{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HVNPLN6VAWRB4ZP33FV4UXNK3I","short_pith_number":"pith:HVNPLN6V","schema_version":"1.0","canonical_sha256":"3d5af5b7d505a21e65fbd96bca5daada08f10080a5f255f0075c8721ed0273cb","source":{"kind":"arxiv","id":"2412.20595","version":1},"attestation_state":"computed","paper":{"title":"Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dmitri Roussinov, Nadezhda Puchnina, Serge Sharoff","submitted_at":"2024-12-29T21:54:39Z","abstract_excerpt":"This study demonstrates that the modern generation of Large Language Models (LLMs, such as GPT-4) suffers from the same out-of-domain (OOD) performance gap observed in prior research on pre-trained Language Models (PLMs, such as BERT). We demonstrate this across two non-topical classification tasks: 1) genre classification and 2) generated text detection. Our results show that when demonstration examples for In-Context Learning (ICL) come from one domain (e.g., travel) and the system is tested on another domain (e.g., history), classification performance declines significantly.\n  To address th"},"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":"2412.20595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T21:54:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3e0de88c7a6f7b2dcc00d2b642fde8d9150d1aeff5d5ba218abb68b243f85253","abstract_canon_sha256":"d6d1bba4aae6bb9871bae8f4528afa26ffc1f5d8ac3153a5259268b53e411649"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:19.529021Z","signature_b64":"0jL5GEhP8Zq9kAdOifAPUMnil1BS7BJO/Gw3s5kFNCN2HdNnuaaFDotaYLa+NysTcT4yVYelCIlCu389hSxdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d5af5b7d505a21e65fbd96bca5daada08f10080a5f255f0075c8721ed0273cb","last_reissued_at":"2026-07-05T09:55:19.528547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:19.528547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dmitri Roussinov, Nadezhda Puchnina, Serge Sharoff","submitted_at":"2024-12-29T21:54:39Z","abstract_excerpt":"This study demonstrates that the modern generation of Large Language Models (LLMs, such as GPT-4) suffers from the same out-of-domain (OOD) performance gap observed in prior research on pre-trained Language Models (PLMs, such as BERT). We demonstrate this across two non-topical classification tasks: 1) genre classification and 2) generated text detection. Our results show that when demonstration examples for In-Context Learning (ICL) come from one domain (e.g., travel) and the system is tested on another domain (e.g., history), classification performance declines significantly.\n  To address th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20595","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/2412.20595/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":"2412.20595","created_at":"2026-07-05T09:55:19.528605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20595v1","created_at":"2026-07-05T09:55:19.528605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20595","created_at":"2026-07-05T09:55:19.528605+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVNPLN6VAWRB","created_at":"2026-07-05T09:55:19.528605+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVNPLN6VAWRB4ZP3","created_at":"2026-07-05T09:55:19.528605+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVNPLN6V","created_at":"2026-07-05T09:55:19.528605+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/HVNPLN6VAWRB4ZP33FV4UXNK3I","json":"https://pith.science/pith/HVNPLN6VAWRB4ZP33FV4UXNK3I.json","graph_json":"https://pith.science/api/pith-number/HVNPLN6VAWRB4ZP33FV4UXNK3I/graph.json","events_json":"https://pith.science/api/pith-number/HVNPLN6VAWRB4ZP33FV4UXNK3I/events.json","paper":"https://pith.science/paper/HVNPLN6V"},"agent_actions":{"view_html":"https://pith.science/pith/HVNPLN6VAWRB4ZP33FV4UXNK3I","download_json":"https://pith.science/pith/HVNPLN6VAWRB4ZP33FV4UXNK3I.json","view_paper":"https://pith.science/paper/HVNPLN6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20595&json=true","fetch_graph":"https://pith.science/api/pith-number/HVNPLN6VAWRB4ZP33FV4UXNK3I/graph.json","fetch_events":"https://pith.science/api/pith-number/HVNPLN6VAWRB4ZP33FV4UXNK3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVNPLN6VAWRB4ZP33FV4UXNK3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVNPLN6VAWRB4ZP33FV4UXNK3I/action/storage_attestation","attest_author":"https://pith.science/pith/HVNPLN6VAWRB4ZP33FV4UXNK3I/action/author_attestation","sign_citation":"https://pith.science/pith/HVNPLN6VAWRB4ZP33FV4UXNK3I/action/citation_signature","submit_replication":"https://pith.science/pith/HVNPLN6VAWRB4ZP33FV4UXNK3I/action/replication_record"}},"created_at":"2026-07-05T09:55:19.528605+00:00","updated_at":"2026-07-05T09:55:19.528605+00:00"}