{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VCR7LX57ZYP762I2NS5APGFP5W","short_pith_number":"pith:VCR7LX57","schema_version":"1.0","canonical_sha256":"a8a3f5dfbfce1fff691a6cba0798afeda886f9c27bc30bb73258bf45cea3c961","source":{"kind":"arxiv","id":"2107.11350","version":2},"attestation_state":"computed","paper":{"title":"Heteroscedastic Temporal Variational Autoencoder For Irregular 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":"2021-07-23T16:59:21Z","abstract_excerpt":"Irregularly sampled time series commonly occur in several domains where they present a significant challenge to standard deep learning models. In this paper, we propose a new deep learning framework for probabilistic interpolation of irregularly sampled time series that we call the Heteroscedastic Temporal Variational Autoencoder (HeTVAE). HeTVAE includes a novel input layer to encode information about input observation sparsity, a temporal VAE architecture to propagate uncertainty due to input sparsity, and a heteroscedastic output layer to enable variable uncertainty in output interpolations"},"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":"2107.11350","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-23T16:59:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54eb4394a58b3bc1a8a0ce13c7b74e9431fd87d42292516fb3cd1ec212825548","abstract_canon_sha256":"f1e2153b5597a139ff6052bd321ac05076ceb2a7d1bb7dc3b3794ca856d8d969"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:28.605536Z","signature_b64":"dXh6B1sGMYEiEPY3mwWo4D0qM/MvVMW38vC4+ZFs1uejlFql21UGercqp+9Rv/PBWkW5qjomyG7/SgAmSeXCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8a3f5dfbfce1fff691a6cba0798afeda886f9c27bc30bb73258bf45cea3c961","last_reissued_at":"2026-07-05T09:31:28.602163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:28.602163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heteroscedastic Temporal Variational Autoencoder For Irregular 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":"2021-07-23T16:59:21Z","abstract_excerpt":"Irregularly sampled time series commonly occur in several domains where they present a significant challenge to standard deep learning models. In this paper, we propose a new deep learning framework for probabilistic interpolation of irregularly sampled time series that we call the Heteroscedastic Temporal Variational Autoencoder (HeTVAE). HeTVAE includes a novel input layer to encode information about input observation sparsity, a temporal VAE architecture to propagate uncertainty due to input sparsity, and a heteroscedastic output layer to enable variable uncertainty in output interpolations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.11350","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/2107.11350/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":"2107.11350","created_at":"2026-07-05T09:31:28.604107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.11350v2","created_at":"2026-07-05T09:31:28.604107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.11350","created_at":"2026-07-05T09:31:28.604107+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCR7LX57ZYP7","created_at":"2026-07-05T09:31:28.604107+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCR7LX57ZYP762I2","created_at":"2026-07-05T09:31:28.604107+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCR7LX57","created_at":"2026-07-05T09:31:28.604107+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/VCR7LX57ZYP762I2NS5APGFP5W","json":"https://pith.science/pith/VCR7LX57ZYP762I2NS5APGFP5W.json","graph_json":"https://pith.science/api/pith-number/VCR7LX57ZYP762I2NS5APGFP5W/graph.json","events_json":"https://pith.science/api/pith-number/VCR7LX57ZYP762I2NS5APGFP5W/events.json","paper":"https://pith.science/paper/VCR7LX57"},"agent_actions":{"view_html":"https://pith.science/pith/VCR7LX57ZYP762I2NS5APGFP5W","download_json":"https://pith.science/pith/VCR7LX57ZYP762I2NS5APGFP5W.json","view_paper":"https://pith.science/paper/VCR7LX57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.11350&json=true","fetch_graph":"https://pith.science/api/pith-number/VCR7LX57ZYP762I2NS5APGFP5W/graph.json","fetch_events":"https://pith.science/api/pith-number/VCR7LX57ZYP762I2NS5APGFP5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCR7LX57ZYP762I2NS5APGFP5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCR7LX57ZYP762I2NS5APGFP5W/action/storage_attestation","attest_author":"https://pith.science/pith/VCR7LX57ZYP762I2NS5APGFP5W/action/author_attestation","sign_citation":"https://pith.science/pith/VCR7LX57ZYP762I2NS5APGFP5W/action/citation_signature","submit_replication":"https://pith.science/pith/VCR7LX57ZYP762I2NS5APGFP5W/action/replication_record"}},"created_at":"2026-07-05T09:31:28.604107+00:00","updated_at":"2026-07-05T09:31:28.604107+00:00"}