{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:TBIMU3IVIESWVMW2OI3ZCURMFF","short_pith_number":"pith:TBIMU3IV","schema_version":"1.0","canonical_sha256":"9850ca6d1541256ab2da723791522c296eed44ebb9e8d494571c3a15708c6c53","source":{"kind":"arxiv","id":"1511.01169","version":5},"attestation_state":"computed","paper":{"title":"adaQN: An Adaptive Quasi-Newton Algorithm for Training RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Albert S. Berahas, Nitish Shirish Keskar","submitted_at":"2015-11-04T00:38:03Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are powerful models that achieve exceptional performance on several pattern recognition problems. However, the training of RNNs is a computationally difficult task owing to the well-known \"vanishing/exploding\" gradient problem. Algorithms proposed for training RNNs either exploit no (or limited) curvature information and have cheap per-iteration complexity, or attempt to gain significant curvature information at the cost of increased per-iteration cost. The former set includes diagonally-scaled first-order methods such as ADAGRAD and ADAM, while the latter cons"},"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":"1511.01169","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-04T00:38:03Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"cc639500517bbd528b99b21015863fe56f531360a317dd500742a0c436552d13","abstract_canon_sha256":"3d069913c4824540bfe8da7d94db6cf40330a1b3fa32e414422db9ed8a049db3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:06.385788Z","signature_b64":"YM/OQETYjR192O2+MmE8OZvFIVLmSfngAS1uqTT2vdCgTHv0ALFTI8v15j2hSvHNYEPGa0RW8CzQYQtOO9ymDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9850ca6d1541256ab2da723791522c296eed44ebb9e8d494571c3a15708c6c53","last_reissued_at":"2026-05-18T01:20:06.385066Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:06.385066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"adaQN: An Adaptive Quasi-Newton Algorithm for Training RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Albert S. Berahas, Nitish Shirish Keskar","submitted_at":"2015-11-04T00:38:03Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are powerful models that achieve exceptional performance on several pattern recognition problems. However, the training of RNNs is a computationally difficult task owing to the well-known \"vanishing/exploding\" gradient problem. Algorithms proposed for training RNNs either exploit no (or limited) curvature information and have cheap per-iteration complexity, or attempt to gain significant curvature information at the cost of increased per-iteration cost. The former set includes diagonally-scaled first-order methods such as ADAGRAD and ADAM, while the latter cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.01169","kind":"arxiv","version":5},"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":"1511.01169","created_at":"2026-05-18T01:20:06.385172+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.01169v5","created_at":"2026-05-18T01:20:06.385172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.01169","created_at":"2026-05-18T01:20:06.385172+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBIMU3IVIESW","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBIMU3IVIESWVMW2","created_at":"2026-05-18T12:29:42.218222+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBIMU3IV","created_at":"2026-05-18T12:29:42.218222+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/TBIMU3IVIESWVMW2OI3ZCURMFF","json":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF.json","graph_json":"https://pith.science/api/pith-number/TBIMU3IVIESWVMW2OI3ZCURMFF/graph.json","events_json":"https://pith.science/api/pith-number/TBIMU3IVIESWVMW2OI3ZCURMFF/events.json","paper":"https://pith.science/paper/TBIMU3IV"},"agent_actions":{"view_html":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF","download_json":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF.json","view_paper":"https://pith.science/paper/TBIMU3IV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.01169&json=true","fetch_graph":"https://pith.science/api/pith-number/TBIMU3IVIESWVMW2OI3ZCURMFF/graph.json","fetch_events":"https://pith.science/api/pith-number/TBIMU3IVIESWVMW2OI3ZCURMFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/action/storage_attestation","attest_author":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/action/author_attestation","sign_citation":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/action/citation_signature","submit_replication":"https://pith.science/pith/TBIMU3IVIESWVMW2OI3ZCURMFF/action/replication_record"}},"created_at":"2026-05-18T01:20:06.385172+00:00","updated_at":"2026-05-18T01:20:06.385172+00:00"}