{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4LCDCIB3VUUDJ4RKQFEP7KBKBI","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":"e59a863cf28c34ae87885e33b6c9f776e9db737da20dcc090de5a6af00af1746","cross_cats_sorted":["math.HO","physics.pop-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-10T17:22:28Z","title_canon_sha256":"b6cc3d538cab86c09e0812cc7d654daedcd647452f374a881b29fff83b62dd63"},"schema_version":"1.0","source":{"id":"2308.05713","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.05713","created_at":"2026-07-05T10:17:04Z"},{"alias_kind":"arxiv_version","alias_value":"2308.05713v4","created_at":"2026-07-05T10:17:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05713","created_at":"2026-07-05T10:17:04Z"},{"alias_kind":"pith_short_12","alias_value":"4LCDCIB3VUUD","created_at":"2026-07-05T10:17:04Z"},{"alias_kind":"pith_short_16","alias_value":"4LCDCIB3VUUDJ4RK","created_at":"2026-07-05T10:17:04Z"},{"alias_kind":"pith_short_8","alias_value":"4LCDCIB3","created_at":"2026-07-05T10:17:04Z"}],"graph_snapshots":[{"event_id":"sha256:26b857329d316accc25f8d06ba97b28075024f21d40f5f4174aef0c7dd4b7d3d","target":"graph","created_at":"2026-07-05T10:17:04Z","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/2308.05713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This report describes a test of the large language model GPT-4 with the Wolfram Alpha and the Code Interpreter plug-ins on 105 original problems in science and math, at the high school and college levels, carried out in June-August 2023. Our tests suggest that the plug-ins significantly enhance GPT's ability to solve these problems. Having said that, there are still often \"interface\" failures; that is, GPT often has trouble formulating problems in a way that elicits useful answers from the plug-ins. Fixing these interface failures seems like a central challenge in making GPT a reliable tool fo","authors_text":"Ernest Davis, Scott Aaronson","cross_cats":["math.HO","physics.pop-ph"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-10T17:22:28Z","title":"Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05713","kind":"arxiv","version":4},"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:c21e44d4ebf8cdadfdc94dddfa9ff781aa4f4de628d9dad868ccc2619ec54d80","target":"record","created_at":"2026-07-05T10:17:04Z","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":"e59a863cf28c34ae87885e33b6c9f776e9db737da20dcc090de5a6af00af1746","cross_cats_sorted":["math.HO","physics.pop-ph"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-10T17:22:28Z","title_canon_sha256":"b6cc3d538cab86c09e0812cc7d654daedcd647452f374a881b29fff83b62dd63"},"schema_version":"1.0","source":{"id":"2308.05713","kind":"arxiv","version":4}},"canonical_sha256":"e2c431203bad2834f22a8148ffa82a0a1f37936a82cb6041a7db1e783efd9c70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2c431203bad2834f22a8148ffa82a0a1f37936a82cb6041a7db1e783efd9c70","first_computed_at":"2026-07-05T10:17:04.954438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:04.954438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ViyGMBzMXgXfoCgpckrjviSs3uo66TgSfH48foaM6ZDoMwizA+ULwUDB94KWnOwWWb4bJwL7bskgke7+vCg6AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:04.954853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.05713","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c21e44d4ebf8cdadfdc94dddfa9ff781aa4f4de628d9dad868ccc2619ec54d80","sha256:26b857329d316accc25f8d06ba97b28075024f21d40f5f4174aef0c7dd4b7d3d"],"state_sha256":"0d992a84ec57bbbd0351b86d1f5d000c125832765f6801a34632c9e1fc947590"}