{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PD35AOYM2TZH2JH2XAIHVC32SD","short_pith_number":"pith:PD35AOYM","schema_version":"1.0","canonical_sha256":"78f7d03b0cd4f27d24fab8107a8b7a90d11e5d7a7f9f4bea6d3584789ba5d2e7","source":{"kind":"arxiv","id":"2209.08473","version":2},"attestation_state":"computed","paper":{"title":"Bootstrap Generalization Ability from Loss Landscape Perspective","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huanran Chen, Jin Chen, Shitong Shao, Xiaofeng Ji, Xinxiao Wu, Zirui Shang, Ziyi Wang","submitted_at":"2022-09-18T04:40:32Z","abstract_excerpt":"Domain generalization aims to learn a model that can generalize well on the unseen test dataset, i.e., out-of-distribution data, which has different distribution from the training dataset. To address domain generalization in computer vision, we introduce the loss landscape theory into this field. Specifically, we bootstrap the generalization ability of the deep learning model from the loss landscape perspective in four aspects, including backbone, regularization, training paradigm, and learning rate. We verify the proposed theory on the NICO++, PACS, and VLCS datasets by doing extensive ablati"},"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":"2209.08473","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-18T04:40:32Z","cross_cats_sorted":[],"title_canon_sha256":"1c1d9e86d310912516c9f852350f469d1af4f740009f6da1c5ed5e1066ed1418","abstract_canon_sha256":"49c6fdc17385c3cc1a3fa8fe37fad09be3d1ae7d464c58d07fc1340b5f8c7623"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:09.420278Z","signature_b64":"44mP2GLUXWxbeDuQm1bXS2iGm94dK2qiG+HFQEqmOvvOJwC3Di9BUHZoEPcAx3xhKrTs6wADrMpVX5AdDNUzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78f7d03b0cd4f27d24fab8107a8b7a90d11e5d7a7f9f4bea6d3584789ba5d2e7","last_reissued_at":"2026-07-05T06:03:09.419793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:09.419793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrap Generalization Ability from Loss Landscape Perspective","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huanran Chen, Jin Chen, Shitong Shao, Xiaofeng Ji, Xinxiao Wu, Zirui Shang, Ziyi Wang","submitted_at":"2022-09-18T04:40:32Z","abstract_excerpt":"Domain generalization aims to learn a model that can generalize well on the unseen test dataset, i.e., out-of-distribution data, which has different distribution from the training dataset. To address domain generalization in computer vision, we introduce the loss landscape theory into this field. Specifically, we bootstrap the generalization ability of the deep learning model from the loss landscape perspective in four aspects, including backbone, regularization, training paradigm, and learning rate. We verify the proposed theory on the NICO++, PACS, and VLCS datasets by doing extensive ablati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08473","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/2209.08473/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":"2209.08473","created_at":"2026-07-05T06:03:09.419856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08473v2","created_at":"2026-07-05T06:03:09.419856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08473","created_at":"2026-07-05T06:03:09.419856+00:00"},{"alias_kind":"pith_short_12","alias_value":"PD35AOYM2TZH","created_at":"2026-07-05T06:03:09.419856+00:00"},{"alias_kind":"pith_short_16","alias_value":"PD35AOYM2TZH2JH2","created_at":"2026-07-05T06:03:09.419856+00:00"},{"alias_kind":"pith_short_8","alias_value":"PD35AOYM","created_at":"2026-07-05T06:03:09.419856+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/PD35AOYM2TZH2JH2XAIHVC32SD","json":"https://pith.science/pith/PD35AOYM2TZH2JH2XAIHVC32SD.json","graph_json":"https://pith.science/api/pith-number/PD35AOYM2TZH2JH2XAIHVC32SD/graph.json","events_json":"https://pith.science/api/pith-number/PD35AOYM2TZH2JH2XAIHVC32SD/events.json","paper":"https://pith.science/paper/PD35AOYM"},"agent_actions":{"view_html":"https://pith.science/pith/PD35AOYM2TZH2JH2XAIHVC32SD","download_json":"https://pith.science/pith/PD35AOYM2TZH2JH2XAIHVC32SD.json","view_paper":"https://pith.science/paper/PD35AOYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08473&json=true","fetch_graph":"https://pith.science/api/pith-number/PD35AOYM2TZH2JH2XAIHVC32SD/graph.json","fetch_events":"https://pith.science/api/pith-number/PD35AOYM2TZH2JH2XAIHVC32SD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PD35AOYM2TZH2JH2XAIHVC32SD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PD35AOYM2TZH2JH2XAIHVC32SD/action/storage_attestation","attest_author":"https://pith.science/pith/PD35AOYM2TZH2JH2XAIHVC32SD/action/author_attestation","sign_citation":"https://pith.science/pith/PD35AOYM2TZH2JH2XAIHVC32SD/action/citation_signature","submit_replication":"https://pith.science/pith/PD35AOYM2TZH2JH2XAIHVC32SD/action/replication_record"}},"created_at":"2026-07-05T06:03:09.419856+00:00","updated_at":"2026-07-05T06:03:09.419856+00:00"}