{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:Z23VVRHQ2UXX3AF27XURHV36IR","short_pith_number":"pith:Z23VVRHQ","canonical_record":{"source":{"id":"1705.10306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-29T17:54:11Z","cross_cats_sorted":[],"title_canon_sha256":"6442884cbc183ee7735a43de322225c901cc0204ea21599e89aa2258690ca6d6","abstract_canon_sha256":"47e4ed68b06936c8d2df3742be8b9c578fec72d43c834414431bf7e6fadf9252"},"schema_version":"1.0"},"canonical_sha256":"ceb75ac4f0d52f7d80bafde913d77e4467116cf6b4cb654f161d358c29cab388","source":{"kind":"arxiv","id":"1705.10306","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10306","created_at":"2026-05-18T00:19:14Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10306v2","created_at":"2026-05-18T00:19:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10306","created_at":"2026-05-18T00:19:14Z"},{"alias_kind":"pith_short_12","alias_value":"Z23VVRHQ2UXX","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z23VVRHQ2UXX3AF2","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z23VVRHQ","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:Z23VVRHQ2UXX3AF27XURHV36IR","target":"record","payload":{"canonical_record":{"source":{"id":"1705.10306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-29T17:54:11Z","cross_cats_sorted":[],"title_canon_sha256":"6442884cbc183ee7735a43de322225c901cc0204ea21599e89aa2258690ca6d6","abstract_canon_sha256":"47e4ed68b06936c8d2df3742be8b9c578fec72d43c834414431bf7e6fadf9252"},"schema_version":"1.0"},"canonical_sha256":"ceb75ac4f0d52f7d80bafde913d77e4467116cf6b4cb654f161d358c29cab388","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:14.033869Z","signature_b64":"XR8T8hwTbw9DhOl7mpC2dgIBj46ocXLd7lr0E8DFlYb9qw+qFUrYmmpYqrYKmHSzkcWMy9CyevLe7FRSbp26DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceb75ac4f0d52f7d80bafde913d77e4467116cf6b4cb654f161d358c29cab388","last_reissued_at":"2026-05-18T00:19:14.033141Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:14.033141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.10306","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":"2026-05-18T00:19:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vBBMLRvMuo2y5TX52z8t0cFhycXdBfYXo3wrxAl/L6a9d143T/K6agUwxW/2vvZ6Rs4Vla0RvvUKIK/EtvXGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T02:33:20.226170Z"},"content_sha256":"b9fc175ab6f9f26732c54426e0919a7da73196349540bca44b9f5515d7a83e1b","schema_version":"1.0","event_id":"sha256:b9fc175ab6f9f26732c54426e0919a7da73196349540bca44b9f5515d7a83e1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:Z23VVRHQ2UXX3AF27XURHV36IR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto-Encoding Sequential Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Frank Wood, Maximilian Igl, Tom Jin, Tom Rainforth, Tuan Anh Le","submitted_at":"2017-05-29T17:54:11Z","abstract_excerpt":"We build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad family of structured probabilistic models. Our approach relies on the efficiency of sequential Monte Carlo (SMC) for performing inference in structured probabilistic models and the flexibility of deep neural networks to model complex conditional probability distributions. We develop additional theoretical insights and introduce a new training procedure which improves both model and proposal learning. We demonstrate that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10306","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":"2026-05-18T00:19:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wFQrnEirt6oa03l0A8LWk/A/+Pk3G2hWUTZjdBsLQWWfPvF57NV+6wDW5n7cjckIOzTYCosVuiCdbIFb2iFaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T02:33:20.226534Z"},"content_sha256":"b90e371df199cc1fc29d420efb97ab04f1b10bc8861db5cad21eaa71ac6bbd8d","schema_version":"1.0","event_id":"sha256:b90e371df199cc1fc29d420efb97ab04f1b10bc8861db5cad21eaa71ac6bbd8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z23VVRHQ2UXX3AF27XURHV36IR/bundle.json","state_url":"https://pith.science/pith