{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Y6WNCFQ7OZLJNTTJ3BBGI6VLBB","short_pith_number":"pith:Y6WNCFQ7","canonical_record":{"source":{"id":"1806.08593","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-22T10:40:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3b9dcfd09e4390267e7df789be3e47450a33cce644c458b266a0172c8aa3e118","abstract_canon_sha256":"d24ada63e6dec71fc1e55434202bb4fc2a1642d175decd3ba6de9fa9de5e4898"},"schema_version":"1.0"},"canonical_sha256":"c7acd1161f765696ce69d842647aab087a0820db5d9d43d3005b66c3d3362622","source":{"kind":"arxiv","id":"1806.08593","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.08593","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"arxiv_version","alias_value":"1806.08593v3","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08593","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"pith_short_12","alias_value":"Y6WNCFQ7OZLJ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y6WNCFQ7OZLJNTTJ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y6WNCFQ7","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Y6WNCFQ7OZLJNTTJ3BBGI6VLBB","target":"record","payload":{"canonical_record":{"source":{"id":"1806.08593","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-22T10:40:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3b9dcfd09e4390267e7df789be3e47450a33cce644c458b266a0172c8aa3e118","abstract_canon_sha256":"d24ada63e6dec71fc1e55434202bb4fc2a1642d175decd3ba6de9fa9de5e4898"},"schema_version":"1.0"},"canonical_sha256":"c7acd1161f765696ce69d842647aab087a0820db5d9d43d3005b66c3d3362622","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:09.872487Z","signature_b64":"sugHwZffckchNkx8NpYMqNKqGwv3Xe2ZV9kJ35cShVgJjqHR7p7sSQyfTImQHQhsKCv2rqGL14RbwQJZ4DB3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7acd1161f765696ce69d842647aab087a0820db5d9d43d3005b66c3d3362622","last_reissued_at":"2026-05-17T23:56:09.871738Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:09.871738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.08593","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZN/7IzphgLo4LBy7KgIlPfdwSCFD1OUZtlZoARGHTIgD9ATqAs5qWFzjwPw+62PJyTO1RtsX+KmN44alOqWnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T06:35:17.505470Z"},"content_sha256":"715c867c670322cc1b215620d0c61efbf7b8b6791821866c1c3b7d93133066cc","schema_version":"1.0","event_id":"sha256:715c867c670322cc1b215620d0c61efbf7b8b6791821866c1c3b7d93133066cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Y6WNCFQ7OZLJNTTJ3BBGI6VLBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tensor Monte Carlo: particle methods for the GPU era","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Laurence Aitchison","submitted_at":"2018-06-22T10:40:39Z","abstract_excerpt":"Multi-sample, importance-weighted variational autoencoders (IWAE) give tighter bounds and more accurate uncertainty estimates than variational autoencoders (VAE) trained with a standard single-sample objective. However, IWAEs scale poorly: as the latent dimensionality grows, they require exponentially many samples to retain the benefits of importance weighting. While sequential Monte-Carlo (SMC) can address this problem, it is prohibitively slow because the resampling step imposes sequential structure which cannot be parallelised, and moreover, resampling is non-differentiable which is problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08593","kind":"arxiv","version":3},"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":"2026-05-17T23:56:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nYPMj+hIp9Yi8bDfUKeyRc6Xud6XUI/jKrgvQidbX+e3VEJgAuaz9ggMoZC6gWZTwOoFq8EJOa/oslu7ijAFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T06:35:17.505816Z"},"content_sha256":"2fda57bd9bf39df298267352ddc7e15ca8d1a72290612e12427a9533ce6db791","schema_version":"1.0","event_id":"sha256:2fda57bd9bf39df298267352ddc7e15ca8d1a72290612e12427a9533ce6db791"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y6WNCFQ7OZLJNTTJ3BBGI6VLBB/bundle.json","state_url":"https://pith.science/pith/Y6WNCFQ7OZLJNTTJ3BBGI6VLBