{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AIZ2E3IPEVUGPPFV7ODCWQSW3V","short_pith_number":"pith:AIZ2E3IP","schema_version":"1.0","canonical_sha256":"0233a26d0f256867bcb5fb862b4256dd6363dff6cb8cadf3c4b6bd192c0194bd","source":{"kind":"arxiv","id":"1702.07805","version":4},"attestation_state":"computed","paper":{"title":"Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term Dependencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Christian Rupprecht, Gregory D. Hager, Nassir Navab, Robert DiPietro","submitted_at":"2017-02-24T23:48:11Z","abstract_excerpt":"Recurrent neural networks (RNNs) have achieved state-of-the-art performance on many diverse tasks, from machine translation to surgical activity recognition, yet training RNNs to capture long-term dependencies remains difficult. To date, the vast majority of successful RNN architectures alleviate this problem using nearly-additive connections between states, as introduced by long short-term memory (LSTM). We take an orthogonal approach and introduce MIST RNNs, a NARX RNN architecture that allows direct connections from the very distant past. We show that MIST RNNs 1) exhibit superior vanishing"},"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":"1702.07805","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-02-24T23:48:11Z","cross_cats_sorted":[],"title_canon_sha256":"f0a3e7a5a71b09d14d7834b86fbb2961cd3c87c808759eaec8f26e6d6a4dd95f","abstract_canon_sha256":"e10874d6a03f0747fbe79df76c5a62c44bb8e604459ceb0865078ccf486cbf7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:54.930499Z","signature_b64":"v4US8vquVofW+ZMB4Zx0hegB/6I1nferzEDODfz+OGIgqEmdCFclB5UL4M6TdfMrRRwBj+2Pq3mZv0t6jGVgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0233a26d0f256867bcb5fb862b4256dd6363dff6cb8cadf3c4b6bd192c0194bd","last_reissued_at":"2026-05-18T00:17:54.929856Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:54.929856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term Dependencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Christian Rupprecht, Gregory D. Hager, Nassir Navab, Robert DiPietro","submitted_at":"2017-02-24T23:48:11Z","abstract_excerpt":"Recurrent neural networks (RNNs) have achieved state-of-the-art performance on many diverse tasks, from machine translation to surgical activity recognition, yet training RNNs to capture long-term dependencies remains difficult. To date, the vast majority of successful RNN architectures alleviate this problem using nearly-additive connections between states, as introduced by long short-term memory (LSTM). We take an orthogonal approach and introduce MIST RNNs, a NARX RNN architecture that allows direct connections from the very distant past. We show that MIST RNNs 1) exhibit superior vanishing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07805","kind":"arxiv","version":4},"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":"1702.07805","created_at":"2026-05-18T00:17:54.929943+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.07805v4","created_at":"2026-05-18T00:17:54.929943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07805","created_at":"2026-05-18T00:17:54.929943+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIZ2E3IPEVUG","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIZ2E3IPEVUGPPFV","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIZ2E3IP","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12809","citing_title":"A Review of the Long Horizon Forecasting Problem in Time Series Analysis","ref_index":2017,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AIZ2E3IPEVUGPPFV7ODCWQSW3V","json":"https://pith.science/pith/AIZ2E3IPEVUGPPFV7ODCWQSW3V.json","graph_json":"https://pith.science/api/pith-number/AIZ2E3IPEVUGPPFV7ODCWQSW3V/graph.json","events_json":"https://pith.science/api/pith-number/AIZ2E3IPEVUGPPFV7ODCWQSW3V/events.json","paper":"https://pith.science/paper/AIZ2E3IP"},"agent_actions":{"view_html":"https://pith.science/pith/AIZ2E3IPEVUGPPFV7ODCWQSW3V","download_json":"https://pith.science/pith/AIZ2E3IPEVUGPPFV7ODCWQSW3V.json","view_paper":"https://pith.science/paper/AIZ2E3IP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.07805&json=true","fetch_graph":"https://pith.science/api/pith-number/AIZ2E3IPEVUGPPFV7ODCWQSW3V/graph.json","fetch_events":"https://pith.science/api/pith-number/AIZ2E3IPEVUGPPFV7ODCWQSW3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIZ2E3IPEVUGPPFV7ODCWQSW3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIZ2E3IPEVUGPPFV7ODCWQSW3V/action/storage_attestation","attest_author":"https://pith.science/pith/AIZ2E3IPEVUGPPFV7ODCWQSW3V/action/author_attestation","sign_citation":"https://pith.science/pith/AIZ2E3IPEVUGPPFV7ODCWQSW3V/action/citation_signature","submit_replication":"https://pith.science/pith/AIZ2E3IPEVUGPPFV7ODCWQSW3V/action/replication_record"}},"created_at":"2026-05-18T00:17:54.929943+00:00","updated_at":"2026-05-18T00:17:54.929943+00:00"}