{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:B2Z6IVEKCTF6EUVEW2O53H6LXX","short_pith_number":"pith:B2Z6IVEK","canonical_record":{"source":{"id":"1711.00695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T11:40:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6e6d233dd6ce6a07ef4c335c8898779185e122157ade8700a63bcccd7b489c95","abstract_canon_sha256":"f85ca244cb967b5fcbe4b08e3dfb05ed52d254fe33fbd687f8d65c7e613bbfeb"},"schema_version":"1.0"},"canonical_sha256":"0eb3e4548a14cbe252a4b69ddd9fcbbdd6442d6c873285f0bafb19107e8a45a5","source":{"kind":"arxiv","id":"1711.00695","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00695","created_at":"2026-05-18T00:31:29Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00695v1","created_at":"2026-05-18T00:31:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00695","created_at":"2026-05-18T00:31:29Z"},{"alias_kind":"pith_short_12","alias_value":"B2Z6IVEKCTF6","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"B2Z6IVEKCTF6EUVE","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"B2Z6IVEK","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:B2Z6IVEKCTF6EUVEW2O53H6LXX","target":"record","payload":{"canonical_record":{"source":{"id":"1711.00695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T11:40:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6e6d233dd6ce6a07ef4c335c8898779185e122157ade8700a63bcccd7b489c95","abstract_canon_sha256":"f85ca244cb967b5fcbe4b08e3dfb05ed52d254fe33fbd687f8d65c7e613bbfeb"},"schema_version":"1.0"},"canonical_sha256":"0eb3e4548a14cbe252a4b69ddd9fcbbdd6442d6c873285f0bafb19107e8a45a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:29.779967Z","signature_b64":"GuiUR7b2fVk3i8vSqEKdVLRNrJDl0vlZue8QkSp0FAyfyiqcrXyWp59UP44tbA04ZQEuaM2wnD6IEjgl6W2WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eb3e4548a14cbe252a4b69ddd9fcbbdd6442d6c873285f0bafb19107e8a45a5","last_reissued_at":"2026-05-18T00:31:29.779390Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:29.779390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.00695","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b5kcixxrqoN7RNZpRHYxbO+/qBlqmQ5PX9J3mrMorqtMDXSqWVJVG69OgiEO1FS/UQtTAtf1Y2SJKcgdDw4PCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:33:22.411095Z"},"content_sha256":"a318a965826f901518e2f5eeab54a31edcaa17595a9a393ef042079b4e2e663b","schema_version":"1.0","event_id":"sha256:a318a965826f901518e2f5eeab54a31edcaa17595a9a393ef042079b4e2e663b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:B2Z6IVEKCTF6EUVEW2O53H6LXX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Universal Marginalizer for Amortized Inference in Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Baker, Chris Hart, Chris Lucas, Iliyan Zarov, Konstantinos Gourgoulias, Laura Douglas, Maneesh Sahani, Saurabh Johri, Yura Perov","submitted_at":"2017-11-02T11:40:09Z","abstract_excerpt":"We consider the problem of inference in a causal generative model where the set of available observations differs between data instances. We show how combining samples drawn from the graphical model with an appropriate masking function makes it possible to train a single neural network to approximate all the corresponding conditional marginal distributions and thus amortize the cost of inference. We further demonstrate that the efficiency of importance sampling may be improved by basing proposals on the output of the neural network. We also outline how the same network can be used to generate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00695","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kte+iXBZ6Pg0L6XZl/+DMoEns6+eLMPdudvnEjfJQ6KHG19Xwf3JuH2OHBrMYEJxkFWXfzZJ53I/NMjuh1enBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T15:33:22.411752Z"},"content_sha256":"f5fb2dfd9f2f1aae383a256046d87bf3186c022e7977bb60e56cf6b9528b4273","schema_version":"1.0","event_id":"sha256:f5fb2dfd9f2f1aae383a256046d87bf3186c022e7977bb60e56cf6b9528b4273"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B2Z6IVEKCTF6EUVEW2O53H6LXX/bundle.json","state_url":"https://pith.science/pith/B2Z6IVEKCTF6EUVEW2O53H6LXX