{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SY47AXNLNB4DZV2SLZPKYLUNVF","short_pith_number":"pith:SY47AXNL","schema_version":"1.0","canonical_sha256":"9639f05dab68783cd7525e5eac2e8da95c319768438242c488ebcf65b447e31a","source":{"kind":"arxiv","id":"2007.10507","version":2},"attestation_state":"computed","paper":{"title":"Moment-Matching Graph-Networks for Causal Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael Park","submitted_at":"2020-07-20T22:07:43Z","abstract_excerpt":"In this note we explore a fully unsupervised deep-learning framework for simulating non-linear structural equation models from observational training data. The main contribution of this note is an architecture for applying moment-matching loss functions to the edges of a causal Bayesian graph, resulting in a generative conditional-moment-matching graph-neural-network. This framework thus enables automated sampling of latent space conditional probability distributions for various graphical interventions, and is capable of generating out-of-sample interventional probabilities that are often fait"},"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":"2007.10507","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-20T22:07:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4443a9b9af85f0eba4d5ad44b17ab9aef0dec26989f0a27f597bf1f50dc33b82","abstract_canon_sha256":"64611d949d729b56bdddf86f6eae85fd72175630c9982e6dbb4ed35e0f8c74d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:20.530182Z","signature_b64":"Q+iISiStaduBNBqJRWMT7d932fBlclwUHDTzhlL3+V+imqHladq8UWkqfumaqMVOMIeayh4ncCtrT1Lmrp3tAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9639f05dab68783cd7525e5eac2e8da95c319768438242c488ebcf65b447e31a","last_reissued_at":"2026-07-05T01:22:20.529713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:20.529713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moment-Matching Graph-Networks for Causal Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael Park","submitted_at":"2020-07-20T22:07:43Z","abstract_excerpt":"In this note we explore a fully unsupervised deep-learning framework for simulating non-linear structural equation models from observational training data. The main contribution of this note is an architecture for applying moment-matching loss functions to the edges of a causal Bayesian graph, resulting in a generative conditional-moment-matching graph-neural-network. This framework thus enables automated sampling of latent space conditional probability distributions for various graphical interventions, and is capable of generating out-of-sample interventional probabilities that are often fait"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.10507","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/2007.10507/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":"2007.10507","created_at":"2026-07-05T01:22:20.529788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.10507v2","created_at":"2026-07-05T01:22:20.529788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.10507","created_at":"2026-07-05T01:22:20.529788+00:00"},{"alias_kind":"pith_short_12","alias_value":"SY47AXNLNB4D","created_at":"2026-07-05T01:22:20.529788+00:00"},{"alias_kind":"pith_short_16","alias_value":"SY47AXNLNB4DZV2S","created_at":"2026-07-05T01:22:20.529788+00:00"},{"alias_kind":"pith_short_8","alias_value":"SY47AXNL","created_at":"2026-07-05T01:22:20.529788+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/SY47AXNLNB4DZV2SLZPKYLUNVF","json":"https://pith.science/pith/SY47AXNLNB4DZV2SLZPKYLUNVF.json","graph_json":"https://pith.science/api/pith-number/SY47AXNLNB4DZV2SLZPKYLUNVF/graph.json","events_json":"https://pith.science/api/pith-number/SY47AXNLNB4DZV2SLZPKYLUNVF/events.json","paper":"https://pith.science/paper/SY47AXNL"},"agent_actions":{"view_html":"https://pith.science/pith/SY47AXNLNB4DZV2SLZPKYLUNVF","download_json":"https://pith.science/pith/SY47AXNLNB4DZV2SLZPKYLUNVF.json","view_paper":"https://pith.science/paper/SY47AXNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.10507&json=true","fetch_graph":"https://pith.science/api/pith-number/SY47AXNLNB4DZV2SLZPKYLUNVF/graph.json","fetch_events":"https://pith.science/api/pith-number/SY47AXNLNB4DZV2SLZPKYLUNVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SY47AXNLNB4DZV2SLZPKYLUNVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SY47AXNLNB4DZV2SLZPKYLUNVF/action/storage_attestation","attest_author":"https://pith.science/pith/SY47AXNLNB4DZV2SLZPKYLUNVF/action/author_attestation","sign_citation":"https://pith.science/pith/SY47AXNLNB4DZV2SLZPKYLUNVF/action/citation_signature","submit_replication":"https://pith.science/pith/SY47AXNLNB4DZV2SLZPKYLUNVF/action/replication_record"}},"created_at":"2026-07-05T01:22:20.529788+00:00","updated_at":"2026-07-05T01:22:20.529788+00:00"}