that this remediation has improved a model. Improvement must be measured in a separate before and after experiment using untouched held-out data.

Held-Out Validation

A separate 1,000-row SEC held-out set is reserved for post-training evaluation. It is not used for proof scoring, remediation generation, prompt tuning, training, or checkpoint selection.

What Buyers Receive
500-row SEC EDGAR proof evaluation with deterministic source-aware grading
10,000 targeted remediation rows for numeric, temporal, date, and calculation failures
1,000 untouched held-out validation rows for before and after measurement
364 DPO pairs where rejected answers are real observed model errors
SFT, eval, and DPO JSONL formats with SEC provenance and validation reports
Pricing
Legacy SEC diagnostic exportdiagnostic eval
$299 reference price

41 actual rows

Existing published JSON export with verified SEC financial-filing rows.

Request package
SEC / EDGAR Financial Proof Evalproof eval
$1,299 reference price

500 actual rows

Fresh SEC EDGAR proof set with completed chatgpt-web browser run and deterministic source-aware grading.

Request package
SEC / EDGAR Remediation 10kremediation training
$6,900 reference price

10,000 actual rows

Validated SEC companyfacts/companyconcept remediation records targeting observed numeric, temporal, and calculation failures.

Request package
SEC / EDGAR Held-Out Validationheld out validation
$1,500 reference price

1,000 actual rows

Untouched SEC EDGAR validation rows excluded from proof and remediation source records.

Request package
SEC Financial Grounding Improvement Packfull improvement pack
$8,500 reference price

11,500 actual rows

500-row proof eval, 10,000 remediation rows, and 1,000 held-out validation rows. No model improvement result is included yet.

Request package
SEC 25k+ expansioncustom dataset
Custom quote

Requires a separate source-supply and validation review before any larger package is claimed.

Request package
Limitations

Request the SEC / EDGAR package

We can package the proof evaluation, 10k remediation data, observed-failure DPO pairs, and held-out validation set for your training or evaluation workflow.

Contact Groundtruth Data