{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H3L7DXCA2OIRIXVBE7I5HQJTOC","short_pith_number":"pith:H3L7DXCA","schema_version":"1.0","canonical_sha256":"3ed7f1dc40d391145ea127d1d3c13370a92bf1b476205ad75306d340a3251ec9","source":{"kind":"arxiv","id":"2604.04932","version":3},"attestation_state":"computed","paper":{"title":"Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"RACE separates creator intent from editor style to enable four-class detection of LLM-generated text.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danding Wang, Juan Cao, Qiang Sheng, Yang Li, Yehan Yang, Zhengjia Wang","submitted_at":"2026-04-06T17:59:55Z","abstract_excerpt":"The misuse of large language models (LLMs) requires precise detection of synthetic text. Existing works mainly follow binary or ternary classification settings, which can only distinguish pure human/LLM text or collaborative text at best. This remains insufficient for the nuanced regulation, as the LLM-polished human text and humanized LLM text often trigger different policy consequences. In this paper, we explore fine-grained LLM-generated text detection under a rigorous four-class setting. To handle such complexities, we propose RACE (Rhetorical Analysis for Creator-Editor Modeling), a fine-"},"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":true},"canonical_record":{"source":{"id":"2604.04932","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-06T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"79023ffe90622d7d170bad0569622f6d7cc71a74ebd4c3fde8c328d018fe4e35","abstract_canon_sha256":"ffd7133861e7d2c32839b61d0c1af9d7c8244f3984ffd760ea6dcfd0aa0f5a6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:30.830894Z","signature_b64":"hvEwZ0FkUhJy44lb80kf5HqG47xuamqoLQI1FK8Ezs109KdtR+Em4Mwt2ucRFcep/tg4cak7jFEGofBRkrpwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ed7f1dc40d391145ea127d1d3c13370a92bf1b476205ad75306d340a3251ec9","last_reissued_at":"2026-05-20T00:04:30.830038Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:30.830038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"RACE separates creator intent from editor style to enable four-class detection of LLM-generated text.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danding Wang, Juan Cao, Qiang Sheng, Yang Li, Yehan Yang, Zhengjia Wang","submitted_at":"2026-04-06T17:59:55Z","abstract_excerpt":"The misuse of large language models (LLMs) requires precise detection of synthetic text. Existing works mainly follow binary or ternary classification settings, which can only distinguish pure human/LLM text or collaborative text at best. This remains insufficient for the nuanced regulation, as the LLM-polished human text and humanized LLM text often trigger different policy consequences. In this paper, we explore fine-grained LLM-generated text detection under a rigorous four-class setting. To handle such complexities, we propose RACE (Rhetorical Analysis for Creator-Editor Modeling), a fine-"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"RACE outperforms 12 baselines in identifying fine-grained types with low false alarms, offering a policy-aligned solution for LLM regulation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That Rhetorical Structure Theory graphs and Elementary Discourse Unit features reliably separate creator intent from editor style even when both roles are played by LLMs or when editing is subtle.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RACE uses Rhetorical Structure Theory for creator logic graphs and Elementary Discourse Unit features for editor style to outperform baselines on four-class LLM text detection.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RACE separates creator intent from editor style to enable four-class detection of LLM-generated text.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1217cfe0c92c8742fbe3e493f677288d456d301f5f9fec63c205101d99f2ecd0"},"source":{"id":"2604.04932","kind":"arxiv","version":3},"verdict":{"id":"99fdee9b-4a81-42b3-8849-241e38a5108f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T19:40:57.031848Z","strongest_claim":"RACE outperforms 12 baselines in identifying fine-grained types with low false alarms, offering a policy-aligned solution for LLM regulation.","one_line_summary":"RACE uses Rhetorical Structure Theory for creator logic graphs and Elementary Discourse Unit features for editor style to outperform baselines on four-class LLM text detection.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That Rhetorical Structure Theory graphs and Elementary Discourse Unit features reliably separate creator intent from editor style even when both roles are played by LLMs or when editing is subtle.","pith_extraction_headline":"RACE separates creator intent from editor style to enable four-class detection of LLM-generated text."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.04932/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":2,"snapshot_sha256":"ef9040cb5e8db973a3121c7baf342644e1a94cbeca71c09d4249607926b94e29"},"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":"2604.04932","created_at":"2026-05-20T00:04:30.830181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.04932v3","created_at":"2026-05-20T00:04:30.830181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04932","created_at":"2026-05-20T00:04:30.830181+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3L7DXCA2OIR","created_at":"2026-05-20T00:04:30.830181+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3L7DXCA2OIRIXVB","created_at":"2026-05-20T00:04:30.830181+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3L7DXCA","created_at":"2026-05-20T00:04:30.830181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3L7DXCA2OIRIXVBE7I5HQJTOC","json":"https://pith.science/pith/H3L7DXCA2OIRIXVBE7I5HQJTOC.json","graph_json":"https://pith.science/api/pith-number/H3L7DXCA2OIRIXVBE7I5HQJTOC/graph.json","events_json":"https://pith.science/api/pith-number/H3L7DXCA2OIRIXVBE7I5HQJTOC/events.json","paper":"https://pith.science/paper/H3L7DXCA"},"agent_actions":{"view_html":"https://pith.science/pith/H3L7DXCA2OIRIXVBE7I5HQJTOC","download_json":"https://pith.science/pith/H3L7DXCA2OIRIXVBE7I5HQJTOC.json","view_paper":"https://pith.science/paper/H3L7DXCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.04932&json=true","fetch_graph":"https://pith.science/api/pith-number/H3L7DXCA2OIRIXVBE7I5HQJTOC/graph.json","fetch_events":"https://pith.science/api/pith-number/H3L7DXCA2OIRIXVBE7I5HQJTOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3L7DXCA2OIRIXVBE7I5HQJTOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3L7DXCA2OIRIXVBE7I5HQJTOC/action/storage_attestation","attest_author":"https://pith.science/pith/H3L7DXCA2OIRIXVBE7I5HQJTOC/action/author_attestation","sign_citation":"https://pith.science/pith/H3L7DXCA2OIRIXVBE7I5HQJTOC/action/citation_signature","submit_replication":"https://pith.science/pith/H3L7DXCA2OIRIXVBE7I5HQJTOC/action/replication_record"}},"created_at":"2026-05-20T00:04:30.830181+00:00","updated_at":"2026-05-20T00:04:30.830181+00:00"}