{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2FJ7H4VS2QX3L6MAVFQV3UO6JL","short_pith_number":"pith:2FJ7H4VS","schema_version":"1.0","canonical_sha256":"d153f3f2b2d42fb5f980a9615dd1de4af70447744753d55015972ca97a1ff5f5","source":{"kind":"arxiv","id":"2302.13814","version":2},"attestation_state":"computed","paper":{"title":"An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhinav Koyyalamudi, Lakshmivihari Mareedu, Noel Ngu, Paulo Shakarian","submitted_at":"2023-02-23T16:06:16Z","abstract_excerpt":"We study the performance of a commercially available large language model (LLM) known as ChatGPT on math word problems (MWPs) from the dataset DRAW-1K. To our knowledge, this is the first independent evaluation of ChatGPT. We found that ChatGPT's performance changes dramatically based on the requirement to show its work, failing 20% of the time when it provides work compared with 84% when it does not. Further several factors about MWPs relating to the number of unknowns and number of operations that lead to a higher probability of failure when compared with the prior, specifically noting (acro"},"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":"2302.13814","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-23T16:06:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"eced63e2ca9bdfd99cb08d934ecfb445ae0ab3f9698aba52f872cd2ea12a6426","abstract_canon_sha256":"d9a9168e523cb3f38e4f09630343b028030451344c45a28e1b8825482c677318"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:39.890273Z","signature_b64":"uP34ZYSO54iogGRsIwkpmrFYn95jbVYunEYVriQywGFFTOHqK2hMHF45UhcM5EmyJiuymRv7ZtPEAhq27m4MAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d153f3f2b2d42fb5f980a9615dd1de4af70447744753d55015972ca97a1ff5f5","last_reissued_at":"2026-07-05T05:46:39.889823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:39.889823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhinav Koyyalamudi, Lakshmivihari Mareedu, Noel Ngu, Paulo Shakarian","submitted_at":"2023-02-23T16:06:16Z","abstract_excerpt":"We study the performance of a commercially available large language model (LLM) known as ChatGPT on math word problems (MWPs) from the dataset DRAW-1K. To our knowledge, this is the first independent evaluation of ChatGPT. We found that ChatGPT's performance changes dramatically based on the requirement to show its work, failing 20% of the time when it provides work compared with 84% when it does not. Further several factors about MWPs relating to the number of unknowns and number of operations that lead to a higher probability of failure when compared with the prior, specifically noting (acro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13814","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/2302.13814/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":"2302.13814","created_at":"2026-07-05T05:46:39.889883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.13814v2","created_at":"2026-07-05T05:46:39.889883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13814","created_at":"2026-07-05T05:46:39.889883+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FJ7H4VS2QX3","created_at":"2026-07-05T05:46:39.889883+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FJ7H4VS2QX3L6MA","created_at":"2026-07-05T05:46:39.889883+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FJ7H4VS","created_at":"2026-07-05T05:46:39.889883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04857","citing_title":"Neuro-Symbolic Data Generation for Math Reasoning","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FJ7H4VS2QX3L6MAVFQV3UO6JL","json":"https://pith.science/pith/2FJ7H4VS2QX3L6MAVFQV3UO6JL.json","graph_json":"https://pith.science/api/pith-number/2FJ7H4VS2QX3L6MAVFQV3UO6JL/graph.json","events_json":"https://pith.science/api/pith-number/2FJ7H4VS2QX3L6MAVFQV3UO6JL/events.json","paper":"https://pith.science/paper/2FJ7H4VS"},"agent_actions":{"view_html":"https://pith.science/pith/2FJ7H4VS2QX3L6MAVFQV3UO6JL","download_json":"https://pith.science/pith/2FJ7H4VS2QX3L6MAVFQV3UO6JL.json","view_paper":"https://pith.science/paper/2FJ7H4VS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.13814&json=true","fetch_graph":"https://pith.science/api/pith-number/2FJ7H4VS2QX3L6MAVFQV3UO6JL/graph.json","fetch_events":"https://pith.science/api/pith-number/2FJ7H4VS2QX3L6MAVFQV3UO6JL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FJ7H4VS2QX3L6MAVFQV3UO6JL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FJ7H4VS2QX3L6MAVFQV3UO6JL/action/storage_attestation","attest_author":"https://pith.science/pith/2FJ7H4VS2QX3L6MAVFQV3UO6JL/action/author_attestation","sign_citation":"https://pith.science/pith/2FJ7H4VS2QX3L6MAVFQV3UO6JL/action/citation_signature","submit_replication":"https://pith.science/pith/2FJ7H4VS2QX3L6MAVFQV3UO6JL/action/replication_record"}},"created_at":"2026-07-05T05:46:39.889883+00:00","updated_at":"2026-07-05T05:46:39.889883+00:00"}