{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:F6PBFEOVSUGGVGPRVLXRLCP2WF","short_pith_number":"pith:F6PBFEOV","schema_version":"1.0","canonical_sha256":"2f9e1291d5950c6a99f1aaef1589fab163dec11f9812ce2e0c0f11625f65747c","source":{"kind":"arxiv","id":"2006.04418","version":4},"attestation_state":"computed","paper":{"title":"Learning Long-Term Dependencies in Irregularly-Sampled Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mathias Lechner, Ramin Hasani","submitted_at":"2020-06-08T08:46:58Z","abstract_excerpt":"Recurrent neural networks (RNNs) with continuous-time hidden states are a natural fit for modeling irregularly-sampled time series. These models, however, face difficulties when the input data possess long-term dependencies. We prove that similar to standard RNNs, the underlying reason for this issue is the vanishing or exploding of the gradient during training. This phenomenon is expressed by the ordinary differential equation (ODE) representation of the hidden state, regardless of the ODE solver's choice. We provide a solution by designing a new algorithm based on the long short-term memory "},"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":"2006.04418","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T08:46:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b2a8de4b3c45dc66c17d4473b338938b9ff502242f3e69bd6918382339cb85ff","abstract_canon_sha256":"e2e7acdf9d72a6ba99f08cf55791d66ba12a3241a2e1c8af6ea9172371c5469c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:05.962942Z","signature_b64":"sHZaeqjna9MVNz1mlKb20p8Rf4OcnEm1eVcahJXdz5sD/Nfb4+uwZQ9RJMULFbcJ3Qz/uwsfmB0p+wqQctidDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f9e1291d5950c6a99f1aaef1589fab163dec11f9812ce2e0c0f11625f65747c","last_reissued_at":"2026-07-05T01:57:05.962511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:05.962511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Long-Term Dependencies in Irregularly-Sampled Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mathias Lechner, Ramin Hasani","submitted_at":"2020-06-08T08:46:58Z","abstract_excerpt":"Recurrent neural networks (RNNs) with continuous-time hidden states are a natural fit for modeling irregularly-sampled time series. These models, however, face difficulties when the input data possess long-term dependencies. We prove that similar to standard RNNs, the underlying reason for this issue is the vanishing or exploding of the gradient during training. This phenomenon is expressed by the ordinary differential equation (ODE) representation of the hidden state, regardless of the ODE solver's choice. We provide a solution by designing a new algorithm based on the long short-term memory "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04418","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.04418/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":"2006.04418","created_at":"2026-07-05T01:57:05.962569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04418v4","created_at":"2026-07-05T01:57:05.962569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04418","created_at":"2026-07-05T01:57:05.962569+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6PBFEOVSUGG","created_at":"2026-07-05T01:57:05.962569+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6PBFEOVSUGGVGPR","created_at":"2026-07-05T01:57:05.962569+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6PBFEOV","created_at":"2026-07-05T01:57:05.962569+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21021","citing_title":"Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00931","citing_title":"Semi-Supervised Bayesian GANs with Log-Signatures for Uncertainty-Aware Credit Card Fraud Detection","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12116","citing_title":"Neural CDEs as Correctors for Learned Time Series Models","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F6PBFEOVSUGGVGPRVLXRLCP2WF","json":"https://pith.science/pith/F6PBFEOVSUGGVGPRVLXRLCP2WF.json","graph_json":"https://pith.science/api/pith-number/F6PBFEOVSUGGVGPRVLXRLCP2WF/graph.json","events_json":"https://pith.science/api/pith-number/F6PBFEOVSUGGVGPRVLXRLCP2WF/events.json","paper":"https://pith.science/paper/F6PBFEOV"},"agent_actions":{"view_html":"https://pith.science/pith/F6PBFEOVSUGGVGPRVLXRLCP2WF","download_json":"https://pith.science/pith/F6PBFEOVSUGGVGPRVLXRLCP2WF.json","view_paper":"https://pith.science/paper/F6PBFEOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04418&json=true","fetch_graph":"https://pith.science/api/pith-number/F6PBFEOVSUGGVGPRVLXRLCP2WF/graph.json","fetch_events":"https://pith.science/api/pith-number/F6PBFEOVSUGGVGPRVLXRLCP2WF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6PBFEOVSUGGVGPRVLXRLCP2WF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6PBFEOVSUGGVGPRVLXRLCP2WF/action/storage_attestation","attest_author":"https://pith.science/pith/F6PBFEOVSUGGVGPRVLXRLCP2WF/action/author_attestation","sign_citation":"https://pith.science/pith/F6PBFEOVSUGGVGPRVLXRLCP2WF/action/citation_signature","submit_replication":"https://pith.science/pith/F6PBFEOVSUGGVGPRVLXRLCP2WF/action/replication_record"}},"created_at":"2026-07-05T01:57:05.962569+00:00","updated_at":"2026-07-05T01:57:05.962569+00:00"}