{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FNNTEDSDKRHGMSD5PQOPPEBP64","short_pith_number":"pith:FNNTEDSD","schema_version":"1.0","canonical_sha256":"2b5b320e43544e66487d7c1cf7902ff705777349ab27b98a5039b26e0af5457d","source":{"kind":"arxiv","id":"1908.08574","version":2},"attestation_state":"computed","paper":{"title":"RNNs Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anil Kag, Venkatesh Saligrama, Ziming Zhang","submitted_at":"2019-08-22T19:35:13Z","abstract_excerpt":"Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential rate. While a number of works attempt to mitigate this effect through gated recurrent units, well-chosen parametric constraints, and skip-connections, we develop a novel perspective that seeks to evolve the hidden state on the equilibrium manifold of an ordinary differential equation (ODE). We propose a family of novel RNNs, namely {\\em Equilibriated Recurren"},"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":"1908.08574","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T19:35:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"14b85a853fd14c4faa6f7f76d04912ab0e3540d5cdb03485c426f9b4f5ad21f1","abstract_canon_sha256":"42cf89458493fd678eb72ad02e76d6c1f9a819ff0f9ed0993ca5381074d08e2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:51.109610Z","signature_b64":"cRkGHlyK2EhstF8pM+yJExnj1RTtaVpbRwp2MFX66gbgDrw+jQD4Bu6PylK/ajQK/QQIZSwPn64UIMDpr0IPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b5b320e43544e66487d7c1cf7902ff705777349ab27b98a5039b26e0af5457d","last_reissued_at":"2026-07-04T23:59:51.109210Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:51.109210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RNNs Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anil Kag, Venkatesh Saligrama, Ziming Zhang","submitted_at":"2019-08-22T19:35:13Z","abstract_excerpt":"Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential rate. While a number of works attempt to mitigate this effect through gated recurrent units, well-chosen parametric constraints, and skip-connections, we develop a novel perspective that seeks to evolve the hidden state on the equilibrium manifold of an ordinary differential equation (ODE). We propose a family of novel RNNs, namely {\\em Equilibriated Recurren"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08574","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.08574/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1908.08574","created_at":"2026-07-04T23:59:51.109265+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.08574v2","created_at":"2026-07-04T23:59:51.109265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08574","created_at":"2026-07-04T23:59:51.109265+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNNTEDSDKRHG","created_at":"2026-07-04T23:59:51.109265+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNNTEDSDKRHGMSD5","created_at":"2026-07-04T23:59:51.109265+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNNTEDSD","created_at":"2026-07-04T23:59:51.109265+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/FNNTEDSDKRHGMSD5PQOPPEBP64","json":"https://pith.science/pith/FNNTEDSDKRHGMSD5PQOPPEBP64.json","graph_json":"https://pith.science/api/pith-number/FNNTEDSDKRHGMSD5PQOPPEBP64/graph.json","events_json":"https://pith.science/api/pith-number/FNNTEDSDKRHGMSD5PQOPPEBP64/events.json","paper":"https://pith.science/paper/FNNTEDSD"},"agent_actions":{"view_html":"https://pith.science/pith/FNNTEDSDKRHGMSD5PQOPPEBP64","download_json":"https://pith.science/pith/FNNTEDSDKRHGMSD5PQOPPEBP64.json","view_paper":"https://pith.science/paper/FNNTEDSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.08574&json=true","fetch_graph":"https://pith.science/api/pith-number/FNNTEDSDKRHGMSD5PQOPPEBP64/graph.json","fetch_events":"https://pith.science/api/pith-number/FNNTEDSDKRHGMSD5PQOPPEBP64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNNTEDSDKRHGMSD5PQOPPEBP64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNNTEDSDKRHGMSD5PQOPPEBP64/action/storage_attestation","attest_author":"https://pith.science/pith/FNNTEDSDKRHGMSD5PQOPPEBP64/action/author_attestation","sign_citation":"https://pith.science/pith/FNNTEDSDKRHGMSD5PQOPPEBP64/action/citation_signature","submit_replication":"https://pith.science/pith/FNNTEDSDKRHGMSD5PQOPPEBP64/action/replication_record"}},"created_at":"2026-07-04T23:59:51.109265+00:00","updated_at":"2026-07-04T23:59:51.109265+00:00"}