{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZSEYJUEVBHZH7Q7OCIHOWAA2GX","short_pith_number":"pith:ZSEYJUEV","schema_version":"1.0","canonical_sha256":"cc8984d09509f27fc3ee120eeb001a35c8df5f3e7fddc9f7c22b7948796196f9","source":{"kind":"arxiv","id":"2507.09961","version":1},"attestation_state":"computed","paper":{"title":"Text-Driven Causal Representation Learning for Source-Free Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongbin Liu, Jiebo Luo, Jinlin Wu, Lei Deng, Lihua Zhou, Mao Ye, Nianxin Li, Shuaifeng Li, Xiatian Zhu, Zhen Lei","submitted_at":"2025-07-14T06:20:42Z","abstract_excerpt":"Deep learning often struggles when training and test data distributions differ. Traditional domain generalization (DG) tackles this by including data from multiple source domains, which is impractical due to expensive data collection and annotation. Recent vision-language models like CLIP enable source-free domain generalization (SFDG) by using text prompts to simulate visual representations, reducing data demands. However, existing SFDG methods struggle with domain-specific confounders, limiting their generalization capabilities. To address this issue, we propose TDCRL (\\textbf{T}ext-\\textbf{"},"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":"2507.09961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T06:20:42Z","cross_cats_sorted":[],"title_canon_sha256":"11b18ed9436d0ebbe00aad70cb87ac8ffd1a12573d6482011d89aa56d982765f","abstract_canon_sha256":"7d7300eb75abd49b9de4b7470039beb0e35c76d558be094e66aaf9266c4b093c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:42.869596Z","signature_b64":"K2P+ZbDb8SsPRqyEObKVgAkzX17DRNeFsJGpLI3kxQWWa1VE15t9m6LUiZMBmxlg9/d+7k1V0YHg+Vw5p8ysCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc8984d09509f27fc3ee120eeb001a35c8df5f3e7fddc9f7c22b7948796196f9","last_reissued_at":"2026-07-05T11:36:42.869142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:42.869142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-Driven Causal Representation Learning for Source-Free Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongbin Liu, Jiebo Luo, Jinlin Wu, Lei Deng, Lihua Zhou, Mao Ye, Nianxin Li, Shuaifeng Li, Xiatian Zhu, Zhen Lei","submitted_at":"2025-07-14T06:20:42Z","abstract_excerpt":"Deep learning often struggles when training and test data distributions differ. Traditional domain generalization (DG) tackles this by including data from multiple source domains, which is impractical due to expensive data collection and annotation. Recent vision-language models like CLIP enable source-free domain generalization (SFDG) by using text prompts to simulate visual representations, reducing data demands. However, existing SFDG methods struggle with domain-specific confounders, limiting their generalization capabilities. To address this issue, we propose TDCRL (\\textbf{T}ext-\\textbf{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09961","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/2507.09961/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":"2507.09961","created_at":"2026-07-05T11:36:42.869201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09961v1","created_at":"2026-07-05T11:36:42.869201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09961","created_at":"2026-07-05T11:36:42.869201+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSEYJUEVBHZH","created_at":"2026-07-05T11:36:42.869201+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSEYJUEVBHZH7Q7O","created_at":"2026-07-05T11:36:42.869201+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSEYJUEV","created_at":"2026-07-05T11:36:42.869201+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/ZSEYJUEVBHZH7Q7OCIHOWAA2GX","json":"https://pith.science/pith/ZSEYJUEVBHZH7Q7OCIHOWAA2GX.json","graph_json":"https://pith.science/api/pith-number/ZSEYJUEVBHZH7Q7OCIHOWAA2GX/graph.json","events_json":"https://pith.science/api/pith-number/ZSEYJUEVBHZH7Q7OCIHOWAA2GX/events.json","paper":"https://pith.science/paper/ZSEYJUEV"},"agent_actions":{"view_html":"https://pith.science/pith/ZSEYJUEVBHZH7Q7OCIHOWAA2GX","download_json":"https://pith.science/pith/ZSEYJUEVBHZH7Q7OCIHOWAA2GX.json","view_paper":"https://pith.science/paper/ZSEYJUEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09961&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSEYJUEVBHZH7Q7OCIHOWAA2GX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSEYJUEVBHZH7Q7OCIHOWAA2GX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSEYJUEVBHZH7Q7OCIHOWAA2GX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSEYJUEVBHZH7Q7OCIHOWAA2GX/action/storage_attestation","attest_author":"https://pith.science/pith/ZSEYJUEVBHZH7Q7OCIHOWAA2GX/action/author_attestation","sign_citation":"https://pith.science/pith/ZSEYJUEVBHZH7Q7OCIHOWAA2GX/action/citation_signature","submit_replication":"https://pith.science/pith/ZSEYJUEVBHZH7Q7OCIHOWAA2GX/action/replication_record"}},"created_at":"2026-07-05T11:36:42.869201+00:00","updated_at":"2026-07-05T11:36:42.869201+00:00"}