{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FI45EZ2K65OU6EOQLF4BXJ2FOJ","short_pith_number":"pith:FI45EZ2K","schema_version":"1.0","canonical_sha256":"2a39d2674af75d4f11d059781ba745727e817f12303639f2ad44aef4f4199c70","source":{"kind":"arxiv","id":"2006.07886","version":3},"attestation_state":"computed","paper":{"title":"On Disentangled Representations Learned From Correlated Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Dittadi, Anirudh Goyal, Bernhard Sch\\\"olkopf, Elliot Creager, Francesco Locatello, Frederik Tr\\\"auble, Niki Kilbertus, Stefan Bauer","submitted_at":"2020-06-14T12:47:34Z","abstract_excerpt":"The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data in a large-scale empirical study (including 4260 models). We show and quantify that systematically induced correlations in the dataset are being learned and reflected in the latent representations, which has implications for downstream ap"},"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":"2006.07886","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T12:47:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6c2fe2a3c8a158f98dda0cc06255ec73b07e6c5dc58de7133541881ab49bbaa4","abstract_canon_sha256":"7359a4888d1f4870294ebb62604d963b4893806a02cc1ffb47a5378f14cbdf0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:22.216458Z","signature_b64":"QOPqniqmUTksMu8Wj0RH8o39cA59tB/JKtLNP1lDJfmjZefP6N3Oc/MXVF8V9ve1mPVmS2p6PA2PzA+LQEuwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a39d2674af75d4f11d059781ba745727e817f12303639f2ad44aef4f4199c70","last_reissued_at":"2026-07-05T02:58:22.216037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:22.216037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Disentangled Representations Learned From Correlated Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Dittadi, Anirudh Goyal, Bernhard Sch\\\"olkopf, Elliot Creager, Francesco Locatello, Frederik Tr\\\"auble, Niki Kilbertus, Stefan Bauer","submitted_at":"2020-06-14T12:47:34Z","abstract_excerpt":"The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data in a large-scale empirical study (including 4260 models). We show and quantify that systematically induced correlations in the dataset are being learned and reflected in the latent representations, which has implications for downstream ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07886","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/2006.07886/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":"2006.07886","created_at":"2026-07-05T02:58:22.216089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07886v3","created_at":"2026-07-05T02:58:22.216089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07886","created_at":"2026-07-05T02:58:22.216089+00:00"},{"alias_kind":"pith_short_12","alias_value":"FI45EZ2K65OU","created_at":"2026-07-05T02:58:22.216089+00:00"},{"alias_kind":"pith_short_16","alias_value":"FI45EZ2K65OU6EOQ","created_at":"2026-07-05T02:58:22.216089+00:00"},{"alias_kind":"pith_short_8","alias_value":"FI45EZ2K","created_at":"2026-07-05T02:58:22.216089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20771","citing_title":"Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20732","citing_title":"Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FI45EZ2K65OU6EOQLF4BXJ2FOJ","json":"https://pith.science/pith/FI45EZ2K65OU6EOQLF4BXJ2FOJ.json","graph_json":"https://pith.science/api/pith-number/FI45EZ2K65OU6EOQLF4BXJ2FOJ/graph.json","events_json":"https://pith.science/api/pith-number/FI45EZ2K65OU6EOQLF4BXJ2FOJ/events.json","paper":"https://pith.science/paper/FI45EZ2K"},"agent_actions":{"view_html":"https://pith.science/pith/FI45EZ2K65OU6EOQLF4BXJ2FOJ","download_json":"https://pith.science/pith/FI45EZ2K65OU6EOQLF4BXJ2FOJ.json","view_paper":"https://pith.science/paper/FI45EZ2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07886&json=true","fetch_graph":"https://pith.science/api/pith-number/FI45EZ2K65OU6EOQLF4BXJ2FOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FI45EZ2K65OU6EOQLF4BXJ2FOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FI45EZ2K65OU6EOQLF4BXJ2FOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FI45EZ2K65OU6EOQLF4BXJ2FOJ/action/storage_attestation","attest_author":"https://pith.science/pith/FI45EZ2K65OU6EOQLF4BXJ2FOJ/action/author_attestation","sign_citation":"https://pith.science/pith/FI45EZ2K65OU6EOQLF4BXJ2FOJ/action/citation_signature","submit_replication":"https://pith.science/pith/FI45EZ2K65OU6EOQLF4BXJ2FOJ/action/replication_record"}},"created_at":"2026-07-05T02:58:22.216089+00:00","updated_at":"2026-07-05T02:58:22.216089+00:00"}