Smaller than the full landscape dataset, and priced for it — each one is a real, verified, one-time snapshot. No estimated fields, no synthetic trajectories, no forced true/false calls where the honest answer is "unverifiable."
Theorem, constant, and attribution claims checked by real computation, not recall
Forty-three real mathematical claims (famous theorem statements, numeric sequence/constant properties, computational results, open-problem status checks, and "who first proved X" attributions), each checked against code actually written and run (Python sympy/mpmath, a from-scratch BigInt library, and an exhaustive brute-force combinatorial search), the real Wikidata knowledge graph, real published papers via OpenAlex, and, for one live current-events check, primary web sources fetched live. An AI model asked to check its own math claim just restates it more confidently; this dataset actually computes, queries, and looks the answer up, and says so honestly on the rare row where a second independent check genuinely doesn't exist. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Physical constants and discovery claims checked against NIST, OpenAlex, Wikidata, and real independent computation
Forty-three real claims about physical constants, first-discovery/first-measurement attributions, and specific published experimental results across physics, chemistry, astronomy, biology, and earth science, each checked against NIST's live CODATA fundamental-constants database, the actual paper reporting a result via OpenAlex, Wikidata's structured discoverer/date/value statements, or, new this pass, real independently executed computation deriving one fundamental constant from others. Fills the gap between Groundtruth's clinical-trial and citation-graph products, which don't touch general physical-science claims, and is now the catalog's most methodologically diverse verification product. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Patent and IP claims checked against the live USPTO record, not what a company says about them
Forty real claims companies and named inventors have made about patents ("we hold a patent on X," "patent number Y covers Z," "first to patent W"), each checked against the actual live record at USPTO's Patent Public Search system: does the patent exist, is it assigned to the claimed entity, do its real granted claims actually cover what's being claimed, and is it still valid today. Every row is now also cross-checked against a second, independent USPTO data feed — the live Patent Assignment and PTAB docket history tracking what actually happened to a patent after it was granted, not just its bibliographic snapshot — which caught patents that quietly lapsed for non-payment years after being cited in litigation, ownership chains that don't match a company's own marketing page, and three real errors in this dataset's own earlier release, corrected in place and disclosed rather than silently fixed. The original 23 rows also carry a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
"Case X held Y" claims checked against the real opinion text, not a paraphrase
Forty-two real claims of the form "Case X held Y," each verified by fetching the actual opinion text of Case X from Harvard Law School's Caselaw Access Project (CC0 public domain, confirmed live) and checking whether the claimed holding, quote, vote count, or date genuinely appears in the primary source — now cross-checked against a second independent source, Wikidata's structured case-law statements, on most rows. Grew from a 20-case constitutional-law pilot into a wider set spanning antitrust, torts, foundational property law, copyright, trademark, and federal appellate law, including this dataset's first non-Supreme-Court cases (New York's Court of Appeals, an 1805 property-law ruling, and the D.C. Circuit's Microsoft antitrust decision). CourtListener was deliberately not used, its commercial-resale licensing remains unconfirmed with Free Law Project. The original 20 rows also carry a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Does the trial data behind a drug claim actually back it up — checked against the real registry
Forty-seven real claims about clinical trial outcomes and FDA drug approvals — from company press releases, SEC filings, FDA announcements, and news coverage — each checked against the actual ClinicalTrials.gov registration and results record, openFDA's real approval data, FDA's Drugs@FDA and Purple Book databases, and, where a specific paper is claimed, the real linked publication via PubMed/OpenAlex. Surfaces genuine, checkable gaps and traps: several FDA-approved, NEJM-published drugs — including the first-ever CRISPR therapy — have zero structured results posted on their own government registry entry; two different drugs (bardoxolone methyl and sotorasib) met their trial's own statistically significant primary endpoint and were still rejected or held back by FDA anyway; and two real 2023 drug-label expansions (Trikafta, Vyvgart) turned out to require an entirely new FDA application number rather than a supplement — a trap the model falls into when asked cold. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Federal contracting claims checked against the actual USASpending.gov award record
