{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2FWG4H5NRCPZI5HBG7JUGJZBPE","short_pith_number":"pith:2FWG4H5N","schema_version":"1.0","canonical_sha256":"d16c6e1fad889f9474e137d34327217922ccd1b3c6e2e40f469c7ef869d82e7d","source":{"kind":"arxiv","id":"2002.11297","version":2},"attestation_state":"computed","paper":{"title":"Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Hongxia Jin, Yen-Chang Hsu, Yilin Shen, Zsolt Kira","submitted_at":"2020-02-26T04:18:25Z","abstract_excerpt":"Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is out-of-distribution (OoD) is crucial to enable a system that can reject such samples or alert users. Recent works have made significant progress on OoD benchmarks consisting of small image datasets. However, many recent methods based on neural networks rely on training or tuning with both in-distribution and out-of-distribution data. The latter is generally hard to de"},"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":"2002.11297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-26T04:18:25Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"24aee454f77d9080c71f4a1046775febf879b518a132d304b054f01cb88c97ee","abstract_canon_sha256":"159ae0aa95c965fdf5178f09bbe07713731acf45647b12e1c9cda6da0a65db04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:54.452064Z","signature_b64":"nzb0vSgP+VJeevmL3QTgren2lJHzl7CtJyHHj+FXHqBbxUtW4L0rfkLUJygrrBtQnREa7ban0wENuOuwTa/wCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d16c6e1fad889f9474e137d34327217922ccd1b3c6e2e40f469c7ef869d82e7d","last_reissued_at":"2026-07-05T00:51:54.451664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:54.451664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Hongxia Jin, Yen-Chang Hsu, Yilin Shen, Zsolt Kira","submitted_at":"2020-02-26T04:18:25Z","abstract_excerpt":"Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is out-of-distribution (OoD) is crucial to enable a system that can reject such samples or alert users. Recent works have made significant progress on OoD benchmarks consisting of small image datasets. However, many recent methods based on neural networks rely on training or tuning with both in-distribution and out-of-distribution data. The latter is generally hard to de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11297","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/2002.11297/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":"2002.11297","created_at":"2026-07-05T00:51:54.451726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.11297v2","created_at":"2026-07-05T00:51:54.451726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11297","created_at":"2026-07-05T00:51:54.451726+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FWG4H5NRCPZ","created_at":"2026-07-05T00:51:54.451726+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FWG4H5NRCPZI5HB","created_at":"2026-07-05T00:51:54.451726+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FWG4H5N","created_at":"2026-07-05T00:51:54.451726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10089","citing_title":"Optimizing Latent Dimension Allocation in Hierarchical VAEs: Balancing Attenuation and Information Retention for OOD Detection","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FWG4H5NRCPZI5HBG7JUGJZBPE","json":"https://pith.science/pith/2FWG4H5NRCPZI5HBG7JUGJZBPE.json","graph_json":"https://pith.science/api/pith-number/2FWG4H5NRCPZI5HBG7JUGJZBPE/graph.json","events_json":"https://pith.science/api/pith-number/2FWG4H5NRCPZI5HBG7JUGJZBPE/events.json","paper":"https://pith.science/paper/2FWG4H5N"},"agent_actions":{"view_html":"https://pith.science/pith/2FWG4H5NRCPZI5HBG7JUGJZBPE","download_json":"https://pith.science/pith/2FWG4H5NRCPZI5HBG7JUGJZBPE.json","view_paper":"https://pith.science/paper/2FWG4H5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.11297&json=true","fetch_graph":"https://pith.science/api/pith-number/2FWG4H5NRCPZI5HBG7JUGJZBPE/graph.json","fetch_events":"https://pith.science/api/pith-number/2FWG4H5NRCPZI5HBG7JUGJZBPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FWG4H5NRCPZI5HBG7JUGJZBPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FWG4H5NRCPZI5HBG7JUGJZBPE/action/storage_attestation","attest_author":"https://pith.science/pith/2FWG4H5NRCPZI5HBG7JUGJZBPE/action/author_attestation","sign_citation":"https://pith.science/pith/2FWG4H5NRCPZI5HBG7JUGJZBPE/action/citation_signature","submit_replication":"https://pith.science/pith/2FWG4H5NRCPZI5HBG7JUGJZBPE/action/replication_record"}},"created_at":"2026-07-05T00:51:54.451726+00:00","updated_at":"2026-07-05T00:51:54.451726+00:00"}