{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KUPSGVJOCOZ2AOWUZEEJJINEVM","short_pith_number":"pith:KUPSGVJO","schema_version":"1.0","canonical_sha256":"551f23552e13b3a03ad4c90894a1a4ab26978b51ceae15fca59211a430502f06","source":{"kind":"arxiv","id":"2506.09108","version":1},"attestation_state":"computed","paper":{"title":"SensorLM: Learning the Language of Wearable Sensors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"A. Ali Heydari, Ahmed A. Metwally, Cecilia Mascolo, Daniel McDuff, Girish Narayanswamy, Jake Garrison, Jiening Zhan, Kumar Ayush, Mark Malhotra, Maxwell A. Xu, Pushmeet Kohli, Shawn Xu, Shwetak Patel, Siyuan Qiao, Tim Althoff, Xin Liu, Xuhai Xu, Yun Liu, Yuwei Zhang, Yuzhe Yang","submitted_at":"2025-06-10T17:13:09Z","abstract_excerpt":"We present SensorLM, a family of sensor-language foundation models that enable wearable sensor data understanding with natural language. Despite its pervasive nature, aligning and interpreting sensor data with language remains challenging due to the lack of paired, richly annotated sensor-text descriptions in uncurated, real-world wearable data. We introduce a hierarchical caption generation pipeline designed to capture statistical, structural, and semantic information from sensor data. This approach enabled the curation of the largest sensor-language dataset to date, comprising over 59.7 mill"},"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":"2506.09108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T17:13:09Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"44cfbf05df8901e2dde3089d008d61df03166d504a84ab9b2e5aec17eebf27ef","abstract_canon_sha256":"fe24d33994619c4b3f5122c15e805089bc5340f3034e7d18ed11d65453a85989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:31.707619Z","signature_b64":"kuw5q9z4EIzDJh2zjFpx+CJbZIunXgVfbC1U2TYmN3Bsyx3Lz6F3WmhdbWZ8PxX88zyi/g970Ea6+Za7VknqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"551f23552e13b3a03ad4c90894a1a4ab26978b51ceae15fca59211a430502f06","last_reissued_at":"2026-07-05T11:19:31.707092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:31.707092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SensorLM: Learning the Language of Wearable Sensors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"A. Ali Heydari, Ahmed A. Metwally, Cecilia Mascolo, Daniel McDuff, Girish Narayanswamy, Jake Garrison, Jiening Zhan, Kumar Ayush, Mark Malhotra, Maxwell A. Xu, Pushmeet Kohli, Shawn Xu, Shwetak Patel, Siyuan Qiao, Tim Althoff, Xin Liu, Xuhai Xu, Yun Liu, Yuwei Zhang, Yuzhe Yang","submitted_at":"2025-06-10T17:13:09Z","abstract_excerpt":"We present SensorLM, a family of sensor-language foundation models that enable wearable sensor data understanding with natural language. Despite its pervasive nature, aligning and interpreting sensor data with language remains challenging due to the lack of paired, richly annotated sensor-text descriptions in uncurated, real-world wearable data. We introduce a hierarchical caption generation pipeline designed to capture statistical, structural, and semantic information from sensor data. This approach enabled the curation of the largest sensor-language dataset to date, comprising over 59.7 mill"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09108","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/2506.09108/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":"2506.09108","created_at":"2026-07-05T11:19:31.707159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09108v1","created_at":"2026-07-05T11:19:31.707159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09108","created_at":"2026-07-05T11:19:31.707159+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUPSGVJOCOZ2","created_at":"2026-07-05T11:19:31.707159+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUPSGVJOCOZ2AOWU","created_at":"2026-07-05T11:19:31.707159+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUPSGVJO","created_at":"2026-07-05T11:19:31.707159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07365","citing_title":"A robust PPG foundation model using multimodal physiological supervision","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07692","citing_title":"BCG-FM: A Foundation Model for Ambient Cardiac Health Sensing","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04019","citing_title":"Gravity-Aware Hierarchical Routing for Lightweight SensorLLM on Human Activity Recognition","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23938","citing_title":"Authority Inversion in LLM-Mediated Ubiquitous Systems: When Models Trust Users Over Sensors","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00174","citing_title":"MyoSem: Aligning Electromyography to Natural-Language Action Semantics for Hand Action Understanding","ref_index":6,"is_internal_anchor":false},{"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":79,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03331","citing_title":"PulseLM: A Foundation Dataset and Benchmark for PPG-Text Learning","ref_index":50,"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":174,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04791","citing_title":"OpenWatch: A Multimodal Benchmark for Hand Gesture Recognition on Smartwatches","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21926","citing_title":"Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10183","citing_title":"RF-LEGO: Modularized Signal Processing-Deep Learning Co-Design for RF Sensing via Deep Unrolling","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10172","citing_title":"Wearable AI in the Era of Large Sensor Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18058","citing_title":"Sonata: A Hybrid World Model for Inertial Kinematics under Clinical Data Scarcity","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUPSGVJOCOZ2AOWUZEEJJINEVM","json":"https://pith.science/pith/KUPSGVJOCOZ2AOWUZEEJJINEVM.json","graph_json":"https://pith.science/api/pith-number/KUPSGVJOCOZ2AOWUZEEJJINEVM/graph.json","events_json":"https://pith.science/api/pith-number/KUPSGVJOCOZ2AOWUZEEJJINEVM/events.json","paper":"https://pith.science/paper/KUPSGVJO"},"agent_actions":{"view_html":"https://pith.science/pith/KUPSGVJOCOZ2AOWUZEEJJINEVM","download_json":"https://pith.science/pith/KUPSGVJOCOZ2AOWUZEEJJINEVM.json","view_paper":"https://pith.science/paper/KUPSGVJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09108&json=true","fetch_graph":"https://pith.science/api/pith-number/KUPSGVJOCOZ2AOWUZEEJJINEVM/graph.json","fetch_events":"https://pith.science/api/pith-number/KUPSGVJOCOZ2AOWUZEEJJINEVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUPSGVJOCOZ2AOWUZEEJJINEVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUPSGVJOCOZ2AOWUZEEJJINEVM/action/storage_attestation","attest_author":"https://pith.science/pith/KUPSGVJOCOZ2AOWUZEEJJINEVM/action/author_attestation","sign_citation":"https://pith.science/pith/KUPSGVJOCOZ2AOWUZEEJJINEVM/action/citation_signature","submit_replication":"https://pith.science/pith/KUPSGVJOCOZ2AOWUZEEJJINEVM/action/replication_record"}},"created_at":"2026-07-05T11:19:31.707159+00:00","updated_at":"2026-07-05T11:19:31.707159+00:00"}