{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DYJMNL6NGKTURTLX26ERIB2Q52","short_pith_number":"pith:DYJMNL6N","schema_version":"1.0","canonical_sha256":"1e12c6afcd32a748cd77d789140750eeb34d07f80400265c3982677801ca73a2","source":{"kind":"arxiv","id":"2301.06442","version":1},"attestation_state":"computed","paper":{"title":"Modeling Uncertain Feature Representation for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jun Liu, Ling-Yu Duan, Xiaotong Li, Yixiao Ge, Yongxing Dai, Zixuan Hu","submitted_at":"2023-01-16T14:25:02Z","abstract_excerpt":"Though deep neural networks have achieved impressive success on various vision tasks, obvious performance degradation still exists when models are tested in out-of-distribution scenarios. In addressing this limitation, we ponder that the feature statistics (mean and standard deviation), which carry the domain characteristics of the training data, can be properly manipulated to improve the generalization ability of deep learning models. Existing methods commonly consider feature statistics as deterministic values measured from the learned features and do not explicitly model the uncertain stati"},"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":"2301.06442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-16T14:25:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f91c5641975fdd12c602f1aa376b3364cdaa5c31b7a69ac6e52ce8c8df188e0f","abstract_canon_sha256":"7482e738bfc7ab03569c0b4518c1b5392efb435205d99ae69746101fc733150b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:31.642231Z","signature_b64":"Vye9j8pZ+fLj/qgMqhbN5b3d0RH1imoGPOuCMGKy0mOmtWs+r0Ble15fPhRoAEQNA2rmzSXBS7KcDzU0Gmc3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e12c6afcd32a748cd77d789140750eeb34d07f80400265c3982677801ca73a2","last_reissued_at":"2026-07-05T05:33:31.641770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:31.641770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Uncertain Feature Representation for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jun Liu, Ling-Yu Duan, Xiaotong Li, Yixiao Ge, Yongxing Dai, Zixuan Hu","submitted_at":"2023-01-16T14:25:02Z","abstract_excerpt":"Though deep neural networks have achieved impressive success on various vision tasks, obvious performance degradation still exists when models are tested in out-of-distribution scenarios. In addressing this limitation, we ponder that the feature statistics (mean and standard deviation), which carry the domain characteristics of the training data, can be properly manipulated to improve the generalization ability of deep learning models. Existing methods commonly consider feature statistics as deterministic values measured from the learned features and do not explicitly model the uncertain stati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06442","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/2301.06442/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":"2301.06442","created_at":"2026-07-05T05:33:31.641834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06442v1","created_at":"2026-07-05T05:33:31.641834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06442","created_at":"2026-07-05T05:33:31.641834+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYJMNL6NGKTU","created_at":"2026-07-05T05:33:31.641834+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYJMNL6NGKTURTLX","created_at":"2026-07-05T05:33:31.641834+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYJMNL6N","created_at":"2026-07-05T05:33:31.641834+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/DYJMNL6NGKTURTLX26ERIB2Q52","json":"https://pith.science/pith/DYJMNL6NGKTURTLX26ERIB2Q52.json","graph_json":"https://pith.science/api/pith-number/DYJMNL6NGKTURTLX26ERIB2Q52/graph.json","events_json":"https://pith.science/api/pith-number/DYJMNL6NGKTURTLX26ERIB2Q52/events.json","paper":"https://pith.science/paper/DYJMNL6N"},"agent_actions":{"view_html":"https://pith.science/pith/DYJMNL6NGKTURTLX26ERIB2Q52","download_json":"https://pith.science/pith/DYJMNL6NGKTURTLX26ERIB2Q52.json","view_paper":"https://pith.science/paper/DYJMNL6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06442&json=true","fetch_graph":"https://pith.science/api/pith-number/DYJMNL6NGKTURTLX26ERIB2Q52/graph.json","fetch_events":"https://pith.science/api/pith-number/DYJMNL6NGKTURTLX26ERIB2Q52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYJMNL6NGKTURTLX26ERIB2Q52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYJMNL6NGKTURTLX26ERIB2Q52/action/storage_attestation","attest_author":"https://pith.science/pith/DYJMNL6NGKTURTLX26ERIB2Q52/action/author_attestation","sign_citation":"https://pith.science/pith/DYJMNL6NGKTURTLX26ERIB2Q52/action/citation_signature","submit_replication":"https://pith.science/pith/DYJMNL6NGKTURTLX26ERIB2Q52/action/replication_record"}},"created_at":"2026-07-05T05:33:31.641834+00:00","updated_at":"2026-07-05T05:33:31.641834+00:00"}