{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DPLRNUZS6D2LYDLPBNTFVNXI3O","short_pith_number":"pith:DPLRNUZS","schema_version":"1.0","canonical_sha256":"1bd716d332f0f4bc0d6f0b665ab6e8dbb5a669062a848ea7b2576cef8b67e9f9","source":{"kind":"arxiv","id":"1901.02358","version":1},"attestation_state":"computed","paper":{"title":"FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Kusupati, Ashish Kumar, Kush Bhatia, Manik Varma, Manish Singh, Prateek Jain","submitted_at":"2019-01-08T15:19:13Z","abstract_excerpt":"This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them infeasible for resource-constrained and real-time applications. Unitary RNNs have increased accuracy somewhat by restricting the range of the state transition matrix's singular values but have also increased the model size as they require a larger number of hidden units to make up for the loss in expressive power. Gated RNNs have obtained state-of-the-art accuracie"},"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":"1901.02358","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T15:19:13Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"3f285ada1dd57b548d135b498bf4711d36bc992fe8509265d49f393d16ab60e6","abstract_canon_sha256":"b4dc88f9ca56b375ec1cb3d40442b1f22f4c573d0499f05df1ee64e92d218cc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:43.506613Z","signature_b64":"wj0WKeGZR5VZAEjzXyPG5jKLlhS8Htt555XZIItGzPmGEZY1BSuLr+A0wObTd59/sReOWeGt0zL35GEjaJdFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bd716d332f0f4bc0d6f0b665ab6e8dbb5a669062a848ea7b2576cef8b67e9f9","last_reissued_at":"2026-05-17T23:56:43.506089Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:43.506089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Kusupati, Ashish Kumar, Kush Bhatia, Manik Varma, Manish Singh, Prateek Jain","submitted_at":"2019-01-08T15:19:13Z","abstract_excerpt":"This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them infeasible for resource-constrained and real-time applications. Unitary RNNs have increased accuracy somewhat by restricting the range of the state transition matrix's singular values but have also increased the model size as they require a larger number of hidden units to make up for the loss in expressive power. Gated RNNs have obtained state-of-the-art accuracie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02358","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1901.02358","created_at":"2026-05-17T23:56:43.506168+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.02358v1","created_at":"2026-05-17T23:56:43.506168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02358","created_at":"2026-05-17T23:56:43.506168+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPLRNUZS6D2L","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPLRNUZS6D2LYDLP","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPLRNUZS","created_at":"2026-05-18T12:33:15.570797+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/DPLRNUZS6D2LYDLPBNTFVNXI3O","json":"https://pith.science/pith/DPLRNUZS6D2LYDLPBNTFVNXI3O.json","graph_json":"https://pith.science/api/pith-number/DPLRNUZS6D2LYDLPBNTFVNXI3O/graph.json","events_json":"https://pith.science/api/pith-number/DPLRNUZS6D2LYDLPBNTFVNXI3O/events.json","paper":"https://pith.science/paper/DPLRNUZS"},"agent_actions":{"view_html":"https://pith.science/pith/DPLRNUZS6D2LYDLPBNTFVNXI3O","download_json":"https://pith.science/pith/DPLRNUZS6D2LYDLPBNTFVNXI3O.json","view_paper":"https://pith.science/paper/DPLRNUZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.02358&json=true","fetch_graph":"https://pith.science/api/pith-number/DPLRNUZS6D2LYDLPBNTFVNXI3O/graph.json","fetch_events":"https://pith.science/api/pith-number/DPLRNUZS6D2LYDLPBNTFVNXI3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPLRNUZS6D2LYDLPBNTFVNXI3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPLRNUZS6D2LYDLPBNTFVNXI3O/action/storage_attestation","attest_author":"https://pith.science/pith/DPLRNUZS6D2LYDLPBNTFVNXI3O/action/author_attestation","sign_citation":"https://pith.science/pith/DPLRNUZS6D2LYDLPBNTFVNXI3O/action/citation_signature","submit_replication":"https://pith.science/pith/DPLRNUZS6D2LYDLPBNTFVNXI3O/action/replication_record"}},"created_at":"2026-05-17T23:56:43.506168+00:00","updated_at":"2026-05-17T23:56:43.506168+00:00"}