{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BAXS5P6QOUKWR4S7GEQTEXFGWD","short_pith_number":"pith:BAXS5P6Q","schema_version":"1.0","canonical_sha256":"082f2ebfd0751568f25f3121325ca6b0e08d44609e3ea72924a635051a63456c","source":{"kind":"arxiv","id":"2412.07219","version":1},"attestation_state":"computed","paper":{"title":"Taylor Outlier Exposure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hiroaki Aizawa, Kohei Fukuda","submitted_at":"2024-12-10T06:17:07Z","abstract_excerpt":"Out-of-distribution (OOD) detection is the task of identifying data sampled from distributions that were not used during training. This task is essential for reliable machine learning and a better understanding of their generalization capabilities. Among OOD detection methods, Outlier Exposure (OE) significantly enhances OOD detection performance and generalization ability by exposing auxiliary OOD data to the model. However, constructing clean auxiliary OOD datasets, uncontaminated by in-distribution (ID) samples, is essential for OE; generally, a noisy OOD dataset contaminated with ID sample"},"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":"2412.07219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T06:17:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"deeaab7ed82475af5ee783a28f82248b9d0ab5a43e604f7717cedc3a3151433c","abstract_canon_sha256":"5bc808c63f9211f85b749234075b27209995b8cc73a708dc3abd33080832204d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:06.169771Z","signature_b64":"v4MMF0e6weJ0xG8V5S8aBfWNTAFhhgnZcP0QmMQFNEeaM/wUPGywJHi3ld3dsVhdcifEZRENUtRV6OUP7eeHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"082f2ebfd0751568f25f3121325ca6b0e08d44609e3ea72924a635051a63456c","last_reissued_at":"2026-07-05T09:47:06.169293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:06.169293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taylor Outlier Exposure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hiroaki Aizawa, Kohei Fukuda","submitted_at":"2024-12-10T06:17:07Z","abstract_excerpt":"Out-of-distribution (OOD) detection is the task of identifying data sampled from distributions that were not used during training. This task is essential for reliable machine learning and a better understanding of their generalization capabilities. Among OOD detection methods, Outlier Exposure (OE) significantly enhances OOD detection performance and generalization ability by exposing auxiliary OOD data to the model. However, constructing clean auxiliary OOD datasets, uncontaminated by in-distribution (ID) samples, is essential for OE; generally, a noisy OOD dataset contaminated with ID sample"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07219","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/2412.07219/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":"2412.07219","created_at":"2026-07-05T09:47:06.169355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07219v1","created_at":"2026-07-05T09:47:06.169355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07219","created_at":"2026-07-05T09:47:06.169355+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAXS5P6QOUKW","created_at":"2026-07-05T09:47:06.169355+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAXS5P6QOUKWR4S7","created_at":"2026-07-05T09:47:06.169355+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAXS5P6Q","created_at":"2026-07-05T09:47:06.169355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23373","citing_title":"Polynomial Dice Loss for Medical Image Segmentation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAXS5P6QOUKWR4S7GEQTEXFGWD","json":"https://pith.science/pith/BAXS5P6QOUKWR4S7GEQTEXFGWD.json","graph_json":"https://pith.science/api/pith-number/BAXS5P6QOUKWR4S7GEQTEXFGWD/graph.json","events_json":"https://pith.science/api/pith-number/BAXS5P6QOUKWR4S7GEQTEXFGWD/events.json","paper":"https://pith.science/paper/BAXS5P6Q"},"agent_actions":{"view_html":"https://pith.science/pith/BAXS5P6QOUKWR4S7GEQTEXFGWD","download_json":"https://pith.science/pith/BAXS5P6QOUKWR4S7GEQTEXFGWD.json","view_paper":"https://pith.science/paper/BAXS5P6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07219&json=true","fetch_graph":"https://pith.science/api/pith-number/BAXS5P6QOUKWR4S7GEQTEXFGWD/graph.json","fetch_events":"https://pith.science/api/pith-number/BAXS5P6QOUKWR4S7GEQTEXFGWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAXS5P6QOUKWR4S7GEQTEXFGWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAXS5P6QOUKWR4S7GEQTEXFGWD/action/storage_attestation","attest_author":"https://pith.science/pith/BAXS5P6QOUKWR4S7GEQTEXFGWD/action/author_attestation","sign_citation":"https://pith.science/pith/BAXS5P6QOUKWR4S7GEQTEXFGWD/action/citation_signature","submit_replication":"https://pith.science/pith/BAXS5P6QOUKWR4S7GEQTEXFGWD/action/replication_record"}},"created_at":"2026-07-05T09:47:06.169355+00:00","updated_at":"2026-07-05T09:47:06.169355+00:00"}