{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JSCZKRAU6YB4KLWDD6UNFJJNCZ","short_pith_number":"pith:JSCZKRAU","schema_version":"1.0","canonical_sha256":"4c85954414f603c52ec31fa8d2a52d1649647c37f8f0b721ed3dfb89fb74ba7f","source":{"kind":"arxiv","id":"2402.18853","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Multi-domain Generalization with A General Learning Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Kaizhu Huang, Xi Yang, Zhaorui Tan","submitted_at":"2024-02-29T05:00:30Z","abstract_excerpt":"Multi-domain generalization (mDG) is universally aimed to minimize the discrepancy between training and testing distributions to enhance marginal-to-label distribution mapping. However, existing mDG literature lacks a general learning objective paradigm and often imposes constraints on static target marginal distributions. In this paper, we propose to leverage a $Y$-mapping to relax the constraint. We rethink the learning objective for mDG and design a new \\textbf{general learning objective} to interpret and analyze most existing mDG wisdom. This general objective is bifurcated into two synerg"},"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":"2402.18853","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T05:00:30Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"1d4393e6cdc38a1db38f93057edd3d6393854515270ca24fa5faff15814519be","abstract_canon_sha256":"0b07e817286287090f87a490d32358b34b610d6834ea289651dbcb585c28c773"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:45.742265Z","signature_b64":"3Ez3usu/FxGw5CVMxLJ8TY4bPDI+Sq04uEGRzuFiIZ7xReSZbMP8iYL8ZdjWL42Hbdfx+edlG64JvrMJ95AFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c85954414f603c52ec31fa8d2a52d1649647c37f8f0b721ed3dfb89fb74ba7f","last_reissued_at":"2026-07-05T09:50:45.741763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:45.741763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Multi-domain Generalization with A General Learning Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Kaizhu Huang, Xi Yang, Zhaorui Tan","submitted_at":"2024-02-29T05:00:30Z","abstract_excerpt":"Multi-domain generalization (mDG) is universally aimed to minimize the discrepancy between training and testing distributions to enhance marginal-to-label distribution mapping. However, existing mDG literature lacks a general learning objective paradigm and often imposes constraints on static target marginal distributions. In this paper, we propose to leverage a $Y$-mapping to relax the constraint. We rethink the learning objective for mDG and design a new \\textbf{general learning objective} to interpret and analyze most existing mDG wisdom. This general objective is bifurcated into two synerg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18853","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/2402.18853/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":"2402.18853","created_at":"2026-07-05T09:50:45.741823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18853v2","created_at":"2026-07-05T09:50:45.741823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18853","created_at":"2026-07-05T09:50:45.741823+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSCZKRAU6YB4","created_at":"2026-07-05T09:50:45.741823+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSCZKRAU6YB4KLWD","created_at":"2026-07-05T09:50:45.741823+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSCZKRAU","created_at":"2026-07-05T09:50:45.741823+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14654","citing_title":"Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging","ref_index":216,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSCZKRAU6YB4KLWDD6UNFJJNCZ","json":"https://pith.science/pith/JSCZKRAU6YB4KLWDD6UNFJJNCZ.json","graph_json":"https://pith.science/api/pith-number/JSCZKRAU6YB4KLWDD6UNFJJNCZ/graph.json","events_json":"https://pith.science/api/pith-number/JSCZKRAU6YB4KLWDD6UNFJJNCZ/events.json","paper":"https://pith.science/paper/JSCZKRAU"},"agent_actions":{"view_html":"https://pith.science/pith/JSCZKRAU6YB4KLWDD6UNFJJNCZ","download_json":"https://pith.science/pith/JSCZKRAU6YB4KLWDD6UNFJJNCZ.json","view_paper":"https://pith.science/paper/JSCZKRAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18853&json=true","fetch_graph":"https://pith.science/api/pith-number/JSCZKRAU6YB4KLWDD6UNFJJNCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JSCZKRAU6YB4KLWDD6UNFJJNCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSCZKRAU6YB4KLWDD6UNFJJNCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSCZKRAU6YB4KLWDD6UNFJJNCZ/action/storage_attestation","attest_author":"https://pith.science/pith/JSCZKRAU6YB4KLWDD6UNFJJNCZ/action/author_attestation","sign_citation":"https://pith.science/pith/JSCZKRAU6YB4KLWDD6UNFJJNCZ/action/citation_signature","submit_replication":"https://pith.science/pith/JSCZKRAU6YB4KLWDD6UNFJJNCZ/action/replication_record"}},"created_at":"2026-07-05T09:50:45.741823+00:00","updated_at":"2026-07-05T09:50:45.741823+00:00"}