{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:7NU2HLJ3MLIEMI26SJRSZBUA6J","short_pith_number":"pith:7NU2HLJ3","canonical_record":{"source":{"id":"1607.05690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-07-19T18:37:00Z","cross_cats_sorted":[],"title_canon_sha256":"e6a2c1d46588d7543e8766faf4709d195ee85749287aa1446da245e8630616a8","abstract_canon_sha256":"43a621f5822026d2a33f0f802a58f0823a50aac788b3e241e3e14f8349fbac05"},"schema_version":"1.0"},"canonical_sha256":"fb69a3ad3b62d046235e92632c8680f2730e54e031db684b8aa55bbbe0ece7c7","source":{"kind":"arxiv","id":"1607.05690","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.05690","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"arxiv_version","alias_value":"1607.05690v1","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05690","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"pith_short_12","alias_value":"7NU2HLJ3MLIE","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"7NU2HLJ3MLIEMI26","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"7NU2HLJ3","created_at":"2026-05-18T12:30:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:7NU2HLJ3MLIEMI26SJRSZBUA6J","target":"record","payload":{"canonical_record":{"source":{"id":"1607.05690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-07-19T18:37:00Z","cross_cats_sorted":[],"title_canon_sha256":"e6a2c1d46588d7543e8766faf4709d195ee85749287aa1446da245e8630616a8","abstract_canon_sha256":"43a621f5822026d2a33f0f802a58f0823a50aac788b3e241e3e14f8349fbac05"},"schema_version":"1.0"},"canonical_sha256":"fb69a3ad3b62d046235e92632c8680f2730e54e031db684b8aa55bbbe0ece7c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:46.250727Z","signature_b64":"8nakyCVOqKx8ujiist1YrHFlDHSgN5auX0+cF/Hn9+8k4BQp4dFcI3MObvr4yO0qPGUQBkAC/FtLlO0Dy+S8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb69a3ad3b62d046235e92632c8680f2730e54e031db684b8aa55bbbe0ece7c7","last_reissued_at":"2026-05-18T01:10:46.250310Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:46.250310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.05690","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":"2026-05-18T01:10:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGrZ+E/KrZ45tJVbFx1GLPwkzWC4FFhAkZ9C0PqeUGDtliLqn4qCvyEnX0jg7ZfKURUCgwedxcUWbGMqrDKxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T07:04:47.346796Z"},"content_sha256":"04169b278d667dd4b2d82623087b2c83eaa5f41e489c23482490d85037091691","schema_version":"1.0","event_id":"sha256:04169b278d667dd4b2d82623087b2c83eaa5f41e489c23482490d85037091691"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:7NU2HLJ3MLIEMI26SJRSZBUA6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Backpropagation through Mixture Density Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Alex Graves","submitted_at":"2016-07-19T18:37:00Z","abstract_excerpt":"The ability to backpropagate stochastic gradients through continuous latent distributions has been crucial to the emergence of variational autoencoders and stochastic gradient variational Bayes. The key ingredient is an unbiased and low-variance way of estimating gradients with respect to distribution parameters from gradients evaluated at distribution samples. The \"reparameterization trick\" provides a class of transforms yielding such estimators for many continuous distributions, including the Gaussian and other members of the location-scale family. However the trick does not readily extend t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05690","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":"2026-05-18T01:10:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V/SKxIc+RzFHbUPlOJHDeIJYSmdmxGYQXKm+Vor+QOxlTW9O/KH/sfE5TaoYo63ORfIHnpKTDeEj79ExGvAbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T07:04:47.347526Z"},"content_sha256":"c683cb393eb47d82aa901e760bf4bfa582677c27b82da89fb7fdb3776e64b7e6","schema_version":"1.0","event_id":"sha256:c683cb393eb47d82aa901e760bf4bfa582677c27b82da89fb7fdb3776e64b7e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7NU2HLJ3MLIEMI26SJRSZBUA6J/bundle.json","state_url":"https://pith.science/pith/7NU2HLJ3MLIEMI26SJRSZBUA6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7NU2HLJ3MLIEMI26SJRSZBUA6J/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":"2026-06-10T07:04:47Z","links":{"resolver":"https://pith.science/pith/7NU2HLJ3MLIEMI26SJRSZBUA6J","bundle":"https://pith.science/pith/7NU2HLJ3MLIEMI26SJRSZBUA6J/bundle.json","state":"https://pith.science/pith/7NU2HLJ3MLIEMI26SJRSZBUA6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7NU2HLJ3MLIEMI26SJRSZBUA6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:7NU2HLJ3MLIEMI26SJRSZBUA6J","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":"43a621f5822026d2a33f0f802a58f0823a50aac788b3e241e3e14f8349fbac05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-07-19T18:37:00Z","title_canon_sha256":"e6a2c1d46588d7543e8766faf4709d195ee85749287aa1446da245e8630616a8"},"schema_version":"1.0","source":{"id":"1607.05690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.05690","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"arxiv_version","alias_value":"1607.05690v1","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05690","created_at":"2026-05-18T01:10:46Z"},{"alias_kind":"pith_short_12","alias_value":"7NU2HLJ3MLIE","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"7NU2HLJ3MLIEMI26","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"7NU2HLJ3","created_at":"2026-05-18T12:30:04Z"}],"graph_snapshots":[{"event_id":"sha256:c683cb393eb47d82aa901e760bf4bfa582677c27b82da89fb7fdb3776e64b7e6","target":"graph","created_at":"2026-05-18T01:10:46Z","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":"The ability to backpropagate stochastic gradients through continuous latent distributions has been crucial to the emergence of variational autoencoders and stochastic gradient variational Bayes. The key ingredient is an unbiased and low-variance way of estimating gradients with respect to distribution parameters from gradients evaluated at distribution samples. The \"reparameterization trick\" provides a class of transforms yielding such estimators for many continuous distributions, including the Gaussian and other members of the location-scale family. However the trick does not readily extend t","authors_text":"Alex Graves","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-07-19T18:37:00Z","title":"Stochastic Backpropagation through Mixture Density Distributions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05690","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":"sha256:04169b278d667dd4b2d82623087b2c83eaa5f41e489c23482490d85037091691","target":"record","created_at":"2026-05-18T01:10:46Z","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":"43a621f5822026d2a33f0f802a58f0823a50aac788b3e241e3e14f8349fbac05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-07-19T18:37:00Z","title_canon_sha256":"e6a2c1d46588d7543e8766faf4709d195ee85749287aa1446da245e8630616a8"},"schema_version":"1.0","source":{"id":"1607.05690","kind":"arxiv","version":1}},"canonical_sha256":"fb69a3ad3b62d046235e92632c8680f2730e54e031db684b8aa55bbbe0ece7c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb69a3ad3b62d046235e92632c8680f2730e54e031db684b8aa55bbbe0ece7c7","first_computed_at":"2026-05-18T01:10:46.250310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:10:46.250310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8nakyCVOqKx8ujiist1YrHFlDHSgN5auX0+cF/Hn9+8k4BQp4dFcI3MObvr4yO0qPGUQBkAC/FtLlO0Dy+S8DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:10:46.250727Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.05690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04169b278d667dd4b2d82623087b2c83eaa5f41e489c23482490d85037091691","sha256:c683cb393eb47d82aa901e760bf4bfa582677c27b82da89fb7fdb3776e64b7e6"],"state_sha256":"93367be5d6a59a244d7ddbdf487ead6ee6e3045846d95f846723875349c0e45e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xIi+tqx8G43iCGzK5wSUvz2N71KVrOWrX/d1hcwGXJXxM72/A1DKW3MdCslCavzVL+hOuIjgmmRYKRikSY4kCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T07:04:47.351380Z","bundle_sha256":"6a4b9988d6b70f38e1f2eb3d2906eeac2fcdfd26eada24c6c39deb87f9d74056"}}