{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3BEROQOD6G4IQNZVFOCMM7VLID","short_pith_number":"pith:3BEROQOD","schema_version":"1.0","canonical_sha256":"d8491741c3f1b88837352b84c67eab40c2160ef26dbea47ac84da1208954ef53","source":{"kind":"arxiv","id":"2212.08645","version":2},"attestation_state":"computed","paper":{"title":"Efficient Conditionally Invariant Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Gretton, Danica J. Sutherland, Namrata Deka, Roman Pogodin, Victor Veitch, Yazhe Li","submitted_at":"2022-12-16T18:39:32Z","abstract_excerpt":"We introduce the Conditional Independence Regression CovariancE (CIRCE), a measure of conditional independence for multivariate continuous-valued variables. CIRCE applies as a regularizer in settings where we wish to learn neural features $\\varphi(X)$ of data $X$ to estimate a target $Y$, while being conditionally independent of a distractor $Z$ given $Y$. Both $Z$ and $Y$ are assumed to be continuous-valued but relatively low dimensional, whereas $X$ and its features may be complex and high dimensional. Relevant settings include domain-invariant learning, fairness, and causal learning. The pr"},"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":"2212.08645","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-16T18:39:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fe45bbd33138ae71fb7e32841d10e91cf51727886b69f66e485312a844cdf957","abstract_canon_sha256":"e433abdd89030bcd79893d0f4f6d50fabf5be869f1f81bae39fd6dc50ebd22a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:38.767563Z","signature_b64":"zaFQUfXtH7Ow//IwdbHB93UeJhGCFV1jBhBYo3SGJt475skC/AOGhYjxCCVL2hXSzWH3cFTT/UCp7O+C7fwKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8491741c3f1b88837352b84c67eab40c2160ef26dbea47ac84da1208954ef53","last_reissued_at":"2026-07-05T07:25:38.767071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:38.767071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Conditionally Invariant Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Gretton, Danica J. Sutherland, Namrata Deka, Roman Pogodin, Victor Veitch, Yazhe Li","submitted_at":"2022-12-16T18:39:32Z","abstract_excerpt":"We introduce the Conditional Independence Regression CovariancE (CIRCE), a measure of conditional independence for multivariate continuous-valued variables. CIRCE applies as a regularizer in settings where we wish to learn neural features $\\varphi(X)$ of data $X$ to estimate a target $Y$, while being conditionally independent of a distractor $Z$ given $Y$. Both $Z$ and $Y$ are assumed to be continuous-valued but relatively low dimensional, whereas $X$ and its features may be complex and high dimensional. Relevant settings include domain-invariant learning, fairness, and causal learning. The pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08645","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/2212.08645/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":"2212.08645","created_at":"2026-07-05T07:25:38.767129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08645v2","created_at":"2026-07-05T07:25:38.767129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08645","created_at":"2026-07-05T07:25:38.767129+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BEROQOD6G4I","created_at":"2026-07-05T07:25:38.767129+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BEROQOD6G4IQNZV","created_at":"2026-07-05T07:25:38.767129+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BEROQOD","created_at":"2026-07-05T07:25:38.767129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01775","citing_title":"A Semi-Supervised Kernel Two-Sample Test","ref_index":127,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3BEROQOD6G4IQNZVFOCMM7VLID","json":"https://pith.science/pith/3BEROQOD6G4IQNZVFOCMM7VLID.json","graph_json":"https://pith.science/api/pith-number/3BEROQOD6G4IQNZVFOCMM7VLID/graph.json","events_json":"https://pith.science/api/pith-number/3BEROQOD6G4IQNZVFOCMM7VLID/events.json","paper":"https://pith.science/paper/3BEROQOD"},"agent_actions":{"view_html":"https://pith.science/pith/3BEROQOD6G4IQNZVFOCMM7VLID","download_json":"https://pith.science/pith/3BEROQOD6G4IQNZVFOCMM7VLID.json","view_paper":"https://pith.science/paper/3BEROQOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08645&json=true","fetch_graph":"https://pith.science/api/pith-number/3BEROQOD6G4IQNZVFOCMM7VLID/graph.json","fetch_events":"https://pith.science/api/pith-number/3BEROQOD6G4IQNZVFOCMM7VLID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BEROQOD6G4IQNZVFOCMM7VLID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BEROQOD6G4IQNZVFOCMM7VLID/action/storage_attestation","attest_author":"https://pith.science/pith/3BEROQOD6G4IQNZVFOCMM7VLID/action/author_attestation","sign_citation":"https://pith.science/pith/3BEROQOD6G4IQNZVFOCMM7VLID/action/citation_signature","submit_replication":"https://pith.science/pith/3BEROQOD6G4IQNZVFOCMM7VLID/action/replication_record"}},"created_at":"2026-07-05T07:25:38.767129+00:00","updated_at":"2026-07-05T07:25:38.767129+00:00"}