{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MAULLFVB5BCO27UHVXACFOAX36","short_pith_number":"pith:MAULLFVB","schema_version":"1.0","canonical_sha256":"6028b596a1e844ed7e87adc022b817dfba3d9618391fcc6f2312adbc56875314","source":{"kind":"arxiv","id":"2301.13867","version":2},"attestation_state":"computed","paper":{"title":"Mathematical Capabilities of ChatGPT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexis Chevalier, Julius Berner, Luca Pinchetti, Philipp Christian Petersen, Ryan-Rhys Griffiths, Simon Frieder, Thomas Lukasiewicz, Tommaso Salvatori","submitted_at":"2023-01-31T18:59:03Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.13867","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T18:59:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a7f06d292bb47fe17c08ebbc6f9265da52c05293531189ae2c8b65846f3f49d1","abstract_canon_sha256":"d913270dd940255acfccf11feb35307f7814d896ef33d8487e62dc3a898c2d7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:15.180419Z","signature_b64":"4VHBFj7Mn+Zq+92p+2TBO/+Rr9PXt+dbzTu4SoDVgN9hB4vPVepPmGLqabexA5zYfOAKj/t3g2+bQuMbD6uSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6028b596a1e844ed7e87adc022b817dfba3d9618391fcc6f2312adbc56875314","last_reissued_at":"2026-07-05T07:22:15.179934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:15.179934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mathematical Capabilities of ChatGPT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexis Chevalier, Julius Berner, Luca Pinchetti, Philipp Christian Petersen, Ryan-Rhys Griffiths, Simon Frieder, Thomas Lukasiewicz, Tommaso Salvatori","submitted_at":"2023-01-31T18:59:03Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13867","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.13867/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.13867","created_at":"2026-07-05T07:22:15.179989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13867v2","created_at":"2026-07-05T07:22:15.179989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13867","created_at":"2026-07-05T07:22:15.179989+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAULLFVB5BCO","created_at":"2026-07-05T07:22:15.179989+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAULLFVB5BCO27UH","created_at":"2026-07-05T07:22:15.179989+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAULLFVB","created_at":"2026-07-05T07:22:15.179989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23668","citing_title":"On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17289","citing_title":"Nothing from Something: Can a Language Model Discover 0?","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2503.13533","citing_title":"The Status Quo and Future of AI-TPACK for Mathematics Teacher Education Students: A Case Study in Chinese Universities","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2307.10635","citing_title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2302.11382","citing_title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08904","citing_title":"OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MAULLFVB5BCO27UHVXACFOAX36","json":"https://pith.science/pith/MAULLFVB5BCO27UHVXACFOAX36.json","graph_json":"https://pith.science/api/pith-number/MAULLFVB5BCO27UHVXACFOAX36/graph.json","events_json":"https://pith.science/api/pith-number/MAULLFVB5BCO27UHVXACFOAX36/events.json","paper":"https://pith.science/paper/MAULLFVB"},"agent_actions":{"view_html":"https://pith.science/pith/MAULLFVB5BCO27UHVXACFOAX36","download_json":"https://pith.science/pith/MAULLFVB5BCO27UHVXACFOAX36.json","view_paper":"https://pith.science/paper/MAULLFVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13867&json=true","fetch_graph":"https://pith.science/api/pith-number/MAULLFVB5BCO27UHVXACFOAX36/graph.json","fetch_events":"https://pith.science/api/pith-number/MAULLFVB5BCO27UHVXACFOAX36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAULLFVB5BCO27UHVXACFOAX36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAULLFVB5BCO27UHVXACFOAX36/action/storage_attestation","attest_author":"https://pith.science/pith/MAULLFVB5BCO27UHVXACFOAX36/action/author_attestation","sign_citation":"https://pith.science/pith/MAULLFVB5BCO27UHVXACFOAX36/action/citation_signature","submit_replication":"https://pith.science/pith/MAULLFVB5BCO27UHVXACFOAX36/action/replication_record"}},"created_at":"2026-07-05T07:22:15.179989+00:00","updated_at":"2026-07-05T07:22:15.179989+00:00"}