{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FQYG54ZTBO2GOPEZHAVGD5ZLMF","short_pith_number":"pith:FQYG54ZT","schema_version":"1.0","canonical_sha256":"2c306ef3330bb4673c99382a61f72b615b70f28ac9d7d9d5b17d7f088ea91430","source":{"kind":"arxiv","id":"2605.28021","version":1},"attestation_state":"computed","paper":{"title":"AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fengqiang Wan, Qing-Yuan Jiang, Yang Yang","submitted_at":"2026-05-27T06:26:09Z","abstract_excerpt":"Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios, where test inputs may deviate from the training distribution and overconfident predictions on unknown samples can lead to unreliable decisions. Outlier Exposure (OE) has emerged as a promising OOD detection paradigm by introducing auxiliary outliers during training to enlarge the margin between in-distribution (ID) and OOD samples. Existing OE-based methods typically enlarge this margin by employing uniform labels to maximize the entropy of OOD samples over ID cat"},"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":"2605.28021","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T06:26:09Z","cross_cats_sorted":[],"title_canon_sha256":"16df671f22ecdf6e74ceb166cf2bec765a72f59f02fa589b903120b38ecd4292","abstract_canon_sha256":"aead6b02342655155ac66c70ab9f1b2d4c00cae67853fa2b953d2e2e98b0486c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:56.220670Z","signature_b64":"339vtAyAyfRqg8h/IPz5D5I3voslSn9n7DYKduOu+7ZoIK7Kdz0n4/+UBoKU0bAOwvr1D1Yz4D322kQDxWJfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c306ef3330bb4673c99382a61f72b615b70f28ac9d7d9d5b17d7f088ea91430","last_reissued_at":"2026-05-28T01:04:56.220276Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:56.220276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fengqiang Wan, Qing-Yuan Jiang, Yang Yang","submitted_at":"2026-05-27T06:26:09Z","abstract_excerpt":"Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios, where test inputs may deviate from the training distribution and overconfident predictions on unknown samples can lead to unreliable decisions. Outlier Exposure (OE) has emerged as a promising OOD detection paradigm by introducing auxiliary outliers during training to enlarge the margin between in-distribution (ID) and OOD samples. Existing OE-based methods typically enlarge this margin by employing uniform labels to maximize the entropy of OOD samples over ID cat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28021","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/2605.28021/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":"2605.28021","created_at":"2026-05-28T01:04:56.220338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28021v1","created_at":"2026-05-28T01:04:56.220338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28021","created_at":"2026-05-28T01:04:56.220338+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQYG54ZTBO2G","created_at":"2026-05-28T01:04:56.220338+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQYG54ZTBO2GOPEZ","created_at":"2026-05-28T01:04:56.220338+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQYG54ZT","created_at":"2026-05-28T01:04:56.220338+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/FQYG54ZTBO2GOPEZHAVGD5ZLMF","json":"https://pith.science/pith/FQYG54ZTBO2GOPEZHAVGD5ZLMF.json","graph_json":"https://pith.science/api/pith-number/FQYG54ZTBO2GOPEZHAVGD5ZLMF/graph.json","events_json":"https://pith.science/api/pith-number/FQYG54ZTBO2GOPEZHAVGD5ZLMF/events.json","paper":"https://pith.science/paper/FQYG54ZT"},"agent_actions":{"view_html":"https://pith.science/pith/FQYG54ZTBO2GOPEZHAVGD5ZLMF","download_json":"https://pith.science/pith/FQYG54ZTBO2GOPEZHAVGD5ZLMF.json","view_paper":"https://pith.science/paper/FQYG54ZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28021&json=true","fetch_graph":"https://pith.science/api/pith-number/FQYG54ZTBO2GOPEZHAVGD5ZLMF/graph.json","fetch_events":"https://pith.science/api/pith-number/FQYG54ZTBO2GOPEZHAVGD5ZLMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQYG54ZTBO2GOPEZHAVGD5ZLMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQYG54ZTBO2GOPEZHAVGD5ZLMF/action/storage_attestation","attest_author":"https://pith.science/pith/FQYG54ZTBO2GOPEZHAVGD5ZLMF/action/author_attestation","sign_citation":"https://pith.science/pith/FQYG54ZTBO2GOPEZHAVGD5ZLMF/action/citation_signature","submit_replication":"https://pith.science/pith/FQYG54ZTBO2GOPEZHAVGD5ZLMF/action/replication_record"}},"created_at":"2026-05-28T01:04:56.220338+00:00","updated_at":"2026-05-28T01:04:56.220338+00:00"}