{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WMOO6QJL3JXRA2UZR426XANDG3","short_pith_number":"pith:WMOO6QJL","schema_version":"1.0","canonical_sha256":"b31cef412bda6f106a998f35eb81a336c7582105373aa399ed28259f799ae0ed","source":{"kind":"arxiv","id":"2309.02731","version":4},"attestation_state":"computed","paper":{"title":"HC3 Plus: A Semantic-Invariant Human ChatGPT Comparison Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangyuan Ma, Songlin Hu, Wei Zhou, Xing Wu, Zhenpeng Su","submitted_at":"2023-09-06T05:33:57Z","abstract_excerpt":"ChatGPT has garnered significant interest due to its impressive performance; however, there is growing concern about its potential risks, particularly in the detection of AI-generated content (AIGC), which is often challenging for untrained individuals to identify. Current datasets used for detecting ChatGPT-generated text primarily focus on question-answering tasks, often overlooking tasks with semantic-invariant properties, such as summarization, translation, and paraphrasing. In this paper, we demonstrate that detecting model-generated text in semantic-invariant tasks is more challenging. T"},"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":"2309.02731","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-06T05:33:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d52b8562622450f00a2d8a66cd08c9c380e08ebbcabce783089f08d39cb73fd3","abstract_canon_sha256":"5b71699fbbe71e2a71b9d74cbc45bad17b6dae00d97ec11f109d39224b90449b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:10.622603Z","signature_b64":"TJJRMI/0VRIj38aqe8caFwfRLWSBdEO1zanYjKdaKQ4EyROndJIKlnEl9X+4UyLRGdmvEEFfLal5ilcKXUI1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b31cef412bda6f106a998f35eb81a336c7582105373aa399ed28259f799ae0ed","last_reissued_at":"2026-07-05T09:17:10.622184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:10.622184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HC3 Plus: A Semantic-Invariant Human ChatGPT Comparison Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangyuan Ma, Songlin Hu, Wei Zhou, Xing Wu, Zhenpeng Su","submitted_at":"2023-09-06T05:33:57Z","abstract_excerpt":"ChatGPT has garnered significant interest due to its impressive performance; however, there is growing concern about its potential risks, particularly in the detection of AI-generated content (AIGC), which is often challenging for untrained individuals to identify. Current datasets used for detecting ChatGPT-generated text primarily focus on question-answering tasks, often overlooking tasks with semantic-invariant properties, such as summarization, translation, and paraphrasing. In this paper, we demonstrate that detecting model-generated text in semantic-invariant tasks is more challenging. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02731","kind":"arxiv","version":4},"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/2309.02731/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":"2309.02731","created_at":"2026-07-05T09:17:10.622240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02731v4","created_at":"2026-07-05T09:17:10.622240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02731","created_at":"2026-07-05T09:17:10.622240+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMOO6QJL3JXR","created_at":"2026-07-05T09:17:10.622240+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMOO6QJL3JXRA2UZ","created_at":"2026-07-05T09:17:10.622240+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMOO6QJL","created_at":"2026-07-05T09:17:10.622240+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25152","citing_title":"Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04205","citing_title":"DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03969","citing_title":"Feature-Augmented Transformers for Robust AI-Text Detection Across Domains and Generators","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMOO6QJL3JXRA2UZR426XANDG3","json":"https://pith.science/pith/WMOO6QJL3JXRA2UZR426XANDG3.json","graph_json":"https://pith.science/api/pith-number/WMOO6QJL3JXRA2UZR426XANDG3/graph.json","events_json":"https://pith.science/api/pith-number/WMOO6QJL3JXRA2UZR426XANDG3/events.json","paper":"https://pith.science/paper/WMOO6QJL"},"agent_actions":{"view_html":"https://pith.science/pith/WMOO6QJL3JXRA2UZR426XANDG3","download_json":"https://pith.science/pith/WMOO6QJL3JXRA2UZR426XANDG3.json","view_paper":"https://pith.science/paper/WMOO6QJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02731&json=true","fetch_graph":"https://pith.science/api/pith-number/WMOO6QJL3JXRA2UZR426XANDG3/graph.json","fetch_events":"https://pith.science/api/pith-number/WMOO6QJL3JXRA2UZR426XANDG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMOO6QJL3JXRA2UZR426XANDG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMOO6QJL3JXRA2UZR426XANDG3/action/storage_attestation","attest_author":"https://pith.science/pith/WMOO6QJL3JXRA2UZR426XANDG3/action/author_attestation","sign_citation":"https://pith.science/pith/WMOO6QJL3JXRA2UZR426XANDG3/action/citation_signature","submit_replication":"https://pith.science/pith/WMOO6QJL3JXRA2UZR426XANDG3/action/replication_record"}},"created_at":"2026-07-05T09:17:10.622240+00:00","updated_at":"2026-07-05T09:17:10.622240+00:00"}