Bulk Data
10 million state and federal opinions — the standard case set the legal industry works from — with the citation graph, U.S. Code, federal rules, full-text index, and semantic vectors that make it queryable. Licensed for direct database access, replication into your own environment, or API integration.
Every layer below is a queryable store in its own right, not a derived export. The AI analysis layer carries its own vector set, embedded separately from the opinion text, so meaning-based retrieval runs against both.
10 million rows
One row per opinion — majority, concurrence, and dissent each addressable — with normalized court, jurisdiction tier, filing date, docket, publication status, and full body text.
Separate tables
Party filings — complaints, briefs, motions, amicus — stored apart from court opinions, grouped by litigation matter, and included as their own section in the synthesized case report.
100 million edges
Resolved opinion-to-opinion edges, traversable in both directions: what a case cites, and everything that has cited it since.
183 million rows
Every citation as it appears in the prose, with character offsets, pin cite, and the short-form/supra/id resolution chain — extracted by GoodLaw / EyeDiver (built on eyecite, then extended in-house) across 10 million completed scans, with an LLM pass for what the deterministic parser misses.
18 million rows
Parallel citations with a normalized reporter key per row, so official, regional, and vendor cites all resolve to the same decision.
10 million docs / 133 GB
Apache Lucene inverted index (OpenSearch) over the whole corpus, with per-field boosting, positional offsets for phrase and proximity queries, and BM25 relevance scoring.
5.95 million vectors
1024-dimension Qwen3-Embedding-8B embeddings, stored as pgvector halfvec and indexed with binary-quantized HNSW. Two sets are built separately and searched together: AI analysis embeddings and opinion-body embeddings.
250,000 opinions
Model-authored issue, holding, posture, and quotation extraction — with its own dedicated vector set, embedded and indexed separately from the opinion body, for higher precision on hard-to-find caselaw. Authored by LawDiver; not derived from Westlaw, Lexis, or Shepard’s.
2024 edition
The 2024 edition is stored for search (43,330 current sections). Superseded text is also stored for 2016–2023, about 890 sections a year across 38 titles, not a complete annual code. A section that is not stored is retrieved from GovInfo when cited. Edition years are on the database index.
Full federal sets
The Federal Rules of Civil Procedure, Criminal Procedure, Evidence, and Appellate Procedure, plus related federal rule sets, stored as addressable rules and subdivisions and linked to the opinions that cite them.
7,422 current sections
Stored for search: a 2026-09-28 snapshot (6,011 sections), the 2025 edition (1,173 sections), and smaller slices from 2026, 2024, and a handful of earlier years. This is not a complete annual C.F.R. A section that is not stored is retrieved from eCFR when cited.
over 1.5 million
Primary codes for all fifty states and the District of Columbia — over 1.5 million state statutes, addressable by jurisdiction and section.
more than 1,300
Treaties, protocols, and conventions the United States is a party to, stored for search by name, citation, and summary.
more than 8,000
Official pattern jury instructions from published state civil and criminal sets, stored for lookup by jurisdiction, set, and instruction number.
Four purpose-built stores rather than one. Retrieval by citation, by name, by keyword, and by meaning are different physical problems, and each gets the index that suits it.
The 350 GB store of record: opinions, litigant pleadings, the citation graph, in-text citations, reporter citations, and the AI analysis tables. Relational and queryable, not a document dump.
16.6 million rows keyed on a normalized reporter key, isolated in its own database so a lookup by citation is a single indexed hit rather than a scan of the main corpus.
10 million rows with trigram (GIN/pg_trgm) indexes on case name and both party names, for fuzzy retrieval by name that tolerates abbreviation and misspelling.
Stemmed, ASCII-folded analysis with positional offsets, supporting boolean, phrase, and proximity queries with BM25 ranking and field-level boosts across body, name, and syllabus.
5.95 million Qwen3-Embedding-8B vectors at 1024 dimensions, stored as halfvec and indexed by binary-quantized HNSW (Hamming first pass, full-precision rerank) for cheap recall at scale.
