{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G5RNB2AZFHXFELQFOG7PW76RVF","short_pith_number":"pith:G5RNB2AZ","schema_version":"1.0","canonical_sha256":"3762d0e81929ee522e0571befb7fd1a94f04369c366da91a7ad0956090d13fd7","source":{"kind":"arxiv","id":"2202.03958","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty Modeling for Out-of-Distribution 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, Ying Shan, Yixiao Ge, Yongxing Dai","submitted_at":"2022-02-08T16:09:12Z","abstract_excerpt":"Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue 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. Common methods often consider the feature statistics as deterministic values measured from the learned features and do not explicitly consider the uncertain statistics discrepancy caused by potentia"},"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":"2202.03958","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-08T16:09:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"744bbb100d9a95d3a374a87276c35d553e75bf9cbe42d9c77bf5fa0fa8de3ad7","abstract_canon_sha256":"123e2d3fa7840b1210b4884a846ba64153bf6bc224778bcd8217df4aff476b76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:54.386366Z","signature_b64":"4JEpsGCgmTd1sxDR5jcbQZcVs0rn7sZXGdFuxvW02wh3qtc/FtgR39KRejO2GMHLaTz0fQRn/G03y9TKqIHzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3762d0e81929ee522e0571befb7fd1a94f04369c366da91a7ad0956090d13fd7","last_reissued_at":"2026-07-05T04:16:54.385934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:54.385934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Modeling for Out-of-Distribution 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, Ying Shan, Yixiao Ge, Yongxing Dai","submitted_at":"2022-02-08T16:09:12Z","abstract_excerpt":"Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue 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. Common methods often consider the feature statistics as deterministic values measured from the learned features and do not explicitly consider the uncertain statistics discrepancy caused by potentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03958","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/2202.03958/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":"2202.03958","created_at":"2026-07-05T04:16:54.385989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03958v2","created_at":"2026-07-05T04:16:54.385989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03958","created_at":"2026-07-05T04:16:54.385989+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5RNB2AZFHXF","created_at":"2026-07-05T04:16:54.385989+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5RNB2AZFHXFELQF","created_at":"2026-07-05T04:16:54.385989+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5RNB2AZ","created_at":"2026-07-05T04:16:54.385989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21736","citing_title":"Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5RNB2AZFHXFELQFOG7PW76RVF","json":"https://pith.science/pith/G5RNB2AZFHXFELQFOG7PW76RVF.json","graph_json":"https://pith.science/api/pith-number/G5RNB2AZFHXFELQFOG7PW76RVF/graph.json","events_json":"https://pith.science/api/pith-number/G5RNB2AZFHXFELQFOG7PW76RVF/events.json","paper":"https://pith.science/paper/G5RNB2AZ"},"agent_actions":{"view_html":"https://pith.science/pith/G5RNB2AZFHXFELQFOG7PW76RVF","download_json":"https://pith.science/pith/G5RNB2AZFHXFELQFOG7PW76RVF.json","view_paper":"https://pith.science/paper/G5RNB2AZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03958&json=true","fetch_graph":"https://pith.science/api/pith-number/G5RNB2AZFHXFELQFOG7PW76RVF/graph.json","fetch_events":"https://pith.science/api/pith-number/G5RNB2AZFHXFELQFOG7PW76RVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5RNB2AZFHXFELQFOG7PW76RVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5RNB2AZFHXFELQFOG7PW76RVF/action/storage_attestation","attest_author":"https://pith.science/pith/G5RNB2AZFHXFELQFOG7PW76RVF/action/author_attestation","sign_citation":"https://pith.science/pith/G5RNB2AZFHXFELQFOG7PW76RVF/action/citation_signature","submit_replication":"https://pith.science/pith/G5RNB2AZFHXFELQFOG7PW76RVF/action/replication_record"}},"created_at":"2026-07-05T04:16:54.385989+00:00","updated_at":"2026-07-05T04:16:54.385989+00:00"}