{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:QUEIDXFVK2C5ONKH6OZS2PEFNW","short_pith_number":"pith:QUEIDXFV","canonical_record":{"source":{"id":"1603.06170","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-20T00:55:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"020f372a4da0b6ca0d1315565c3eb54a8e91cd953b80cfe49c0d3f7dd126727d","abstract_canon_sha256":"b7253b5b859d4a0067f286fd3abd58e36cb48406ab2d9e20cb14318fa881fc17"},"schema_version":"1.0"},"canonical_sha256":"850881dcb55685d73547f3b32d3c856d97a06851582e1f9077e4e4aeeb256040","source":{"kind":"arxiv","id":"1603.06170","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.06170","created_at":"2026-05-18T00:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"1603.06170v2","created_at":"2026-05-18T00:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.06170","created_at":"2026-05-18T00:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"QUEIDXFVK2C5","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QUEIDXFVK2C5ONKH","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QUEIDXFV","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:QUEIDXFVK2C5ONKH6OZS2PEFNW","target":"record","payload":{"canonical_record":{"source":{"id":"1603.06170","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-20T00:55:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"020f372a4da0b6ca0d1315565c3eb54a8e91cd953b80cfe49c0d3f7dd126727d","abstract_canon_sha256":"b7253b5b859d4a0067f286fd3abd58e36cb48406ab2d9e20cb14318fa881fc17"},"schema_version":"1.0"},"canonical_sha256":"850881dcb55685d73547f3b32d3c856d97a06851582e1f9077e4e4aeeb256040","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:34.352087Z","signature_b64":"qYCfI1/KlCzlJwSYnYSmBLW/htRa7lECeXqQ0W510/6BApjx+tHsF3SVL22BK8vjvmPsuGdWXgfp1BGrQ9dwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"850881dcb55685d73547f3b32d3c856d97a06851582e1f9077e4e4aeeb256040","last_reissued_at":"2026-05-18T00:04:34.351256Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:34.351256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.06170","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":"2026-05-18T00:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j3jDYfL1Xhq5yHcwm8o00PJfH/+9zFKGD1y1YNVUGGEmKyaEJ2ylsUudG0C7h5+hSVQlBT0OL5BgLM5d6tEwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T22:47:40.562376Z"},"content_sha256":"4fe94376cf6d6038f142406aa89903b3dbb1d0b27458378d81857c462bfd5e95","schema_version":"1.0","event_id":"sha256:4fe94376cf6d6038f142406aa89903b3dbb1d0b27458378d81857c462bfd5e95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:QUEIDXFVK2C5ONKH6OZS2PEFNW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Stochastic Approximation learning of Helmholtz Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haotian Xu, Zhijian Ou","submitted_at":"2016-03-20T00:55:06Z","abstract_excerpt":"Though with progress, model learning and performing posterior inference still remains a common challenge for using deep generative models, especially for handling discrete hidden variables. This paper is mainly concerned with algorithms for learning Helmholz machines, which is characterized by pairing the generative model with an auxiliary inference model. A common drawback of previous learning algorithms is that they indirectly optimize some bounds of the targeted marginal log-likelihood. In contrast, we successfully develop a new class of algorithms, based on stochastic approximation (SA) th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.06170","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":"2026-05-18T00:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xpaXyppcoKIreXLARuAPxUvyrFFNWp4qeRsNijLEKYEAIt55IjVMaLJjoVCsCMS/m79YlMyvuuHJev6kce4ADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T22:47:40.562983Z"},"content_sha256":"7fa8def67547cfb38fb84152e9b41872151e4883a8e807e2a20897acc297e653","schema_version":"1.0","event_id":"sha256:7fa8def67547cfb38fb84152e9b41872151e4883a8e807e2a20897acc297e653"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUEIDXFVK2C5ONKH6OZS2PEFNW/bundle.json","state_url":"https://pith.science/pith/QUEIDXFVK2C5ONKH6OZS2PEFNW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUEIDXFVK2C5ONKH6OZS2PEFNW/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":"2026-05-30T22:47:40Z","links":{"resolver":"https://pith.science/pith/QUEIDXFVK2C5ONKH6OZS2PEFNW","bundle":"https://pith.science/pith/QUEIDXFVK2C5ONKH6OZS2PEFNW/bundle.json","state":"https://pith.science/pith/QUEIDXFVK2C5ONKH6OZS2PEFNW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUEIDXFVK2C5ONKH6OZS2PEFNW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QUEIDXFVK2C5ONKH6OZS2PEFNW","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":"b7253b5b859d4a0067f286fd3abd58e36cb48406ab2d9e20cb14318fa881fc17","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-20T00:55:06Z","title_canon_sha256":"020f372a4da0b6ca0d1315565c3eb54a8e91cd953b80cfe49c0d3f7dd126727d"},"schema_version":"1.0","source":{"id":"1603.06170","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.06170","created_at":"2026-05-18T00:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"1603.06170v2","created_at":"2026-05-18T00:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.06170","created_at":"2026-05-18T00:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"QUEIDXFVK2C5","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QUEIDXFVK2C5ONKH","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QUEIDXFV","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:7fa8def67547cfb38fb84152e9b41872151e4883a8e807e2a20897acc297e653","target":"graph","created_at":"2026-05-18T00:04:34Z","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":"Though with progress, model learning and performing posterior inference still remains a common challenge for using deep generative models, especially for handling discrete hidden variables. This paper is mainly concerned with algorithms for learning Helmholz machines, which is characterized by pairing the generative model with an auxiliary inference model. A common drawback of previous learning algorithms is that they indirectly optimize some bounds of the targeted marginal log-likelihood. In contrast, we successfully develop a new class of algorithms, based on stochastic approximation (SA) th","authors_text":"Haotian Xu, Zhijian Ou","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-20T00:55:06Z","title":"Joint Stochastic Approximation learning of Helmholtz Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.06170","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":"sha256:4fe94376cf6d6038f142406aa89903b3dbb1d0b27458378d81857c462bfd5e95","target":"record","created_at":"2026-05-18T00:04:34Z","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":"b7253b5b859d4a0067f286fd3abd58e36cb48406ab2d9e20cb14318fa881fc17","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-20T00:55:06Z","title_canon_sha256":"020f372a4da0b6ca0d1315565c3eb54a8e91cd953b80cfe49c0d3f7dd126727d"},"schema_version":"1.0","source":{"id":"1603.06170","kind":"arxiv","version":2}},"canonical_sha256":"850881dcb55685d73547f3b32d3c856d97a06851582e1f9077e4e4aeeb256040","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"850881dcb55685d73547f3b32d3c856d97a06851582e1f9077e4e4aeeb256040","first_computed_at":"2026-05-18T00:04:34.351256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:34.351256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qYCfI1/KlCzlJwSYnYSmBLW/htRa7lECeXqQ0W510/6BApjx+tHsF3SVL22BK8vjvmPsuGdWXgfp1BGrQ9dwBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:34.352087Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.06170","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fe94376cf6d6038f142406aa89903b3dbb1d0b27458378d81857c462bfd5e95","sha256:7fa8def67547cfb38fb84152e9b41872151e4883a8e807e2a20897acc297e653"],"state_sha256":"f0465076d40acd536835c3fcdc28bb7935429683a536131a15106d3628c19201"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GQZIDEarT619VMoHWIzEKM6NzUPnaC5f9h92pp28ACMcdAR6XUa6vAg8wic1XOjxweQEETpLfpCn6wtcoKwpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T22:47:40.566106Z","bundle_sha256":"d71488de17e5473634f2a9f1cfb06ba07e9effc8f06498e6b6563fe72f7245b3"}}