{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QPAITU6S3S6QTN4TSGNPWNAP36","short_pith_number":"pith:QPAITU6S","schema_version":"1.0","canonical_sha256":"83c089d3d2dcbd09b793919afb340fdf9c993e285cb6d37c677b6ce6ed9629dc","source":{"kind":"arxiv","id":"2209.06612","version":1},"attestation_state":"computed","paper":{"title":"Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Keqing He, Pei Wang, Weiran Xu, Yanan Wu, Yutao Mou, Zhiyuan Zeng","submitted_at":"2022-09-14T13:04:09Z","abstract_excerpt":"Out-of-Domain (OOD) detection is a key component in a task-oriented dialog system, which aims to identify whether a query falls outside the predefined supported intent set. Previous softmax-based detection algorithms are proved to be overconfident for OOD samples. In this paper, we analyze overconfident OOD comes from distribution uncertainty due to the mismatch between the training and test distributions, which makes the model can't confidently make predictions thus probably causing abnormal softmax scores. We propose a Bayesian OOD detection framework to calibrate distribution uncertainty us"},"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":"2209.06612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-14T13:04:09Z","cross_cats_sorted":[],"title_canon_sha256":"2a0261bb3141687f99a62adc9c1b76990bb9dbc6d7540197bc28e34cc1107c61","abstract_canon_sha256":"fe24a2efd0b84e71b177413f452b20c204b0c3dd893fbe1cba84501470e60905"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:32.790741Z","signature_b64":"RcWhTx1NOicXMN8MROn/cTBuO4Xn4uvc/P254xxCn9sE6VMdYNu+ecbmwgl1FVRsWt3a0VRGawKdivA/kcQ/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83c089d3d2dcbd09b793919afb340fdf9c993e285cb6d37c677b6ce6ed9629dc","last_reissued_at":"2026-07-05T04:57:32.790351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:32.790351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Keqing He, Pei Wang, Weiran Xu, Yanan Wu, Yutao Mou, Zhiyuan Zeng","submitted_at":"2022-09-14T13:04:09Z","abstract_excerpt":"Out-of-Domain (OOD) detection is a key component in a task-oriented dialog system, which aims to identify whether a query falls outside the predefined supported intent set. Previous softmax-based detection algorithms are proved to be overconfident for OOD samples. In this paper, we analyze overconfident OOD comes from distribution uncertainty due to the mismatch between the training and test distributions, which makes the model can't confidently make predictions thus probably causing abnormal softmax scores. We propose a Bayesian OOD detection framework to calibrate distribution uncertainty us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06612","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/2209.06612/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":"2209.06612","created_at":"2026-07-05T04:57:32.790411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.06612v1","created_at":"2026-07-05T04:57:32.790411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06612","created_at":"2026-07-05T04:57:32.790411+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPAITU6S3S6Q","created_at":"2026-07-05T04:57:32.790411+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPAITU6S3S6QTN4T","created_at":"2026-07-05T04:57:32.790411+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPAITU6S","created_at":"2026-07-05T04:57:32.790411+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/QPAITU6S3S6QTN4TSGNPWNAP36","json":"https://pith.science/pith/QPAITU6S3S6QTN4TSGNPWNAP36.json","graph_json":"https://pith.science/api/pith-number/QPAITU6S3S6QTN4TSGNPWNAP36/graph.json","events_json":"https://pith.science/api/pith-number/QPAITU6S3S6QTN4TSGNPWNAP36/events.json","paper":"https://pith.science/paper/QPAITU6S"},"agent_actions":{"view_html":"https://pith.science/pith/QPAITU6S3S6QTN4TSGNPWNAP36","download_json":"https://pith.science/pith/QPAITU6S3S6QTN4TSGNPWNAP36.json","view_paper":"https://pith.science/paper/QPAITU6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.06612&json=true","fetch_graph":"https://pith.science/api/pith-number/QPAITU6S3S6QTN4TSGNPWNAP36/graph.json","fetch_events":"https://pith.science/api/pith-number/QPAITU6S3S6QTN4TSGNPWNAP36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPAITU6S3S6QTN4TSGNPWNAP36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPAITU6S3S6QTN4TSGNPWNAP36/action/storage_attestation","attest_author":"https://pith.science/pith/QPAITU6S3S6QTN4TSGNPWNAP36/action/author_attestation","sign_citation":"https://pith.science/pith/QPAITU6S3S6QTN4TSGNPWNAP36/action/citation_signature","submit_replication":"https://pith.science/pith/QPAITU6S3S6QTN4TSGNPWNAP36/action/replication_record"}},"created_at":"2026-07-05T04:57:32.790411+00:00","updated_at":"2026-07-05T04:57:32.790411+00:00"}