/Z23VVRHQ2UXX3AF27XURHV36IR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z23VVRHQ2UXX3AF27XURHV36IR/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":"2026-05-28T02:33:20Z","links":{"resolver":"https://pith.science/pith/Z23VVRHQ2UXX3AF27XURHV36IR","bundle":"https://pith.science/pith/Z23VVRHQ2UXX3AF27XURHV36IR/bundle.json","state":"https://pith.science/pith/Z23VVRHQ2UXX3AF27XURHV36IR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z23VVRHQ2UXX3AF27XURHV36IR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Z23VVRHQ2UXX3AF27XURHV36IR","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":"47e4ed68b06936c8d2df3742be8b9c578fec72d43c834414431bf7e6fadf9252","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-29T17:54:11Z","title_canon_sha256":"6442884cbc183ee7735a43de322225c901cc0204ea21599e89aa2258690ca6d6"},"schema_version":"1.0","source":{"id":"1705.10306","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10306","created_at":"2026-05-18T00:19:14Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10306v2","created_at":"2026-05-18T00:19:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10306","created_at":"2026-05-18T00:19:14Z"},{"alias_kind":"pith_short_12","alias_value":"Z23VVRHQ2UXX","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z23VVRHQ2UXX3AF2","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z23VVRHQ","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:b90e371df199cc1fc29d420efb97ab04f1b10bc8861db5cad21eaa71ac6bbd8d","target":"graph","created_at":"2026-05-18T00:19:14Z","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 build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad family of structured probabilistic models. Our approach relies on the efficiency of sequential Monte Carlo (SMC) for performing inference in structured probabilistic models and the flexibility of deep neural networks to model complex conditional probability distributions. We develop additional theoretical insights and introduce a new training procedure which improves both model and proposal learning. We demonstrate that","authors_text":"Frank Wood, Maximilian Igl, Tom Jin, Tom Rainforth, Tuan Anh Le","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-29T17:54:11Z","title":"Auto-Encoding Sequential Monte Carlo"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10306","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:b9fc175ab6f9f26732c54426e0919a7da73196349540bca44b9f5515d7a83e1b","target":"record","created_at":"2026-05-18T00:19:14Z","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":"47e4ed68b06936c8d2df3742be8b9c578fec72d43c834414431bf7e6fadf9252","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-29T17:54:11Z","title_canon_sha256":"6442884cbc183ee7735a43de322225c901cc0204ea21599e89aa2258690ca6d6"},"schema_version":"1.0","source":{"id":"1705.10306","kind":"arxiv","version":2}},"canonical_sha256":"ceb75ac4f0d52f7d80bafde913d77e4467116cf6b4cb654f161d358c29cab388","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ceb75ac4f0d52f7d80bafde913d77e4467116cf6b4cb654f161d358c29cab388","first_computed_at":"2026-05-18T00:19:14.033141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:14.033141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XR8T8hwTbw9DhOl7mpC2dgIBj46ocXLd7lr0E8DFlYb9qw+qFUrYmmpYqrYKmHSzkcWMy9CyevLe7FRSbp26DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:14.033869Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.10306","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9fc175ab6f9f26732c54426e0919a7da73196349540bca44b9f5515d7a83e1b","sha256:b90e371df199cc1fc29d420efb97ab04f1b10bc8861db5cad21eaa71ac6bbd8d"],"state_sha256":"a4ffb8e6cdfb25d494cdf3c31adccc5ba808fdc2ac4e98d6d17d61b9e7a4b07f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h5gnVFpxcTEReZKBMGXHPlWNTriicwg3tt4mF8jOmgB7pB3oyOTzabOY8lLsBYvjPhZ4NwKF42O+Dq7AqTwaAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T02:33:20.228449Z","bundle_sha256":"eb7ed3e4afab75b0addb645110fe560247753f502d329fd809fe8489d2281966"}}