{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EG2JIRTRN634FY6K4CBQYYQLSQ","short_pith_number":"pith:EG2JIRTR","schema_version":"1.0","canonical_sha256":"21b49446716fb7c2e3cae0830c620b9415b215dda4a4d8d19737eeaff53bf426","source":{"kind":"arxiv","id":"2305.18149","version":4},"attestation_state":"computed","paper":{"title":"Multiscale Positive-Unlabeled Detection of AI-Generated Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Xu, Hanting Chen, Qinghua Zhang, Ruifeng Li, Xutao Wang, Yuchuan Tian, Yunhe Wang, Zheyuan Bai","submitted_at":"2023-05-29T15:25:00Z","abstract_excerpt":"Recent releases of Large Language Models (LLMs), e.g. ChatGPT, are astonishing at generating human-like texts, but they may impact the authenticity of texts. Previous works proposed methods to detect these AI-generated texts, including simple ML classifiers, pretrained-model-based zero-shot methods, and finetuned language classification models. However, mainstream detectors always fail on short texts, like SMSes, Tweets, and reviews. In this paper, a Multiscale Positive-Unlabeled (MPU) training framework is proposed to address the difficulty of short-text detection without sacrificing long-tex"},"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":"2305.18149","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T15:25:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f372a8cdff9c39a605f3f9cd72d9ee10b5b042dba8c7f9d6457f41cd2776f727","abstract_canon_sha256":"604ed549f22a645d6f591062260638df0185f3fc64fb27ab3ce992a5aad0ff6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:10.091342Z","signature_b64":"1UIv4I1h8cAw/6nRR7oZilQniaDwv+LZoFIgtJvYs+CB8v6ZHiOKaGJ+jAW/u2Pc3J3pMTNPxUzTvMwcATBFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21b49446716fb7c2e3cae0830c620b9415b215dda4a4d8d19737eeaff53bf426","last_reissued_at":"2026-07-05T07:52:10.090904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:10.090904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiscale Positive-Unlabeled Detection of AI-Generated Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chao Xu, Hanting Chen, Qinghua Zhang, Ruifeng Li, Xutao Wang, Yuchuan Tian, Yunhe Wang, Zheyuan Bai","submitted_at":"2023-05-29T15:25:00Z","abstract_excerpt":"Recent releases of Large Language Models (LLMs), e.g. ChatGPT, are astonishing at generating human-like texts, but they may impact the authenticity of texts. Previous works proposed methods to detect these AI-generated texts, including simple ML classifiers, pretrained-model-based zero-shot methods, and finetuned language classification models. However, mainstream detectors always fail on short texts, like SMSes, Tweets, and reviews. In this paper, a Multiscale Positive-Unlabeled (MPU) training framework is proposed to address the difficulty of short-text detection without sacrificing long-tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18149","kind":"arxiv","version":4},"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/2305.18149/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":"2305.18149","created_at":"2026-07-05T07:52:10.090959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18149v4","created_at":"2026-07-05T07:52:10.090959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18149","created_at":"2026-07-05T07:52:10.090959+00:00"},{"alias_kind":"pith_short_12","alias_value":"EG2JIRTRN634","created_at":"2026-07-05T07:52:10.090959+00:00"},{"alias_kind":"pith_short_16","alias_value":"EG2JIRTRN634FY6K","created_at":"2026-07-05T07:52:10.090959+00:00"},{"alias_kind":"pith_short_8","alias_value":"EG2JIRTR","created_at":"2026-07-05T07:52:10.090959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25152","citing_title":"Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27921","citing_title":"Show, Don't TELL: Explainable AI-Generated Text Detection","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25152","citing_title":"MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EG2JIRTRN634FY6K4CBQYYQLSQ","json":"https://pith.science/pith/EG2JIRTRN634FY6K4CBQYYQLSQ.json","graph_json":"https://pith.science/api/pith-number/EG2JIRTRN634FY6K4CBQYYQLSQ/graph.json","events_json":"https://pith.science/api/pith-number/EG2JIRTRN634FY6K4CBQYYQLSQ/events.json","paper":"https://pith.science/paper/EG2JIRTR"},"agent_actions":{"view_html":"https://pith.science/pith/EG2JIRTRN634FY6K4CBQYYQLSQ","download_json":"https://pith.science/pith/EG2JIRTRN634FY6K4CBQYYQLSQ.json","view_paper":"https://pith.science/paper/EG2JIRTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18149&json=true","fetch_graph":"https://pith.science/api/pith-number/EG2JIRTRN634FY6K4CBQYYQLSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EG2JIRTRN634FY6K4CBQYYQLSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EG2JIRTRN634FY6K4CBQYYQLSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EG2JIRTRN634FY6K4CBQYYQLSQ/action/storage_attestation","attest_author":"https://pith.science/pith/EG2JIRTRN634FY6K4CBQYYQLSQ/action/author_attestation","sign_citation":"https://pith.science/pith/EG2JIRTRN634FY6K4CBQYYQLSQ/action/citation_signature","submit_replication":"https://pith.science/pith/EG2JIRTRN634FY6K4CBQYYQLSQ/action/replication_record"}},"created_at":"2026-07-05T07:52:10.090959+00:00","updated_at":"2026-07-05T07:52:10.090959+00:00"}