{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z3LWI2PZY42HF6ZKNLI7NN4XN6","short_pith_number":"pith:Z3LWI2PZ","schema_version":"1.0","canonical_sha256":"ced76469f9c73472fb2a6ad1f6b7976fa699b76fd451506165af97d054a127c9","source":{"kind":"arxiv","id":"2204.11041","version":3},"attestation_state":"computed","paper":{"title":"Learning by Erasing: Conditional Entropy based Transferable Out-Of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjae Oh, Meng Xing, Yong Su, Zhiyong Feng","submitted_at":"2022-04-23T10:19:58Z","abstract_excerpt":"Out-of-distribution (OOD) detection is essential to handle the distribution shifts between training and test scenarios. For a new in-distribution (ID) dataset, existing methods require retraining to capture the dataset-specific feature representation or data distribution. In this paper, we propose a deep generative models (DGM) based transferable OOD detection method, which is unnecessary to retrain on a new ID dataset. We design an image erasing strategy to equip exclusive conditional entropy distribution for each ID dataset, which determines the discrepancy of DGM's posteriori ucertainty dis"},"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":"2204.11041","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-23T10:19:58Z","cross_cats_sorted":[],"title_canon_sha256":"58aab7315e3ef8812ee1a8cfa053752ec487fbbefd6f4bf890ba4179f36337f9","abstract_canon_sha256":"cd11c3c22046652e228c10c416a00898b15f8828f7f12fc1a32cd53d0981b378"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:13.277571Z","signature_b64":"8lL/YoksGQwHSCPxdoTGI1gonUC5Xgz6p1uk46EDXUW+wk0UXom5sXBZoxV6AVI8vZImGCMN90BR+L46zg4YDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ced76469f9c73472fb2a6ad1f6b7976fa699b76fd451506165af97d054a127c9","last_reissued_at":"2026-07-05T08:01:13.277155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:13.277155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning by Erasing: Conditional Entropy based Transferable Out-Of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjae Oh, Meng Xing, Yong Su, Zhiyong Feng","submitted_at":"2022-04-23T10:19:58Z","abstract_excerpt":"Out-of-distribution (OOD) detection is essential to handle the distribution shifts between training and test scenarios. For a new in-distribution (ID) dataset, existing methods require retraining to capture the dataset-specific feature representation or data distribution. In this paper, we propose a deep generative models (DGM) based transferable OOD detection method, which is unnecessary to retrain on a new ID dataset. We design an image erasing strategy to equip exclusive conditional entropy distribution for each ID dataset, which determines the discrepancy of DGM's posteriori ucertainty dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11041","kind":"arxiv","version":3},"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/2204.11041/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":"2204.11041","created_at":"2026-07-05T08:01:13.277207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.11041v3","created_at":"2026-07-05T08:01:13.277207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11041","created_at":"2026-07-05T08:01:13.277207+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3LWI2PZY42H","created_at":"2026-07-05T08:01:13.277207+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3LWI2PZY42HF6ZK","created_at":"2026-07-05T08:01:13.277207+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3LWI2PZ","created_at":"2026-07-05T08:01:13.277207+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/Z3LWI2PZY42HF6ZKNLI7NN4XN6","json":"https://pith.science/pith/Z3LWI2PZY42HF6ZKNLI7NN4XN6.json","graph_json":"https://pith.science/api/pith-number/Z3LWI2PZY42HF6ZKNLI7NN4XN6/graph.json","events_json":"https://pith.science/api/pith-number/Z3LWI2PZY42HF6ZKNLI7NN4XN6/events.json","paper":"https://pith.science/paper/Z3LWI2PZ"},"agent_actions":{"view_html":"https://pith.science/pith/Z3LWI2PZY42HF6ZKNLI7NN4XN6","download_json":"https://pith.science/pith/Z3LWI2PZY42HF6ZKNLI7NN4XN6.json","view_paper":"https://pith.science/paper/Z3LWI2PZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.11041&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3LWI2PZY42HF6ZKNLI7NN4XN6/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3LWI2PZY42HF6ZKNLI7NN4XN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3LWI2PZY42HF6ZKNLI7NN4XN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3LWI2PZY42HF6ZKNLI7NN4XN6/action/storage_attestation","attest_author":"https://pith.science/pith/Z3LWI2PZY42HF6ZKNLI7NN4XN6/action/author_attestation","sign_citation":"https://pith.science/pith/Z3LWI2PZY42HF6ZKNLI7NN4XN6/action/citation_signature","submit_replication":"https://pith.science/pith/Z3LWI2PZY42HF6ZKNLI7NN4XN6/action/replication_record"}},"created_at":"2026-07-05T08:01:13.277207+00:00","updated_at":"2026-07-05T08:01:13.277207+00:00"}