Forty real claims companies make about their US federal and defense contracting relationships — "prime DoD contractor," specific dollar figures, named agency relationships — each checked against the real award data on USASpending.gov, the federal government's own system of record for who it has actually paid, with a second independent method (real SEC EDGAR filings) added wherever one genuinely exists. Surfaces real, checkable failure modes: contract-ceiling figures presented as if already earned, a real NYSE-listed company with billions in current federal work that's entirely invisible under its own name because every dollar is still filed under its pre-merger legal entity, and — new this pass — a household-name defense prime whose federal business is invisible to a simple name search because the identical legal entity is registered under more than 100 separate, un-consolidated USASpending IDs. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Real claims, two independent sources each, honest verdicts including disagreement
Two hundred thirty-seven real-world claims across AI/tech, business, science, medicine, history, geography, culture, sports, entertainment, law, and government, each checked against a real cited source AND a second, genuinely independent source, with the two sources' agreement recorded explicitly. Built specifically to probe plausible-sounding falsehoods and implausible-sounding truths, not just easy trivia — and to surface the cases where two independent sources actually disagree, which a single-source lookup would never catch. A 2026-07-12 expansion added 37 new claims leaning into current events genuinely beyond any model's training cutoff (Nvidia's fiscal-2026 earnings, the 2026 Winter Olympics medal table, Super Bowl LX, the 98th Academy Awards), verified live via real API calls, Wikidata SPARQL queries, and independent web sources, alongside a full re-audit of the original 200 that found the existing data held up with zero new errors. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Does this library API claim actually match what shipped — checked against the real published artifact
Forty-two real claims about specific npm, PyPI, and (new this release) crates.io package APIs at exact versions, each checked by actually downloading and inspecting the real published tarball/sdist/crate file — and, for 38 of the 42 rows, confirmed a second, independent way by actually installing the real package and running the real code (or, for two Rust API-removal claims, capturing a real compiler error from trying to build against the claimed symbol). Targets the exact failure mode of hallucinated library APIs: functions, parameters, and behaviors that sound plausible but were never shipped, shipped differently, or existed only in a different version than the one claimed. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Does Paper A really cite Paper B, and is B legally quotable — checked end to end
43 real multi-hop citation claims of the form "Paper A cites a paper titled X," each verified by walking Paper A's actual OpenAlex reference graph (not just checking that both papers individually exist) and, where the citation is real, checking Paper B's legally-quotable open-access status via Unpaywall. This pass re-audited every existing row live, added Semantic Scholar as a genuinely independent second citation-graph provider wherever it added real coverage, caught and openly corrected one real error from the original release (a citation OpenAlex's own graph was silently missing), and expanded into new sub-areas -- NLP embeddings, biomedical segmentation, distributed systems, clinical vaccine trials, classical neurophysiology, modern LLMs, diffusion models, and protein structure prediction -- including a live-discovered case where OpenAlex's own citation-graph data contains a chronologically impossible "citation," which a naive automated checker would wrongly certify as real.
Director, incorporation, status, and beneficial-ownership claims checked against the real UK company register
55 real claims about UK-registered companies (mostly AI/tech firms) — director identity, incorporation dates, company status, registered addresses, beneficial ownership (PSC), cross-company appointment history, previous company names, SIC industry classification, filing history, and registered charges — each independently checked against the live UK Companies House register via both its free public website and its authenticated REST API. 82% of rows are backed by two genuinely independent, separately-coded verification paths; the rest are honestly single-sourced because no second method exists (PSC and appointment data have no public-HTML equivalent at all). Includes a real bug found and fixed in the dataset's own verification tooling this release, plus live model-graded testing on every row: asked cold with no tools, Claude Sonnet 5 hedges correctly on 95% of these claims and hallucinates a specific wrong answer on 2%, showing why a live register lookup beats an LLM's memory for this kind of fact.
Cross-model-tier refusal divergence and consistency, not a single one-shot test
Thirty real prompts drawn from two published, MIT-licensed AI-safety benchmarks (JailbreakBench, HarmBench), each individually screened against a strict category allowlist (several on-allowlist-labeled candidates, including a nuclear-weapon prompt mislabeled "Government decision-making," were excluded on individual review) and tested fresh against three model capability tiers with repeated sampling per tier (180 total live invocations), not a single one-shot test against one model. Every row now also carries a second, independent verification method — a live re-fetch of the source benchmark's own raw data confirming an exact prompt/category match — after a full re-audit of the original 21 rows found zero drift. Strictly scoped to lower-severity categories only — nothing touching weapons, hacking, violence, sexual content, trafficking, or self-harm — and stores only classifications, never generated harmful content.
