{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MAULLFVB5BCO27UHVXACFOAX36","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":"d913270dd940255acfccf11feb35307f7814d896ef33d8487e62dc3a898c2d7e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T18:59:03Z","title_canon_sha256":"a7f06d292bb47fe17c08ebbc6f9265da52c05293531189ae2c8b65846f3f49d1"},"schema_version":"1.0","source":{"id":"2301.13867","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13867","created_at":"2026-07-05T07:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13867v2","created_at":"2026-07-05T07:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13867","created_at":"2026-07-05T07:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"MAULLFVB5BCO","created_at":"2026-07-05T07:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"MAULLFVB5BCO27UH","created_at":"2026-07-05T07:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"MAULLFVB","created_at":"2026-07-05T07:22:15Z"}],"graph_snapshots":[{"event_id":"sha256:7b806505adbb2f0e26a3ce74017b21cf6e36eb73ef1cfcebc6f496e300e5e0b7","target":"graph","created_at":"2026-07-05T07:22:15Z","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/2301.13867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the mathematical capabilities of two iterations of ChatGPT (released 9-January-2023 and 30-January-2023) and of GPT-4 by testing them on publicly available datasets, as well as hand-crafted ones, using a novel methodology. In contrast to formal mathematics, where large databases of formal proofs are available (e.g., the Lean Mathematical Library), current datasets of natural-language mathematics, used to benchmark language models, either cover only elementary mathematics or are very small. We address this by publicly releasing two new datasets: GHOSTS and miniGHOSTS. These are t","authors_text":"Alexis Chevalier, Julius Berner, Luca Pinchetti, Philipp Christian Petersen, Ryan-Rhys Griffiths, Simon Frieder, Thomas Lukasiewicz, Tommaso Salvatori","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T18:59:03Z","title":"Mathematical Capabilities of ChatGPT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13867","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:a9f4ed964043bad96c567a7e8059c5bc5fb44fb46f58b0f260535e4a50c7e07a","target":"record","created_at":"2026-07-05T07:22:15Z","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":"d913270dd940255acfccf11feb35307f7814d896ef33d8487e62dc3a898c2d7e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T18:59:03Z","title_canon_sha256":"a7f06d292bb47fe17c08ebbc6f9265da52c05293531189ae2c8b65846f3f49d1"},"schema_version":"1.0","source":{"id":"2301.13867","kind":"arxiv","version":2}},"canonical_sha256":"6028b596a1e844ed7e87adc022b817dfba3d9618391fcc6f2312adbc56875314","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6028b596a1e844ed7e87adc022b817dfba3d9618391fcc6f2312adbc56875314","first_computed_at":"2026-07-05T07:22:15.179934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:15.179934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4VHBFj7Mn+Zq+92p+2TBO/+Rr9PXt+dbzTu4SoDVgN9hB4vPVepPmGLqabexA5zYfOAKj/t3g2+bQuMbD6uSCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:15.180419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13867","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9f4ed964043bad96c567a7e8059c5bc5fb44fb46f58b0f260535e4a50c7e07a","sha256:7b806505adbb2f0e26a3ce74017b21cf6e36eb73ef1cfcebc6f496e300e5e0b7"],"state_sha256":"bfa189c0f02831a049b419f679604abf9787b66116b9259f72d5fa558e695b28"}