{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TPZDKWLEIKI4FVKP72HTIHW6XK","short_pith_number":"pith:TPZDKWLE","schema_version":"1.0","canonical_sha256":"9bf23559644291c2d54ffe8f341edeba98a0d09338d186aae3cc86034fdc8a6c","source":{"kind":"arxiv","id":"2205.12934","version":4},"attestation_state":"computed","paper":{"title":"Amortized Inference for Causal Structure Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bernhard Sch\\\"olkopf, Jonas Rothfuss, Lars Lorch, Scott Sussex","submitted_at":"2022-05-25T17:37:08Z","abstract_excerpt":"Inferring causal structure poses a combinatorial search problem that typically involves evaluating structures with a score or independence test. The resulting search is costly, and designing suitable scores or tests that capture prior knowledge is difficult. In this work, we propose to amortize causal structure learning. Rather than searching over structures, we train a variational inference model to directly predict the causal structure from observational or interventional data. This allows our inference model to acquire domain-specific inductive biases for causal discovery solely from data g"},"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":"2205.12934","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T17:37:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b345dc0cc49bb63523473b8b4d0fba45e2f671e201775605f638829bd130f93f","abstract_canon_sha256":"9fe472a901c95244dad06bff7b7618ab0eb8be2a43632554ceb9fd216c4d6308"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:29.046730Z","signature_b64":"30a5C9ATJluXE615vekTN9Z5CMbzQwaU5wFVm0NjHbjFfOPBtqyNfIVCY10TMCKLorhny8XO3iOeoFPNbe7nAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bf23559644291c2d54ffe8f341edeba98a0d09338d186aae3cc86034fdc8a6c","last_reissued_at":"2026-07-05T05:25:29.046262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:29.046262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Amortized Inference for Causal Structure Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bernhard Sch\\\"olkopf, Jonas Rothfuss, Lars Lorch, Scott Sussex","submitted_at":"2022-05-25T17:37:08Z","abstract_excerpt":"Inferring causal structure poses a combinatorial search problem that typically involves evaluating structures with a score or independence test. The resulting search is costly, and designing suitable scores or tests that capture prior knowledge is difficult. In this work, we propose to amortize causal structure learning. Rather than searching over structures, we train a variational inference model to directly predict the causal structure from observational or interventional data. This allows our inference model to acquire domain-specific inductive biases for causal discovery solely from data g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12934","kind":"arxiv","version":4},"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/2205.12934/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":"2205.12934","created_at":"2026-07-05T05:25:29.046323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12934v4","created_at":"2026-07-05T05:25:29.046323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12934","created_at":"2026-07-05T05:25:29.046323+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPZDKWLEIKI4","created_at":"2026-07-05T05:25:29.046323+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPZDKWLEIKI4FVKP","created_at":"2026-07-05T05:25:29.046323+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPZDKWLE","created_at":"2026-07-05T05:25:29.046323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19594","citing_title":"Unsupervised Causal Abstractions Discovery","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPZDKWLEIKI4FVKP72HTIHW6XK","json":"https://pith.science/pith/TPZDKWLEIKI4FVKP72HTIHW6XK.json","graph_json":"https://pith.science/api/pith-number/TPZDKWLEIKI4FVKP72HTIHW6XK/graph.json","events_json":"https://pith.science/api/pith-number/TPZDKWLEIKI4FVKP72HTIHW6XK/events.json","paper":"https://pith.science/paper/TPZDKWLE"},"agent_actions":{"view_html":"https://pith.science/pith/TPZDKWLEIKI4FVKP72HTIHW6XK","download_json":"https://pith.science/pith/TPZDKWLEIKI4FVKP72HTIHW6XK.json","view_paper":"https://pith.science/paper/TPZDKWLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12934&json=true","fetch_graph":"https://pith.science/api/pith-number/TPZDKWLEIKI4FVKP72HTIHW6XK/graph.json","fetch_events":"https://pith.science/api/pith-number/TPZDKWLEIKI4FVKP72HTIHW6XK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPZDKWLEIKI4FVKP72HTIHW6XK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPZDKWLEIKI4FVKP72HTIHW6XK/action/storage_attestation","attest_author":"https://pith.science/pith/TPZDKWLEIKI4FVKP72HTIHW6XK/action/author_attestation","sign_citation":"https://pith.science/pith/TPZDKWLEIKI4FVKP72HTIHW6XK/action/citation_signature","submit_replication":"https://pith.science/pith/TPZDKWLEIKI4FVKP72HTIHW6XK/action/replication_record"}},"created_at":"2026-07-05T05:25:29.046323+00:00","updated_at":"2026-07-05T05:25:29.046323+00:00"}