{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5LQ7GNWEBKOUEAKJBU2S2MU5TO","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":"5de7b612f7a60bcc07de677c5149d01e7195bdd5a916ca5bd63b30b73a69433d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-18T06:56:08Z","title_canon_sha256":"c4c9097321802a2ca081f6e0104b8a2c4ae58369ef2a7b3514055cb957cf7c96"},"schema_version":"1.0","source":{"id":"2307.09009","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.09009","created_at":"2026-07-05T07:07:13Z"},{"alias_kind":"arxiv_version","alias_value":"2307.09009v3","created_at":"2026-07-05T07:07:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09009","created_at":"2026-07-05T07:07:13Z"},{"alias_kind":"pith_short_12","alias_value":"5LQ7GNWEBKOU","created_at":"2026-07-05T07:07:13Z"},{"alias_kind":"pith_short_16","alias_value":"5LQ7GNWEBKOUEAKJ","created_at":"2026-07-05T07:07:13Z"},{"alias_kind":"pith_short_8","alias_value":"5LQ7GNWE","created_at":"2026-07-05T07:07:13Z"}],"graph_snapshots":[{"event_id":"sha256:9221957a0a070c64838b39a9a58e6777335c6f7ac60f2fa14030b2cfff65d52b","target":"graph","created_at":"2026-07-05T07:07:13Z","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/2307.09009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"GPT-3.5 and GPT-4 are the two most widely used large language model (LLM) services. However, when and how these models are updated over time is opaque. Here, we evaluate the March 2023 and June 2023 versions of GPT-3.5 and GPT-4 on several diverse tasks: 1) math problems, 2) sensitive/dangerous questions, 3) opinion surveys, 4) multi-hop knowledge-intensive questions, 5) generating code, 6) US Medical License tests, and 7) visual reasoning. We find that the performance and behavior of both GPT-3.5 and GPT-4 can vary greatly over time. For example, GPT-4 (March 2023) was reasonable at identifyi","authors_text":"James Zou, Lingjiao Chen, Matei Zaharia","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-18T06:56:08Z","title":"How is ChatGPT's behavior changing over time?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09009","kind":"arxiv","version":3},"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":"sha256:27f1f4ef0d5550a46650e6a06a7f5c82e7fa8aedbbd872c44c56c6bd3fb94677","target":"record","created_at":"2026-07-05T07:07:13Z","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":"5de7b612f7a60bcc07de677c5149d01e7195bdd5a916ca5bd63b30b73a69433d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-18T06:56:08Z","title_canon_sha256":"c4c9097321802a2ca081f6e0104b8a2c4ae58369ef2a7b3514055cb957cf7c96"},"schema_version":"1.0","source":{"id":"2307.09009","kind":"arxiv","version":3}},"canonical_sha256":"eae1f336c40a9d4201490d352d329d9bb3a70cc96e5588b2482993e7b6345775","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eae1f336c40a9d4201490d352d329d9bb3a70cc96e5588b2482993e7b6345775","first_computed_at":"2026-07-05T07:07:13.479475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:13.479475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vtyeGMlhRUVIqr1UHzh32TRe4ieCJkKITvV7AOVhurb9s8eodPqGrVzl4HLfMPQIkYD+OzMiirICclgsePpTBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:13.480060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.09009","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27f1f4ef0d5550a46650e6a06a7f5c82e7fa8aedbbd872c44c56c6bd3fb94677","sha256:9221957a0a070c64838b39a9a58e6777335c6f7ac60f2fa14030b2cfff65d52b"],"state_sha256":"9501bbd919a1cdefb75a448a139bd80cfb45704537f993993720e6b29ddef607"}