{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NB5P4HCQPOLXBEJZBM6UZZZJI7","short_pith_number":"pith:NB5P4HCQ","schema_version":"1.0","canonical_sha256":"687afe1c507b977091390b3d4ce72947df1cc0d337cd166de3546de554f8ce95","source":{"kind":"arxiv","id":"2603.06638","version":3},"attestation_state":"computed","paper":{"title":"HEARTS: Benchmarking LLM Reasoning on Health Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ahmed Metwally, Daniel McDuff, Mihir Joshi, Shuhan Xiao, Sirui Li, Wei Wang, Yuzhe Yang","submitted_at":"2026-02-25T05:23:23Z","abstract_excerpt":"The rise of large language models (LLMs) has shifted time series analysis from narrow analytics to general-purpose reasoning. Yet, existing benchmarks cover only a small set of health time series modalities and tasks, failing to reflect the diverse domains and extensive temporal dependencies inherent in real-world physiological modeling. To bridge these gaps, we introduce HEARTS (Health Reasoning over Time Series), a unified benchmark for evaluating hierarchical reasoning capabilities of LLMs over general health time series. HEARTS integrates 16 real-world datasets across 12 health domains and"},"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":"2603.06638","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-25T05:23:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b78c16d0a59545aea6bc28cfff9226a1f393a4f01d511edbe3f002e6cbcd48d5","abstract_canon_sha256":"481c38b3849fa1ca9b258b64b088e446b9139575f449f270dadbd1d463007f66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:35.759276Z","signature_b64":"oty8+ZOvzVj9cCo1D6Iq2OMHhWAR9X23hW0MIQWj8WwxJ5mzgVIVYwD3kftfRet12hFhWF9bRdV2+nFBl+ccDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"687afe1c507b977091390b3d4ce72947df1cc0d337cd166de3546de554f8ce95","last_reissued_at":"2026-06-30T01:17:35.758666Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:35.758666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HEARTS: Benchmarking LLM Reasoning on Health Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ahmed Metwally, Daniel McDuff, Mihir Joshi, Shuhan Xiao, Sirui Li, Wei Wang, Yuzhe Yang","submitted_at":"2026-02-25T05:23:23Z","abstract_excerpt":"The rise of large language models (LLMs) has shifted time series analysis from narrow analytics to general-purpose reasoning. Yet, existing benchmarks cover only a small set of health time series modalities and tasks, failing to reflect the diverse domains and extensive temporal dependencies inherent in real-world physiological modeling. To bridge these gaps, we introduce HEARTS (Health Reasoning over Time Series), a unified benchmark for evaluating hierarchical reasoning capabilities of LLMs over general health time series. HEARTS integrates 16 real-world datasets across 12 health domains and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.06638","kind":"arxiv","version":3},"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/2603.06638/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":"2603.06638","created_at":"2026-06-30T01:17:35.758743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.06638v3","created_at":"2026-06-30T01:17:35.758743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.06638","created_at":"2026-06-30T01:17:35.758743+00:00"},{"alias_kind":"pith_short_12","alias_value":"NB5P4HCQPOLX","created_at":"2026-06-30T01:17:35.758743+00:00"},{"alias_kind":"pith_short_16","alias_value":"NB5P4HCQPOLXBEJZ","created_at":"2026-06-30T01:17:35.758743+00:00"},{"alias_kind":"pith_short_8","alias_value":"NB5P4HCQ","created_at":"2026-06-30T01:17:35.758743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.30865","citing_title":"GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21295","citing_title":"TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NB5P4HCQPOLXBEJZBM6UZZZJI7","json":"https://pith.science/pith/NB5P4HCQPOLXBEJZBM6UZZZJI7.json","graph_json":"https://pith.science/api/pith-number/NB5P4HCQPOLXBEJZBM6UZZZJI7/graph.json","events_json":"https://pith.science/api/pith-number/NB5P4HCQPOLXBEJZBM6UZZZJI7/events.json","paper":"https://pith.science/paper/NB5P4HCQ"},"agent_actions":{"view_html":"https://pith.science/pith/NB5P4HCQPOLXBEJZBM6UZZZJI7","download_json":"https://pith.science/pith/NB5P4HCQPOLXBEJZBM6UZZZJI7.json","view_paper":"https://pith.science/paper/NB5P4HCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.06638&json=true","fetch_graph":"https://pith.science/api/pith-number/NB5P4HCQPOLXBEJZBM6UZZZJI7/graph.json","fetch_events":"https://pith.science/api/pith-number/NB5P4HCQPOLXBEJZBM6UZZZJI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NB5P4HCQPOLXBEJZBM6UZZZJI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NB5P4HCQPOLXBEJZBM6UZZZJI7/action/storage_attestation","attest_author":"https://pith.science/pith/NB5P4HCQPOLXBEJZBM6UZZZJI7/action/author_attestation","sign_citation":"https://pith.science/pith/NB5P4HCQPOLXBEJZBM6UZZZJI7/action/citation_signature","submit_replication":"https://pith.science/pith/NB5P4HCQPOLXBEJZBM6UZZZJI7/action/replication_record"}},"created_at":"2026-06-30T01:17:35.758743+00:00","updated_at":"2026-06-30T01:17:35.758743+00:00"}