{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EFKMHEIAZOTJL7I3QYUWEPLPFV","short_pith_number":"pith:EFKMHEIA","schema_version":"1.0","canonical_sha256":"2154c39100cba695fd1b8629623d6f2d45478fe5cbdf42e2d97b5b955b4dd1b6","source":{"kind":"arxiv","id":"2206.09387","version":2},"attestation_state":"computed","paper":{"title":"Dual Representation Learning for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Longbing Cao, Zhilin Zhao","submitted_at":"2022-06-19T12:11:13Z","abstract_excerpt":"To classify in-distribution samples, deep neural networks explore strongly label-related information and discard weakly label-related information according to the information bottleneck. Out-of-distribution samples drawn from distributions differing from that of in-distribution samples could be assigned with unexpected high-confidence predictions because they could obtain minimum strongly label-related information. To distinguish in- and out-of-distribution samples, Dual Representation Learning (DRL) makes out-of-distribution samples harder to have high-confidence predictions by exploring both"},"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":"2206.09387","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-19T12:11:13Z","cross_cats_sorted":[],"title_canon_sha256":"ed1aa9b450bc00d7a7a2940bfe6b711f543c81d49a3cd62484363052de62131f","abstract_canon_sha256":"ba3a6d137f713c26082a0c7860eda0b4d8b7c99a10e2c5f7f8466971fca1263f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:12.037794Z","signature_b64":"jMAiYbacIGzTjuBY3arZYNlxC4Moti8aZOKKIAc0kwTAezMKJpPuG5UIRfPus9b4OWAhceQthRYZFtYYIUbKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2154c39100cba695fd1b8629623d6f2d45478fe5cbdf42e2d97b5b955b4dd1b6","last_reissued_at":"2026-07-05T06:45:12.037343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:12.037343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Representation Learning for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Longbing Cao, Zhilin Zhao","submitted_at":"2022-06-19T12:11:13Z","abstract_excerpt":"To classify in-distribution samples, deep neural networks explore strongly label-related information and discard weakly label-related information according to the information bottleneck. Out-of-distribution samples drawn from distributions differing from that of in-distribution samples could be assigned with unexpected high-confidence predictions because they could obtain minimum strongly label-related information. To distinguish in- and out-of-distribution samples, Dual Representation Learning (DRL) makes out-of-distribution samples harder to have high-confidence predictions by exploring both"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09387","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/2206.09387/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":"2206.09387","created_at":"2026-07-05T06:45:12.037403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09387v2","created_at":"2026-07-05T06:45:12.037403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09387","created_at":"2026-07-05T06:45:12.037403+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFKMHEIAZOTJ","created_at":"2026-07-05T06:45:12.037403+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFKMHEIAZOTJL7I3","created_at":"2026-07-05T06:45:12.037403+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFKMHEIA","created_at":"2026-07-05T06:45:12.037403+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/EFKMHEIAZOTJL7I3QYUWEPLPFV","json":"https://pith.science/pith/EFKMHEIAZOTJL7I3QYUWEPLPFV.json","graph_json":"https://pith.science/api/pith-number/EFKMHEIAZOTJL7I3QYUWEPLPFV/graph.json","events_json":"https://pith.science/api/pith-number/EFKMHEIAZOTJL7I3QYUWEPLPFV/events.json","paper":"https://pith.science/paper/EFKMHEIA"},"agent_actions":{"view_html":"https://pith.science/pith/EFKMHEIAZOTJL7I3QYUWEPLPFV","download_json":"https://pith.science/pith/EFKMHEIAZOTJL7I3QYUWEPLPFV.json","view_paper":"https://pith.science/paper/EFKMHEIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09387&json=true","fetch_graph":"https://pith.science/api/pith-number/EFKMHEIAZOTJL7I3QYUWEPLPFV/graph.json","fetch_events":"https://pith.science/api/pith-number/EFKMHEIAZOTJL7I3QYUWEPLPFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFKMHEIAZOTJL7I3QYUWEPLPFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFKMHEIAZOTJL7I3QYUWEPLPFV/action/storage_attestation","attest_author":"https://pith.science/pith/EFKMHEIAZOTJL7I3QYUWEPLPFV/action/author_attestation","sign_citation":"https://pith.science/pith/EFKMHEIAZOTJL7I3QYUWEPLPFV/action/citation_signature","submit_replication":"https://pith.science/pith/EFKMHEIAZOTJL7I3QYUWEPLPFV/action/replication_record"}},"created_at":"2026-07-05T06:45:12.037403+00:00","updated_at":"2026-07-05T06:45:12.037403+00:00"}