{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5EO3QKFAFHEUD46FO3W2KSX4TI","short_pith_number":"pith:5EO3QKFA","canonical_record":{"source":{"id":"1712.08773","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-23T13:23:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"08d7612a4682540d13cd49b722cb57a6d4db43e0ce8218b02710794206b7f587","abstract_canon_sha256":"41e2cb3397021b61e32ddabb82a454a8efb876ba6e1e52f9e08fb9da1b4af3f6"},"schema_version":"1.0"},"canonical_sha256":"e91db828a029c941f3c576eda54afc9a17c60f66b87e757ef8e6363471eecb84","source":{"kind":"arxiv","id":"1712.08773","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.08773","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"1712.08773v2","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.08773","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"5EO3QKFAFHEU","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5EO3QKFAFHEUD46F","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5EO3QKFA","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5EO3QKFAFHEUD46FO3W2KSX4TI","target":"record","payload":{"canonical_record":{"source":{"id":"1712.08773","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-23T13:23:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"08d7612a4682540d13cd49b722cb57a6d4db43e0ce8218b02710794206b7f587","abstract_canon_sha256":"41e2cb3397021b61e32ddabb82a454a8efb876ba6e1e52f9e08fb9da1b4af3f6"},"schema_version":"1.0"},"canonical_sha256":"e91db828a029c941f3c576eda54afc9a17c60f66b87e757ef8e6363471eecb84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:22.837486Z","signature_b64":"rKDZhkpMqo+MrZcQpxxfwUps9usEpuUjMuWQ8yDMFKU3NMSZekIZHZ0T3w7NsswEPHWA4IUKILy6qjX4A8foBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e91db828a029c941f3c576eda54afc9a17c60f66b87e757ef8e6363471eecb84","last_reissued_at":"2026-05-17T23:44:22.836869Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:22.836869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.08773","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":"2026-05-17T23:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PctM0L52v6/D+yWCSMmLD6LTREcelywjy37K/56fKzOAuQ6aiwWc03dM5EY7PMnSsGbjBwRk7LuIxugZ7U7IDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T01:44:26.515176Z"},"content_sha256":"39315befb8aeede8d90feab77e068cf40ffcc2913a9e60cc6dbf9fb84fce3a8a","schema_version":"1.0","event_id":"sha256:39315befb8aeede8d90feab77e068cf40ffcc2913a9e60cc6dbf9fb84fce3a8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5EO3QKFAFHEUD46FO3W2KSX4TI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Approximate Bayesian Long Short-Term Memory Algorithm for Outlier Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Chen, Gabriel Terejanu, Xiao Lin","submitted_at":"2017-12-23T13:23:26Z","abstract_excerpt":"Long Short-Term Memory networks trained with gradient descent and back-propagation have received great success in various applications. However, point estimation of the weights of the networks is prone to over-fitting problems and lacks important uncertainty information associated with the estimation. However, exact Bayesian neural network methods are intractable and non-applicable for real-world applications. In this study, we propose an approximate estimation of the weights uncertainty using Ensemble Kalman Filter, which is easily scalable to a large number of weights. Furthermore, we optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.08773","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":"2026-05-17T23:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JaS6vzS/wS8YnigKeUQ1eCTT2SUwU+aXn9BFk20hkCPCv44p4PifcQz19E1O1bXwpZFq89n3j5kAuNaA2IRzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T01:44:26.515547Z"},"content_sha256":"031de3656a5e5b71a6bebab8e03d39e4d9261c34863bee6a321ba0a014756dcd","schema_version":"1.0","event_id":"sha256:031de3656a5e5b71a6bebab8e03d39e4d9261c34863bee6a321ba0a014756dcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5EO3QKFAFHEUD46FO3W2KSX4TI/bundle.json","state_url":"https://pith.science/pith/5EO3QKFAFHEUD46FO3W2KSX4TI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5EO3QKFAFHEUD46FO3W2KSX4TI/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":"2026-06-12T01:44:26Z","links":{"resolver":"https://pith.science/pith/5EO3QKFAFHEUD46FO3W2KSX4TI","bundle":"https://pith.science/pith/5EO3QKFAFHEUD46FO3W2KSX4TI/bundle.json","state":"https://pith.science/pith/5EO3QKFAFHEUD46FO3W2KSX4TI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5EO3QKFAFHEUD46FO3W2KSX4TI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5EO3QKFAFHEUD46FO3W2KSX4TI","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":"41e2cb3397021b61e32ddabb82a454a8efb876ba6e1e52f9e08fb9da1b4af3f6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-23T13:23:26Z","title_canon_sha256":"08d7612a4682540d13cd49b722cb57a6d4db43e0ce8218b02710794206b7f587"},"schema_version":"1.0","source":{"id":"1712.08773","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.08773","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"1712.08773v2","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.08773","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"5EO3QKFAFHEU","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5EO3QKFAFHEUD46F","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5EO3QKFA","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:031de3656a5e5b71a6bebab8e03d39e4d9261c34863bee6a321ba0a014756dcd","target":"graph","created_at":"2026-05-17T23:44:22Z","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":"Long Short-Term Memory networks trained with gradient descent and back-propagation have received great success in various applications. However, point estimation of the weights of the networks is prone to over-fitting problems and lacks important uncertainty information associated with the estimation. However, exact Bayesian neural network methods are intractable and non-applicable for real-world applications. In this study, we propose an approximate estimation of the weights uncertainty using Ensemble Kalman Filter, which is easily scalable to a large number of weights. Furthermore, we optimi","authors_text":"Chao Chen, Gabriel Terejanu, Xiao Lin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-23T13:23:26Z","title":"An Approximate Bayesian Long Short-Term Memory Algorithm for Outlier Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.08773","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":"sha256:39315befb8aeede8d90feab77e068cf40ffcc2913a9e60cc6dbf9fb84fce3a8a","target":"record","created_at":"2026-05-17T23:44:22Z","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":"41e2cb3397021b61e32ddabb82a454a8efb876ba6e1e52f9e08fb9da1b4af3f6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-23T13:23:26Z","title_canon_sha256":"08d7612a4682540d13cd49b722cb57a6d4db43e0ce8218b02710794206b7f587"},"schema_version":"1.0","source":{"id":"1712.08773","kind":"arxiv","version":2}},"canonical_sha256":"e91db828a029c941f3c576eda54afc9a17c60f66b87e757ef8e6363471eecb84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e91db828a029c941f3c576eda54afc9a17c60f66b87e757ef8e6363471eecb84","first_computed_at":"2026-05-17T23:44:22.836869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:22.836869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rKDZhkpMqo+MrZcQpxxfwUps9usEpuUjMuWQ8yDMFKU3NMSZekIZHZ0T3w7NsswEPHWA4IUKILy6qjX4A8foBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:22.837486Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.08773","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39315befb8aeede8d90feab77e068cf40ffcc2913a9e60cc6dbf9fb84fce3a8a","sha256:031de3656a5e5b71a6bebab8e03d39e4d9261c34863bee6a321ba0a014756dcd"],"state_sha256":"f0a564f5534c1cae87a14b1d8c6414f24ec59dede97fa5501b7969c66bfb429d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fYJL/7JeamC7KFdwAEbqNP4z48e+Cijsym51USWnw6lUdJbi4V7fkNtRtQpZPfy/291ib09Vxmp56M2Shzw9CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T01:44:26.517478Z","bundle_sha256":"6d00484e2e6346646dac004da98c9b01571015ce367ab6f03590a5cee1f1b62c"}}