{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2FJ7H4VS2QX3L6MAVFQV3UO6JL","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":"d9a9168e523cb3f38e4f09630343b028030451344c45a28e1b8825482c677318","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-23T16:06:16Z","title_canon_sha256":"eced63e2ca9bdfd99cb08d934ecfb445ae0ab3f9698aba52f872cd2ea12a6426"},"schema_version":"1.0","source":{"id":"2302.13814","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.13814","created_at":"2026-07-05T05:46:39Z"},{"alias_kind":"arxiv_version","alias_value":"2302.13814v2","created_at":"2026-07-05T05:46:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13814","created_at":"2026-07-05T05:46:39Z"},{"alias_kind":"pith_short_12","alias_value":"2FJ7H4VS2QX3","created_at":"2026-07-05T05:46:39Z"},{"alias_kind":"pith_short_16","alias_value":"2FJ7H4VS2QX3L6MA","created_at":"2026-07-05T05:46:39Z"},{"alias_kind":"pith_short_8","alias_value":"2FJ7H4VS","created_at":"2026-07-05T05:46:39Z"}],"graph_snapshots":[{"event_id":"sha256:bd85a183a8342f4b980adba9370ae669c515bd803b5f59ea7642c48ebeaa2768","target":"graph","created_at":"2026-07-05T05:46:39Z","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/2302.13814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abhinav Koyyalamudi, Lakshmivihari Mareedu, Noel Ngu, Paulo Shakarian","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-23T16:06:16Z","title":"An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13814","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":"sha256:7f325d698a381ecc0244afcaa2128a79c2482eae0debb682bfaabfad74d974a5","target":"record","created_at":"2026-07-05T05:46:39Z","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":"d9a9168e523cb3f38e4f09630343b028030451344c45a28e1b8825482c677318","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-23T16:06:16Z","title_canon_sha256":"eced63e2ca9bdfd99cb08d934ecfb445ae0ab3f9698aba52f872cd2ea12a6426"},"schema_version":"1.0","source":{"id":"2302.13814","kind":"arxiv","version":2}},"canonical_sha256":"d153f3f2b2d42fb5f980a9615dd1de4af70447744753d55015972ca97a1ff5f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d153f3f2b2d42fb5f980a9615dd1de4af70447744753d55015972ca97a1ff5f5","first_computed_at":"2026-07-05T05:46:39.889823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:46:39.889823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uP34ZYSO54iogGRsIwkpmrFYn95jbVYunEYVriQywGFFTOHqK2hMHF45UhcM5EmyJiuymRv7ZtPEAhq27m4MAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:46:39.890273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.13814","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f325d698a381ecc0244afcaa2128a79c2482eae0debb682bfaabfad74d974a5","sha256:bd85a183a8342f4b980adba9370ae669c515bd803b5f59ea7642c48ebeaa2768"],"state_sha256":"cf00e7981d0b45160432f9d5e4976216d00f43ba681898d684ef42ff5aaaa282"}