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B2Z6IVEKCTF6EUVEW2O53H6LXX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T15:33:22Z","links":{"resolver":"https://pith.science/pith/B2Z6IVEKCTF6EUVEW2O53H6LXX","bundle":"https://pith.science/pith/B2Z6IVEKCTF6EUVEW2O53H6LXX/bundle.json","state":"https://pith.science/pith/B2Z6IVEKCTF6EUVEW2O53H6LXX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B2Z6IVEKCTF6EUVEW2O53H6LXX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:B2Z6IVEKCTF6EUVEW2O53H6LXX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f85ca244cb967b5fcbe4b08e3dfb05ed52d254fe33fbd687f8d65c7e613bbfeb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T11:40:09Z","title_canon_sha256":"6e6d233dd6ce6a07ef4c335c8898779185e122157ade8700a63bcccd7b489c95"},"schema_version":"1.0","source":{"id":"1711.00695","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00695","created_at":"2026-05-18T00:31:29Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00695v1","created_at":"2026-05-18T00:31:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00695","created_at":"2026-05-18T00:31:29Z"},{"alias_kind":"pith_short_12","alias_value":"B2Z6IVEKCTF6","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"B2Z6IVEKCTF6EUVE","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"B2Z6IVEK","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:f5fb2dfd9f2f1aae383a256046d87bf3186c022e7977bb60e56cf6b9528b4273","target":"graph","created_at":"2026-05-18T00:31:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We consider the problem of inference in a causal generative model where the set of available observations differs between data instances. We show how combining samples drawn from the graphical model with an appropriate masking function makes it possible to train a single neural network to approximate all the corresponding conditional marginal distributions and thus amortize the cost of inference. We further demonstrate that the efficiency of importance sampling may be improved by basing proposals on the output of the neural network. We also outline how the same network can be used to generate ","authors_text":"Adam Baker, Chris Hart, Chris Lucas, Iliyan Zarov, Konstantinos Gourgoulias, Laura Douglas, Maneesh Sahani, Saurabh Johri, Yura Perov","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T11:40:09Z","title":"A Universal Marginalizer for Amortized Inference in Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00695","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a318a965826f901518e2f5eeab54a31edcaa17595a9a393ef042079b4e2e663b","target":"record","created_at":"2026-05-18T00:31:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f85ca244cb967b5fcbe4b08e3dfb05ed52d254fe33fbd687f8d65c7e613bbfeb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T11:40:09Z","title_canon_sha256":"6e6d233dd6ce6a07ef4c335c8898779185e122157ade8700a63bcccd7b489c95"},"schema_version":"1.0","source":{"id":"1711.00695","kind":"arxiv","version":1}},"canonical_sha256":"0eb3e4548a14cbe252a4b69ddd9fcbbdd6442d6c873285f0bafb19107e8a45a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0eb3e4548a14cbe252a4b69ddd9fcbbdd6442d6c873285f0bafb19107e8a45a5","first_computed_at":"2026-05-18T00:31:29.779390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:29.779390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GuiUR7b2fVk3i8vSqEKdVLRNrJDl0vlZue8QkSp0FAyfyiqcrXyWp59UP44tbA04ZQEuaM2wnD6IEjgl6W2WBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:29.779967Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.00695","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a318a965826f901518e2f5eeab54a31edcaa17595a9a393ef042079b4e2e663b","sha256:f5fb2dfd9f2f1aae383a256046d87bf3186c022e7977bb60e56cf6b9528b4273"],"state_sha256":"491034f789b897dd332ea13f66f6b9d5baf3184a467dd38851a506923169469d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AzemS4aHXhKPM0S7iVMrcOeo1WvE87qYaTzRrtetjoo9eq3U5mI4zQr5VrV2QlW5jRRI+r3uD8oDdCjMHspJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T15:33:22.414714Z","bundle_sha256":"4b3fef514ab56124e8d56478be97895e7a6a5afd60acd6b399005ef917d29423"}}