{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:R6DND4YMVTVQVDBOGMZDTQ4P2A","short_pith_number":"pith:R6DND4YM","schema_version":"1.0","canonical_sha256":"8f86d1f30caceb0a8c2e333239c38fd03d978b7f8289816e3c30a4bd00b68e33","source":{"kind":"arxiv","id":"1611.06188","version":2},"attestation_state":"computed","paper":{"title":"Variable Computation in Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Armand Joulin, Edouard Grave, Tomas Mikolov, Yacine Jernite","submitted_at":"2016-11-18T18:13:46Z","abstract_excerpt":"Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the flexibility to capture complex statistics in the data, such as long range dependency or localized attention phenomena. However, while many sequential data (such as video, speech or language) can have highly variable information flow, most recurrent models still consume input features at a constant rate and perform a constant number of computations per time step, whic"},"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":"1611.06188","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-18T18:13:46Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7de251d1ae6acab55a78ff97ac77b58060fe54ed9cf61e0dbb55bbed0c7b766e","abstract_canon_sha256":"f34b6f2967a77c00c93c4a8793c45bc0db2033f791394adc2d366140ff8d14d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:37.754641Z","signature_b64":"cC09LKi/keStjUjJ9iMVZp0iY1E1JgBbEKRFtaAGGZcmN11sDAafVkrWiuic9T7KJ8rkwLn6+1D/zD6JvMpZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f86d1f30caceb0a8c2e333239c38fd03d978b7f8289816e3c30a4bd00b68e33","last_reissued_at":"2026-05-18T00:49:37.753961Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:37.753961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variable Computation in Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Armand Joulin, Edouard Grave, Tomas Mikolov, Yacine Jernite","submitted_at":"2016-11-18T18:13:46Z","abstract_excerpt":"Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the flexibility to capture complex statistics in the data, such as long range dependency or localized attention phenomena. However, while many sequential data (such as video, speech or language) can have highly variable information flow, most recurrent models still consume input features at a constant rate and perform a constant number of computations per time step, whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06188","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1611.06188","created_at":"2026-05-18T00:49:37.754051+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.06188v2","created_at":"2026-05-18T00:49:37.754051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06188","created_at":"2026-05-18T00:49:37.754051+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6DND4YMVTVQ","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6DND4YMVTVQVDBO","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6DND4YM","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1806.07366","citing_title":"Neural Ordinary Differential Equations","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6DND4YMVTVQVDBOGMZDTQ4P2A","json":"https://pith.science/pith/R6DND4YMVTVQVDBOGMZDTQ4P2A.json","graph_json":"https://pith.science/api/pith-number/R6DND4YMVTVQVDBOGMZDTQ4P2A/graph.json","events_json":"https://pith.science/api/pith-number/R6DND4YMVTVQVDBOGMZDTQ4P2A/events.json","paper":"https://pith.science/paper/R6DND4YM"},"agent_actions":{"view_html":"https://pith.science/pith/R6DND4YMVTVQVDBOGMZDTQ4P2A","download_json":"https://pith.science/pith/R6DND4YMVTVQVDBOGMZDTQ4P2A.json","view_paper":"https://pith.science/paper/R6DND4YM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.06188&json=true","fetch_graph":"https://pith.science/api/pith-number/R6DND4YMVTVQVDBOGMZDTQ4P2A/graph.json","fetch_events":"https://pith.science/api/pith-number/R6DND4YMVTVQVDBOGMZDTQ4P2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6DND4YMVTVQVDBOGMZDTQ4P2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6DND4YMVTVQVDBOGMZDTQ4P2A/action/storage_attestation","attest_author":"https://pith.science/pith/R6DND4YMVTVQVDBOGMZDTQ4P2A/action/author_attestation","sign_citation":"https://pith.science/pith/R6DND4YMVTVQVDBOGMZDTQ4P2A/action/citation_signature","submit_replication":"https://pith.science/pith/R6DND4YMVTVQVDBOGMZDTQ4P2A/action/replication_record"}},"created_at":"2026-05-18T00:49:37.754051+00:00","updated_at":"2026-05-18T00:49:37.754051+00:00"}