{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6I6GO6TI6353IPXC6BMOOVKR67","short_pith_number":"pith:6I6GO6TI","schema_version":"1.0","canonical_sha256":"f23c677a68f6fbb43ee2f058e75551f7d6235c57999f7e659137e0b0fffe8eeb","source":{"kind":"arxiv","id":"2401.12326","version":1},"attestation_state":"computed","paper":{"title":"Fine-tuning Large Language Models for Multigenerator, Multidomain, and Multilingual Machine-Generated Text Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Feng Xiong, Huizhi Liang, Subin Jung, Thanet Markchom, Varun Ojha, Ziwei Zheng","submitted_at":"2024-01-22T19:39:05Z","abstract_excerpt":"SemEval-2024 Task 8 introduces the challenge of identifying machine-generated texts from diverse Large Language Models (LLMs) in various languages and domains. The task comprises three subtasks: binary classification in monolingual and multilingual (Subtask A), multi-class classification (Subtask B), and mixed text detection (Subtask C). This paper focuses on Subtask A & B. Each subtask is supported by three datasets for training, development, and testing. To tackle this task, two methods: 1) using traditional machine learning (ML) with natural language preprocessing (NLP) for feature extracti"},"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":"2401.12326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T19:39:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"74128feadd0a24d90360620eb3de3799febf4b2a38e568530da54b5594ef279c","abstract_canon_sha256":"98c369b522c4d7f88a279757a59cc04075a01605f87fd827112013dafd9b6223"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:29.052082Z","signature_b64":"rvBroBPwzn0774RD3lPJX+Hlm1nDwnKdywb0l0XuLKinfprZS8JZx0B/xba7dD0rAgzQ8q0NCBb9nGlQiZBDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f23c677a68f6fbb43ee2f058e75551f7d6235c57999f7e659137e0b0fffe8eeb","last_reissued_at":"2026-07-05T07:36:29.051740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:29.051740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-tuning Large Language Models for Multigenerator, Multidomain, and Multilingual Machine-Generated Text Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Feng Xiong, Huizhi Liang, Subin Jung, Thanet Markchom, Varun Ojha, Ziwei Zheng","submitted_at":"2024-01-22T19:39:05Z","abstract_excerpt":"SemEval-2024 Task 8 introduces the challenge of identifying machine-generated texts from diverse Large Language Models (LLMs) in various languages and domains. The task comprises three subtasks: binary classification in monolingual and multilingual (Subtask A), multi-class classification (Subtask B), and mixed text detection (Subtask C). This paper focuses on Subtask A & B. Each subtask is supported by three datasets for training, development, and testing. To tackle this task, two methods: 1) using traditional machine learning (ML) with natural language preprocessing (NLP) for feature extracti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12326","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/2401.12326/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":"2401.12326","created_at":"2026-07-05T07:36:29.051794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12326v1","created_at":"2026-07-05T07:36:29.051794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12326","created_at":"2026-07-05T07:36:29.051794+00:00"},{"alias_kind":"pith_short_12","alias_value":"6I6GO6TI6353","created_at":"2026-07-05T07:36:29.051794+00:00"},{"alias_kind":"pith_short_16","alias_value":"6I6GO6TI6353IPXC","created_at":"2026-07-05T07:36:29.051794+00:00"},{"alias_kind":"pith_short_8","alias_value":"6I6GO6TI","created_at":"2026-07-05T07:36:29.051794+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/6I6GO6TI6353IPXC6BMOOVKR67","json":"https://pith.science/pith/6I6GO6TI6353IPXC6BMOOVKR67.json","graph_json":"https://pith.science/api/pith-number/6I6GO6TI6353IPXC6BMOOVKR67/graph.json","events_json":"https://pith.science/api/pith-number/6I6GO6TI6353IPXC6BMOOVKR67/events.json","paper":"https://pith.science/paper/6I6GO6TI"},"agent_actions":{"view_html":"https://pith.science/pith/6I6GO6TI6353IPXC6BMOOVKR67","download_json":"https://pith.science/pith/6I6GO6TI6353IPXC6BMOOVKR67.json","view_paper":"https://pith.science/paper/6I6GO6TI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12326&json=true","fetch_graph":"https://pith.science/api/pith-number/6I6GO6TI6353IPXC6BMOOVKR67/graph.json","fetch_events":"https://pith.science/api/pith-number/6I6GO6TI6353IPXC6BMOOVKR67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6I6GO6TI6353IPXC6BMOOVKR67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6I6GO6TI6353IPXC6BMOOVKR67/action/storage_attestation","attest_author":"https://pith.science/pith/6I6GO6TI6353IPXC6BMOOVKR67/action/author_attestation","sign_citation":"https://pith.science/pith/6I6GO6TI6353IPXC6BMOOVKR67/action/citation_signature","submit_replication":"https://pith.science/pith/6I6GO6TI6353IPXC6BMOOVKR67/action/replication_record"}},"created_at":"2026-07-05T07:36:29.051794+00:00","updated_at":"2026-07-05T07:36:29.051794+00:00"}