{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FSBWGUE7ONAFX72WO4Q43GDUBE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"398d59fb230b3dde5b8609d073d28e9134a69c0f6dc57fe9ef106cb5bd1be905","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:41:35Z","title_canon_sha256":"906bb2423398070156cf4941268533f0733b2617925559f43a739efad3f6fb5f"},"schema_version":"1.0","source":{"id":"2506.21521","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21521","created_at":"2026-07-05T11:29:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21521v2","created_at":"2026-07-05T11:29:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21521","created_at":"2026-07-05T11:29:14Z"},{"alias_kind":"pith_short_12","alias_value":"FSBWGUE7ONAF","created_at":"2026-07-05T11:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"FSBWGUE7ONAFX72W","created_at":"2026-07-05T11:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"FSBWGUE7","created_at":"2026-07-05T11:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:c484c076f8cba2af111cfc08abed85ea51036692959364330fb7f4877c7f30a1","target":"graph","created_at":"2026-07-05T11:29:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.21521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are regularly evaluated using benchmark datasets. But what justifies making inferences about an LLM's capabilities based on its answers to a curated set of questions? This paper first introduces a formal framework to address this question. The key is to note that the benchmarks used to test LLMs -- such as AP exams -- are also those used to test people. However, this raises an implication: these benchmarks are only valid tests if LLMs misunderstand concepts in ways that mirror human misunderstandings. Otherwise, success on benchmarks only demonstrates potemkin unde","authors_text":"Bec Weeks, Keyon Vafa, Marina Mancoridis, Sendhil Mullainathan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:41:35Z","title":"Potemkin Understanding in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21521","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d11c6914546ea800987e52efcf50ae3d8b60b5bb2a85b659255dc2442a08b52d","target":"record","created_at":"2026-07-05T11:29:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"398d59fb230b3dde5b8609d073d28e9134a69c0f6dc57fe9ef106cb5bd1be905","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T17:41:35Z","title_canon_sha256":"906bb2423398070156cf4941268533f0733b2617925559f43a739efad3f6fb5f"},"schema_version":"1.0","source":{"id":"2506.21521","kind":"arxiv","version":2}},"canonical_sha256":"2c8363509f73405bff567721cd9874093cc0071f6cb0189dbe0384c2d6657c7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c8363509f73405bff567721cd9874093cc0071f6cb0189dbe0384c2d6657c7e","first_computed_at":"2026-07-05T11:29:14.464122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:14.464122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R4o+B/S9gkowJwxxaklaCEGAFpdgw6IDnI0yb6i4jEkX/GiYh6v/3aLJvDcKz7gk1yxS6yHj77ZIX7eAOvn5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:14.464723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21521","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d11c6914546ea800987e52efcf50ae3d8b60b5bb2a85b659255dc2442a08b52d","sha256:c484c076f8cba2af111cfc08abed85ea51036692959364330fb7f4877c7f30a1"],"state_sha256":"d66aa70be3eec2866aa0444d583a9b4396b30a9a8fec94eeee52e0b8a20b22ee"}