{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BXY6E3USJPA2UASULT2TH5OLX7","short_pith_number":"pith:BXY6E3US","schema_version":"1.0","canonical_sha256":"0df1e26e924bc1aa02545cf533f5cbbfc54bb1f12c9f2f5f04873b12856736c0","source":{"kind":"arxiv","id":"2401.10176","version":1},"attestation_state":"computed","paper":{"title":"Comprehensive OOD Detection Improvements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amol Khanna, Anish Lakkapragada, Edward Raff, Nathan Inkawhich","submitted_at":"2024-01-18T18:05:35Z","abstract_excerpt":"As machine learning becomes increasingly prevalent in impactful decisions, recognizing when inference data is outside the model's expected input distribution is paramount for giving context to predictions. Out-of-distribution (OOD) detection methods have been created for this task. Such methods can be split into representation-based or logit-based methods from whether they respectively utilize the model's embeddings or predictions for OOD detection. In contrast to most papers which solely focus on one such group, we address both. We employ dimensionality reduction on feature embeddings in repr"},"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":"2401.10176","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T18:05:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"383de84af3535a6a56a249ddb604dbc1a73fb442bed8da5979a05027b3805997","abstract_canon_sha256":"aa7ebf1e415e7b58a6820e5d11e51c383a3f6822cbd285c11dbf42845c0df967"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:07.571193Z","signature_b64":"pB6jtW0b6DqdEJypxFKwc2zfLY7JQUNUyzyeoxQjTaAd2bFfxDLBqIbIE4IAISvOon1uOTh1Y6MaYR9ACImnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0df1e26e924bc1aa02545cf533f5cbbfc54bb1f12c9f2f5f04873b12856736c0","last_reissued_at":"2026-07-05T07:35:07.570761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:07.570761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comprehensive OOD Detection Improvements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amol Khanna, Anish Lakkapragada, Edward Raff, Nathan Inkawhich","submitted_at":"2024-01-18T18:05:35Z","abstract_excerpt":"As machine learning becomes increasingly prevalent in impactful decisions, recognizing when inference data is outside the model's expected input distribution is paramount for giving context to predictions. Out-of-distribution (OOD) detection methods have been created for this task. Such methods can be split into representation-based or logit-based methods from whether they respectively utilize the model's embeddings or predictions for OOD detection. In contrast to most papers which solely focus on one such group, we address both. We employ dimensionality reduction on feature embeddings in repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10176","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/2401.10176/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":"2401.10176","created_at":"2026-07-05T07:35:07.570825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10176v1","created_at":"2026-07-05T07:35:07.570825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10176","created_at":"2026-07-05T07:35:07.570825+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXY6E3USJPA2","created_at":"2026-07-05T07:35:07.570825+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXY6E3USJPA2UASU","created_at":"2026-07-05T07:35:07.570825+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXY6E3US","created_at":"2026-07-05T07:35:07.570825+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/BXY6E3USJPA2UASULT2TH5OLX7","json":"https://pith.science/pith/BXY6E3USJPA2UASULT2TH5OLX7.json","graph_json":"https://pith.science/api/pith-number/BXY6E3USJPA2UASULT2TH5OLX7/graph.json","events_json":"https://pith.science/api/pith-number/BXY6E3USJPA2UASULT2TH5OLX7/events.json","paper":"https://pith.science/paper/BXY6E3US"},"agent_actions":{"view_html":"https://pith.science/pith/BXY6E3USJPA2UASULT2TH5OLX7","download_json":"https://pith.science/pith/BXY6E3USJPA2UASULT2TH5OLX7.json","view_paper":"https://pith.science/paper/BXY6E3US","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10176&json=true","fetch_graph":"https://pith.science/api/pith-number/BXY6E3USJPA2UASULT2TH5OLX7/graph.json","fetch_events":"https://pith.science/api/pith-number/BXY6E3USJPA2UASULT2TH5OLX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXY6E3USJPA2UASULT2TH5OLX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXY6E3USJPA2UASULT2TH5OLX7/action/storage_attestation","attest_author":"https://pith.science/pith/BXY6E3USJPA2UASULT2TH5OLX7/action/author_attestation","sign_citation":"https://pith.science/pith/BXY6E3USJPA2UASULT2TH5OLX7/action/citation_signature","submit_replication":"https://pith.science/pith/BXY6E3USJPA2UASULT2TH5OLX7/action/replication_record"}},"created_at":"2026-07-05T07:35:07.570825+00:00","updated_at":"2026-07-05T07:35:07.570825+00:00"}