{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UW2GMA6LFED3JMT25TZX4SUI4C","short_pith_number":"pith:UW2GMA6L","schema_version":"1.0","canonical_sha256":"a5b46603cb2907b4b27aecf37e4a88e09dbf9720dd967f8799fba2cd9d50b6eb","source":{"kind":"arxiv","id":"2103.15213","version":1},"attestation_state":"computed","paper":{"title":"A Temporal Kernel Approach for Deep Learning with Continuous-time Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuanwei Ruan, Da Xu, Evren Korpeoglu, Kannan Achan, Sushant Kumar","submitted_at":"2021-03-28T20:13:53Z","abstract_excerpt":"Sequential deep learning models such as RNN, causal CNN and attention mechanism do not readily consume continuous-time information. Discretizing the temporal data, as we show, causes inconsistency even for simple continuous-time processes. Current approaches often handle time in a heuristic manner to be consistent with the existing deep learning architectures and implementations. In this paper, we provide a principled way to characterize continuous-time systems using deep learning tools. Notably, the proposed approach applies to all the major deep learning architectures and requires little mod"},"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":"2103.15213","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-28T20:13:53Z","cross_cats_sorted":[],"title_canon_sha256":"071b2fe9d5eaff352662efe092849935a3a6c4c4e067efa388469f8f1ad31d1a","abstract_canon_sha256":"8255ce383cfd72132b76f7461a5189468e1013832bf93118aaf787b130ad0dc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:03.689154Z","signature_b64":"EfSS5hGEBLPLe1RSy6S7zLMYQ2EmKWXBiE+nLNFb1kDUdxGLtJdEmpKwg50eErOarNbgtIiArF6SMveNHHb1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5b46603cb2907b4b27aecf37e4a88e09dbf9720dd967f8799fba2cd9d50b6eb","last_reissued_at":"2026-07-05T02:27:03.688736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:03.688736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Temporal Kernel Approach for Deep Learning with Continuous-time Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuanwei Ruan, Da Xu, Evren Korpeoglu, Kannan Achan, Sushant Kumar","submitted_at":"2021-03-28T20:13:53Z","abstract_excerpt":"Sequential deep learning models such as RNN, causal CNN and attention mechanism do not readily consume continuous-time information. Discretizing the temporal data, as we show, causes inconsistency even for simple continuous-time processes. Current approaches often handle time in a heuristic manner to be consistent with the existing deep learning architectures and implementations. In this paper, we provide a principled way to characterize continuous-time systems using deep learning tools. Notably, the proposed approach applies to all the major deep learning architectures and requires little mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15213","kind":"arxiv","version":1},"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/2103.15213/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":"2103.15213","created_at":"2026-07-05T02:27:03.688796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.15213v1","created_at":"2026-07-05T02:27:03.688796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15213","created_at":"2026-07-05T02:27:03.688796+00:00"},{"alias_kind":"pith_short_12","alias_value":"UW2GMA6LFED3","created_at":"2026-07-05T02:27:03.688796+00:00"},{"alias_kind":"pith_short_16","alias_value":"UW2GMA6LFED3JMT2","created_at":"2026-07-05T02:27:03.688796+00:00"},{"alias_kind":"pith_short_8","alias_value":"UW2GMA6L","created_at":"2026-07-05T02:27:03.688796+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/UW2GMA6LFED3JMT25TZX4SUI4C","json":"https://pith.science/pith/UW2GMA6LFED3JMT25TZX4SUI4C.json","graph_json":"https://pith.science/api/pith-number/UW2GMA6LFED3JMT25TZX4SUI4C/graph.json","events_json":"https://pith.science/api/pith-number/UW2GMA6LFED3JMT25TZX4SUI4C/events.json","paper":"https://pith.science/paper/UW2GMA6L"},"agent_actions":{"view_html":"https://pith.science/pith/UW2GMA6LFED3JMT25TZX4SUI4C","download_json":"https://pith.science/pith/UW2GMA6LFED3JMT25TZX4SUI4C.json","view_paper":"https://pith.science/paper/UW2GMA6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.15213&json=true","fetch_graph":"https://pith.science/api/pith-number/UW2GMA6LFED3JMT25TZX4SUI4C/graph.json","fetch_events":"https://pith.science/api/pith-number/UW2GMA6LFED3JMT25TZX4SUI4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UW2GMA6LFED3JMT25TZX4SUI4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UW2GMA6LFED3JMT25TZX4SUI4C/action/storage_attestation","attest_author":"https://pith.science/pith/UW2GMA6LFED3JMT25TZX4SUI4C/action/author_attestation","sign_citation":"https://pith.science/pith/UW2GMA6LFED3JMT25TZX4SUI4C/action/citation_signature","submit_replication":"https://pith.science/pith/UW2GMA6LFED3JMT25TZX4SUI4C/action/replication_record"}},"created_at":"2026-07-05T02:27:03.688796+00:00","updated_at":"2026-07-05T02:27:03.688796+00:00"}