{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7KRNX3EPVUOIFXEKHIW6K5RRKN","short_pith_number":"pith:7KRNX3EP","schema_version":"1.0","canonical_sha256":"faa2dbec8fad1c82dc8a3a2de57631537fb7a79e8164518ba29fa9b4a10889d2","source":{"kind":"arxiv","id":"2210.10722","version":1},"attestation_state":"computed","paper":{"title":"UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingang Wang, Keqing He, Pei Wang, Weiran Xu, Wei Wu, Yanan Wu, Yutao Mou","submitted_at":"2022-10-19T17:06:34Z","abstract_excerpt":"Detecting out-of-domain (OOD) intents from user queries is essential for avoiding wrong operations in task-oriented dialogue systems. The key challenge is how to distinguish in-domain (IND) and OOD intents. Previous methods ignore the alignment between representation learning and scoring function, limiting the OOD detection performance. In this paper, we propose a unified neighborhood learning framework (UniNL) to detect OOD intents. Specifically, we design a K-nearest neighbor contrastive learning (KNCL) objective for representation learning and introduce a KNN-based scoring function for OOD "},"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":"2210.10722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T17:06:34Z","cross_cats_sorted":[],"title_canon_sha256":"1578b90a358cf18f01aab9e3e14ee57e799c19c416c23845db110bb3f14f18c5","abstract_canon_sha256":"878d775b5823a4d97e60376d6fe06d51bed67db1ccb912e0cd3f9460ba10a65d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:23.077441Z","signature_b64":"2IyYb7ByaLZrnYuvYQGnFd7GBs4vIw6GU6sLldtxkc9aaQ45K9rJhqDEAD7EndUp1YYof1Fab5x/YzysfeOIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faa2dbec8fad1c82dc8a3a2de57631537fb7a79e8164518ba29fa9b4a10889d2","last_reissued_at":"2026-07-05T05:08:23.076938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:23.076938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingang Wang, Keqing He, Pei Wang, Weiran Xu, Wei Wu, Yanan Wu, Yutao Mou","submitted_at":"2022-10-19T17:06:34Z","abstract_excerpt":"Detecting out-of-domain (OOD) intents from user queries is essential for avoiding wrong operations in task-oriented dialogue systems. The key challenge is how to distinguish in-domain (IND) and OOD intents. Previous methods ignore the alignment between representation learning and scoring function, limiting the OOD detection performance. In this paper, we propose a unified neighborhood learning framework (UniNL) to detect OOD intents. Specifically, we design a K-nearest neighbor contrastive learning (KNCL) objective for representation learning and introduce a KNN-based scoring function for OOD "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10722","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/2210.10722/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":"2210.10722","created_at":"2026-07-05T05:08:23.076996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.10722v1","created_at":"2026-07-05T05:08:23.076996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10722","created_at":"2026-07-05T05:08:23.076996+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KRNX3EPVUOI","created_at":"2026-07-05T05:08:23.076996+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KRNX3EPVUOIFXEK","created_at":"2026-07-05T05:08:23.076996+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KRNX3EP","created_at":"2026-07-05T05:08:23.076996+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/7KRNX3EPVUOIFXEKHIW6K5RRKN","json":"https://pith.science/pith/7KRNX3EPVUOIFXEKHIW6K5RRKN.json","graph_json":"https://pith.science/api/pith-number/7KRNX3EPVUOIFXEKHIW6K5RRKN/graph.json","events_json":"https://pith.science/api/pith-number/7KRNX3EPVUOIFXEKHIW6K5RRKN/events.json","paper":"https://pith.science/paper/7KRNX3EP"},"agent_actions":{"view_html":"https://pith.science/pith/7KRNX3EPVUOIFXEKHIW6K5RRKN","download_json":"https://pith.science/pith/7KRNX3EPVUOIFXEKHIW6K5RRKN.json","view_paper":"https://pith.science/paper/7KRNX3EP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.10722&json=true","fetch_graph":"https://pith.science/api/pith-number/7KRNX3EPVUOIFXEKHIW6K5RRKN/graph.json","fetch_events":"https://pith.science/api/pith-number/7KRNX3EPVUOIFXEKHIW6K5RRKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KRNX3EPVUOIFXEKHIW6K5RRKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KRNX3EPVUOIFXEKHIW6K5RRKN/action/storage_attestation","attest_author":"https://pith.science/pith/7KRNX3EPVUOIFXEKHIW6K5RRKN/action/author_attestation","sign_citation":"https://pith.science/pith/7KRNX3EPVUOIFXEKHIW6K5RRKN/action/citation_signature","submit_replication":"https://pith.science/pith/7KRNX3EPVUOIFXEKHIW6K5RRKN/action/replication_record"}},"created_at":"2026-07-05T05:08:23.076996+00:00","updated_at":"2026-07-05T05:08:23.076996+00:00"}