{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T6ITUQAM463G4UOIZDMNATMTX6","short_pith_number":"pith:T6ITUQAM","schema_version":"1.0","canonical_sha256":"9f913a400ce7b66e51c8c8d8d04d93bfb20e2c36e0642ddb461b1d216bf016ac","source":{"kind":"arxiv","id":"2011.02268","version":2},"attestation_state":"computed","paper":{"title":"Causal Autoregressive Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aapo Hyv\\\"arinen, Ilyes Khemakhem, Ricardo Pio Monti, Robert Leech","submitted_at":"2020-11-04T13:17:35Z","abstract_excerpt":"Two apparently unrelated fields -- normalizing flows and causality -- have recently received considerable attention in the machine learning community. In this work, we highlight an intrinsic correspondence between a simple family of autoregressive normalizing flows and identifiable causal models. We exploit the fact that autoregressive flow architectures define an ordering over variables, analogous to a causal ordering, to show that they are well-suited to performing a range of causal inference tasks, ranging from causal discovery to making interventional and counterfactual predictions. First,"},"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":"2011.02268","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-11-04T13:17:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b2a98b2c0be671f3f6e6b1b004700de9562f6b4ca54faee5b1c1a768d59578dc","abstract_canon_sha256":"fd5ccd115b6c40b795b7a08af68dae33ec2fdd74275625223a1211647a8d96a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:06.427694Z","signature_b64":"JkzZ0ohR90ik5wQrQ5UUH4i3MBh0eJWJZBk+vhR+SZyv4CbA/El3fqNj7R59IJCAELyBI+XV1C4IjUDKeZ4nDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f913a400ce7b66e51c8c8d8d04d93bfb20e2c36e0642ddb461b1d216bf016ac","last_reissued_at":"2026-07-05T02:18:06.427212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:06.427212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Autoregressive Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aapo Hyv\\\"arinen, Ilyes Khemakhem, Ricardo Pio Monti, Robert Leech","submitted_at":"2020-11-04T13:17:35Z","abstract_excerpt":"Two apparently unrelated fields -- normalizing flows and causality -- have recently received considerable attention in the machine learning community. In this work, we highlight an intrinsic correspondence between a simple family of autoregressive normalizing flows and identifiable causal models. We exploit the fact that autoregressive flow architectures define an ordering over variables, analogous to a causal ordering, to show that they are well-suited to performing a range of causal inference tasks, ranging from causal discovery to making interventional and counterfactual predictions. First,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02268","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/2011.02268/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":"2011.02268","created_at":"2026-07-05T02:18:06.427270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.02268v2","created_at":"2026-07-05T02:18:06.427270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02268","created_at":"2026-07-05T02:18:06.427270+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6ITUQAM463G","created_at":"2026-07-05T02:18:06.427270+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6ITUQAM463G4UOI","created_at":"2026-07-05T02:18:06.427270+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6ITUQAM","created_at":"2026-07-05T02:18:06.427270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03045","citing_title":"TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations","ref_index":276,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6ITUQAM463G4UOIZDMNATMTX6","json":"https://pith.science/pith/T6ITUQAM463G4UOIZDMNATMTX6.json","graph_json":"https://pith.science/api/pith-number/T6ITUQAM463G4UOIZDMNATMTX6/graph.json","events_json":"https://pith.science/api/pith-number/T6ITUQAM463G4UOIZDMNATMTX6/events.json","paper":"https://pith.science/paper/T6ITUQAM"},"agent_actions":{"view_html":"https://pith.science/pith/T6ITUQAM463G4UOIZDMNATMTX6","download_json":"https://pith.science/pith/T6ITUQAM463G4UOIZDMNATMTX6.json","view_paper":"https://pith.science/paper/T6ITUQAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.02268&json=true","fetch_graph":"https://pith.science/api/pith-number/T6ITUQAM463G4UOIZDMNATMTX6/graph.json","fetch_events":"https://pith.science/api/pith-number/T6ITUQAM463G4UOIZDMNATMTX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6ITUQAM463G4UOIZDMNATMTX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6ITUQAM463G4UOIZDMNATMTX6/action/storage_attestation","attest_author":"https://pith.science/pith/T6ITUQAM463G4UOIZDMNATMTX6/action/author_attestation","sign_citation":"https://pith.science/pith/T6ITUQAM463G4UOIZDMNATMTX6/action/citation_signature","submit_replication":"https://pith.science/pith/T6ITUQAM463G4UOIZDMNATMTX6/action/replication_record"}},"created_at":"2026-07-05T02:18:06.427270+00:00","updated_at":"2026-07-05T02:18:06.427270+00:00"}