{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:KTLMDS5Q77HNF42S277Z3Q3CA5","short_pith_number":"pith:KTLMDS5Q","canonical_record":{"source":{"id":"1402.0030","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-31T23:33:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5f12837bc820af5b4804566827d84e277be0f787318171a6c9c6e9fda8070c16","abstract_canon_sha256":"a62bb5b20335207cea18e379ca1dad5f78be0919c9a4673c755df482c8540295"},"schema_version":"1.0"},"canonical_sha256":"54d6c1cbb0ffced2f352d7ff9dc362077377694b672fbd83a1bf7ccf358fc2bc","source":{"kind":"arxiv","id":"1402.0030","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.0030","created_at":"2026-05-18T01:13:00Z"},{"alias_kind":"arxiv_version","alias_value":"1402.0030v2","created_at":"2026-05-18T01:13:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.0030","created_at":"2026-05-18T01:13:00Z"},{"alias_kind":"pith_short_12","alias_value":"KTLMDS5Q77HN","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"KTLMDS5Q77HNF42S","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"KTLMDS5Q","created_at":"2026-05-18T12:28:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:KTLMDS5Q77HNF42S277Z3Q3CA5","target":"record","payload":{"canonical_record":{"source":{"id":"1402.0030","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-31T23:33:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5f12837bc820af5b4804566827d84e277be0f787318171a6c9c6e9fda8070c16","abstract_canon_sha256":"a62bb5b20335207cea18e379ca1dad5f78be0919c9a4673c755df482c8540295"},"schema_version":"1.0"},"canonical_sha256":"54d6c1cbb0ffced2f352d7ff9dc362077377694b672fbd83a1bf7ccf358fc2bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:00.441586Z","signature_b64":"9lJxZSwo7dN1xVSss8SMFClkZHTfrAVJVQX7z0t2Ilpw9vTRwvbvphEdRQuyxAvypIvVyfQlH2LB0gddIjyVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d6c1cbb0ffced2f352d7ff9dc362077377694b672fbd83a1bf7ccf358fc2bc","last_reissued_at":"2026-05-18T01:13:00.441239Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:00.441239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1402.0030","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:13:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nqty+WYtsSmzOYAy3CfxCNsqAQn1svtHP8CKALG3ZkabDUPu8DSPXQd+IYqzByMfwEjSx0388Dsg9Zas947jDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:36:58.974170Z"},"content_sha256":"a0af3df3f5bda5504fd84692de61cf534e80221954b01c64103aab9f78169411","schema_version":"1.0","event_id":"sha256:a0af3df3f5bda5504fd84692de61cf534e80221954b01c64103aab9f78169411"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:KTLMDS5Q77HNF42S277Z3Q3CA5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Variational Inference and Learning in Belief Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andriy Mnih, Karol Gregor","submitted_at":"2014-01-31T23:33:21Z","abstract_excerpt":"Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied to them scale well. We propose a fast non-iterative approximate inference method that uses a feedforward network to implement efficient exact sampling from the variational posterior. The model and this inference network are trained jointly by maximizing a variational lower bound on the log-likelihood. Although the naive estimator of the inference model grad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.0030","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":""},"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":"2026-05-18T01:13:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v3W3ftpffv34a3n5fxu9CaWWTu4dFRwRcMTVMwlCRgjEPcYA+UtOPrkBdU/eGHyY9mHUTKxMl4oExIHPloSaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:36:58.974799Z"},"content_sha256":"baa7f8d2859b1f8ff1258c8f4cede085295eb13b89789bd5baa3dd51bd8857e9","schema_version":"1.0","event_id":"sha256:baa7f8d2859b1f8ff1258c8f4cede085295eb13b89789bd5baa3dd51bd8857e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTLMDS5Q77HNF42S277Z3Q3CA5/bundle.json","state_url":"https://pith.science