{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:APVX25DVSGALN24IUHWYFBIHR6","short_pith_number":"pith:APVX25DV","canonical_record":{"source":{"id":"1704.02798","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-10T10:59:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b403861c742487865c4fcd2e2338acf32d6a725a08958420e8e79a4e27d9bb9b","abstract_canon_sha256":"02e99bd2d347e16396a04e6563f7189b8412f7118adfb962fb17c7be180cc485"},"schema_version":"1.0"},"canonical_sha256":"03eb7d74759180b6eb88a1ed8285078f99964522f40670c2eb2adc374455b66b","source":{"kind":"arxiv","id":"1704.02798","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.02798","created_at":"2026-05-17T23:46:36Z"},{"alias_kind":"arxiv_version","alias_value":"1704.02798v4","created_at":"2026-05-17T23:46:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02798","created_at":"2026-05-17T23:46:36Z"},{"alias_kind":"pith_short_12","alias_value":"APVX25DVSGAL","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"APVX25DVSGALN24I","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"APVX25DV","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:APVX25DVSGALN24IUHWYFBIHR6","target":"record","payload":{"canonical_record":{"source":{"id":"1704.02798","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-10T10:59:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b403861c742487865c4fcd2e2338acf32d6a725a08958420e8e79a4e27d9bb9b","abstract_canon_sha256":"02e99bd2d347e16396a04e6563f7189b8412f7118adfb962fb17c7be180cc485"},"schema_version":"1.0"},"canonical_sha256":"03eb7d74759180b6eb88a1ed8285078f99964522f40670c2eb2adc374455b66b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:36.551969Z","signature_b64":"LonpBSntjWmckoZyYC67p1+t4k+t2Fv+8VMaJa/iVL2PTVaVYoYAqEsohko2QSvQpuXqiRH/TSYrMpA85AyyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03eb7d74759180b6eb88a1ed8285078f99964522f40670c2eb2adc374455b66b","last_reissued_at":"2026-05-17T23:46:36.551391Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:36.551391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.02798","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f36hxGMuk+OGlmkbr6lVeytLPqDwJUQvPAAguhmUvzvWjpSbWCo4dfaKHLq9cEbXkyx/PWbTgjs8lvnZjSgPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T04:06:38.007817Z"},"content_sha256":"7d03b58ae6d77f0ac274d37cb3b93a0eb8be7d2c16452963b630497b5af0350f","schema_version":"1.0","event_id":"sha256:7d03b58ae6d77f0ac274d37cb3b93a0eb8be7d2c16452963b630497b5af0350f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:APVX25DVSGALN24IUHWYFBIHR6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Blundell, Meire Fortunato, Oriol Vinyals","submitted_at":"2017-04-10T10:59:05Z","abstract_excerpt":"In this work we explore a straightforward variational Bayes scheme for Recurrent Neural Networks. Firstly, we show that a simple adaptation of truncated backpropagation through time can yield good quality uncertainty estimates and superior regularisation at only a small extra computational cost during training, also reducing the amount of parameters by 80\\%. Secondly, we demonstrate how a novel kind of posterior approximation yields further improvements to the performance of Bayesian RNNs. We incorporate local gradient information into the approximate posterior to sharpen it around the current"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02798","kind":"arxiv","version":4},"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":"2026-05-17T23:46:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0DdK4DrTtMaw8OZE7uwez9Exjso6R4igRD8TL/c9X5njRMIvA1qLJR4K1YTTjp45Nm6tvhcwiyQ3ldpUnag/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T04:06:38.008157Z"},"content_sha256":"b56a1ebaf2bdefb4ee05dd1c6269f766e79dfb70d5d29fb43a3f9df6be27bfe9","schema_version":"1.0","event_id":"sha256:b56a1ebaf2bdefb4ee05dd1c6269f766e79dfb70d5d29fb43a3f9df6be27bfe9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/APVX25DVSGALN24IUHWYFBIHR6/bundle.json","state_url":"https://pith.science/pith/APVX25DVSGALN24IUHWYFBIHR6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