{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RUASZ4XOZB7E5MRYR2UVCXZDM7","short_pith_number":"pith:RUASZ4XO","schema_version":"1.0","canonical_sha256":"8d012cf2eec87e4eb2388ea9515f2367eec8a40e0582a4aca6f0eaaebef78e69","source":{"kind":"arxiv","id":"2402.17888","version":5},"attestation_state":"computed","paper":{"title":"ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Peng, Yadan Luo, Yixuan Li, Yonggang Zhang, Zhen Fang","submitted_at":"2024-02-27T21:02:47Z","abstract_excerpt":"Post-hoc out-of-distribution (OOD) detection has garnered intensive attention in reliable machine learning. Many efforts have been dedicated to deriving score functions based on logits, distances, or rigorous data distribution assumptions to identify low-scoring OOD samples. Nevertheless, these estimate scores may fail to accurately reflect the true data density or impose impractical constraints. To provide a unified perspective on density-based score design, we propose a novel theoretical framework grounded in Bregman divergence, which extends distribution considerations to encompass an expon"},"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":"2402.17888","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T21:02:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18a2f3cd7ebfc9a295c43fd72374683f84759899b27165af23f4bb8c847fc6da","abstract_canon_sha256":"2198a06cf0fbe28d388e6faeac9cdb2ea5d954bd933c77420dda65ad0d01bb41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:00.613077Z","signature_b64":"VWoaHTWCL2moHFI5QfG/de+0Uj9kTZ+nN4f4kLsqvHNrcmBwSCaWsaTrTgzHEYhTDVhVzpbM/j+Tw9CkmoDsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d012cf2eec87e4eb2388ea9515f2367eec8a40e0582a4aca6f0eaaebef78e69","last_reissued_at":"2026-05-25T02:01:00.612341Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:00.612341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Peng, Yadan Luo, Yixuan Li, Yonggang Zhang, Zhen Fang","submitted_at":"2024-02-27T21:02:47Z","abstract_excerpt":"Post-hoc out-of-distribution (OOD) detection has garnered intensive attention in reliable machine learning. Many efforts have been dedicated to deriving score functions based on logits, distances, or rigorous data distribution assumptions to identify low-scoring OOD samples. Nevertheless, these estimate scores may fail to accurately reflect the true data density or impose impractical constraints. To provide a unified perspective on density-based score design, we propose a novel theoretical framework grounded in Bregman divergence, which extends distribution considerations to encompass an expon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17888","kind":"arxiv","version":5},"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/2402.17888/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":"2402.17888","created_at":"2026-05-25T02:01:00.612448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17888v5","created_at":"2026-05-25T02:01:00.612448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17888","created_at":"2026-05-25T02:01:00.612448+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUASZ4XOZB7E","created_at":"2026-05-25T02:01:00.612448+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUASZ4XOZB7E5MRY","created_at":"2026-05-25T02:01:00.612448+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUASZ4XO","created_at":"2026-05-25T02:01:00.612448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.16335","citing_title":"On the Provable Importance of Gradients for Language-Assisted Image Clustering","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUASZ4XOZB7E5MRYR2UVCXZDM7","json":"https://pith.science/pith/RUASZ4XOZB7E5MRYR2UVCXZDM7.json","graph_json":"https://pith.science/api/pith-number/RUASZ4XOZB7E5MRYR2UVCXZDM7/graph.json","events_json":"https://pith.science/api/pith-number/RUASZ4XOZB7E5MRYR2UVCXZDM7/events.json","paper":"https://pith.science/paper/RUASZ4XO"},"agent_actions":{"view_html":"https://pith.science/pith/RUASZ4XOZB7E5MRYR2UVCXZDM7","download_json":"https://pith.science/pith/RUASZ4XOZB7E5MRYR2UVCXZDM7.json","view_paper":"https://pith.science/paper/RUASZ4XO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17888&json=true","fetch_graph":"https://pith.science/api/pith-number/RUASZ4XOZB7E5MRYR2UVCXZDM7/graph.json","fetch_events":"https://pith.science/api/pith-number/RUASZ4XOZB7E5MRYR2UVCXZDM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUASZ4XOZB7E5MRYR2UVCXZDM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUASZ4XOZB7E5MRYR2UVCXZDM7/action/storage_attestation","attest_author":"https://pith.science/pith/RUASZ4XOZB7E5MRYR2UVCXZDM7/action/author_attestation","sign_citation":"https://pith.science/pith/RUASZ4XOZB7E5MRYR2UVCXZDM7/action/citation_signature","submit_replication":"https://pith.science/pith/RUASZ4XOZB7E5MRYR2UVCXZDM7/action/replication_record"}},"created_at":"2026-05-25T02:01:00.612448+00:00","updated_at":"2026-05-25T02:01:00.612448+00:00"}