{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MLHDXZDPBBCHWEEGSBJYMMQYDV","short_pith_number":"pith:MLHDXZDP","schema_version":"1.0","canonical_sha256":"62ce3be46f08447b108690538632181d54bceba345da44a28dbd8c8ff5888425","source":{"kind":"arxiv","id":"2109.02429","version":2},"attestation_state":"computed","paper":{"title":"Learning Neural Causal Models with Active Interventions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anirudh Goyal, Bernhard Sch\\\"olkopf, Michael C. Mozer, Nan Rosemary Ke, Nino Scherrer, Olexa Bilaniuk, Patrick Schwab, Stefan Bauer, Yashas Annadani, Yoshua Bengio","submitted_at":"2021-09-06T13:10:37Z","abstract_excerpt":"Discovering causal structures from data is a challenging inference problem of fundamental importance in all areas of science. The appealing properties of neural networks have recently led to a surge of interest in differentiable neural network-based methods for learning causal structures from data. So far, differentiable causal discovery has focused on static datasets of observational or fixed interventional origin. In this work, we introduce an active intervention targeting (AIT) method which enables a quick identification of the underlying causal structure of the data-generating process. Our"},"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":"2109.02429","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-09-06T13:10:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b0e67c3e872a7818516696bc3788d8c07cade2c429e466d1485076effd701d46","abstract_canon_sha256":"ad7fc8e37a5b341a919445b43d3684d6826efd3acc5232b3e0208c6a4e1a848d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:18.585103Z","signature_b64":"E8cve7BtT5xCfi4hST7+HzE2XK5cr1Z9ihuzr/qHS4WW8WB/qQXajhcXRlJJhxSWRtIdkCmd4RM3aVtyV0cJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62ce3be46f08447b108690538632181d54bceba345da44a28dbd8c8ff5888425","last_reissued_at":"2026-07-05T04:02:18.584660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:18.584660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Neural Causal Models with Active Interventions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anirudh Goyal, Bernhard Sch\\\"olkopf, Michael C. Mozer, Nan Rosemary Ke, Nino Scherrer, Olexa Bilaniuk, Patrick Schwab, Stefan Bauer, Yashas Annadani, Yoshua Bengio","submitted_at":"2021-09-06T13:10:37Z","abstract_excerpt":"Discovering causal structures from data is a challenging inference problem of fundamental importance in all areas of science. The appealing properties of neural networks have recently led to a surge of interest in differentiable neural network-based methods for learning causal structures from data. So far, differentiable causal discovery has focused on static datasets of observational or fixed interventional origin. In this work, we introduce an active intervention targeting (AIT) method which enables a quick identification of the underlying causal structure of the data-generating process. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02429","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/2109.02429/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":"2109.02429","created_at":"2026-07-05T04:02:18.584718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.02429v2","created_at":"2026-07-05T04:02:18.584718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02429","created_at":"2026-07-05T04:02:18.584718+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLHDXZDPBBCH","created_at":"2026-07-05T04:02:18.584718+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLHDXZDPBBCHWEEG","created_at":"2026-07-05T04:02:18.584718+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLHDXZDP","created_at":"2026-07-05T04:02:18.584718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27567","citing_title":"Why LLMs Fail at Causal Discovery and How Interventional Agents Escape","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLHDXZDPBBCHWEEGSBJYMMQYDV","json":"https://pith.science/pith/MLHDXZDPBBCHWEEGSBJYMMQYDV.json","graph_json":"https://pith.science/api/pith-number/MLHDXZDPBBCHWEEGSBJYMMQYDV/graph.json","events_json":"https://pith.science/api/pith-number/MLHDXZDPBBCHWEEGSBJYMMQYDV/events.json","paper":"https://pith.science/paper/MLHDXZDP"},"agent_actions":{"view_html":"https://pith.science/pith/MLHDXZDPBBCHWEEGSBJYMMQYDV","download_json":"https://pith.science/pith/MLHDXZDPBBCHWEEGSBJYMMQYDV.json","view_paper":"https://pith.science/paper/MLHDXZDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.02429&json=true","fetch_graph":"https://pith.science/api/pith-number/MLHDXZDPBBCHWEEGSBJYMMQYDV/graph.json","fetch_events":"https://pith.science/api/pith-number/MLHDXZDPBBCHWEEGSBJYMMQYDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLHDXZDPBBCHWEEGSBJYMMQYDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLHDXZDPBBCHWEEGSBJYMMQYDV/action/storage_attestation","attest_author":"https://pith.science/pith/MLHDXZDPBBCHWEEGSBJYMMQYDV/action/author_attestation","sign_citation":"https://pith.science/pith/MLHDXZDPBBCHWEEGSBJYMMQYDV/action/citation_signature","submit_replication":"https://pith.science/pith/MLHDXZDPBBCHWEEGSBJYMMQYDV/action/replication_record"}},"created_at":"2026-07-05T04:02:18.584718+00:00","updated_at":"2026-07-05T04:02:18.584718+00:00"}