{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R3C2BMWLWOLZRNWTTLERH4ZKWS","short_pith_number":"pith:R3C2BMWL","schema_version":"1.0","canonical_sha256":"8ec5a0b2cbb39798b6d39ac913f32ab483fc700f998e925ee5b58e3dc20c5524","source":{"kind":"arxiv","id":"2210.07347","version":3},"attestation_state":"computed","paper":{"title":"Disentanglement of Correlated Factors via Hausdorff Factorized Support","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Diane Bouchacourt, Karsten Roth, Mark Ibrahim, Pascal Vincent, Zeynep Akata","submitted_at":"2022-10-13T20:46:42Z","abstract_excerpt":"A grand goal in deep learning research is to learn representations capable of generalizing across distribution shifts. Disentanglement is one promising direction aimed at aligning a model's representation with the underlying factors generating the data (e.g. color or background). Existing disentanglement methods, however, rely on an often unrealistic assumption: that factors are statistically independent. In reality, factors (like object color and shape) are correlated. To address this limitation, we consider the use of a relaxed disentanglement criterion -- the Hausdorff Factorized Support (H"},"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":"2210.07347","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T20:46:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"353e350516247c68a799551f4843350a9c305a77362f90719e190e7fa2001476","abstract_canon_sha256":"5d23f8db2c7e92611857c402428e3277822fa3da51822d7790f62ef604919eb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:33.783571Z","signature_b64":"bPBvyRnHWVkLvBIK9kOfL91iqwTlxPAMyb+EsMySiCrMbuYqnAe0Ww+w4yBHvF7v6vYDTPN41u8ozrc3UVfoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ec5a0b2cbb39798b6d39ac913f32ab483fc700f998e925ee5b58e3dc20c5524","last_reissued_at":"2026-07-05T05:45:33.783058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:33.783058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentanglement of Correlated Factors via Hausdorff Factorized Support","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Diane Bouchacourt, Karsten Roth, Mark Ibrahim, Pascal Vincent, Zeynep Akata","submitted_at":"2022-10-13T20:46:42Z","abstract_excerpt":"A grand goal in deep learning research is to learn representations capable of generalizing across distribution shifts. Disentanglement is one promising direction aimed at aligning a model's representation with the underlying factors generating the data (e.g. color or background). Existing disentanglement methods, however, rely on an often unrealistic assumption: that factors are statistically independent. In reality, factors (like object color and shape) are correlated. To address this limitation, we consider the use of a relaxed disentanglement criterion -- the Hausdorff Factorized Support (H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07347","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/2210.07347/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":"2210.07347","created_at":"2026-07-05T05:45:33.783120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07347v3","created_at":"2026-07-05T05:45:33.783120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07347","created_at":"2026-07-05T05:45:33.783120+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3C2BMWLWOLZ","created_at":"2026-07-05T05:45:33.783120+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3C2BMWLWOLZRNWT","created_at":"2026-07-05T05:45:33.783120+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3C2BMWL","created_at":"2026-07-05T05:45:33.783120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.16161","citing_title":"Emotion Collider: Dual Hyperbolic Mirror Manifolds for Sentiment Recovery via Anti Emotion Reflection","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3C2BMWLWOLZRNWTTLERH4ZKWS","json":"https://pith.science/pith/R3C2BMWLWOLZRNWTTLERH4ZKWS.json","graph_json":"https://pith.science/api/pith-number/R3C2BMWLWOLZRNWTTLERH4ZKWS/graph.json","events_json":"https://pith.science/api/pith-number/R3C2BMWLWOLZRNWTTLERH4ZKWS/events.json","paper":"https://pith.science/paper/R3C2BMWL"},"agent_actions":{"view_html":"https://pith.science/pith/R3C2BMWLWOLZRNWTTLERH4ZKWS","download_json":"https://pith.science/pith/R3C2BMWLWOLZRNWTTLERH4ZKWS.json","view_paper":"https://pith.science/paper/R3C2BMWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07347&json=true","fetch_graph":"https://pith.science/api/pith-number/R3C2BMWLWOLZRNWTTLERH4ZKWS/graph.json","fetch_events":"https://pith.science/api/pith-number/R3C2BMWLWOLZRNWTTLERH4ZKWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3C2BMWLWOLZRNWTTLERH4ZKWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3C2BMWLWOLZRNWTTLERH4ZKWS/action/storage_attestation","attest_author":"https://pith.science/pith/R3C2BMWLWOLZRNWTTLERH4ZKWS/action/author_attestation","sign_citation":"https://pith.science/pith/R3C2BMWLWOLZRNWTTLERH4ZKWS/action/citation_signature","submit_replication":"https://pith.science/pith/R3C2BMWLWOLZRNWTTLERH4ZKWS/action/replication_record"}},"created_at":"2026-07-05T05:45:33.783120+00:00","updated_at":"2026-07-05T05:45:33.783120+00:00"}