{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6MTGNF5X7BHWQUYYXQXC4BB623","short_pith_number":"pith:6MTGNF5X","schema_version":"1.0","canonical_sha256":"f3266697b7f84f685318bc2e2e043ed6e805c847660e4c99196b6ba8cdb03ffc","source":{"kind":"arxiv","id":"2303.12267","version":2},"attestation_state":"computed","paper":{"title":"AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jian Liang, Jie Cao, Puning Yang, Ran He","submitted_at":"2023-03-22T02:28:54Z","abstract_excerpt":"Out-of-distribution (OOD) detection aims to detect test samples that do not fall into any training in-distribution (ID) classes. Prior efforts focus on regularizing models with ID data only, largely underperforming counterparts that utilize auxiliary outliers. However, data safety and privacy make it infeasible to collect task-specific outliers in advance for different scenarios. Besides, using task-irrelevant outliers leads to inferior OOD detection performance. To address the above issue, we present a new setup called test-time OOD detection, which allows the deployed model to utilize real O"},"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":"2303.12267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-22T02:28:54Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fd74f78dba0b39a86ab1552d21f4a61b69a6a98b16420083b841babb57cd1db2","abstract_canon_sha256":"34bbad447c737ee7c2777300e9cd765d4c805fcbfb56eeefa56eac90adaea8ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:33.711255Z","signature_b64":"ctYSJnB+gUUysHetsb6Gnf4sQg65kOnSsv0j/sinA5sWnVR+jgg62tQ+6xDi/R8SI+/XXOQnl0KrGKWzKizzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3266697b7f84f685318bc2e2e043ed6e805c847660e4c99196b6ba8cdb03ffc","last_reissued_at":"2026-07-05T11:04:33.710789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:33.710789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jian Liang, Jie Cao, Puning Yang, Ran He","submitted_at":"2023-03-22T02:28:54Z","abstract_excerpt":"Out-of-distribution (OOD) detection aims to detect test samples that do not fall into any training in-distribution (ID) classes. Prior efforts focus on regularizing models with ID data only, largely underperforming counterparts that utilize auxiliary outliers. However, data safety and privacy make it infeasible to collect task-specific outliers in advance for different scenarios. Besides, using task-irrelevant outliers leads to inferior OOD detection performance. To address the above issue, we present a new setup called test-time OOD detection, which allows the deployed model to utilize real O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12267","kind":"arxiv","version":2},"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/2303.12267/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":"2303.12267","created_at":"2026-07-05T11:04:33.710841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12267v2","created_at":"2026-07-05T11:04:33.710841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12267","created_at":"2026-07-05T11:04:33.710841+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MTGNF5X7BHW","created_at":"2026-07-05T11:04:33.710841+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MTGNF5X7BHWQUYY","created_at":"2026-07-05T11:04:33.710841+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MTGNF5X","created_at":"2026-07-05T11:04:33.710841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15756","citing_title":"TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Models","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MTGNF5X7BHWQUYYXQXC4BB623","json":"https://pith.science/pith/6MTGNF5X7BHWQUYYXQXC4BB623.json","graph_json":"https://pith.science/api/pith-number/6MTGNF5X7BHWQUYYXQXC4BB623/graph.json","events_json":"https://pith.science/api/pith-number/6MTGNF5X7BHWQUYYXQXC4BB623/events.json","paper":"https://pith.science/paper/6MTGNF5X"},"agent_actions":{"view_html":"https://pith.science/pith/6MTGNF5X7BHWQUYYXQXC4BB623","download_json":"https://pith.science/pith/6MTGNF5X7BHWQUYYXQXC4BB623.json","view_paper":"https://pith.science/paper/6MTGNF5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12267&json=true","fetch_graph":"https://pith.science/api/pith-number/6MTGNF5X7BHWQUYYXQXC4BB623/graph.json","fetch_events":"https://pith.science/api/pith-number/6MTGNF5X7BHWQUYYXQXC4BB623/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MTGNF5X7BHWQUYYXQXC4BB623/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MTGNF5X7BHWQUYYXQXC4BB623/action/storage_attestation","attest_author":"https://pith.science/pith/6MTGNF5X7BHWQUYYXQXC4BB623/action/author_attestation","sign_citation":"https://pith.science/pith/6MTGNF5X7BHWQUYYXQXC4BB623/action/citation_signature","submit_replication":"https://pith.science/pith/6MTGNF5X7BHWQUYYXQXC4BB623/action/replication_record"}},"created_at":"2026-07-05T11:04:33.710841+00:00","updated_at":"2026-07-05T11:04:33.710841+00:00"}