{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ORMPTQWIGWZIY2UWH44R4VMBWC","short_pith_number":"pith:ORMPTQWI","schema_version":"1.0","canonical_sha256":"7458f9c2c835b28c6a963f391e5581b08165cdd064d8fa2bbea1af8183ecc85a","source":{"kind":"arxiv","id":"2404.05483","version":1},"attestation_state":"computed","paper":{"title":"PetKaz at SemEval-2024 Task 8: Can Linguistics Capture the Specifics of LLM-generated Text?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ekaterina Kochmar, Kseniia Petukhova, Roman Kazakov","submitted_at":"2024-04-08T13:05:02Z","abstract_excerpt":"In this paper, we present our submission to the SemEval-2024 Task 8 \"Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection\", focusing on the detection of machine-generated texts (MGTs) in English. Specifically, our approach relies on combining embeddings from the RoBERTa-base with diversity features and uses a resampled training set. We score 12th from 124 in the ranking for Subtask A (monolingual track), and our results show that our approach is generalizable across unseen models and domains, achieving an accuracy of 0.91."},"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":"2404.05483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T13:05:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2198f559065c9ba94a6ed3190ff593dcc72404f7147d03f58920e10783c1360","abstract_canon_sha256":"f2014031351a3e16485680ad5e0d4cc323ca924426cbd56ffa2dc5dbbdc244fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:41.190290Z","signature_b64":"ZgIoWfNDwtcrNv7ODINuruZrmPSmSVw82ixoq/2swWXhLym+rhYEwsWxJdleglPtuKkRfegQLB3eL9Clj2gRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7458f9c2c835b28c6a963f391e5581b08165cdd064d8fa2bbea1af8183ecc85a","last_reissued_at":"2026-07-05T08:05:41.189830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:41.189830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PetKaz at SemEval-2024 Task 8: Can Linguistics Capture the Specifics of LLM-generated Text?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ekaterina Kochmar, Kseniia Petukhova, Roman Kazakov","submitted_at":"2024-04-08T13:05:02Z","abstract_excerpt":"In this paper, we present our submission to the SemEval-2024 Task 8 \"Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection\", focusing on the detection of machine-generated texts (MGTs) in English. Specifically, our approach relies on combining embeddings from the RoBERTa-base with diversity features and uses a resampled training set. We score 12th from 124 in the ranking for Subtask A (monolingual track), and our results show that our approach is generalizable across unseen models and domains, achieving an accuracy of 0.91."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05483","kind":"arxiv","version":1},"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/2404.05483/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":"2404.05483","created_at":"2026-07-05T08:05:41.189887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05483v1","created_at":"2026-07-05T08:05:41.189887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05483","created_at":"2026-07-05T08:05:41.189887+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORMPTQWIGWZI","created_at":"2026-07-05T08:05:41.189887+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORMPTQWIGWZIY2UW","created_at":"2026-07-05T08:05:41.189887+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORMPTQWI","created_at":"2026-07-05T08:05:41.189887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORMPTQWIGWZIY2UWH44R4VMBWC","json":"https://pith.science/pith/ORMPTQWIGWZIY2UWH44R4VMBWC.json","graph_json":"https://pith.science/api/pith-number/ORMPTQWIGWZIY2UWH44R4VMBWC/graph.json","events_json":"https://pith.science/api/pith-number/ORMPTQWIGWZIY2UWH44R4VMBWC/events.json","paper":"https://pith.science/paper/ORMPTQWI"},"agent_actions":{"view_html":"https://pith.science/pith/ORMPTQWIGWZIY2UWH44R4VMBWC","download_json":"https://pith.science/pith/ORMPTQWIGWZIY2UWH44R4VMBWC.json","view_paper":"https://pith.science/paper/ORMPTQWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05483&json=true","fetch_graph":"https://pith.science/api/pith-number/ORMPTQWIGWZIY2UWH44R4VMBWC/graph.json","fetch_events":"https://pith.science/api/pith-number/ORMPTQWIGWZIY2UWH44R4VMBWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORMPTQWIGWZIY2UWH44R4VMBWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORMPTQWIGWZIY2UWH44R4VMBWC/action/storage_attestation","attest_author":"https://pith.science/pith/ORMPTQWIGWZIY2UWH44R4VMBWC/action/author_attestation","sign_citation":"https://pith.science/pith/ORMPTQWIGWZIY2UWH44R4VMBWC/action/citation_signature","submit_replication":"https://pith.science/pith/ORMPTQWIGWZIY2UWH44R4VMBWC/action/replication_record"}},"created_at":"2026-07-05T08:05:41.189887+00:00","updated_at":"2026-07-05T08:05:41.189887+00:00"}