/pith/KTLMDS5Q77HNF42S277Z3Q3CA5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTLMDS5Q77HNF42S277Z3Q3CA5/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":"2026-08-03T17:36:58Z","links":{"resolver":"https://pith.science/pith/KTLMDS5Q77HNF42S277Z3Q3CA5","bundle":"https://pith.science/pith/KTLMDS5Q77HNF42S277Z3Q3CA5/bundle.json","state":"https://pith.science/pith/KTLMDS5Q77HNF42S277Z3Q3CA5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTLMDS5Q77HNF42S277Z3Q3CA5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:KTLMDS5Q77HNF42S277Z3Q3CA5","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":"a62bb5b20335207cea18e379ca1dad5f78be0919c9a4673c755df482c8540295","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-31T23:33:21Z","title_canon_sha256":"5f12837bc820af5b4804566827d84e277be0f787318171a6c9c6e9fda8070c16"},"schema_version":"1.0","source":{"id":"1402.0030","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.0030","created_at":"2026-05-18T01:13:00Z"},{"alias_kind":"arxiv_version","alias_value":"1402.0030v2","created_at":"2026-05-18T01:13:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.0030","created_at":"2026-05-18T01:13:00Z"},{"alias_kind":"pith_short_12","alias_value":"KTLMDS5Q77HN","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"KTLMDS5Q77HNF42S","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"KTLMDS5Q","created_at":"2026-05-18T12:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:baa7f8d2859b1f8ff1258c8f4cede085295eb13b89789bd5baa3dd51bd8857e9","target":"graph","created_at":"2026-05-18T01:13:00Z","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":"Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied to them scale well. We propose a fast non-iterative approximate inference method that uses a feedforward network to implement efficient exact sampling from the variational posterior. The model and this inference network are trained jointly by maximizing a variational lower bound on the log-likelihood. Although the naive estimator of the inference model grad","authors_text":"Andriy Mnih, Karol Gregor","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-31T23:33:21Z","title":"Neural Variational Inference and Learning in Belief Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.0030","kind":"arxiv","version":2},"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:a0af3df3f5bda5504fd84692de61cf534e80221954b01c64103aab9f78169411","target":"record","created_at":"2026-05-18T01:13:00Z","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":"a62bb5b20335207cea18e379ca1dad5f78be0919c9a4673c755df482c8540295","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-01-31T23:33:21Z","title_canon_sha256":"5f12837bc820af5b4804566827d84e277be0f787318171a6c9c6e9fda8070c16"},"schema_version":"1.0","source":{"id":"1402.0030","kind":"arxiv","version":2}},"canonical_sha256":"54d6c1cbb0ffced2f352d7ff9dc362077377694b672fbd83a1bf7ccf358fc2bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54d6c1cbb0ffced2f352d7ff9dc362077377694b672fbd83a1bf7ccf358fc2bc","first_computed_at":"2026-05-18T01:13:00.441239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:00.441239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9lJxZSwo7dN1xVSss8SMFClkZHTfrAVJVQX7z0t2Ilpw9vTRwvbvphEdRQuyxAvypIvVyfQlH2LB0gddIjyVCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:00.441586Z","signed_message":"canonical_sha256_bytes"},"source_id":"1402.0030","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0af3df3f5bda5504fd84692de61cf534e80221954b01c64103aab9f78169411","sha256:baa7f8d2859b1f8ff1258c8f4cede085295eb13b89789bd5baa3dd51bd8857e9"],"state_sha256":"a3f86b70b3baf9f29547468b3a5655434eb9f00ff2881b18b69f5c7146394f27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/iTQu/EBxLE3XGRS3d0ezH3Dov2LuIxabf1mJ6gRDAgvuh1iNzSUIdm85W6OSzJzGTSxEXnERfWKf93KR00HCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:36:58.980214Z","bundle_sha256":"3e161d67fd727c5d4fe4e2f44574dd603d72314779c71d8236599e70bfbb33b8"}}