{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IAE5AHEKCQXOELVZRYLLLADADY","short_pith_number":"pith:IAE5AHEK","schema_version":"1.0","canonical_sha256":"4009d01c8a142ee22eb98e16b580601e2d52c26cc3b77baed79297adbecc5fc8","source":{"kind":"arxiv","id":"2506.05321","version":1},"attestation_state":"computed","paper":{"title":"LSM-2: Learning from Incomplete Wearable Sensor Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"A. Ali Heydari, Ahmed Metwally, Daniel McDuff, Dimitris Spathis, Girish Narayanswamy, Jacob Sunshine, Jake Garrison, James M. Rehg, Ken Gu, Kumar Ayush, Mark Malhotra, Maxwell A. Xu, Ming-Zher Poh, Pushmeet Kohli, Samy Abdel-Ghaffar, Shrikanth Narayanan, Shun Liao, Shwetak Patel, Shyam A. Tailor, Tim Althoff, Xin Liu, Xuhai Xu, Yun Liu, Yuwei Zhang, Yuzhe Yang","submitted_at":"2025-06-05T17:57:11Z","abstract_excerpt":"Foundation models, a cornerstone of recent advancements in machine learning, have predominantly thrived on complete and well-structured data. Wearable sensor data frequently suffers from significant missingness, posing a substantial challenge for self-supervised learning (SSL) models that typically assume complete data inputs. This paper introduces the second generation of Large Sensor Model (LSM-2) with Adaptive and Inherited Masking (AIM), a novel SSL approach that learns robust representations directly from incomplete data without requiring explicit imputation. AIM's core novelty lies in it"},"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":"2506.05321","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T17:57:11Z","cross_cats_sorted":[],"title_canon_sha256":"2bbd7c9aa37f0549274424f25c33a8e919564c0e33b438a3f2b01402d2473449","abstract_canon_sha256":"9f3c153e0f466d8e209dc4f6f839e89c3e74d3a43c62a90f4411b9d59ed008ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:45.968416Z","signature_b64":"rtyL4xeJwyG6OQLyHRK4fSfSnnFNDR1neHMGvTzhbcU4RkKUIU0INFz5wQ1IbWpVCXVb06OdsKqggBDJNeUqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4009d01c8a142ee22eb98e16b580601e2d52c26cc3b77baed79297adbecc5fc8","last_reissued_at":"2026-07-05T11:16:45.967753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:45.967753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LSM-2: Learning from Incomplete Wearable Sensor Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"A. Ali Heydari, Ahmed Metwally, Daniel McDuff, Dimitris Spathis, Girish Narayanswamy, Jacob Sunshine, Jake Garrison, James M. Rehg, Ken Gu, Kumar Ayush, Mark Malhotra, Maxwell A. Xu, Ming-Zher Poh, Pushmeet Kohli, Samy Abdel-Ghaffar, Shrikanth Narayanan, Shun Liao, Shwetak Patel, Shyam A. Tailor, Tim Althoff, Xin Liu, Xuhai Xu, Yun Liu, Yuwei Zhang, Yuzhe Yang","submitted_at":"2025-06-05T17:57:11Z","abstract_excerpt":"Foundation models, a cornerstone of recent advancements in machine learning, have predominantly thrived on complete and well-structured data. Wearable sensor data frequently suffers from significant missingness, posing a substantial challenge for self-supervised learning (SSL) models that typically assume complete data inputs. This paper introduces the second generation of Large Sensor Model (LSM-2) with Adaptive and Inherited Masking (AIM), a novel SSL approach that learns robust representations directly from incomplete data without requiring explicit imputation. AIM's core novelty lies in it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05321","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/2506.05321/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":"2506.05321","created_at":"2026-07-05T11:16:45.967830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05321v1","created_at":"2026-07-05T11:16:45.967830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05321","created_at":"2026-07-05T11:16:45.967830+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAE5AHEKCQXO","created_at":"2026-07-05T11:16:45.967830+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAE5AHEKCQXOELVZ","created_at":"2026-07-05T11:16:45.967830+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAE5AHEK","created_at":"2026-07-05T11:16:45.967830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18628","citing_title":"Self-Supervised Mask-Aware Transformers for Fault-Tolerant FBG Force Sensing in Minimally Invasive Surgical Robotics","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18147","citing_title":"WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning","ref_index":197,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30865","citing_title":"GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18837","citing_title":"VCR: Learning Valid Contextual Representation for Incomplete Wearable Signals","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09173","citing_title":"WavesFM: Hierarchical Representation Learning for Longitudinal Wearable Sensor Waveforms","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00973","citing_title":"Physiology-Aware Masked Cross-Modal Reconstruction for Biosignal Representation Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08971","citing_title":"Modality-Aware Zero-Shot Pruning and Sparse Attention for Efficient Multimodal Edge Inference","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IAE5AHEKCQXOELVZRYLLLADADY","json":"https://pith.science/pith/IAE5AHEKCQXOELVZRYLLLADADY.json","graph_json":"https://pith.science/api/pith-number/IAE5AHEKCQXOELVZRYLLLADADY/graph.json","events_json":"https://pith.science/api/pith-number/IAE5AHEKCQXOELVZRYLLLADADY/events.json","paper":"https://pith.science/paper/IAE5AHEK"},"agent_actions":{"view_html":"https://pith.science/pith/IAE5AHEKCQXOELVZRYLLLADADY","download_json":"https://pith.science/pith/IAE5AHEKCQXOELVZRYLLLADADY.json","view_paper":"https://pith.science/paper/IAE5AHEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05321&json=true","fetch_graph":"https://pith.science/api/pith-number/IAE5AHEKCQXOELVZRYLLLADADY/graph.json","fetch_events":"https://pith.science/api/pith-number/IAE5AHEKCQXOELVZRYLLLADADY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAE5AHEKCQXOELVZRYLLLADADY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAE5AHEKCQXOELVZRYLLLADADY/action/storage_attestation","attest_author":"https://pith.science/pith/IAE5AHEKCQXOELVZRYLLLADADY/action/author_attestation","sign_citation":"https://pith.science/pith/IAE5AHEKCQXOELVZRYLLLADADY/action/citation_signature","submit_replication":"https://pith.science/pith/IAE5AHEKCQXOELVZRYLLLADADY/action/replication_record"}},"created_at":"2026-07-05T11:16:45.967830+00:00","updated_at":"2026-07-05T11:16:45.967830+00:00"}