{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:NQ2I7QLKVANVHYYGCKJCSBN7AS","short_pith_number":"pith:NQ2I7QLK","canonical_record":{"source":{"id":"1612.04739","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-08T11:17:16Z","cross_cats_sorted":[],"title_canon_sha256":"38ff2d69a9d6bb7057145f5f343e9f0003cb20a2269ba705df3d63c78475f234","abstract_canon_sha256":"40c0c9ecad191aace30a32ef8725b715d6a88ade331de7d7e11df3d61a200de4"},"schema_version":"1.0"},"canonical_sha256":"6c348fc16aa81b53e30612922905bf0496d00270ac5888f931917427cd118649","source":{"kind":"arxiv","id":"1612.04739","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.04739","created_at":"2026-05-18T00:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"1612.04739v1","created_at":"2026-05-18T00:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.04739","created_at":"2026-05-18T00:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"NQ2I7QLKVANV","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"NQ2I7QLKVANVHYYG","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"NQ2I7QLK","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:NQ2I7QLKVANVHYYGCKJCSBN7AS","target":"record","payload":{"canonical_record":{"source":{"id":"1612.04739","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-08T11:17:16Z","cross_cats_sorted":[],"title_canon_sha256":"38ff2d69a9d6bb7057145f5f343e9f0003cb20a2269ba705df3d63c78475f234","abstract_canon_sha256":"40c0c9ecad191aace30a32ef8725b715d6a88ade331de7d7e11df3d61a200de4"},"schema_version":"1.0"},"canonical_sha256":"6c348fc16aa81b53e30612922905bf0496d00270ac5888f931917427cd118649","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:58.705439Z","signature_b64":"/YMweQrOTJ/u9g4p83IgJ54T9U0fb4WEl5+hellMJq6T/Wmx13YDDifPquv9EtMC0KQPQB4vsji8XvvdduyZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c348fc16aa81b53e30612922905bf0496d00270ac5888f931917427cd118649","last_reissued_at":"2026-05-18T00:54:58.704771Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:58.704771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.04739","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":"2026-05-18T00:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+DcccFafVBmMavKb1maSSNBImKrdc2wmV84ez8dEqqDlAp43scsPAtiHVo+PIMk2qDEMx7lbP1x5PJ+j1YHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T06:39:28.769355Z"},"content_sha256":"b030d01e80ec7d4939584013abfaad6aa34fae530cf18c955f9d9721dafb21b3","schema_version":"1.0","event_id":"sha256:b030d01e80ec7d4939584013abfaad6aa34fae530cf18c955f9d9721dafb21b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:NQ2I7QLKVANVHYYGCKJCSBN7AS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Architecture for Deep, Hierarchical Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Philip Bachman","submitted_at":"2016-12-08T11:17:16Z","abstract_excerpt":"We present an architecture which lets us train deep, directed generative models with many layers of latent variables. We include deterministic paths between all latent variables and the generated output, and provide a richer set of connections between computations for inference and generation, which enables more effective communication of information throughout the model during training. To improve performance on natural images, we incorporate a lightweight autoregressive model in the reconstruction distribution. These techniques permit end-to-end training of models with 10+ layers of latent v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.04739","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":"2026-05-18T00:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dCOcAefIhDLHQmzTjDLbPcErxwrHPxMDphtC3dEjjybxCMj4DFlQfT1nObndiwj0gAiGSO1jQSpsZrjVbYEABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T06:39:28.769772Z"},"content_sha256":"34ff75f20f1b5812b355b4bdb4f5956f7250530bd04d4febaaf90fca9fac013f","schema_version":"1.0","event_id":"sha256:34ff75f20f1b5812b355b4bdb4f5956f7250530bd04d4febaaf90fca9fac013f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NQ2I7QLKVANVHYYGCKJCSBN7AS/bundle.json","state_url":"https://pith.science/pith/NQ2I7QLKVANVHYYGCKJCSBN7AS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NQ2I7QLKVANVHYYGCKJCSBN7AS/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":"2026-05-25T06:39:28Z","links":{"resolver":"https://pith.science/pith/NQ2I7QLKVANVHYYGCKJCSBN7AS","bundle":"https://pith.science/pith/NQ2I7QLKVANVHYYGCKJCSBN7AS/bundle.json","state":"https://pith.science/pith/NQ2I7QLKVANVHYYGCKJCSBN7AS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NQ2I7QLKVANVHYYGCKJCSBN7AS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:NQ2I7QLKVANVHYYGCKJCSBN7AS","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":"40c0c9ecad191aace30a32ef8725b715d6a88ade331de7d7e11df3d61a200de4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-08T11:17:16Z","title_canon_sha256":"38ff2d69a9d6bb7057145f5f343e9f0003cb20a2269ba705df3d63c78475f234"},"schema_version":"1.0","source":{"id":"1612.04739","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.04739","created_at":"2026-05-18T00:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"1612.04739v1","created_at":"2026-05-18T00:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.04739","created_at":"2026-05-18T00:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"NQ2I7QLKVANV","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"NQ2I7QLKVANVHYYG","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"NQ2I7QLK","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:34ff75f20f1b5812b355b4bdb4f5956f7250530bd04d4febaaf90fca9fac013f","target":"graph","created_at":"2026-05-18T00:54:58Z","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 present an architecture which lets us train deep, directed generative models with many layers of latent variables. We include deterministic paths between all latent variables and the generated output, and provide a richer set of connections between computations for inference and generation, which enables more effective communication of information throughout the model during training. To improve performance on natural images, we incorporate a lightweight autoregressive model in the reconstruction distribution. These techniques permit end-to-end training of models with 10+ layers of latent v","authors_text":"Philip Bachman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-08T11:17:16Z","title":"An Architecture for Deep, Hierarchical Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.04739","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:b030d01e80ec7d4939584013abfaad6aa34fae530cf18c955f9d9721dafb21b3","target":"record","created_at":"2026-05-18T00:54:58Z","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":"40c0c9ecad191aace30a32ef8725b715d6a88ade331de7d7e11df3d61a200de4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-08T11:17:16Z","title_canon_sha256":"38ff2d69a9d6bb7057145f5f343e9f0003cb20a2269ba705df3d63c78475f234"},"schema_version":"1.0","source":{"id":"1612.04739","kind":"arxiv","version":1}},"canonical_sha256":"6c348fc16aa81b53e30612922905bf0496d00270ac5888f931917427cd118649","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c348fc16aa81b53e30612922905bf0496d00270ac5888f931917427cd118649","first_computed_at":"2026-05-18T00:54:58.704771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:54:58.704771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/YMweQrOTJ/u9g4p83IgJ54T9U0fb4WEl5+hellMJq6T/Wmx13YDDifPquv9EtMC0KQPQB4vsji8XvvdduyZBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:54:58.705439Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.04739","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b030d01e80ec7d4939584013abfaad6aa34fae530cf18c955f9d9721dafb21b3","sha256:34ff75f20f1b5812b355b4bdb4f5956f7250530bd04d4febaaf90fca9fac013f"],"state_sha256":"51904b844833d04fec86f8a0bf3331c34a83aacbc89c86d92426b7cb549a26cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gj8zrvWzT27IRbgwoCOY1YHSnZIyh5lojBTEhvGliiVYgvCRuoZFyzTItnYWPpTCLdNi3XvpqYpz+xrzz9j6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T06:39:28.772332Z","bundle_sha256":"2b00101aed16dd750ace22bb55f9fdd87ff130e2a69d8817ed810a9e29fcd545"}}