{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E4UD7GNZI2SSP6AL2D5JKRV2BH","short_pith_number":"pith:E4UD7GNZ","schema_version":"1.0","canonical_sha256":"27283f99b946a527f80bd0fa9546ba09eedaf056b9caf760f6ca090f5db14f22","source":{"kind":"arxiv","id":"2204.04875","version":2},"attestation_state":"computed","paper":{"title":"Learning to Induce Causal Structure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anirudh Goyal, Danilo Jimenez Rezende, Jane Wang, Jorg Bornschein, Matthew Botvinic, Melanie Rey, Michael Mozer, Nan Rosemary Ke, Silvia Chiappa, Theophane Weber","submitted_at":"2022-04-11T05:38:22Z","abstract_excerpt":"The fundamental challenge in causal induction is to infer the underlying graph structure given observational and/or interventional data. Most existing causal induction algorithms operate by generating candidate graphs and evaluating them using either score-based methods (including continuous optimization) or independence tests. In our work, we instead treat the inference process as a black box and design a neural network architecture that learns the mapping from both observational and interventional data to graph structures via supervised training on synthetic graphs. The learned model general"},"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":"2204.04875","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-11T05:38:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"10da4a4da49bd8e58f569d211b63e7ab9378f37b21c2b266a28bf8ab54a8c965","abstract_canon_sha256":"7d35574c69d2ec17a48548481f15854b3ffc4f7fefc85fcb556c118bb1b4484c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:28.706528Z","signature_b64":"QnRsuZDEyqHyUjLfIJ14IzdP16Zj4ne40nc8oq9oKLfi17q0ahSHQXDoWj5VVVTRKzkiYaFfxekhCGJxH6fdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27283f99b946a527f80bd0fa9546ba09eedaf056b9caf760f6ca090f5db14f22","last_reissued_at":"2026-07-05T05:04:28.706094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:28.706094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Induce Causal Structure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anirudh Goyal, Danilo Jimenez Rezende, Jane Wang, Jorg Bornschein, Matthew Botvinic, Melanie Rey, Michael Mozer, Nan Rosemary Ke, Silvia Chiappa, Theophane Weber","submitted_at":"2022-04-11T05:38:22Z","abstract_excerpt":"The fundamental challenge in causal induction is to infer the underlying graph structure given observational and/or interventional data. Most existing causal induction algorithms operate by generating candidate graphs and evaluating them using either score-based methods (including continuous optimization) or independence tests. In our work, we instead treat the inference process as a black box and design a neural network architecture that learns the mapping from both observational and interventional data to graph structures via supervised training on synthetic graphs. The learned model general"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04875","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/2204.04875/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":"2204.04875","created_at":"2026-07-05T05:04:28.706150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.04875v2","created_at":"2026-07-05T05:04:28.706150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04875","created_at":"2026-07-05T05:04:28.706150+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4UD7GNZI2SS","created_at":"2026-07-05T05:04:28.706150+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4UD7GNZI2SSP6AL","created_at":"2026-07-05T05:04:28.706150+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4UD7GNZ","created_at":"2026-07-05T05:04:28.706150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30015","citing_title":"Test Time Training for Supervised Causal Learning","ref_index":9,"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":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19594","citing_title":"Unsupervised Causal Abstractions Discovery","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06128","citing_title":"Amortized Inference of Causal Models via Conditional Fixed-Point Iterations","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2207.01848","citing_title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4UD7GNZI2SSP6AL2D5JKRV2BH","json":"https://pith.science/pith/E4UD7GNZI2SSP6AL2D5JKRV2BH.json","graph_json":"https://pith.science/api/pith-number/E4UD7GNZI2SSP6AL2D5JKRV2BH/graph.json","events_json":"https://pith.science/api/pith-number/E4UD7GNZI2SSP6AL2D5JKRV2BH/events.json","paper":"https://pith.science/paper/E4UD7GNZ"},"agent_actions":{"view_html":"https://pith.science/pith/E4UD7GNZI2SSP6AL2D5JKRV2BH","download_json":"https://pith.science/pith/E4UD7GNZI2SSP6AL2D5JKRV2BH.json","view_paper":"https://pith.science/paper/E4UD7GNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.04875&json=true","fetch_graph":"https://pith.science/api/pith-number/E4UD7GNZI2SSP6AL2D5JKRV2BH/graph.json","fetch_events":"https://pith.science/api/pith-number/E4UD7GNZI2SSP6AL2D5JKRV2BH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4UD7GNZI2SSP6AL2D5JKRV2BH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4UD7GNZI2SSP6AL2D5JKRV2BH/action/storage_attestation","attest_author":"https://pith.science/pith/E4UD7GNZI2SSP6AL2D5JKRV2BH/action/author_attestation","sign_citation":"https://pith.science/pith/E4UD7GNZI2SSP6AL2D5JKRV2BH/action/citation_signature","submit_replication":"https://pith.science/pith/E4UD7GNZI2SSP6AL2D5JKRV2BH/action/replication_record"}},"created_at":"2026-07-05T05:04:28.706150+00:00","updated_at":"2026-07-05T05:04:28.706150+00:00"}