{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HAI7M7DWIGYVC6LUDYMT5LUHF2","short_pith_number":"pith:HAI7M7DW","schema_version":"1.0","canonical_sha256":"3811f67c7641b15179741e193eae872eabc19332067bb72987223b20d80f8510","source":{"kind":"arxiv","id":"2203.04600","version":1},"attestation_state":"computed","paper":{"title":"Domain Generalization using Pretrained Models without Fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Li, Dongsheng Li, Haipeng Zhang, Kan Ren, Xinyang Jiang, Ziyue Li","submitted_at":"2022-03-09T09:33:59Z","abstract_excerpt":"Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. However, fine-tuning is usually computationally expensive due to the ever-growing size of pretrained models. More importantly, it may cause over-fitting on source domain and compromise their generalization ability as shown in recent works. Generally, pretrained models possess some level of generalization ability and can achieve decent performance regarding specific domains and samples. However, the generalization performance of pretrained models could vary significantly over different test domains even samp"},"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":"2203.04600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-09T09:33:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1baf0a3b277daf6308b8cdd370a24265d8a26cbd6fee00545231310a59b2af08","abstract_canon_sha256":"6d5793f244e00ad3b1142d3e7da65a7fb036b4a725336ae6c90b5105ae5cec8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:20.457249Z","signature_b64":"HeQKECtL8OrmKFPp+X4vRHftPRd9NA0rkF6v4uUy7miJUOUmhzABiiWf4hdo6lxLe6Mn7ZsBKYoES0GKAtyKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3811f67c7641b15179741e193eae872eabc19332067bb72987223b20d80f8510","last_reissued_at":"2026-07-05T04:03:20.456803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:20.456803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Generalization using Pretrained Models without Fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Li, Dongsheng Li, Haipeng Zhang, Kan Ren, Xinyang Jiang, Ziyue Li","submitted_at":"2022-03-09T09:33:59Z","abstract_excerpt":"Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. However, fine-tuning is usually computationally expensive due to the ever-growing size of pretrained models. More importantly, it may cause over-fitting on source domain and compromise their generalization ability as shown in recent works. Generally, pretrained models possess some level of generalization ability and can achieve decent performance regarding specific domains and samples. However, the generalization performance of pretrained models could vary significantly over different test domains even samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04600","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/2203.04600/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":"2203.04600","created_at":"2026-07-05T04:03:20.456847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.04600v1","created_at":"2026-07-05T04:03:20.456847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04600","created_at":"2026-07-05T04:03:20.456847+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAI7M7DWIGYV","created_at":"2026-07-05T04:03:20.456847+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAI7M7DWIGYVC6LU","created_at":"2026-07-05T04:03:20.456847+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAI7M7DW","created_at":"2026-07-05T04:03:20.456847+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20110","citing_title":"FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01657","citing_title":"Domain Generalization via Text-Anchored Information Bottleneck","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01667","citing_title":"Deep neural networks with Fisher vector encoding for medical image classification","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HAI7M7DWIGYVC6LUDYMT5LUHF2","json":"https://pith.science/pith/HAI7M7DWIGYVC6LUDYMT5LUHF2.json","graph_json":"https://pith.science/api/pith-number/HAI7M7DWIGYVC6LUDYMT5LUHF2/graph.json","events_json":"https://pith.science/api/pith-number/HAI7M7DWIGYVC6LUDYMT5LUHF2/events.json","paper":"https://pith.science/paper/HAI7M7DW"},"agent_actions":{"view_html":"https://pith.science/pith/HAI7M7DWIGYVC6LUDYMT5LUHF2","download_json":"https://pith.science/pith/HAI7M7DWIGYVC6LUDYMT5LUHF2.json","view_paper":"https://pith.science/paper/HAI7M7DW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.04600&json=true","fetch_graph":"https://pith.science/api/pith-number/HAI7M7DWIGYVC6LUDYMT5LUHF2/graph.json","fetch_events":"https://pith.science/api/pith-number/HAI7M7DWIGYVC6LUDYMT5LUHF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAI7M7DWIGYVC6LUDYMT5LUHF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAI7M7DWIGYVC6LUDYMT5LUHF2/action/storage_attestation","attest_author":"https://pith.science/pith/HAI7M7DWIGYVC6LUDYMT5LUHF2/action/author_attestation","sign_citation":"https://pith.science/pith/HAI7M7DWIGYVC6LUDYMT5LUHF2/action/citation_signature","submit_replication":"https://pith.science/pith/HAI7M7DWIGYVC6LUDYMT5LUHF2/action/replication_record"}},"created_at":"2026-07-05T04:03:20.456847+00:00","updated_at":"2026-07-05T04:03:20.456847+00:00"}