{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VITDREAWMXG4OXVPHM2YQBLIJI","short_pith_number":"pith:VITDREAW","schema_version":"1.0","canonical_sha256":"aa2638901665cdc75eaf3b358805684a339a9bdb82e653738eb68e09b975eb98","source":{"kind":"arxiv","id":"2007.01754","version":2},"attestation_state":"computed","paper":{"title":"Differentiable Causal Discovery from Interventional Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Drouin, Alexandre Lacoste, Philippe Brouillard, S\\'ebastien Lachapelle, Simon Lacoste-Julien","submitted_at":"2020-07-03T15:19:17Z","abstract_excerpt":"Learning a causal directed acyclic graph from data is a challenging task that involves solving a combinatorial problem for which the solution is not always identifiable. A new line of work reformulates this problem as a continuous constrained optimization one, which is solved via the augmented Lagrangian method. However, most methods based on this idea do not make use of interventional data, which can significantly alleviate identifiability issues. This work constitutes a new step in this direction by proposing a theoretically-grounded method based on neural networks that can leverage interven"},"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":"2007.01754","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T15:19:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"72548f1cabc0e54f81e0a8594b401784e71409a4f4e9b942bfff37908728d4c8","abstract_canon_sha256":"85d93bedf84f8b87585377e5c300773071d3a894bd53d9c049277fa67e3c1ab6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:04.165196Z","signature_b64":"+tmHbZUUU8VYuyhpnwUueyzr0EtyQQrfPfup4W3v+GhuTXHmsF+Y7WviwwmSL/4QmD1NxeElnnS5HGj2D9JiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa2638901665cdc75eaf3b358805684a339a9bdb82e653738eb68e09b975eb98","last_reissued_at":"2026-07-05T01:49:04.164749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:04.164749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Causal Discovery from Interventional Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Drouin, Alexandre Lacoste, Philippe Brouillard, S\\'ebastien Lachapelle, Simon Lacoste-Julien","submitted_at":"2020-07-03T15:19:17Z","abstract_excerpt":"Learning a causal directed acyclic graph from data is a challenging task that involves solving a combinatorial problem for which the solution is not always identifiable. A new line of work reformulates this problem as a continuous constrained optimization one, which is solved via the augmented Lagrangian method. However, most methods based on this idea do not make use of interventional data, which can significantly alleviate identifiability issues. This work constitutes a new step in this direction by proposing a theoretically-grounded method based on neural networks that can leverage interven"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01754","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/2007.01754/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":"2007.01754","created_at":"2026-07-05T01:49:04.164809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.01754v2","created_at":"2026-07-05T01:49:04.164809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01754","created_at":"2026-07-05T01:49:04.164809+00:00"},{"alias_kind":"pith_short_12","alias_value":"VITDREAWMXG4","created_at":"2026-07-05T01:49:04.164809+00:00"},{"alias_kind":"pith_short_16","alias_value":"VITDREAWMXG4OXVP","created_at":"2026-07-05T01:49:04.164809+00:00"},{"alias_kind":"pith_short_8","alias_value":"VITDREAW","created_at":"2026-07-05T01:49:04.164809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00754","citing_title":"Causal Density Functions","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03251","citing_title":"Do Real-World Datasets Contain Natural Experiments? An Empirical Study Using Causal Feature Selection","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18878","citing_title":"Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis","ref_index":290,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11170","citing_title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","ref_index":142,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VITDREAWMXG4OXVPHM2YQBLIJI","json":"https://pith.science/pith/VITDREAWMXG4OXVPHM2YQBLIJI.json","graph_json":"https://pith.science/api/pith-number/VITDREAWMXG4OXVPHM2YQBLIJI/graph.json","events_json":"https://pith.science/api/pith-number/VITDREAWMXG4OXVPHM2YQBLIJI/events.json","paper":"https://pith.science/paper/VITDREAW"},"agent_actions":{"view_html":"https://pith.science/pith/VITDREAWMXG4OXVPHM2YQBLIJI","download_json":"https://pith.science/pith/VITDREAWMXG4OXVPHM2YQBLIJI.json","view_paper":"https://pith.science/paper/VITDREAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.01754&json=true","fetch_graph":"https://pith.science/api/pith-number/VITDREAWMXG4OXVPHM2YQBLIJI/graph.json","fetch_events":"https://pith.science/api/pith-number/VITDREAWMXG4OXVPHM2YQBLIJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VITDREAWMXG4OXVPHM2YQBLIJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VITDREAWMXG4OXVPHM2YQBLIJI/action/storage_attestation","attest_author":"https://pith.science/pith/VITDREAWMXG4OXVPHM2YQBLIJI/action/author_attestation","sign_citation":"https://pith.science/pith/VITDREAWMXG4OXVPHM2YQBLIJI/action/citation_signature","submit_replication":"https://pith.science/pith/VITDREAWMXG4OXVPHM2YQBLIJI/action/replication_record"}},"created_at":"2026-07-05T01:49:04.164809+00:00","updated_at":"2026-07-05T01:49:04.164809+00:00"}