{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GLJM54YCYHIIN2YHRUF2ZHWJWF","short_pith_number":"pith:GLJM54YC","schema_version":"1.0","canonical_sha256":"32d2cef302c1d086eb078d0bac9ec9b173ef446bf4981a8b75a984fe7cfa28d0","source":{"kind":"arxiv","id":"2402.01158","version":1},"attestation_state":"computed","paper":{"title":"LLM-Detector: Improving AI-Generated Chinese Text Detection with Open-Source LLM Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baoyu Fan, Han Ma, Haoming Chen, Rongsheng Wang, Ruizhe Zhou, Songhua Yang, Tao Tan, Yanlan Kang, Yaofei Duan","submitted_at":"2024-02-02T05:54:12Z","abstract_excerpt":"ChatGPT and other general large language models (LLMs) have achieved remarkable success, but they have also raised concerns about the misuse of AI-generated texts. Existing AI-generated text detection models, such as based on BERT and RoBERTa, are prone to in-domain over-fitting, leading to poor out-of-domain (OOD) detection performance. In this paper, we first collected Chinese text responses generated by human experts and 9 types of LLMs, for which to multiple domains questions, and further created a dataset that mixed human-written sentences and sentences polished by LLMs. We then proposed "},"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":"2402.01158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T05:54:12Z","cross_cats_sorted":[],"title_canon_sha256":"caec40036c2c75b9a7f0e8829b3fa20292624947d2914cd02a7429d892da05bf","abstract_canon_sha256":"37418dcb53f03984d670455d1451b5af9796e98942a38ef2ae234f52fe9b293b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:31.562494Z","signature_b64":"ij7hMG2u+R08TkbNoZQ95pcmPLlo9hKzoKYyvt3TWeIJ+w8gJ8OmXHWivz0jgfKQSb5ap+8YFU9LR0VNlHcqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32d2cef302c1d086eb078d0bac9ec9b173ef446bf4981a8b75a984fe7cfa28d0","last_reissued_at":"2026-07-05T07:40:31.562134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:31.562134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Detector: Improving AI-Generated Chinese Text Detection with Open-Source LLM Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baoyu Fan, Han Ma, Haoming Chen, Rongsheng Wang, Ruizhe Zhou, Songhua Yang, Tao Tan, Yanlan Kang, Yaofei Duan","submitted_at":"2024-02-02T05:54:12Z","abstract_excerpt":"ChatGPT and other general large language models (LLMs) have achieved remarkable success, but they have also raised concerns about the misuse of AI-generated texts. Existing AI-generated text detection models, such as based on BERT and RoBERTa, are prone to in-domain over-fitting, leading to poor out-of-domain (OOD) detection performance. In this paper, we first collected Chinese text responses generated by human experts and 9 types of LLMs, for which to multiple domains questions, and further created a dataset that mixed human-written sentences and sentences polished by LLMs. We then proposed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01158","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/2402.01158/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":"2402.01158","created_at":"2026-07-05T07:40:31.562188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01158v1","created_at":"2026-07-05T07:40:31.562188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01158","created_at":"2026-07-05T07:40:31.562188+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLJM54YCYHII","created_at":"2026-07-05T07:40:31.562188+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLJM54YCYHIIN2YH","created_at":"2026-07-05T07:40:31.562188+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLJM54YC","created_at":"2026-07-05T07:40:31.562188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23190","citing_title":"Hidden Human-Like Nature of Machine-Generated Texts: Theory and Detection Enhancement","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GLJM54YCYHIIN2YHRUF2ZHWJWF","json":"https://pith.science/pith/GLJM54YCYHIIN2YHRUF2ZHWJWF.json","graph_json":"https://pith.science/api/pith-number/GLJM54YCYHIIN2YHRUF2ZHWJWF/graph.json","events_json":"https://pith.science/api/pith-number/GLJM54YCYHIIN2YHRUF2ZHWJWF/events.json","paper":"https://pith.science/paper/GLJM54YC"},"agent_actions":{"view_html":"https://pith.science/pith/GLJM54YCYHIIN2YHRUF2ZHWJWF","download_json":"https://pith.science/pith/GLJM54YCYHIIN2YHRUF2ZHWJWF.json","view_paper":"https://pith.science/paper/GLJM54YC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01158&json=true","fetch_graph":"https://pith.science/api/pith-number/GLJM54YCYHIIN2YHRUF2ZHWJWF/graph.json","fetch_events":"https://pith.science/api/pith-number/GLJM54YCYHIIN2YHRUF2ZHWJWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLJM54YCYHIIN2YHRUF2ZHWJWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLJM54YCYHIIN2YHRUF2ZHWJWF/action/storage_attestation","attest_author":"https://pith.science/pith/GLJM54YCYHIIN2YHRUF2ZHWJWF/action/author_attestation","sign_citation":"https://pith.science/pith/GLJM54YCYHIIN2YHRUF2ZHWJWF/action/citation_signature","submit_replication":"https://pith.science/pith/GLJM54YCYHIIN2YHRUF2ZHWJWF/action/replication_record"}},"created_at":"2026-07-05T07:40:31.562188+00:00","updated_at":"2026-07-05T07:40:31.562188+00:00"}