{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U47PRETYE6QBPTDUX5BYXWXNDH","short_pith_number":"pith:U47PRETY","schema_version":"1.0","canonical_sha256":"a73ef8927827a017cc74bf438bdaed19c51be7c22a9cedccea883df1e245f479","source":{"kind":"arxiv","id":"2101.10318","version":2},"attestation_state":"computed","paper":{"title":"Multi-Time Attention Networks for Irregularly Sampled Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin M. Marlin, Satya Narayan Shukla","submitted_at":"2021-01-25T18:57:42Z","abstract_excerpt":"Irregular sampling occurs in many time series modeling applications where it presents a significant challenge to standard deep learning models. This work is motivated by the analysis of physiological time series data in electronic health records, which are sparse, irregularly sampled, and multivariate. In this paper, we propose a new deep learning framework for this setting that we call Multi-Time Attention Networks. Multi-Time Attention Networks learn an embedding of continuous-time values and use an attention mechanism to produce a fixed-length representation of a time series containing a va"},"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":"2101.10318","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-25T18:57:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc210b6b9c82cbe3fbdcde81173b47bcd27b769f675c2f2b7aeccbecb9bde93a","abstract_canon_sha256":"6ccd449e9b45a9ed0fbc89f8b61206b2289302c0d4078f433e4c8b9e7cb16088"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:43.960312Z","signature_b64":"jAouaTXaN22Pf8cRbY1IBiFZJi2pLANeUXWjHzemEGe/mvZ9hh4DLEgBhaqz04Njc9rC0+hteVrwcPMIeLVIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a73ef8927827a017cc74bf438bdaed19c51be7c22a9cedccea883df1e245f479","last_reissued_at":"2026-07-05T02:46:43.959836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:43.959836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Time Attention Networks for Irregularly Sampled Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin M. Marlin, Satya Narayan Shukla","submitted_at":"2021-01-25T18:57:42Z","abstract_excerpt":"Irregular sampling occurs in many time series modeling applications where it presents a significant challenge to standard deep learning models. This work is motivated by the analysis of physiological time series data in electronic health records, which are sparse, irregularly sampled, and multivariate. In this paper, we propose a new deep learning framework for this setting that we call Multi-Time Attention Networks. Multi-Time Attention Networks learn an embedding of continuous-time values and use an attention mechanism to produce a fixed-length representation of a time series containing a va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.10318","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/2101.10318/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":"2101.10318","created_at":"2026-07-05T02:46:43.959900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.10318v2","created_at":"2026-07-05T02:46:43.959900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.10318","created_at":"2026-07-05T02:46:43.959900+00:00"},{"alias_kind":"pith_short_12","alias_value":"U47PRETYE6QB","created_at":"2026-07-05T02:46:43.959900+00:00"},{"alias_kind":"pith_short_16","alias_value":"U47PRETYE6QBPTDU","created_at":"2026-07-05T02:46:43.959900+00:00"},{"alias_kind":"pith_short_8","alias_value":"U47PRETY","created_at":"2026-07-05T02:46:43.959900+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11268","citing_title":"LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06285","citing_title":"TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06328","citing_title":"PAMF: Prior-Aware Multimodal Fusion for Incomplete Time Series Data","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01894","citing_title":"Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28603","citing_title":"Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert Calibration","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16380","citing_title":"ReTAMamba: Reliability-Aware Temporal Aggregation with Mamba for Irregular Clinical Time Series Prediction","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15647","citing_title":"Perforated Neural Networks for Keyword Spotting","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06603","citing_title":"The hidden risks of temporal resampling in clinical reinforcement learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14069","citing_title":"SurF: A Generative Model for Multivariate Irregular Time Series Forecasting","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08679","citing_title":"Attention-based graph neural networks: a survey","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08914","citing_title":"Transformer autoencoder with local attention for sparse and irregular time series with application on risk estimation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09742","citing_title":"TIDES: Implicit Time-Awareness in Selective State Space Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23792","citing_title":"Beyond the Final Label: Exploiting the Untapped Potential of Classification Histories in Astronomical Light Curve Analysis","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04421","citing_title":"FLUID: Continuous-Time Hyperconnected Sparse Transformer for Sink-Free Learning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11842","citing_title":"DBGL: Decay-aware Bipartite Graph Learning for Irregular Medical Time Series Classification","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U47PRETYE6QBPTDUX5BYXWXNDH","json":"https://pith.science/pith/U47PRETYE6QBPTDUX5BYXWXNDH.json","graph_json":"https://pith.science/api/pith-number/U47PRETYE6QBPTDUX5BYXWXNDH/graph.json","events_json":"https://pith.science/api/pith-number/U47PRETYE6QBPTDUX5BYXWXNDH/events.json","paper":"https://pith.science/paper/U47PRETY"},"agent_actions":{"view_html":"https://pith.science/pith/U47PRETYE6QBPTDUX5BYXWXNDH","download_json":"https://pith.science/pith/U47PRETYE6QBPTDUX5BYXWXNDH.json","view_paper":"https://pith.science/paper/U47PRETY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.10318&json=true","fetch_graph":"https://pith.science/api/pith-number/U47PRETYE6QBPTDUX5BYXWXNDH/graph.json","fetch_events":"https://pith.science/api/pith-number/U47PRETYE6QBPTDUX5BYXWXNDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U47PRETYE6QBPTDUX5BYXWXNDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U47PRETYE6QBPTDUX5BYXWXNDH/action/storage_attestation","attest_author":"https://pith.science/pith/U47PRETYE6QBPTDUX5BYXWXNDH/action/author_attestation","sign_citation":"https://pith.science/pith/U47PRETYE6QBPTDUX5BYXWXNDH/action/citation_signature","submit_replication":"https://pith.science/pith/U47PRETYE6QBPTDUX5BYXWXNDH/action/replication_record"}},"created_at":"2026-07-05T02:46:43.959900+00:00","updated_at":"2026-07-05T02:46:43.959900+00:00"}