{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7DCH7JVMPSPWTEVV2NTVYW3R3B","short_pith_number":"pith:7DCH7JVM","schema_version":"1.0","canonical_sha256":"f8c47fa6ac7c9f6992b5d3675c5b71d8556625f15c484b29bec62047824f3eee","source":{"kind":"arxiv","id":"2106.07635","version":1},"attestation_state":"computed","paper":{"title":"Variational Causal Networks: Approximate Bayesian Inference over Causal Structures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Lacoste, Anirudh Goyal, Jonas Rothfuss, Nino Scherrer, Stefan Bauer, Yashas Annadani, Yoshua Bengio","submitted_at":"2021-06-14T17:52:49Z","abstract_excerpt":"Learning the causal structure that underlies data is a crucial step towards robust real-world decision making. The majority of existing work in causal inference focuses on determining a single directed acyclic graph (DAG) or a Markov equivalence class thereof. However, a crucial aspect to acting intelligently upon the knowledge about causal structure which has been inferred from finite data demands reasoning about its uncertainty. For instance, planning interventions to find out more about the causal mechanisms that govern our data requires quantifying epistemic uncertainty over DAGs. While Ba"},"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":"2106.07635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-14T17:52:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7835bb436a806bcb3d3f691e09e44572b2715a4a231ea95dbf7cd0ac4759b779","abstract_canon_sha256":"c95a69aa8412cdbd5fd3d7b953927f2414723a67974426220cbb5869582a6e73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:06.991649Z","signature_b64":"B9jXAjyiNxETG66A1UOU1KzBVV5BVpWnLTBRlH+zitxdLoDpfIy3opSD1f7svecX60D2Q00tW6h2XiHhY2hGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8c47fa6ac7c9f6992b5d3675c5b71d8556625f15c484b29bec62047824f3eee","last_reissued_at":"2026-07-05T02:49:06.991177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:06.991177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Causal Networks: Approximate Bayesian Inference over Causal Structures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Lacoste, Anirudh Goyal, Jonas Rothfuss, Nino Scherrer, Stefan Bauer, Yashas Annadani, Yoshua Bengio","submitted_at":"2021-06-14T17:52:49Z","abstract_excerpt":"Learning the causal structure that underlies data is a crucial step towards robust real-world decision making. The majority of existing work in causal inference focuses on determining a single directed acyclic graph (DAG) or a Markov equivalence class thereof. However, a crucial aspect to acting intelligently upon the knowledge about causal structure which has been inferred from finite data demands reasoning about its uncertainty. For instance, planning interventions to find out more about the causal mechanisms that govern our data requires quantifying epistemic uncertainty over DAGs. While Ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07635","kind":"arxiv","version":1},"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/2106.07635/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":"2106.07635","created_at":"2026-07-05T02:49:06.991229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.07635v1","created_at":"2026-07-05T02:49:06.991229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07635","created_at":"2026-07-05T02:49:06.991229+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DCH7JVMPSPW","created_at":"2026-07-05T02:49:06.991229+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DCH7JVMPSPWTEVV","created_at":"2026-07-05T02:49:06.991229+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DCH7JVM","created_at":"2026-07-05T02:49:06.991229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27477","citing_title":"Iterative Causal Discovery: Per-Edge Impossibility Certificates, Tier-Aware Oracle Queries, and the $1+K$ Lower Bound","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06440","citing_title":"Causal Atlases from Entropic Inference: Bayesian Networks beyond Optimal DAGs","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DCH7JVMPSPWTEVV2NTVYW3R3B","json":"https://pith.science/pith/7DCH7JVMPSPWTEVV2NTVYW3R3B.json","graph_json":"https://pith.science/api/pith-number/7DCH7JVMPSPWTEVV2NTVYW3R3B/graph.json","events_json":"https://pith.science/api/pith-number/7DCH7JVMPSPWTEVV2NTVYW3R3B/events.json","paper":"https://pith.science/paper/7DCH7JVM"},"agent_actions":{"view_html":"https://pith.science/pith/7DCH7JVMPSPWTEVV2NTVYW3R3B","download_json":"https://pith.science/pith/7DCH7JVMPSPWTEVV2NTVYW3R3B.json","view_paper":"https://pith.science/paper/7DCH7JVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.07635&json=true","fetch_graph":"https://pith.science/api/pith-number/7DCH7JVMPSPWTEVV2NTVYW3R3B/graph.json","fetch_events":"https://pith.science/api/pith-number/7DCH7JVMPSPWTEVV2NTVYW3R3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DCH7JVMPSPWTEVV2NTVYW3R3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DCH7JVMPSPWTEVV2NTVYW3R3B/action/storage_attestation","attest_author":"https://pith.science/pith/7DCH7JVMPSPWTEVV2NTVYW3R3B/action/author_attestation","sign_citation":"https://pith.science/pith/7DCH7JVMPSPWTEVV2NTVYW3R3B/action/citation_signature","submit_replication":"https://pith.science/pith/7DCH7JVMPSPWTEVV2NTVYW3R3B/action/replication_record"}},"created_at":"2026-07-05T02:49:06.991229+00:00","updated_at":"2026-07-05T02:49:06.991229+00:00"}