{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PIJ26HKD33FKGEOALBOZIQFYJH","short_pith_number":"pith:PIJ26HKD","schema_version":"1.0","canonical_sha256":"7a13af1d43decaa311c0585d9440b849cfa00486a344d0c21b6757b40ad7c288","source":{"kind":"arxiv","id":"2306.05524","version":2},"attestation_state":"computed","paper":{"title":"On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Luo, Fengjun Li, Zeyan Liu, Zijun Yao","submitted_at":"2023-06-07T12:33:24Z","abstract_excerpt":"With ChatGPT under the spotlight, utilizing large language models (LLMs) to assist academic writing has drawn a significant amount of debate in the community. In this paper, we aim to present a comprehensive study of the detectability of ChatGPT-generated content within the academic literature, particularly focusing on the abstracts of scientific papers, to offer holistic support for the future development of LLM applications and policies in academia. Specifically, we first present GPABench2, a benchmarking dataset of over 2.8 million comparative samples of human-written, GPT-written, GPT-comp"},"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":"2306.05524","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T12:33:24Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"6eea9619dd0518f8129f462a1f014edaa7d59fac8658ba5527dca6ba937f0cbd","abstract_canon_sha256":"f7eac689d7fab8a8c77f4a5ce68c297bd4fd04052135dc58cb258f21e01634a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:49.194338Z","signature_b64":"Uj7bCM4mQtXgwgW9/4r85HTK+0NvSGuOqAVHHfl0XCjPPnYhjRugEbZsBzWxE9TrPMaE8DAFNn4Qmd3auv0qDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a13af1d43decaa311c0585d9440b849cfa00486a344d0c21b6757b40ad7c288","last_reissued_at":"2026-07-05T07:56:49.193842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:49.193842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Luo, Fengjun Li, Zeyan Liu, Zijun Yao","submitted_at":"2023-06-07T12:33:24Z","abstract_excerpt":"With ChatGPT under the spotlight, utilizing large language models (LLMs) to assist academic writing has drawn a significant amount of debate in the community. In this paper, we aim to present a comprehensive study of the detectability of ChatGPT-generated content within the academic literature, particularly focusing on the abstracts of scientific papers, to offer holistic support for the future development of LLM applications and policies in academia. Specifically, we first present GPABench2, a benchmarking dataset of over 2.8 million comparative samples of human-written, GPT-written, GPT-comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05524","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/2306.05524/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":"2306.05524","created_at":"2026-07-05T07:56:49.193902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05524v2","created_at":"2026-07-05T07:56:49.193902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05524","created_at":"2026-07-05T07:56:49.193902+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIJ26HKD33FK","created_at":"2026-07-05T07:56:49.193902+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIJ26HKD33FKGEOA","created_at":"2026-07-05T07:56:49.193902+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIJ26HKD","created_at":"2026-07-05T07:56:49.193902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.23728","citing_title":"GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIJ26HKD33FKGEOALBOZIQFYJH","json":"https://pith.science/pith/PIJ26HKD33FKGEOALBOZIQFYJH.json","graph_json":"https://pith.science/api/pith-number/PIJ26HKD33FKGEOALBOZIQFYJH/graph.json","events_json":"https://pith.science/api/pith-number/PIJ26HKD33FKGEOALBOZIQFYJH/events.json","paper":"https://pith.science/paper/PIJ26HKD"},"agent_actions":{"view_html":"https://pith.science/pith/PIJ26HKD33FKGEOALBOZIQFYJH","download_json":"https://pith.science/pith/PIJ26HKD33FKGEOALBOZIQFYJH.json","view_paper":"https://pith.science/paper/PIJ26HKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05524&json=true","fetch_graph":"https://pith.science/api/pith-number/PIJ26HKD33FKGEOALBOZIQFYJH/graph.json","fetch_events":"https://pith.science/api/pith-number/PIJ26HKD33FKGEOALBOZIQFYJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIJ26HKD33FKGEOALBOZIQFYJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIJ26HKD33FKGEOALBOZIQFYJH/action/storage_attestation","attest_author":"https://pith.science/pith/PIJ26HKD33FKGEOALBOZIQFYJH/action/author_attestation","sign_citation":"https://pith.science/pith/PIJ26HKD33FKGEOALBOZIQFYJH/action/citation_signature","submit_replication":"https://pith.science/pith/PIJ26HKD33FKGEOALBOZIQFYJH/action/replication_record"}},"created_at":"2026-07-05T07:56:49.193902+00:00","updated_at":"2026-07-05T07:56:49.193902+00:00"}