{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:542ZKGNWEF67DDTIUIW6AV3ZKM","short_pith_number":"pith:542ZKGNW","schema_version":"1.0","canonical_sha256":"ef359519b6217df18e68a22de057795324d3ce2268f80f9eb2f31b5be768156b","source":{"kind":"arxiv","id":"2602.10385","version":4},"attestation_state":"computed","paper":{"title":"Capture Timing-Attention of Events in Clinical Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LITT aligns clinical events on a virtual relative timeline to focus attention on their timing for personalized predictions.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jia Li, Rui Zhang, Yu Hou","submitted_at":"2026-02-11T00:13:08Z","abstract_excerpt":"Automatically discovering personalized trajectories (i.e., sequential event patterns) from longitudinal EHR data is crucial for enabling precision medicine in clinical research, yet it remains a formidable challenge even for contemporary AI models. For example, while the attention mechanism of transformers can capture rich associations, it is largely agnostic to event timing and ordering, thereby bypassing potential causal reasoning.\n  Intuitively, we need a method capable of evaluating the ``degree of alignment'' among patient-specific trajectories and identifying their shared patterns, that "},"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":true},"canonical_record":{"source":{"id":"2602.10385","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-11T00:13:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"598b946c6e9980f642d9eb593146c8a80ba583f0cf998cfcf7259ff8c59b719e","abstract_canon_sha256":"1d0d9069103bfe120ac6aca14ea0c1a666ad3c1816e0a3d69e4f50cf008878ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:46.132684Z","signature_b64":"g7bIzZsQ//oc94JykoI9D+LFaapbTAOHs1iho72E7cvUGrgmr2I9S3RsZbFVAObEkthmbJT+BoX0qX4OS/opAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef359519b6217df18e68a22de057795324d3ce2268f80f9eb2f31b5be768156b","last_reissued_at":"2026-05-28T02:04:46.132164Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:46.132164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capture Timing-Attention of Events in Clinical Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LITT aligns clinical events on a virtual relative timeline to focus attention on their timing for personalized predictions.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jia Li, Rui Zhang, Yu Hou","submitted_at":"2026-02-11T00:13:08Z","abstract_excerpt":"Automatically discovering personalized trajectories (i.e., sequential event patterns) from longitudinal EHR data is crucial for enabling precision medicine in clinical research, yet it remains a formidable challenge even for contemporary AI models. For example, while the attention mechanism of transformers can capture rich associations, it is largely agnostic to event timing and ordering, thereby bypassing potential causal reasoning.\n  Intuitively, we need a method capable of evaluating the ``degree of alignment'' among patient-specific trajectories and identifying their shared patterns, that "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LITT enables temporary alignment of sequential events on a virtual relative timeline, thereby enabling event-timing-focused attention and personalized interpretations of clinical trajectories, validated on real-world longitudinal EHR data from 3,276 breast cancer patients to predict the onset timing of cardiotoxicity-induced heart disease.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That treating timing as a computable dimension via relative timestamps on a virtual timeline captures meaningful alignments and causal patterns without introducing artifacts or losing information from the original observed times.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LITT aligns individual clinical event sequences on a relative timeline to enable timing-aware attention and better prediction of personalized health trajectories.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LITT aligns clinical events on a virtual relative timeline to focus attention on their timing for personalized predictions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9713bb2c0ac7ea700496fb94511cd2f1f9ef97cfc4388f4b90e69b27a5b368ac"},"source":{"id":"2602.10385","kind":"arxiv","version":4},"verdict":{"id":"55b077e7-bcd0-43d8-a2d7-eced25d0d4d2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:11:18.846159Z","strongest_claim":"LITT enables temporary alignment of sequential events on a virtual relative timeline, thereby enabling event-timing-focused attention and personalized interpretations of clinical trajectories, validated on real-world longitudinal EHR data from 3,276 breast cancer patients to predict the onset timing of cardiotoxicity-induced heart disease.","one_line_summary":"LITT aligns individual clinical event sequences on a relative timeline to enable timing-aware attention and better prediction of personalized health trajectories.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That treating timing as a computable dimension via relative timestamps on a virtual timeline captures meaningful alignments and causal patterns without introducing artifacts or losing information from the original observed times.","pith_extraction_headline":"LITT aligns clinical events on a virtual relative timeline to focus attention on their timing for personalized predictions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.10385/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":2,"snapshot_sha256":"63b2839170d7d1404bfeaac4114004611a7e035f058d506bed70d5c72b4cb341"},"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":"2602.10385","created_at":"2026-05-28T02:04:46.132238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.10385v4","created_at":"2026-05-28T02:04:46.132238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10385","created_at":"2026-05-28T02:04:46.132238+00:00"},{"alias_kind":"pith_short_12","alias_value":"542ZKGNWEF67","created_at":"2026-05-28T02:04:46.132238+00:00"},{"alias_kind":"pith_short_16","alias_value":"542ZKGNWEF67DDTI","created_at":"2026-05-28T02:04:46.132238+00:00"},{"alias_kind":"pith_short_8","alias_value":"542ZKGNW","created_at":"2026-05-28T02:04:46.132238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/542ZKGNWEF67DDTIUIW6AV3ZKM","json":"https://pith.science/pith/542ZKGNWEF67DDTIUIW6AV3ZKM.json","graph_json":"https://pith.science/api/pith-number/542ZKGNWEF67DDTIUIW6AV3ZKM/graph.json","events_json":"https://pith.science/api/pith-number/542ZKGNWEF67DDTIUIW6AV3ZKM/events.json","paper":"https://pith.science/paper/542ZKGNW"},"agent_actions":{"view_html":"https://pith.science/pith/542ZKGNWEF67DDTIUIW6AV3ZKM","download_json":"https://pith.science/pith/542ZKGNWEF67DDTIUIW6AV3ZKM.json","view_paper":"https://pith.science/paper/542ZKGNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.10385&json=true","fetch_graph":"https://pith.science/api/pith-number/542ZKGNWEF67DDTIUIW6AV3ZKM/graph.json","fetch_events":"https://pith.science/api/pith-number/542ZKGNWEF67DDTIUIW6AV3ZKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/542ZKGNWEF67DDTIUIW6AV3ZKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/542ZKGNWEF67DDTIUIW6AV3ZKM/action/storage_attestation","attest_author":"https://pith.science/pith/542ZKGNWEF67DDTIUIW6AV3ZKM/action/author_attestation","sign_citation":"https://pith.science/pith/542ZKGNWEF67DDTIUIW6AV3ZKM/action/citation_signature","submit_replication":"https://pith.science/pith/542ZKGNWEF67DDTIUIW6AV3ZKM/action/replication_record"}},"created_at":"2026-05-28T02:04:46.132238+00:00","updated_at":"2026-05-28T02:04:46.132238+00:00"}