{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:X42IQNDVJPOL6XNGTVTEDWOFNV","short_pith_number":"pith:X42IQNDV","schema_version":"1.0","canonical_sha256":"bf348834754bdcbf5da69d6641d9c56d6c7fce0c49cc16b9f928d3ca106b89bc","source":{"kind":"arxiv","id":"1809.11086","version":2},"attestation_state":"computed","paper":{"title":"Learning Recurrent Binary/Ternary Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arash Ardakani, Brett H. Meyer, Sean C. Smithson, Warren J. Gross, Zhengyun Ji","submitted_at":"2018-09-28T15:27:29Z","abstract_excerpt":"Recurrent neural networks (RNNs) have shown excellent performance in processing sequence data. However, they are both complex and memory intensive due to their recursive nature. These limitations make RNNs difficult to embed on mobile devices requiring real-time processes with limited hardware resources. To address the above issues, we introduce a method that can learn binary and ternary weights during the training phase to facilitate hardware implementations of RNNs. As a result, using this approach replaces all multiply-accumulate operations by simple accumulations, bringing significant bene"},"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":"1809.11086","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-28T15:27:29Z","cross_cats_sorted":["cs.CC","stat.ML"],"title_canon_sha256":"eefffa10fe2759c4627a7b2ac79b52ffd4367fc9d4d8c77250274e24ad1b93d6","abstract_canon_sha256":"93fbeccf8eee17e80a4c677c498f3dcac10414221078377e3c16290066fc7f9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:34.101384Z","signature_b64":"cHcJ6evlt/bR0UJSmWhnDZJ3zCtNVf9ueAKWhZBilMau26+paHrMoaOL6qx4eQezkvX2KyzmcELI95Ufj/1KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf348834754bdcbf5da69d6641d9c56d6c7fce0c49cc16b9f928d3ca106b89bc","last_reissued_at":"2026-05-17T23:55:34.100763Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:34.100763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Recurrent Binary/Ternary Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arash Ardakani, Brett H. Meyer, Sean C. Smithson, Warren J. Gross, Zhengyun Ji","submitted_at":"2018-09-28T15:27:29Z","abstract_excerpt":"Recurrent neural networks (RNNs) have shown excellent performance in processing sequence data. However, they are both complex and memory intensive due to their recursive nature. These limitations make RNNs difficult to embed on mobile devices requiring real-time processes with limited hardware resources. To address the above issues, we introduce a method that can learn binary and ternary weights during the training phase to facilitate hardware implementations of RNNs. As a result, using this approach replaces all multiply-accumulate operations by simple accumulations, bringing significant bene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.11086","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":"1809.11086","created_at":"2026-05-17T23:55:34.100861+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.11086v2","created_at":"2026-05-17T23:55:34.100861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.11086","created_at":"2026-05-17T23:55:34.100861+00:00"},{"alias_kind":"pith_short_12","alias_value":"X42IQNDVJPOL","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"X42IQNDVJPOL6XNG","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"X42IQNDV","created_at":"2026-05-18T12:33:01.666342+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/X42IQNDVJPOL6XNGTVTEDWOFNV","json":"https://pith.science/pith/X42IQNDVJPOL6XNGTVTEDWOFNV.json","graph_json":"https://pith.science/api/pith-number/X42IQNDVJPOL6XNGTVTEDWOFNV/graph.json","events_json":"https://pith.science/api/pith-number/X42IQNDVJPOL6XNGTVTEDWOFNV/events.json","paper":"https://pith.science/paper/X42IQNDV"},"agent_actions":{"view_html":"https://pith.science/pith/X42IQNDVJPOL6XNGTVTEDWOFNV","download_json":"https://pith.science/pith/X42IQNDVJPOL6XNGTVTEDWOFNV.json","view_paper":"https://pith.science/paper/X42IQNDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.11086&json=true","fetch_graph":"https://pith.science/api/pith-number/X42IQNDVJPOL6XNGTVTEDWOFNV/graph.json","fetch_events":"https://pith.science/api/pith-number/X42IQNDVJPOL6XNGTVTEDWOFNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X42IQNDVJPOL6XNGTVTEDWOFNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X42IQNDVJPOL6XNGTVTEDWOFNV/action/storage_attestation","attest_author":"https://pith.science/pith/X42IQNDVJPOL6XNGTVTEDWOFNV/action/author_attestation","sign_citation":"https://pith.science/pith/X42IQNDVJPOL6XNGTVTEDWOFNV/action/citation_signature","submit_replication":"https://pith.science/pith/X42IQNDVJPOL6XNGTVTEDWOFNV/action/replication_record"}},"created_at":"2026-05-17T23:55:34.100861+00:00","updated_at":"2026-05-17T23:55:34.100861+00:00"}