{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EP6HO3C2HZQSVI4JUCZ3LHVTBV","short_pith_number":"pith:EP6HO3C2","schema_version":"1.0","canonical_sha256":"23fc776c5a3e612aa389a0b3b59eb30d59161197528e6cf3796fad876b92c977","source":{"kind":"arxiv","id":"2207.01160","version":1},"attestation_state":"computed","paper":{"title":"Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Smola, Aston Zhang, Haotao Wang, Mu Li, Shuai Zheng, Yi Zhu, Zhangyang Wang","submitted_at":"2022-07-04T01:53:07Z","abstract_excerpt":"Existing out-of-distribution (OOD) detection methods are typically benchmarked on training sets with balanced class distributions. However, in real-world applications, it is common for the training sets to have long-tailed distributions. In this work, we first demonstrate that existing OOD detection methods commonly suffer from significant performance degradation when the training set is long-tail distributed. Through analysis, we posit that this is because the models struggle to distinguish the minority tail-class in-distribution samples, from the true OOD samples, making the tail classes mor"},"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":"2207.01160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-04T01:53:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b2f281f9760695c3a772b263ed970df26ee9bd6ac53c046ab806cafd4a0a6765","abstract_canon_sha256":"e734308271c1febead3a9c72bb88858aad6edee4444541ee774204744ca78182"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:08.658746Z","signature_b64":"H0A2FM1FJSuIbfEw247BqSDoUskZMav0gtmAy0mG2Z7x3k1Jg5NzrMuhacw55Y00tKAnXbYiYTdviMMEAFiYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23fc776c5a3e612aa389a0b3b59eb30d59161197528e6cf3796fad876b92c977","last_reissued_at":"2026-07-05T04:37:08.658302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:08.658302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Smola, Aston Zhang, Haotao Wang, Mu Li, Shuai Zheng, Yi Zhu, Zhangyang Wang","submitted_at":"2022-07-04T01:53:07Z","abstract_excerpt":"Existing out-of-distribution (OOD) detection methods are typically benchmarked on training sets with balanced class distributions. However, in real-world applications, it is common for the training sets to have long-tailed distributions. In this work, we first demonstrate that existing OOD detection methods commonly suffer from significant performance degradation when the training set is long-tail distributed. Through analysis, we posit that this is because the models struggle to distinguish the minority tail-class in-distribution samples, from the true OOD samples, making the tail classes mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01160","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/2207.01160/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":"2207.01160","created_at":"2026-07-05T04:37:08.658382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01160v1","created_at":"2026-07-05T04:37:08.658382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01160","created_at":"2026-07-05T04:37:08.658382+00:00"},{"alias_kind":"pith_short_12","alias_value":"EP6HO3C2HZQS","created_at":"2026-07-05T04:37:08.658382+00:00"},{"alias_kind":"pith_short_16","alias_value":"EP6HO3C2HZQSVI4J","created_at":"2026-07-05T04:37:08.658382+00:00"},{"alias_kind":"pith_short_8","alias_value":"EP6HO3C2","created_at":"2026-07-05T04:37:08.658382+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/EP6HO3C2HZQSVI4JUCZ3LHVTBV","json":"https://pith.science/pith/EP6HO3C2HZQSVI4JUCZ3LHVTBV.json","graph_json":"https://pith.science/api/pith-number/EP6HO3C2HZQSVI4JUCZ3LHVTBV/graph.json","events_json":"https://pith.science/api/pith-number/EP6HO3C2HZQSVI4JUCZ3LHVTBV/events.json","paper":"https://pith.science/paper/EP6HO3C2"},"agent_actions":{"view_html":"https://pith.science/pith/EP6HO3C2HZQSVI4JUCZ3LHVTBV","download_json":"https://pith.science/pith/EP6HO3C2HZQSVI4JUCZ3LHVTBV.json","view_paper":"https://pith.science/paper/EP6HO3C2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01160&json=true","fetch_graph":"https://pith.science/api/pith-number/EP6HO3C2HZQSVI4JUCZ3LHVTBV/graph.json","fetch_events":"https://pith.science/api/pith-number/EP6HO3C2HZQSVI4JUCZ3LHVTBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EP6HO3C2HZQSVI4JUCZ3LHVTBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EP6HO3C2HZQSVI4JUCZ3LHVTBV/action/storage_attestation","attest_author":"https://pith.science/pith/EP6HO3C2HZQSVI4JUCZ3LHVTBV/action/author_attestation","sign_citation":"https://pith.science/pith/EP6HO3C2HZQSVI4JUCZ3LHVTBV/action/citation_signature","submit_replication":"https://pith.science/pith/EP6HO3C2HZQSVI4JUCZ3LHVTBV/action/replication_record"}},"created_at":"2026-07-05T04:37:08.658382+00:00","updated_at":"2026-07-05T04:37:08.658382+00:00"}