{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RCLXNP2SWIAEQLSQLSTAL7BRLU","short_pith_number":"pith:RCLXNP2S","schema_version":"1.0","canonical_sha256":"889776bf52b200482e505ca605fc315d2fef6f9400683e65063dcab1c4068764","source":{"kind":"arxiv","id":"2303.13648","version":1},"attestation_state":"computed","paper":{"title":"ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoran Wu, Michael Lyu, Wenxiang Jiao, Wenxuan Wang, Yuxuan Wan","submitted_at":"2023-03-15T00:35:50Z","abstract_excerpt":"ChatGPT is a cutting-edge artificial intelligence language model developed by OpenAI, which has attracted a lot of attention due to its surprisingly strong ability in answering follow-up questions. In this report, we aim to evaluate ChatGPT on the Grammatical Error Correction(GEC) task, and compare it with commercial GEC product (e.g., Grammarly) and state-of-the-art models (e.g., GECToR). By testing on the CoNLL2014 benchmark dataset, we find that ChatGPT performs not as well as those baselines in terms of the automatic evaluation metrics (e.g., $F_{0.5}$ score), particularly on long sentence"},"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":"2303.13648","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-15T00:35:50Z","cross_cats_sorted":[],"title_canon_sha256":"76a4fd310903f5b69e919cb0012d7e2873a6f02cfe8f1193477a8e69b56e86d1","abstract_canon_sha256":"56277f92a94577d8d695f197d6953b4332171fd6cd3835d251a8bf407e4f5254"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:17.447831Z","signature_b64":"iNa19W5Mu3F+3HAyZtrpSLI5OzY+HDE8+OeSsLlDrze0GOYMZp0pdugXgctUeoAhHC/A4EJF9DTYDAPhcIQ4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"889776bf52b200482e505ca605fc315d2fef6f9400683e65063dcab1c4068764","last_reissued_at":"2026-07-05T05:54:17.447291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:17.447291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoran Wu, Michael Lyu, Wenxiang Jiao, Wenxuan Wang, Yuxuan Wan","submitted_at":"2023-03-15T00:35:50Z","abstract_excerpt":"ChatGPT is a cutting-edge artificial intelligence language model developed by OpenAI, which has attracted a lot of attention due to its surprisingly strong ability in answering follow-up questions. In this report, we aim to evaluate ChatGPT on the Grammatical Error Correction(GEC) task, and compare it with commercial GEC product (e.g., Grammarly) and state-of-the-art models (e.g., GECToR). By testing on the CoNLL2014 benchmark dataset, we find that ChatGPT performs not as well as those baselines in terms of the automatic evaluation metrics (e.g., $F_{0.5}$ score), particularly on long sentence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13648","kind":"arxiv","version":1},"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/2303.13648/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":"2303.13648","created_at":"2026-07-05T05:54:17.447359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13648v1","created_at":"2026-07-05T05:54:17.447359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13648","created_at":"2026-07-05T05:54:17.447359+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCLXNP2SWIAE","created_at":"2026-07-05T05:54:17.447359+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCLXNP2SWIAEQLSQ","created_at":"2026-07-05T05:54:17.447359+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCLXNP2S","created_at":"2026-07-05T05:54:17.447359+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.00761","citing_title":"Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2305.19118","citing_title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCLXNP2SWIAEQLSQLSTAL7BRLU","json":"https://pith.science/pith/RCLXNP2SWIAEQLSQLSTAL7BRLU.json","graph_json":"https://pith.science/api/pith-number/RCLXNP2SWIAEQLSQLSTAL7BRLU/graph.json","events_json":"https://pith.science/api/pith-number/RCLXNP2SWIAEQLSQLSTAL7BRLU/events.json","paper":"https://pith.science/paper/RCLXNP2S"},"agent_actions":{"view_html":"https://pith.science/pith/RCLXNP2SWIAEQLSQLSTAL7BRLU","download_json":"https://pith.science/pith/RCLXNP2SWIAEQLSQLSTAL7BRLU.json","view_paper":"https://pith.science/paper/RCLXNP2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13648&json=true","fetch_graph":"https://pith.science/api/pith-number/RCLXNP2SWIAEQLSQLSTAL7BRLU/graph.json","fetch_events":"https://pith.science/api/pith-number/RCLXNP2SWIAEQLSQLSTAL7BRLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCLXNP2SWIAEQLSQLSTAL7BRLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCLXNP2SWIAEQLSQLSTAL7BRLU/action/storage_attestation","attest_author":"https://pith.science/pith/RCLXNP2SWIAEQLSQLSTAL7BRLU/action/author_attestation","sign_citation":"https://pith.science/pith/RCLXNP2SWIAEQLSQLSTAL7BRLU/action/citation_signature","submit_replication":"https://pith.science/pith/RCLXNP2SWIAEQLSQLSTAL7BRLU/action/replication_record"}},"created_at":"2026-07-05T05:54:17.447359+00:00","updated_at":"2026-07-05T05:54:17.447359+00:00"}