{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:566RR6YSEV5BIXPYTIGZLOYHFS","short_pith_number":"pith:566RR6YS","schema_version":"1.0","canonical_sha256":"efbd18fb12257a145df89a0d95bb072c86fc3609c779b300e687ba39931c95f8","source":{"kind":"arxiv","id":"2111.13420","version":3},"attestation_state":"computed","paper":{"title":"Confounder Identification-free Causal Visual Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cuiling Lan, Guoqiang Wei, Wenjun Zeng, Xin Jin, Xin Li, Zhibo Chen, Zhizheng Zhang","submitted_at":"2021-11-26T10:57:47Z","abstract_excerpt":"Confounders in deep learning are in general detrimental to model's generalization where they infiltrate feature representations. Therefore, learning causal features that are free of interference from confounders is important. Most previous causal learning based approaches employ back-door criterion to mitigate the adverse effect of certain specific confounder, which require the explicit identification of confounder. However, in real scenarios, confounders are typically diverse and difficult to be identified. In this paper, we propose a novel Confounder Identification-free Causal Visual Feature"},"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":"2111.13420","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-26T10:57:47Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"664b62de6f8ca3de0f01eb90d11759fc65d7f396d3827715e2858380e2251522","abstract_canon_sha256":"3296dd28e2bc9e78077c05531388cbcd5dca39df141755e8d4532a4a22c81b41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:26.069677Z","signature_b64":"frc/9HunAPsMrxfYMQGtvJzWO2AL+DJyVQRDfkBQqAAgq+gG4bbwCBRP8HItyP9XCTaoOb+EFxOVldAkyRQ7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efbd18fb12257a145df89a0d95bb072c86fc3609c779b300e687ba39931c95f8","last_reissued_at":"2026-07-05T05:04:26.069061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:26.069061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confounder Identification-free Causal Visual Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Cuiling Lan, Guoqiang Wei, Wenjun Zeng, Xin Jin, Xin Li, Zhibo Chen, Zhizheng Zhang","submitted_at":"2021-11-26T10:57:47Z","abstract_excerpt":"Confounders in deep learning are in general detrimental to model's generalization where they infiltrate feature representations. Therefore, learning causal features that are free of interference from confounders is important. Most previous causal learning based approaches employ back-door criterion to mitigate the adverse effect of certain specific confounder, which require the explicit identification of confounder. However, in real scenarios, confounders are typically diverse and difficult to be identified. In this paper, we propose a novel Confounder Identification-free Causal Visual Feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13420","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/2111.13420/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":"2111.13420","created_at":"2026-07-05T05:04:26.069113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13420v3","created_at":"2026-07-05T05:04:26.069113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13420","created_at":"2026-07-05T05:04:26.069113+00:00"},{"alias_kind":"pith_short_12","alias_value":"566RR6YSEV5B","created_at":"2026-07-05T05:04:26.069113+00:00"},{"alias_kind":"pith_short_16","alias_value":"566RR6YSEV5BIXPY","created_at":"2026-07-05T05:04:26.069113+00:00"},{"alias_kind":"pith_short_8","alias_value":"566RR6YS","created_at":"2026-07-05T05:04:26.069113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.14375","citing_title":"Causal Fine-Tuning under Latent Confounded Shift","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/566RR6YSEV5BIXPYTIGZLOYHFS","json":"https://pith.science/pith/566RR6YSEV5BIXPYTIGZLOYHFS.json","graph_json":"https://pith.science/api/pith-number/566RR6YSEV5BIXPYTIGZLOYHFS/graph.json","events_json":"https://pith.science/api/pith-number/566RR6YSEV5BIXPYTIGZLOYHFS/events.json","paper":"https://pith.science/paper/566RR6YS"},"agent_actions":{"view_html":"https://pith.science/pith/566RR6YSEV5BIXPYTIGZLOYHFS","download_json":"https://pith.science/pith/566RR6YSEV5BIXPYTIGZLOYHFS.json","view_paper":"https://pith.science/paper/566RR6YS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13420&json=true","fetch_graph":"https://pith.science/api/pith-number/566RR6YSEV5BIXPYTIGZLOYHFS/graph.json","fetch_events":"https://pith.science/api/pith-number/566RR6YSEV5BIXPYTIGZLOYHFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/566RR6YSEV5BIXPYTIGZLOYHFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/566RR6YSEV5BIXPYTIGZLOYHFS/action/storage_attestation","attest_author":"https://pith.science/pith/566RR6YSEV5BIXPYTIGZLOYHFS/action/author_attestation","sign_citation":"https://pith.science/pith/566RR6YSEV5BIXPYTIGZLOYHFS/action/citation_signature","submit_replication":"https://pith.science/pith/566RR6YSEV5BIXPYTIGZLOYHFS/action/replication_record"}},"created_at":"2026-07-05T05:04:26.069113+00:00","updated_at":"2026-07-05T05:04:26.069113+00:00"}