{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AQP2NMJYA2PNZBJJONG4XPCB7B","short_pith_number":"pith:AQP2NMJY","schema_version":"1.0","canonical_sha256":"041fa6b138069edc8529734dcbbc41f86c5a50ebc4420eae1789b97060257ecb","source":{"kind":"arxiv","id":"2412.11542","version":3},"attestation_state":"computed","paper":{"title":"Meta Curvature-Aware Minimization for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Feilong Tang, Yiwen Ye, Yongsheng Pan, Yong Xia, Ziyang Chen","submitted_at":"2024-12-16T08:22:23Z","abstract_excerpt":"Domain generalization (DG) aims to enhance the ability of models trained on source domains to generalize effectively to unseen domains. Recently, Sharpness-Aware Minimization (SAM) has shown promise in this area by reducing the sharpness of the loss landscape to obtain more generalized models. However, SAM and its variants sometimes fail to guide the model toward a flat minimum, and their training processes exhibit limitations, hindering further improvements in model generalization. In this paper, we first propose an improved model training process aimed at encouraging the model to converge to"},"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":"2412.11542","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T08:22:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"008627c0c678639ad28e4bbdbc00399ee9fe213e4ea43cb52efa8e4a22c238ad","abstract_canon_sha256":"1e8f18bb38edd2c173b968afb0728c6d9e85dbc17645fc80104ac0f050b20369"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:11.809880Z","signature_b64":"7DTNxdSSd5B7Aixy7OcouS0cd3zHDcekfc8Rmx3rLZJDY+5wdjUp4WrIEkr2uRCmREumcYn8aFOWGoCy07kBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"041fa6b138069edc8529734dcbbc41f86c5a50ebc4420eae1789b97060257ecb","last_reissued_at":"2026-07-05T10:26:11.808960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:11.808960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta Curvature-Aware Minimization for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Feilong Tang, Yiwen Ye, Yongsheng Pan, Yong Xia, Ziyang Chen","submitted_at":"2024-12-16T08:22:23Z","abstract_excerpt":"Domain generalization (DG) aims to enhance the ability of models trained on source domains to generalize effectively to unseen domains. Recently, Sharpness-Aware Minimization (SAM) has shown promise in this area by reducing the sharpness of the loss landscape to obtain more generalized models. However, SAM and its variants sometimes fail to guide the model toward a flat minimum, and their training processes exhibit limitations, hindering further improvements in model generalization. In this paper, we first propose an improved model training process aimed at encouraging the model to converge to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11542","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/2412.11542/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":"2412.11542","created_at":"2026-07-05T10:26:11.809071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11542v3","created_at":"2026-07-05T10:26:11.809071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11542","created_at":"2026-07-05T10:26:11.809071+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQP2NMJYA2PN","created_at":"2026-07-05T10:26:11.809071+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQP2NMJYA2PNZBJJ","created_at":"2026-07-05T10:26:11.809071+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQP2NMJY","created_at":"2026-07-05T10:26:11.809071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00778","citing_title":"Decoding the Flow: CauseMotion for Emotional Causality Analysis in Long-form Conversations","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQP2NMJYA2PNZBJJONG4XPCB7B","json":"https://pith.science/pith/AQP2NMJYA2PNZBJJONG4XPCB7B.json","graph_json":"https://pith.science/api/pith-number/AQP2NMJYA2PNZBJJONG4XPCB7B/graph.json","events_json":"https://pith.science/api/pith-number/AQP2NMJYA2PNZBJJONG4XPCB7B/events.json","paper":"https://pith.science/paper/AQP2NMJY"},"agent_actions":{"view_html":"https://pith.science/pith/AQP2NMJYA2PNZBJJONG4XPCB7B","download_json":"https://pith.science/pith/AQP2NMJYA2PNZBJJONG4XPCB7B.json","view_paper":"https://pith.science/paper/AQP2NMJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11542&json=true","fetch_graph":"https://pith.science/api/pith-number/AQP2NMJYA2PNZBJJONG4XPCB7B/graph.json","fetch_events":"https://pith.science/api/pith-number/AQP2NMJYA2PNZBJJONG4XPCB7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQP2NMJYA2PNZBJJONG4XPCB7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQP2NMJYA2PNZBJJONG4XPCB7B/action/storage_attestation","attest_author":"https://pith.science/pith/AQP2NMJYA2PNZBJJONG4XPCB7B/action/author_attestation","sign_citation":"https://pith.science/pith/AQP2NMJYA2PNZBJJONG4XPCB7B/action/citation_signature","submit_replication":"https://pith.science/pith/AQP2NMJYA2PNZBJJONG4XPCB7B/action/replication_record"}},"created_at":"2026-07-05T10:26:11.809071+00:00","updated_at":"2026-07-05T10:26:11.809071+00:00"}