{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3WS6BVZKWWEEA24IKHT4M5SRJU","short_pith_number":"pith:3WS6BVZK","schema_version":"1.0","canonical_sha256":"dda5e0d72ab588406b8851e7c676514d0f81d9758b5323cbecf7144ac8ba640a","source":{"kind":"arxiv","id":"2302.00860","version":3},"attestation_state":"computed","paper":{"title":"Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Patrick Bl\\\"obaum, Patrick Chao, Sapan Patel, Shiva Prasad Kasiviswanathan","submitted_at":"2023-02-02T04:08:08Z","abstract_excerpt":"We consider the problem of answering observational, interventional, and counterfactual queries in a causally sufficient setting where only observational data and the causal graph are available. Utilizing the recent developments in diffusion models, we introduce diffusion-based causal models (DCM) to learn causal mechanisms, that generate unique latent encodings. These encodings enable us to directly sample under interventions and perform abduction for counterfactuals. Diffusion models are a natural fit here, since they can encode each node to a latent representation that acts as a proxy for ex"},"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":"2302.00860","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-02-02T04:08:08Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"2ee1b1f85809b2303d12184094accf96e65c0ae2b27c2e170fdc09c9cda47bb3","abstract_canon_sha256":"bdd54711c0c0d1c0b8825c606329dd7200fad228537c96900e7501bd03b4c5b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:18.308475Z","signature_b64":"XxAUhvFBjBrFT3oyx/twXOZNKvnUmYYXn6tNn29YPscpe1dwc+XPUXg5qogcQVq1nruuJIiNNyTo13mr+2hpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dda5e0d72ab588406b8851e7c676514d0f81d9758b5323cbecf7144ac8ba640a","last_reissued_at":"2026-07-05T09:18:18.307993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:18.307993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Patrick Bl\\\"obaum, Patrick Chao, Sapan Patel, Shiva Prasad Kasiviswanathan","submitted_at":"2023-02-02T04:08:08Z","abstract_excerpt":"We consider the problem of answering observational, interventional, and counterfactual queries in a causally sufficient setting where only observational data and the causal graph are available. Utilizing the recent developments in diffusion models, we introduce diffusion-based causal models (DCM) to learn causal mechanisms, that generate unique latent encodings. These encodings enable us to directly sample under interventions and perform abduction for counterfactuals. Diffusion models are a natural fit here, since they can encode each node to a latent representation that acts as a proxy for ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00860","kind":"arxiv","version":3},"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/2302.00860/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":"2302.00860","created_at":"2026-07-05T09:18:18.308053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00860v3","created_at":"2026-07-05T09:18:18.308053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00860","created_at":"2026-07-05T09:18:18.308053+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WS6BVZKWWEE","created_at":"2026-07-05T09:18:18.308053+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WS6BVZKWWEEA24I","created_at":"2026-07-05T09:18:18.308053+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WS6BVZK","created_at":"2026-07-05T09:18:18.308053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.14399","citing_title":"Factored Classifier-Free Guidance","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05890","citing_title":"RepFlow: Representation Enhanced Flow Matching for Causal Effect Estimation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WS6BVZKWWEEA24IKHT4M5SRJU","json":"https://pith.science/pith/3WS6BVZKWWEEA24IKHT4M5SRJU.json","graph_json":"https://pith.science/api/pith-number/3WS6BVZKWWEEA24IKHT4M5SRJU/graph.json","events_json":"https://pith.science/api/pith-number/3WS6BVZKWWEEA24IKHT4M5SRJU/events.json","paper":"https://pith.science/paper/3WS6BVZK"},"agent_actions":{"view_html":"https://pith.science/pith/3WS6BVZKWWEEA24IKHT4M5SRJU","download_json":"https://pith.science/pith/3WS6BVZKWWEEA24IKHT4M5SRJU.json","view_paper":"https://pith.science/paper/3WS6BVZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00860&json=true","fetch_graph":"https://pith.science/api/pith-number/3WS6BVZKWWEEA24IKHT4M5SRJU/graph.json","fetch_events":"https://pith.science/api/pith-number/3WS6BVZKWWEEA24IKHT4M5SRJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WS6BVZKWWEEA24IKHT4M5SRJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WS6BVZKWWEEA24IKHT4M5SRJU/action/storage_attestation","attest_author":"https://pith.science/pith/3WS6BVZKWWEEA24IKHT4M5SRJU/action/author_attestation","sign_citation":"https://pith.science/pith/3WS6BVZKWWEEA24IKHT4M5SRJU/action/citation_signature","submit_replication":"https://pith.science/pith/3WS6BVZKWWEEA24IKHT4M5SRJU/action/replication_record"}},"created_at":"2026-07-05T09:18:18.308053+00:00","updated_at":"2026-07-05T09:18:18.308053+00:00"}