{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FVANSPRATXVPWNFMEV7FQYHNM3","short_pith_number":"pith:FVANSPRA","schema_version":"1.0","canonical_sha256":"2d40d93e209deafb34ac257e5860ed66d12727be17f2b54ede5cd19bcc159e45","source":{"kind":"arxiv","id":"2502.07608","version":3},"attestation_state":"computed","paper":{"title":"Time2Lang: Bridging Time-Series Foundation Models and Large Language Models for Health Sensing Beyond Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Amanda C Collins, Andrew Campbell, Arvind Pillai, Daniel M Mackin, Dimitris Spathis, Michael V Heinz, Nicholas C Jacobson, Subigya Nepal, Tess Z Griffin","submitted_at":"2025-02-11T14:58:54Z","abstract_excerpt":"Large language models (LLMs) show promise for health applications when combined with behavioral sensing data. Traditional approaches convert sensor data into text prompts, but this process is prone to errors, computationally expensive, and requires domain expertise. These challenges are particularly acute when processing extended time series data. While time series foundation models (TFMs) have recently emerged as powerful tools for learning representations from temporal data, bridging TFMs and LLMs remains challenging. Here, we present Time2Lang, a framework that directly maps TFM outputs to "},"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":"2502.07608","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T14:58:54Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"1c7a40bbe01f1e6479b9c94dc8d091d0a2d8777e401ae7b2e54544a9328c7e5d","abstract_canon_sha256":"7c403a6f9946d3f14a06fc4b11ebf27810d2870d70a6b3173d796499ab5b0f2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:30.455051Z","signature_b64":"OAt9ZDBoOWf5FbJoDBqEWGkbTxRw160GRwcUbAuLQVuiTFkKYLY2pvVjvV9Kw8EW4dj2NI4b4P+tbeV+xld8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d40d93e209deafb34ac257e5860ed66d12727be17f2b54ede5cd19bcc159e45","last_reissued_at":"2026-07-05T10:55:30.454551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:30.454551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time2Lang: Bridging Time-Series Foundation Models and Large Language Models for Health Sensing Beyond Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Amanda C Collins, Andrew Campbell, Arvind Pillai, Daniel M Mackin, Dimitris Spathis, Michael V Heinz, Nicholas C Jacobson, Subigya Nepal, Tess Z Griffin","submitted_at":"2025-02-11T14:58:54Z","abstract_excerpt":"Large language models (LLMs) show promise for health applications when combined with behavioral sensing data. Traditional approaches convert sensor data into text prompts, but this process is prone to errors, computationally expensive, and requires domain expertise. These challenges are particularly acute when processing extended time series data. While time series foundation models (TFMs) have recently emerged as powerful tools for learning representations from temporal data, bridging TFMs and LLMs remains challenging. Here, we present Time2Lang, a framework that directly maps TFM outputs to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07608","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/2502.07608/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":"2502.07608","created_at":"2026-07-05T10:55:30.454606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07608v3","created_at":"2026-07-05T10:55:30.454606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07608","created_at":"2026-07-05T10:55:30.454606+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVANSPRATXVP","created_at":"2026-07-05T10:55:30.454606+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVANSPRATXVPWNFM","created_at":"2026-07-05T10:55:30.454606+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVANSPRA","created_at":"2026-07-05T10:55:30.454606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04019","citing_title":"Gravity-Aware Hierarchical Routing for Lightweight SensorLLM on Human Activity Recognition","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17679","citing_title":"PULSE: Agentic Investigation with Passive Sensing for Proactive Intervention in Cancer Survivorship","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23025","citing_title":"LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02711","citing_title":"Foundation Models Defining A New Era In Sensor-based Human Activity Recognition: A Survey And Outlook","ref_index":117,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVANSPRATXVPWNFMEV7FQYHNM3","json":"https://pith.science/pith/FVANSPRATXVPWNFMEV7FQYHNM3.json","graph_json":"https://pith.science/api/pith-number/FVANSPRATXVPWNFMEV7FQYHNM3/graph.json","events_json":"https://pith.science/api/pith-number/FVANSPRATXVPWNFMEV7FQYHNM3/events.json","paper":"https://pith.science/paper/FVANSPRA"},"agent_actions":{"view_html":"https://pith.science/pith/FVANSPRATXVPWNFMEV7FQYHNM3","download_json":"https://pith.science/pith/FVANSPRATXVPWNFMEV7FQYHNM3.json","view_paper":"https://pith.science/paper/FVANSPRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07608&json=true","fetch_graph":"https://pith.science/api/pith-number/FVANSPRATXVPWNFMEV7FQYHNM3/graph.json","fetch_events":"https://pith.science/api/pith-number/FVANSPRATXVPWNFMEV7FQYHNM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVANSPRATXVPWNFMEV7FQYHNM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVANSPRATXVPWNFMEV7FQYHNM3/action/storage_attestation","attest_author":"https://pith.science/pith/FVANSPRATXVPWNFMEV7FQYHNM3/action/author_attestation","sign_citation":"https://pith.science/pith/FVANSPRATXVPWNFMEV7FQYHNM3/action/citation_signature","submit_replication":"https://pith.science/pith/FVANSPRATXVPWNFMEV7FQYHNM3/action/replication_record"}},"created_at":"2026-07-05T10:55:30.454606+00:00","updated_at":"2026-07-05T10:55:30.454606+00:00"}