{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XEX2BKIFHDDYFI2C375HL5IU53","short_pith_number":"pith:XEX2BKIF","schema_version":"1.0","canonical_sha256":"b92fa0a90538c782a342dffa75f514eee3479781693eb1e34bd296fae5f8ffc7","source":{"kind":"arxiv","id":"2304.14106","version":2},"attestation_state":"computed","paper":{"title":"ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunyang Li, Jifan Yu, Juanzi Li, Lei Hou, Shangqing Tu, Xiaozhi Wang","submitted_at":"2023-04-27T11:33:48Z","abstract_excerpt":"ChatGPT has achieved great success and can be considered to have acquired an infrastructural status. There are abundant works for evaluating ChatGPT on benchmarks. However, existing benchmarks encounter two challenges: (1) Disregard for periodical evaluation and (2) Lack of fine-grained features. In this paper, we construct ChatLog, an ever-updating dataset with large-scale records of diverse long-form ChatGPT responses for 21 NLP benchmarks from March, 2023 to now. We conduct a comprehensive performance evaluation to find that most capabilities of ChatGPT improve over time except for some abi"},"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":"2304.14106","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-27T11:33:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"265026598bb536ddbe3166fef092e7e8d80ecb47fa826a0789a7b874d0beea94","abstract_canon_sha256":"a8eb55f10cae05c2dac1a8d0d44fc017674f65af0d2209d3a5ef4798a8cdbc97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:59.054089Z","signature_b64":"u2qw4mVarJHSJsU0SXf2vk2kf2kVqlZbZymH/2j614ENxd0xIUvtKaOZC46XGXroc3S2weJdrwF9AL3hV2hdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b92fa0a90538c782a342dffa75f514eee3479781693eb1e34bd296fae5f8ffc7","last_reissued_at":"2026-07-05T08:32:59.053583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:59.053583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunyang Li, Jifan Yu, Juanzi Li, Lei Hou, Shangqing Tu, Xiaozhi Wang","submitted_at":"2023-04-27T11:33:48Z","abstract_excerpt":"ChatGPT has achieved great success and can be considered to have acquired an infrastructural status. There are abundant works for evaluating ChatGPT on benchmarks. However, existing benchmarks encounter two challenges: (1) Disregard for periodical evaluation and (2) Lack of fine-grained features. In this paper, we construct ChatLog, an ever-updating dataset with large-scale records of diverse long-form ChatGPT responses for 21 NLP benchmarks from March, 2023 to now. We conduct a comprehensive performance evaluation to find that most capabilities of ChatGPT improve over time except for some abi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14106","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/2304.14106/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":"2304.14106","created_at":"2026-07-05T08:32:59.053642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14106v2","created_at":"2026-07-05T08:32:59.053642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14106","created_at":"2026-07-05T08:32:59.053642+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEX2BKIFHDDY","created_at":"2026-07-05T08:32:59.053642+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEX2BKIFHDDYFI2C","created_at":"2026-07-05T08:32:59.053642+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEX2BKIF","created_at":"2026-07-05T08:32:59.053642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31808","citing_title":"Large Databases Need Small, Open-Weight Language Models","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEX2BKIFHDDYFI2C375HL5IU53","json":"https://pith.science/pith/XEX2BKIFHDDYFI2C375HL5IU53.json","graph_json":"https://pith.science/api/pith-number/XEX2BKIFHDDYFI2C375HL5IU53/graph.json","events_json":"https://pith.science/api/pith-number/XEX2BKIFHDDYFI2C375HL5IU53/events.json","paper":"https://pith.science/paper/XEX2BKIF"},"agent_actions":{"view_html":"https://pith.science/pith/XEX2BKIFHDDYFI2C375HL5IU53","download_json":"https://pith.science/pith/XEX2BKIFHDDYFI2C375HL5IU53.json","view_paper":"https://pith.science/paper/XEX2BKIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14106&json=true","fetch_graph":"https://pith.science/api/pith-number/XEX2BKIFHDDYFI2C375HL5IU53/graph.json","fetch_events":"https://pith.science/api/pith-number/XEX2BKIFHDDYFI2C375HL5IU53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEX2BKIFHDDYFI2C375HL5IU53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEX2BKIFHDDYFI2C375HL5IU53/action/storage_attestation","attest_author":"https://pith.science/pith/XEX2BKIFHDDYFI2C375HL5IU53/action/author_attestation","sign_citation":"https://pith.science/pith/XEX2BKIFHDDYFI2C375HL5IU53/action/citation_signature","submit_replication":"https://pith.science/pith/XEX2BKIFHDDYFI2C375HL5IU53/action/replication_record"}},"created_at":"2026-07-05T08:32:59.053642+00:00","updated_at":"2026-07-05T08:32:59.053642+00:00"}