{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XVFAOARQTDGWUZ2BUBIZJTAILN","short_pith_number":"pith:XVFAOARQ","schema_version":"1.0","canonical_sha256":"bd4a07023098cd6a6741a05194cc085b4ea7087f909906b0c4eb419d5193a870","source":{"kind":"arxiv","id":"1903.02082","version":1},"attestation_state":"computed","paper":{"title":"DA-LSTM: A Long Short-Term Memory with Depth Adaptive to Non-uniform Information Flow in Sequential Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Ka-Ho Chow, S.-H. Gary Chan, Yifeng Zhang","submitted_at":"2019-01-18T14:21:12Z","abstract_excerpt":"Much sequential data exhibits highly non-uniform information distribution. This cannot be correctly modeled by traditional Long Short-Term Memory (LSTM). To address that, recent works have extended LSTM by adding more activations between adjacent inputs. However, the approaches often use a fixed depth, which is at the step of the most information content. This one-size-fits-all worst-case approach is not satisfactory, because when little information is distributed to some steps, shallow structures can achieve faster convergence and consume less computation resource. In this paper, we develop a"},"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":"1903.02082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-01-18T14:21:12Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bb78523141b19286cee952a5964c6a776a112a32cfb20c2cd70a627a0ca865a7","abstract_canon_sha256":"b8aaa258b4f9744d8bb1dc333da26043b89608ab66487583eab0aed016c76724"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:56.703854Z","signature_b64":"AdoUJ/p7EBU2omMONnrOnMwcOCEQ1IvexMMlBLemSdqqhbJENLdT/umYamNNAaCD5vr4cU/J9jh7eQz3XqDYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd4a07023098cd6a6741a05194cc085b4ea7087f909906b0c4eb419d5193a870","last_reissued_at":"2026-05-17T23:51:56.703438Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:56.703438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DA-LSTM: A Long Short-Term Memory with Depth Adaptive to Non-uniform Information Flow in Sequential Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Ka-Ho Chow, S.-H. Gary Chan, Yifeng Zhang","submitted_at":"2019-01-18T14:21:12Z","abstract_excerpt":"Much sequential data exhibits highly non-uniform information distribution. This cannot be correctly modeled by traditional Long Short-Term Memory (LSTM). To address that, recent works have extended LSTM by adding more activations between adjacent inputs. However, the approaches often use a fixed depth, which is at the step of the most information content. This one-size-fits-all worst-case approach is not satisfactory, because when little information is distributed to some steps, shallow structures can achieve faster convergence and consume less computation resource. In this paper, we develop a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02082","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":"1903.02082","created_at":"2026-05-17T23:51:56.703513+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.02082v1","created_at":"2026-05-17T23:51:56.703513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02082","created_at":"2026-05-17T23:51:56.703513+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVFAOARQTDGW","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVFAOARQTDGWUZ2B","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVFAOARQ","created_at":"2026-05-18T12:33:33.725879+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/XVFAOARQTDGWUZ2BUBIZJTAILN","json":"https://pith.science/pith/XVFAOARQTDGWUZ2BUBIZJTAILN.json","graph_json":"https://pith.science/api/pith-number/XVFAOARQTDGWUZ2BUBIZJTAILN/graph.json","events_json":"https://pith.science/api/pith-number/XVFAOARQTDGWUZ2BUBIZJTAILN/events.json","paper":"https://pith.science/paper/XVFAOARQ"},"agent_actions":{"view_html":"https://pith.science/pith/XVFAOARQTDGWUZ2BUBIZJTAILN","download_json":"https://pith.science/pith/XVFAOARQTDGWUZ2BUBIZJTAILN.json","view_paper":"https://pith.science/paper/XVFAOARQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.02082&json=true","fetch_graph":"https://pith.science/api/pith-number/XVFAOARQTDGWUZ2BUBIZJTAILN/graph.json","fetch_events":"https://pith.science/api/pith-number/XVFAOARQTDGWUZ2BUBIZJTAILN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVFAOARQTDGWUZ2BUBIZJTAILN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVFAOARQTDGWUZ2BUBIZJTAILN/action/storage_attestation","attest_author":"https://pith.science/pith/XVFAOARQTDGWUZ2BUBIZJTAILN/action/author_attestation","sign_citation":"https://pith.science/pith/XVFAOARQTDGWUZ2BUBIZJTAILN/action/citation_signature","submit_replication":"https://pith.science/pith/XVFAOARQTDGWUZ2BUBIZJTAILN/action/replication_record"}},"created_at":"2026-05-17T23:51:56.703513+00:00","updated_at":"2026-05-17T23:51:56.703513+00:00"}