The AI analysis layer carries its own embeddings, built separately from the opinion-body embeddings and searched alongside them. A query phrased as a legal question matches text already written in the language of issues and holdings, which is what surfaces relevant caselaw that keyword and body-only vector search miss.
Every opinion is scanned with LawDiver’s proprietary GoodLaw system (EyeDiver), built on the open-source eyecite parser and substantially extended in-house. GoodLaw is deterministic: the same opinion yields the same cites. An LLM pass then searches for anything GoodLaw missed, so reliability and completeness are stacked rather than traded off.
Three access models, all reading the same continuously updated corpus.
Credentialed, read-only connections to the Postgres stores and the OpenSearch cluster on our infrastructure. You issue your own SQL and your own queries — no export step, no staleness.
The corpus stood up inside your environment as a mirror, seeded from a bulk snapshot and kept current by incremental sync. Appropriate where data cannot leave your network.
The same corpus over HTTP, for retrieval, search, and citation lookup. No request quota — throughput is bounded by server and network capacity, negotiated per agreement.
New decisions are ingested continuously, normalized, citation-scanned, and propagated across every store and index — so all delivery methods converge on the same current state.
Caselaw is only one layer. The same graph ties opinions to the code, the federal rules, and the C.F.R.
The 2024 edition is stored for search. Partial superseded text is stored for 2016 through 2023. Other years are retrieved from GovInfo when a section is cited. The database index names every edition year on disk.
The federal rules of civil procedure, criminal procedure, evidence, and appellate procedure — and related federal rule sets — are stored as first-class authority, subdivided the way lawyers cite them, and linked to the opinions that invoke them.
The stored C.F.R. is a cache: the 2026-09-28 snapshot, the 2025 edition, and smaller slices from 2024, 2026, and a few earlier years. A section that is not stored is retrieved from eCFR when cited.
Caselaw years, statute edition years, and which authorities are stored for text search versus retrieved from the official source are listed on the database index. Court-by-court counts are on the full inventory.
The corpus is built from public sources only. The backbone is the quarterly CourtListener bulk downloads, which are available without restriction. Around that, LawDiver harvesters run continuously against more than 200 individual court websites, public RSS feeds of newly issued opinions, and the massive GovInfo site (govinfo.gov), which publishes federal statutes, regulations, and caselaw.
Those streams are normalized into one schema, citation-scanned, and folded into the graph, the full-text index, and the vector stores. A longer account of harvest, indexing, embeddings, and GoodLaw — without the licensing terms — is in How Was the LawDiver Caselaw Database Assembled?.
The LawDiver corpus was assembled without accepting any license, terms of service, or other restriction that would constrain how LawDiver uses the data, or how LawDiver customers are able to use the data.
All caselaw analysis in LawDiver was created by LawDiver. Nothing was taken from other research services. Westlaw headnotes were not used. Lexis headnotes were not used. Shepard’s was not used.
Citation extraction and treatment use LawDiver’s proprietary GoodLaw system (EyeDiver). GoodLaw started from the open-source eyecite application and was greatly enhanced by our in-house team to recognize the full range of legal citations and to deliver far more complete results. A deterministic GoodLaw pass is followed by an LLM pass so that nothing the parser misses is left on the table.
Coverage is U.S. Supreme Court, federal courts of appeals, federal district courts, and the appellate and supreme courts of all fifty states. Opinions are sourced from the public record and normalized into a single schema: one row per opinion, so a dissent is addressable separately from the majority it accompanies, with court, jurisdiction tier, circuit, filing date, docket number, and publication status resolved to controlled values rather than left as source strings. Litigant pleadings — party complaints, briefs, motions, and amicus filings — live in their own tables and appear as a separate section of the synthesized case report, never folded into the court opinion.
Model-authored fields are stored in their own tables, physically separate from court-authored text. Nothing a model wrote is ever mixed into an opinion's body, syllabus, or headnotes — so an evidentiary distinction that matters to a court is structural in the schema rather than a naming convention.