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y6WNCFQ7OZLJNTTJ3BBGI6VLBB/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":"2026-06-20T06:35:17Z","links":{"resolver":"https://pith.science/pith/Y6WNCFQ7OZLJNTTJ3BBGI6VLBB","bundle":"https://pith.science/pith/Y6WNCFQ7OZLJNTTJ3BBGI6VLBB/bundle.json","state":"https://pith.science/pith/Y6WNCFQ7OZLJNTTJ3BBGI6VLBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y6WNCFQ7OZLJNTTJ3BBGI6VLBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Y6WNCFQ7OZLJNTTJ3BBGI6VLBB","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":"d24ada63e6dec71fc1e55434202bb4fc2a1642d175decd3ba6de9fa9de5e4898","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-22T10:40:39Z","title_canon_sha256":"3b9dcfd09e4390267e7df789be3e47450a33cce644c458b266a0172c8aa3e118"},"schema_version":"1.0","source":{"id":"1806.08593","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.08593","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"arxiv_version","alias_value":"1806.08593v3","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08593","created_at":"2026-05-17T23:56:09Z"},{"alias_kind":"pith_short_12","alias_value":"Y6WNCFQ7OZLJ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y6WNCFQ7OZLJNTTJ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y6WNCFQ7","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:2fda57bd9bf39df298267352ddc7e15ca8d1a72290612e12427a9533ce6db791","target":"graph","created_at":"2026-05-17T23:56:09Z","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":"Multi-sample, importance-weighted variational autoencoders (IWAE) give tighter bounds and more accurate uncertainty estimates than variational autoencoders (VAE) trained with a standard single-sample objective. However, IWAEs scale poorly: as the latent dimensionality grows, they require exponentially many samples to retain the benefits of importance weighting. While sequential Monte-Carlo (SMC) can address this problem, it is prohibitively slow because the resampling step imposes sequential structure which cannot be parallelised, and moreover, resampling is non-differentiable which is problem","authors_text":"Laurence Aitchison","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-22T10:40:39Z","title":"Tensor Monte Carlo: particle methods for the GPU era"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08593","kind":"arxiv","version":3},"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":"sha256:715c867c670322cc1b215620d0c61efbf7b8b6791821866c1c3b7d93133066cc","target":"record","created_at":"2026-05-17T23:56:09Z","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":"d24ada63e6dec71fc1e55434202bb4fc2a1642d175decd3ba6de9fa9de5e4898","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-22T10:40:39Z","title_canon_sha256":"3b9dcfd09e4390267e7df789be3e47450a33cce644c458b266a0172c8aa3e118"},"schema_version":"1.0","source":{"id":"1806.08593","kind":"arxiv","version":3}},"canonical_sha256":"c7acd1161f765696ce69d842647aab087a0820db5d9d43d3005b66c3d3362622","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7acd1161f765696ce69d842647aab087a0820db5d9d43d3005b66c3d3362622","first_computed_at":"2026-05-17T23:56:09.871738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:09.871738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sugHwZffckchNkx8NpYMqNKqGwv3Xe2ZV9kJ35cShVgJjqHR7p7sSQyfTImQHQhsKCv2rqGL14RbwQJZ4DB3BA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:09.872487Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.08593","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:715c867c670322cc1b215620d0c61efbf7b8b6791821866c1c3b7d93133066cc","sha256:2fda57bd9bf39df298267352ddc7e15ca8d1a72290612e12427a9533ce6db791"],"state_sha256":"426f276c89ca3438e14a6566f5d500835edab88cc73c25ade208740fdd2a1d0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Nl3FmFVb1ekssSj8TLIaSbl2MCo3EnpC17plE6MtSCj2naZddzQ0iyvtOTpbq2J5UahHtY6Tknbn17bWDXBCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T06:35:17.507787Z","bundle_sha256":"cfeef2088db590b9787064f61ea0501a1d2d0985a214a25f83a881dffb21cf05"}}