{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SK5I5JBQU7HCVWNVVRNCB6PEPW","short_pith_number":"pith:SK5I5JBQ","schema_version":"1.0","canonical_sha256":"92ba8ea430a7ce2ad9b5ac5a20f9e47d892cc765951b636b5a5fdfe96bd7c30d","source":{"kind":"arxiv","id":"2402.11175","version":2},"attestation_state":"computed","paper":{"title":"M4GT-Bench: Evaluation Benchmark for 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, Giovanni Puccetti, Iryna Gurevych, Jinyan Su, Jonibek Mansurov, Nizar Habash, Osama Mohanned Afzal, Petar Ivanov, Preslav Nakov, Tarek Mahmoud, Thomas Arnold, Yuxia Wang","submitted_at":"2024-02-17T02:50:33Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has brought an unprecedented surge in machine-generated text (MGT) across diverse channels. This raises legitimate concerns about its potential misuse and societal implications. The need to identify and differentiate such content from genuine human-generated text is critical in combating disinformation, preserving the integrity of education and scientific fields, and maintaining trust in communication. In this work, we address this problem by introducing a new benchmark based on a multilingual, multi-domain, and multi-generator corpus of MGTs -- M4GT-"},"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":"2402.11175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-17T02:50:33Z","cross_cats_sorted":[],"title_canon_sha256":"e2f2cb4aeaee325f6940c9daae3599d334ae8ae99f22ecf3aefbc0d7a40a96b8","abstract_canon_sha256":"14e85a5764c724350665624e7c25747119b94b55e7814fbe3b72752f45487776"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:17.488904Z","signature_b64":"xxIVsl5K9ddLF8zAp+6sXyuU/nb5GOJK5Dspj9r/HjiQtYpiW/t33h14ClW+pM2VbYg1AsNCHbwAw02J6tblBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92ba8ea430a7ce2ad9b5ac5a20f9e47d892cc765951b636b5a5fdfe96bd7c30d","last_reissued_at":"2026-07-05T08:37:17.488402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:17.488402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M4GT-Bench: Evaluation Benchmark for 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, Giovanni Puccetti, Iryna Gurevych, Jinyan Su, Jonibek Mansurov, Nizar Habash, Osama Mohanned Afzal, Petar Ivanov, Preslav Nakov, Tarek Mahmoud, Thomas Arnold, Yuxia Wang","submitted_at":"2024-02-17T02:50:33Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has brought an unprecedented surge in machine-generated text (MGT) across diverse channels. This raises legitimate concerns about its potential misuse and societal implications. The need to identify and differentiate such content from genuine human-generated text is critical in combating disinformation, preserving the integrity of education and scientific fields, and maintaining trust in communication. In this work, we address this problem by introducing a new benchmark based on a multilingual, multi-domain, and multi-generator corpus of MGTs -- M4GT-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11175","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/2402.11175/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":"2402.11175","created_at":"2026-07-05T08:37:17.488462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11175v2","created_at":"2026-07-05T08:37:17.488462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11175","created_at":"2026-07-05T08:37:17.488462+00:00"},{"alias_kind":"pith_short_12","alias_value":"SK5I5JBQU7HC","created_at":"2026-07-05T08:37:17.488462+00:00"},{"alias_kind":"pith_short_16","alias_value":"SK5I5JBQU7HCVWNV","created_at":"2026-07-05T08:37:17.488462+00:00"},{"alias_kind":"pith_short_8","alias_value":"SK5I5JBQ","created_at":"2026-07-05T08:37:17.488462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.23728","citing_title":"GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2502.11614","citing_title":"Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AI","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SK5I5JBQU7HCVWNVVRNCB6PEPW","json":"https://pith.science/pith/SK5I5JBQU7HCVWNVVRNCB6PEPW.json","graph_json":"https://pith.science/api/pith-number/SK5I5JBQU7HCVWNVVRNCB6PEPW/graph.json","events_json":"https://pith.science/api/pith-number/SK5I5JBQU7HCVWNVVRNCB6PEPW/events.json","paper":"https://pith.science/paper/SK5I5JBQ"},"agent_actions":{"view_html":"https://pith.science/pith/SK5I5JBQU7HCVWNVVRNCB6PEPW","download_json":"https://pith.science/pith/SK5I5JBQU7HCVWNVVRNCB6PEPW.json","view_paper":"https://pith.science/paper/SK5I5JBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11175&json=true","fetch_graph":"https://pith.science/api/pith-number/SK5I5JBQU7HCVWNVVRNCB6PEPW/graph.json","fetch_events":"https://pith.science/api/pith-number/SK5I5JBQU7HCVWNVVRNCB6PEPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SK5I5JBQU7HCVWNVVRNCB6PEPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SK5I5JBQU7HCVWNVVRNCB6PEPW/action/storage_attestation","attest_author":"https://pith.science/pith/SK5I5JBQU7HCVWNVVRNCB6PEPW/action/author_attestation","sign_citation":"https://pith.science/pith/SK5I5JBQU7HCVWNVVRNCB6PEPW/action/citation_signature","submit_replication":"https://pith.science/pith/SK5I5JBQU7HCVWNVVRNCB6PEPW/action/replication_record"}},"created_at":"2026-07-05T08:37:17.488462+00:00","updated_at":"2026-07-05T08:37:17.488462+00:00"}