Two independent real sources, checked against each other, not just one
Wikidata vs. live web; SEC filings vs. marketing claims; and, new in this expansion, one acquirer's audited SEC filing vs. another company's widely-reported deal-announcement figure for the same transaction. 42 real cases checking whether a structured official source actually agrees with a second, independent real source — and, where possible, a third. This pass re-verified all 27 original rows live with zero errors found, added a genuine second SEC-filed source to two rows that originally hit Wikidata's total silence (surfacing real gaps between announced and audited deal sizes), and expanded into 15 new rows covering newer AI companies and real corporate M&A, including a materially wrong headline acquisition-price figure caught by comparing an acquirer's own audited books against press coverage.
Historical event, date, and attribution claims independently checked against Wikidata's live structured statements, not model memory
Forty-two real historical claims — a battle date, an assassination's causal framing, who really invented the telephone — each checked against Wikidata's real, live, CC0-licensed structured statements for the specific entity in question, including a purpose-built technique for compound multi-date events (space missions, voyages) where a naive property lookup would silently grab the wrong sub-event's date. most claims match, a documented minority diverge (off-by-one-day/year errors, invention misattributions, an overstated single-cause claim), and 1 is honestly marked unverifiable. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Famous quotes and book-publication claims checked against real public-domain full text and live Wikidata, not recalled
Forty-two claims, each traced back to a real, live-fetched source: exact substring search against the real full plain-text of 25 public-domain books/plays via Project Gutenberg for quote claims, and live Wikidata publication-date/authorship checks. 16 of the original 35 rows (46%) are genuine divergences — misquotes, mixed-up authors, and swapped years that an LLM's training-data recall would very plausibly get wrong with high confidence — a count that grew by one when this dataset's own adversarial audit held a row to its own punctuation-strict standard and flipped it. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Country capitals, populations, land areas, borders, and physical-geography superlatives checked against two independent live sources
Forty real geographic claims — capitals, population figures with year, land areas, bordering countries, and physical-geography superlatives — each cross-checked against two live, independently maintained sources: the CIA World Factbook's last public snapshot (public domain, US government work) and live Wikidata. Surfaces genuinely current, non-obvious findings, including a stale Wikidata population statement that would get "which country is more populous" wrong, and a currently unsettled naming dispute over North America's highest peak. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Claims about Python/JavaScript runtime behavior, each settled by actually running the code or fetching the official changelog
Forty claims about sort stability, integer/float precision, division/modulo sign semantics, string encoding edge cases, and "which version introduced feature X," verified by literally executing python3/node and capturing the real output, or by live-fetching the language's own official changelog. 31 of 40 rows carry real dual-interpreter executed code with literal output; the rest carry a live-fetched changelog snippet. Includes 5 deliberately adversarial rows built from real, commonly-stated wrong claims, to prove the method actually catches errors. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Real claims about public companies' revenue, net income, EPS, and filing dates checked live against SEC EDGAR's structured XBRL data
Forty-one real claims about specific public companies' reported financials — revenue, net income, diluted EPS, shares outstanding, R&D spend, and 10-K filing dates — each checked against a live call to SEC EDGAR's XBRL "company facts" API. Covers 19 major companies across tech, retail, finance, energy, and pharma, including already-filed results more current than most model training cutoffs, a real cross-filing discrepancy between a company's own 10-K and proxy statement, and a currently-live SEC ticker-to-CIK mapping bug affecting a Dow 30 company. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
Real recall, adverse-event, and boxed-warning claims checked live against openFDA, not against memory
Forty real-world drug and medical-device safety claims — recalls, FDA Adverse Event Reporting System/MAUDE report counts, and current FDA-mandated boxed-warning/label text — each independently checked against openFDA, the FDA's own live structured-data API, across four distinct endpoints. Deliberately distinct from this catalog's Clinical Trial Outcomes Verification product, which covers trial results and approvals, not real-world safety data. Built for health-AI products where a wrong safety answer is a high-stakes hallucination, not trivia. Every row also carries a live test: the same fact, asked as an open question cold to Claude Sonnet 5 with no source access, graded against the verified answer, turning this from an answer key into a graded exam.
171 companies across 14 categories, sourced and cited.