{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IROXMRDNIU5VCEZBZ3OTIXBMOK","short_pith_number":"pith:IROXMRDN","schema_version":"1.0","canonical_sha256":"445d76446d453b511321cedd345c2c72a6d76d32f15b983ccddccc86542f9f85","source":{"kind":"arxiv","id":"2507.14178","version":1},"attestation_state":"computed","paper":{"title":"Feature Bank Enhancement for Distance-based Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Shi, Bo Dong, Yuefei Wu, Yuhang Liu","submitted_at":"2025-07-11T13:32:26Z","abstract_excerpt":"Out-of-distribution (OOD) detection is critical to ensuring the reliability of deep learning applications and has attracted significant attention in recent years. A rich body of literature has emerged to develop efficient score functions that assign high scores to in-distribution (ID) samples and low scores to OOD samples, thereby helping distinguish OOD samples. Among these methods, distance-based score functions are widely used because of their efficiency and ease of use. However, deep learning often leads to a biased distribution of data features, and extreme features are inevitable. These "},"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":"2507.14178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T13:32:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9d9ebe90315b64afb61d19537eb25123d91c1d583882e871afce82b17d6a43b0","abstract_canon_sha256":"c50b16278a4461d693c7bb0fde818d37bcdee3a21099608e4b39a320771cca59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:30.214216Z","signature_b64":"zMDOdA9pgIgXYjfFGmFeGC2XUE8A3w0gHp8fyrq3iWRWLnaQGXIowuk7lrf1x4cfsiMaBloZ0Glq/7aov0ckDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"445d76446d453b511321cedd345c2c72a6d76d32f15b983ccddccc86542f9f85","last_reissued_at":"2026-07-05T11:39:30.213808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:30.213808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Bank Enhancement for Distance-based Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Shi, Bo Dong, Yuefei Wu, Yuhang Liu","submitted_at":"2025-07-11T13:32:26Z","abstract_excerpt":"Out-of-distribution (OOD) detection is critical to ensuring the reliability of deep learning applications and has attracted significant attention in recent years. A rich body of literature has emerged to develop efficient score functions that assign high scores to in-distribution (ID) samples and low scores to OOD samples, thereby helping distinguish OOD samples. Among these methods, distance-based score functions are widely used because of their efficiency and ease of use. However, deep learning often leads to a biased distribution of data features, and extreme features are inevitable. These "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14178","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/2507.14178/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":"2507.14178","created_at":"2026-07-05T11:39:30.213864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14178v1","created_at":"2026-07-05T11:39:30.213864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14178","created_at":"2026-07-05T11:39:30.213864+00:00"},{"alias_kind":"pith_short_12","alias_value":"IROXMRDNIU5V","created_at":"2026-07-05T11:39:30.213864+00:00"},{"alias_kind":"pith_short_16","alias_value":"IROXMRDNIU5VCEZB","created_at":"2026-07-05T11:39:30.213864+00:00"},{"alias_kind":"pith_short_8","alias_value":"IROXMRDN","created_at":"2026-07-05T11:39:30.213864+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/IROXMRDNIU5VCEZBZ3OTIXBMOK","json":"https://pith.science/pith/IROXMRDNIU5VCEZBZ3OTIXBMOK.json","graph_json":"https://pith.science/api/pith-number/IROXMRDNIU5VCEZBZ3OTIXBMOK/graph.json","events_json":"https://pith.science/api/pith-number/IROXMRDNIU5VCEZBZ3OTIXBMOK/events.json","paper":"https://pith.science/paper/IROXMRDN"},"agent_actions":{"view_html":"https://pith.science/pith/IROXMRDNIU5VCEZBZ3OTIXBMOK","download_json":"https://pith.science/pith/IROXMRDNIU5VCEZBZ3OTIXBMOK.json","view_paper":"https://pith.science/paper/IROXMRDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14178&json=true","fetch_graph":"https://pith.science/api/pith-number/IROXMRDNIU5VCEZBZ3OTIXBMOK/graph.json","fetch_events":"https://pith.science/api/pith-number/IROXMRDNIU5VCEZBZ3OTIXBMOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IROXMRDNIU5VCEZBZ3OTIXBMOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IROXMRDNIU5VCEZBZ3OTIXBMOK/action/storage_attestation","attest_author":"https://pith.science/pith/IROXMRDNIU5VCEZBZ3OTIXBMOK/action/author_attestation","sign_citation":"https://pith.science/pith/IROXMRDNIU5VCEZBZ3OTIXBMOK/action/citation_signature","submit_replication":"https://pith.science/pith/IROXMRDNIU5VCEZBZ3OTIXBMOK/action/replication_record"}},"created_at":"2026-07-05T11:39:30.213864+00:00","updated_at":"2026-07-05T11:39:30.213864+00:00"}