{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QPXQW2FDU3I77UQAS4UIRLRWIB","short_pith_number":"pith:QPXQW2FD","schema_version":"1.0","canonical_sha256":"83ef0b68a3a6d1ffd200972888ae36406044a15b9c5ac955fe3c874b0477d3f7","source":{"kind":"arxiv","id":"2305.14902","version":2},"attestation_state":"computed","paper":{"title":"M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akim Tsvigun, Alham Fikri Aji, Artem Shelmanov, Chenxi Whitehouse, Iryna Gurevych, Jinyan Su, Jonibek Mansurov, Nizar Habash, Osama Mohammed Afzal, Petar Ivanov, Preslav Nakov, Tarek Mahmoud, Thomas Arnold, Toru Sasaki, Yuxia Wang","submitted_at":"2023-05-24T08:55:11Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capability to generate fluent responses to a wide variety of user queries. However, this has also raised concerns about the potential misuse of such texts in journalism, education, and academia. In this study, we strive to create automated systems that can detect machine-generated texts and pinpoint potential misuse. We first introduce a large-scale benchmark \\textbf{M4}, which is a multi-generator, multi-domain, and multi-lingual corpus for machine-generated text detection. Through an extensive empirical study of this dataset, we show "},"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":"2305.14902","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:55:11Z","cross_cats_sorted":[],"title_canon_sha256":"b738eef8d4fd19f0234ed60de38227164deeebe8d669e798c21e60c26dcc0a08","abstract_canon_sha256":"0d85ea5c43fe898dc9c5e1e23344080b7df69de8ff4233ac70f4e94b9d22ef69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:00.998696Z","signature_b64":"50XMu1GBfL2JIOCTuUHLICSkGSCcNBVleJ7lzwOlcJuc0FzGU3JHYfU+pTvw8oqFBFOaGYErXDg0aD37LCBCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83ef0b68a3a6d1ffd200972888ae36406044a15b9c5ac955fe3c874b0477d3f7","last_reissued_at":"2026-07-05T07:54:00.998189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:00.998189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akim Tsvigun, Alham Fikri Aji, Artem Shelmanov, Chenxi Whitehouse, Iryna Gurevych, Jinyan Su, Jonibek Mansurov, Nizar Habash, Osama Mohammed Afzal, Petar Ivanov, Preslav Nakov, Tarek Mahmoud, Thomas Arnold, Toru Sasaki, Yuxia Wang","submitted_at":"2023-05-24T08:55:11Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capability to generate fluent responses to a wide variety of user queries. However, this has also raised concerns about the potential misuse of such texts in journalism, education, and academia. In this study, we strive to create automated systems that can detect machine-generated texts and pinpoint potential misuse. We first introduce a large-scale benchmark \\textbf{M4}, which is a multi-generator, multi-domain, and multi-lingual corpus for machine-generated text detection. Through an extensive empirical study of this dataset, we show "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14902","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/2305.14902/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":"2305.14902","created_at":"2026-07-05T07:54:00.998249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14902v2","created_at":"2026-07-05T07:54:00.998249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14902","created_at":"2026-07-05T07:54:00.998249+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPXQW2FDU3I7","created_at":"2026-07-05T07:54:00.998249+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPXQW2FDU3I77UQA","created_at":"2026-07-05T07:54:00.998249+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPXQW2FD","created_at":"2026-07-05T07:54:00.998249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19915","citing_title":"LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directions","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21300","citing_title":"Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPXQW2FDU3I77UQAS4UIRLRWIB","json":"https://pith.science/pith/QPXQW2FDU3I77UQAS4UIRLRWIB.json","graph_json":"https://pith.science/api/pith-number/QPXQW2FDU3I77UQAS4UIRLRWIB/graph.json","events_json":"https://pith.science/api/pith-number/QPXQW2FDU3I77UQAS4UIRLRWIB/events.json","paper":"https://pith.science/paper/QPXQW2FD"},"agent_actions":{"view_html":"https://pith.science/pith/QPXQW2FDU3I77UQAS4UIRLRWIB","download_json":"https://pith.science/pith/QPXQW2FDU3I77UQAS4UIRLRWIB.json","view_paper":"https://pith.science/paper/QPXQW2FD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14902&json=true","fetch_graph":"https://pith.science/api/pith-number/QPXQW2FDU3I77UQAS4UIRLRWIB/graph.json","fetch_events":"https://pith.science/api/pith-number/QPXQW2FDU3I77UQAS4UIRLRWIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPXQW2FDU3I77UQAS4UIRLRWIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPXQW2FDU3I77UQAS4UIRLRWIB/action/storage_attestation","attest_author":"https://pith.science/pith/QPXQW2FDU3I77UQAS4UIRLRWIB/action/author_attestation","sign_citation":"https://pith.science/pith/QPXQW2FDU3I77UQAS4UIRLRWIB/action/citation_signature","submit_replication":"https://pith.science/pith/QPXQW2FDU3I77UQAS4UIRLRWIB/action/replication_record"}},"created_at":"2026-07-05T07:54:00.998249+00:00","updated_at":"2026-07-05T07:54:00.998249+00:00"}