{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:J6F7SXXQOHBLT3MQL3542LE3NO","short_pith_number":"pith:J6F7SXXQ","schema_version":"1.0","canonical_sha256":"4f8bf95ef071c2b9ed905efbcd2c9b6b945494531374b58813e720b898b4b70c","source":{"kind":"arxiv","id":"1504.01575","version":3},"attestation_state":"computed","paper":{"title":"Bidirectional Recurrent Neural Networks as Generative Models - Reconstructing Gaps in Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Akos Vetek, Juha Karhunen, Leo K\\\"arkk\\\"ainen, Mathias Berglund, Mikko Honkala, Tapani Raiko","submitted_at":"2015-04-07T12:21:03Z","abstract_excerpt":"Bidirectional recurrent neural networks (RNN) are trained to predict both in the positive and negative time directions simultaneously. They have not been used commonly in unsupervised tasks, because a probabilistic interpretation of the model has been difficult. Recently, two different frameworks, GSN and NADE, provide a connection between reconstruction and probabilistic modeling, which makes the interpretation possible. As far as we know, neither GSN or NADE have been studied in the context of time series before. As an example of an unsupervised task, we study the problem of filling in gaps "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1504.01575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-04-07T12:21:03Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"a8e340556b2f8d461b845d6561d63627c0945e31d4c67917ce870288eb6c96f8","abstract_canon_sha256":"3764096b49ea42c662bd158208d61f9d00f29509c58db817ebfc696861179fb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:28:14.418297Z","signature_b64":"mvhDdtmsXAALlDptIgU1m17H+eZoMS0RIAcu714l3VACK64JA3hPgMG8x1fL53Ii/LlOyoMvHw0SVYwHQYStCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f8bf95ef071c2b9ed905efbcd2c9b6b945494531374b58813e720b898b4b70c","last_reissued_at":"2026-05-18T01:28:14.417499Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:28:14.417499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bidirectional Recurrent Neural Networks as Generative Models - Reconstructing Gaps in Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Akos Vetek, Juha Karhunen, Leo K\\\"arkk\\\"ainen, Mathias Berglund, Mikko Honkala, Tapani Raiko","submitted_at":"2015-04-07T12:21:03Z","abstract_excerpt":"Bidirectional recurrent neural networks (RNN) are trained to predict both in the positive and negative time directions simultaneously. They have not been used commonly in unsupervised tasks, because a probabilistic interpretation of the model has been difficult. Recently, two different frameworks, GSN and NADE, provide a connection between reconstruction and probabilistic modeling, which makes the interpretation possible. As far as we know, neither GSN or NADE have been studied in the context of time series before. As an example of an unsupervised task, we study the problem of filling in gaps "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.01575","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1504.01575","created_at":"2026-05-18T01:28:14.417621+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.01575v3","created_at":"2026-05-18T01:28:14.417621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.01575","created_at":"2026-05-18T01:28:14.417621+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6F7SXXQOHBL","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6F7SXXQOHBLT3MQ","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6F7SXXQ","created_at":"2026-05-18T12:29:27.538025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6F7SXXQOHBLT3MQL3542LE3NO","json":"https://pith.science/pith/J6F7SXXQOHBLT3MQL3542LE3NO.json","graph_json":"https://pith.science/api/pith-number/J6F7SXXQOHBLT3MQL3542LE3NO/graph.json","events_json":"https://pith.science/api/pith-number/J6F7SXXQOHBLT3MQL3542LE3NO/events.json","paper":"https://pith.science/paper/J6F7SXXQ"},"agent_actions":{"view_html":"https://pith.science/pith/J6F7SXXQOHBLT3MQL3542LE3NO","download_json":"https://pith.science/pith/J6F7SXXQOHBLT3MQL3542LE3NO.json","view_paper":"https://pith.science/paper/J6F7SXXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.01575&json=true","fetch_graph":"https://pith.science/api/pith-number/J6F7SXXQOHBLT3MQL3542LE3NO/graph.json","fetch_events":"https://pith.science/api/pith-number/J6F7SXXQOHBLT3MQL3542LE3NO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6F7SXXQOHBLT3MQL3542LE3NO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6F7SXXQOHBLT3MQL3542LE3NO/action/storage_attestation","attest_author":"https://pith.science/pith/J6F7SXXQOHBLT3MQL3542LE3NO/action/author_attestation","sign_citation":"https://pith.science/pith/J6F7SXXQOHBLT3MQL3542LE3NO/action/citation_signature","submit_replication":"https://pith.science/pith/J6F7SXXQOHBLT3MQL3542LE3NO/action/replication_record"}},"created_at":"2026-05-18T01:28:14.417621+00:00","updated_at":"2026-05-18T01:28:14.417621+00:00"}