/APVX25DVSGALN24IUHWYFBIHR6/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":"2026-06-20T04:06:38Z","links":{"resolver":"https://pith.science/pith/APVX25DVSGALN24IUHWYFBIHR6","bundle":"https://pith.science/pith/APVX25DVSGALN24IUHWYFBIHR6/bundle.json","state":"https://pith.science/pith/APVX25DVSGALN24IUHWYFBIHR6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/APVX25DVSGALN24IUHWYFBIHR6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:APVX25DVSGALN24IUHWYFBIHR6","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":"02e99bd2d347e16396a04e6563f7189b8412f7118adfb962fb17c7be180cc485","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-10T10:59:05Z","title_canon_sha256":"b403861c742487865c4fcd2e2338acf32d6a725a08958420e8e79a4e27d9bb9b"},"schema_version":"1.0","source":{"id":"1704.02798","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.02798","created_at":"2026-05-17T23:46:36Z"},{"alias_kind":"arxiv_version","alias_value":"1704.02798v4","created_at":"2026-05-17T23:46:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02798","created_at":"2026-05-17T23:46:36Z"},{"alias_kind":"pith_short_12","alias_value":"APVX25DVSGAL","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"APVX25DVSGALN24I","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"APVX25DV","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:b56a1ebaf2bdefb4ee05dd1c6269f766e79dfb70d5d29fb43a3f9df6be27bfe9","target":"graph","created_at":"2026-05-17T23:46:36Z","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":"In this work we explore a straightforward variational Bayes scheme for Recurrent Neural Networks. Firstly, we show that a simple adaptation of truncated backpropagation through time can yield good quality uncertainty estimates and superior regularisation at only a small extra computational cost during training, also reducing the amount of parameters by 80\\%. Secondly, we demonstrate how a novel kind of posterior approximation yields further improvements to the performance of Bayesian RNNs. We incorporate local gradient information into the approximate posterior to sharpen it around the current","authors_text":"Charles Blundell, Meire Fortunato, Oriol Vinyals","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-10T10:59:05Z","title":"Bayesian Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02798","kind":"arxiv","version":4},"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":"sha256:7d03b58ae6d77f0ac274d37cb3b93a0eb8be7d2c16452963b630497b5af0350f","target":"record","created_at":"2026-05-17T23:46:36Z","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":"02e99bd2d347e16396a04e6563f7189b8412f7118adfb962fb17c7be180cc485","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-10T10:59:05Z","title_canon_sha256":"b403861c742487865c4fcd2e2338acf32d6a725a08958420e8e79a4e27d9bb9b"},"schema_version":"1.0","source":{"id":"1704.02798","kind":"arxiv","version":4}},"canonical_sha256":"03eb7d74759180b6eb88a1ed8285078f99964522f40670c2eb2adc374455b66b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03eb7d74759180b6eb88a1ed8285078f99964522f40670c2eb2adc374455b66b","first_computed_at":"2026-05-17T23:46:36.551391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:36.551391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LonpBSntjWmckoZyYC67p1+t4k+t2Fv+8VMaJa/iVL2PTVaVYoYAqEsohko2QSvQpuXqiRH/TSYrMpA85AyyBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:36.551969Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.02798","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d03b58ae6d77f0ac274d37cb3b93a0eb8be7d2c16452963b630497b5af0350f","sha256:b56a1ebaf2bdefb4ee05dd1c6269f766e79dfb70d5d29fb43a3f9df6be27bfe9"],"state_sha256":"9b1c14a63766de2a3810dc268e4754b67ca9f1d6878e1698c05a60e93b3ec38e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AACJPngeT6jT3IptMU4+HNElJZzh29zdB49gOrZ2qjqwFgyHXtRRnVC4Fd5Ex4cM6CRwgJVRiFf80pBwOV7xAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T04:06:38.010123Z","bundle_sha256":"6dfd438b1034a3ae0652bde34cae9e4bd83fe7d79478c9d50e75cbe83069d2fd"}}