{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KWVZR44LNT56FNIWZEE2FLRTSG","short_pith_number":"pith:KWVZR44L","schema_version":"1.0","canonical_sha256":"55ab98f38b6cfbe2b516c909a2ae3391800636017c969a078cd2e599c3d8e1d6","source":{"kind":"arxiv","id":"2102.10440","version":5},"attestation_state":"computed","paper":{"title":"Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Athresh Karanam, Devendra Singh Dhami, Kristian Kersting, Matej Ze\\v{c}evi\\'c, Sriraam Natarajan","submitted_at":"2021-02-20T20:48:47Z","abstract_excerpt":"While probabilistic models are an important tool for studying causality, doing so suffers from the intractability of inference. As a step towards tractable causal models, we consider the problem of learning interventional distributions using sum-product networks (SPNs) that are over-parameterized by gate functions, e.g., neural networks. Providing an arbitrarily intervened causal graph as input, effectively subsuming Pearl's do-operator, the gate function predicts the parameters of the SPN. The resulting interventional SPNs are motivated and illustrated by a structural causal model themed arou"},"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":"2102.10440","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T20:48:47Z","cross_cats_sorted":[],"title_canon_sha256":"bddde843b547f8567054d2272451602380c9eacc81c751298882a585f79ec419","abstract_canon_sha256":"6b011effdabfbb053f90281f542114f483ac0a90a2f86a9e3343efb26da39a54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:12.399457Z","signature_b64":"GzXknN/mc2OJ1uSpZGs5+eWoI8L4pC+v5/osSVgOPTEY8q3NimADCowNgenNCJfyjs8MykREl5vm4gEaUafVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55ab98f38b6cfbe2b516c909a2ae3391800636017c969a078cd2e599c3d8e1d6","last_reissued_at":"2026-07-05T03:25:12.399023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:12.399023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Athresh Karanam, Devendra Singh Dhami, Kristian Kersting, Matej Ze\\v{c}evi\\'c, Sriraam Natarajan","submitted_at":"2021-02-20T20:48:47Z","abstract_excerpt":"While probabilistic models are an important tool for studying causality, doing so suffers from the intractability of inference. As a step towards tractable causal models, we consider the problem of learning interventional distributions using sum-product networks (SPNs) that are over-parameterized by gate functions, e.g., neural networks. Providing an arbitrarily intervened causal graph as input, effectively subsuming Pearl's do-operator, the gate function predicts the parameters of the SPN. The resulting interventional SPNs are motivated and illustrated by a structural causal model themed arou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10440","kind":"arxiv","version":5},"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/2102.10440/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":"2102.10440","created_at":"2026-07-05T03:25:12.399086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.10440v5","created_at":"2026-07-05T03:25:12.399086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10440","created_at":"2026-07-05T03:25:12.399086+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWVZR44LNT56","created_at":"2026-07-05T03:25:12.399086+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWVZR44LNT56FNIW","created_at":"2026-07-05T03:25:12.399086+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWVZR44L","created_at":"2026-07-05T03:25:12.399086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWVZR44LNT56FNIWZEE2FLRTSG","json":"https://pith.science/pith/KWVZR44LNT56FNIWZEE2FLRTSG.json","graph_json":"https://pith.science/api/pith-number/KWVZR44LNT56FNIWZEE2FLRTSG/graph.json","events_json":"https://pith.science/api/pith-number/KWVZR44LNT56FNIWZEE2FLRTSG/events.json","paper":"https://pith.science/paper/KWVZR44L"},"agent_actions":{"view_html":"https://pith.science/pith/KWVZR44LNT56FNIWZEE2FLRTSG","download_json":"https://pith.science/pith/KWVZR44LNT56FNIWZEE2FLRTSG.json","view_paper":"https://pith.science/paper/KWVZR44L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.10440&json=true","fetch_graph":"https://pith.science/api/pith-number/KWVZR44LNT56FNIWZEE2FLRTSG/graph.json","fetch_events":"https://pith.science/api/pith-number/KWVZR44LNT56FNIWZEE2FLRTSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWVZR44LNT56FNIWZEE2FLRTSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWVZR44LNT56FNIWZEE2FLRTSG/action/storage_attestation","attest_author":"https://pith.science/pith/KWVZR44LNT56FNIWZEE2FLRTSG/action/author_attestation","sign_citation":"https://pith.science/pith/KWVZR44LNT56FNIWZEE2FLRTSG/action/citation_signature","submit_replication":"https://pith.science/pith/KWVZR44LNT56FNIWZEE2FLRTSG/action/replication_record"}},"created_at":"2026-07-05T03:25:12.399086+00:00","updated_at":"2026-07-05T03:25:12.399086+00:00"}