{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PCGG2PSINIR2VKF5JPDA22ZC5P","short_pith_number":"pith:PCGG2PSI","schema_version":"1.0","canonical_sha256":"788c6d3e486a23aaa8bd4bc60d6b22ebd606af1e10c9b065523d978a172bceff","source":{"kind":"arxiv","id":"2203.11819","version":3},"attestation_state":"computed","paper":{"title":"A Broad Study of Pre-training for Domain Generalization and Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donghyun Kim, Kaihong Wang, Kate Saenko, Stan Sclaroff","submitted_at":"2022-03-22T15:38:36Z","abstract_excerpt":"Deep models must learn robust and transferable representations in order to perform well on new domains. While domain transfer methods (e.g., domain adaptation, domain generalization) have been proposed to learn transferable representations across domains, they are typically applied to ResNet backbones pre-trained on ImageNet. Thus, existing works pay little attention to the effects of pre-training on domain transfer tasks. In this paper, we provide a broad study and in-depth analysis of pre-training for domain adaptation and generalization, namely: network architectures, size, pre-training los"},"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":"2203.11819","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T15:38:36Z","cross_cats_sorted":[],"title_canon_sha256":"18ba321c125d859b2c1d2066bafabb9d006b9fc4e2f9aeb00dda5576b141d0f1","abstract_canon_sha256":"664f79d469bdbbc4af1cbfb8aa4288f01f6d23b4ccd8c480741a974799407d9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:17.878296Z","signature_b64":"7vjAedFN+aZIdFfTsEL96I90DUPjLkEDl39nmqYC6qNRxaYOp6hKH0mY0hHQ9hhXR+VwhJmOKUKZS54qcv5uAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"788c6d3e486a23aaa8bd4bc60d6b22ebd606af1e10c9b065523d978a172bceff","last_reissued_at":"2026-07-05T04:42:17.877918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:17.877918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Broad Study of Pre-training for Domain Generalization and Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donghyun Kim, Kaihong Wang, Kate Saenko, Stan Sclaroff","submitted_at":"2022-03-22T15:38:36Z","abstract_excerpt":"Deep models must learn robust and transferable representations in order to perform well on new domains. While domain transfer methods (e.g., domain adaptation, domain generalization) have been proposed to learn transferable representations across domains, they are typically applied to ResNet backbones pre-trained on ImageNet. Thus, existing works pay little attention to the effects of pre-training on domain transfer tasks. In this paper, we provide a broad study and in-depth analysis of pre-training for domain adaptation and generalization, namely: network architectures, size, pre-training los"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11819","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/2203.11819/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":"2203.11819","created_at":"2026-07-05T04:42:17.877975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11819v3","created_at":"2026-07-05T04:42:17.877975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11819","created_at":"2026-07-05T04:42:17.877975+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCGG2PSINIR2","created_at":"2026-07-05T04:42:17.877975+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCGG2PSINIR2VKF5","created_at":"2026-07-05T04:42:17.877975+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCGG2PSI","created_at":"2026-07-05T04:42:17.877975+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/PCGG2PSINIR2VKF5JPDA22ZC5P","json":"https://pith.science/pith/PCGG2PSINIR2VKF5JPDA22ZC5P.json","graph_json":"https://pith.science/api/pith-number/PCGG2PSINIR2VKF5JPDA22ZC5P/graph.json","events_json":"https://pith.science/api/pith-number/PCGG2PSINIR2VKF5JPDA22ZC5P/events.json","paper":"https://pith.science/paper/PCGG2PSI"},"agent_actions":{"view_html":"https://pith.science/pith/PCGG2PSINIR2VKF5JPDA22ZC5P","download_json":"https://pith.science/pith/PCGG2PSINIR2VKF5JPDA22ZC5P.json","view_paper":"https://pith.science/paper/PCGG2PSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11819&json=true","fetch_graph":"https://pith.science/api/pith-number/PCGG2PSINIR2VKF5JPDA22ZC5P/graph.json","fetch_events":"https://pith.science/api/pith-number/PCGG2PSINIR2VKF5JPDA22ZC5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCGG2PSINIR2VKF5JPDA22ZC5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCGG2PSINIR2VKF5JPDA22ZC5P/action/storage_attestation","attest_author":"https://pith.science/pith/PCGG2PSINIR2VKF5JPDA22ZC5P/action/author_attestation","sign_citation":"https://pith.science/pith/PCGG2PSINIR2VKF5JPDA22ZC5P/action/citation_signature","submit_replication":"https://pith.science/pith/PCGG2PSINIR2VKF5JPDA22ZC5P/action/replication_record"}},"created_at":"2026-07-05T04:42:17.877975+00:00","updated_at":"2026-07-05T04:42:17.877975+00:00"}