{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PI3GNZP6T47ZZO7FOEY7VJAYV3","short_pith_number":"pith:PI3GNZP6","schema_version":"1.0","canonical_sha256":"7a3666e5fe9f3f9cbbe57131faa418aed11f10a7fda0557daa10db6872f06ea8","source":{"kind":"arxiv","id":"2403.19857","version":1},"attestation_state":"computed","paper":{"title":"LLMSense: Harnessing LLMs for High-level Reasoning Over Spatiotemporal Sensor Traces","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mani Srivastava, Xiaomin Ouyang","submitted_at":"2024-03-28T22:06:04Z","abstract_excerpt":"Most studies on machine learning in sensing systems focus on low-level perception tasks that process raw sensory data within a short time window. However, many practical applications, such as human routine modeling and occupancy tracking, require high-level reasoning abilities to comprehend concepts and make inferences based on long-term sensor traces. Existing machine learning-based approaches for handling such complex tasks struggle to generalize due to the limited training samples and the high dimensionality of sensor traces, necessitating the integration of human knowledge for designing fi"},"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":"2403.19857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-28T22:06:04Z","cross_cats_sorted":[],"title_canon_sha256":"25d46b6392601eb502f592bf5940dcf711900a5d6002755b62a6fde344250664","abstract_canon_sha256":"953849fa696312ed3e47e2ac15f0772b2a7a56dd4c1f91ce664675394648c56d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:09.902526Z","signature_b64":"8uVbt0Jd+XJSws5DW3j7Q35JEBfx3t4O2kcm4eHPu3DHz41coU31gBYDIW9mlBdn3FZ5pKltqx1gmV2U5dZWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a3666e5fe9f3f9cbbe57131faa418aed11f10a7fda0557daa10db6872f06ea8","last_reissued_at":"2026-07-05T08:02:09.902051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:09.902051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMSense: Harnessing LLMs for High-level Reasoning Over Spatiotemporal Sensor Traces","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mani Srivastava, Xiaomin Ouyang","submitted_at":"2024-03-28T22:06:04Z","abstract_excerpt":"Most studies on machine learning in sensing systems focus on low-level perception tasks that process raw sensory data within a short time window. However, many practical applications, such as human routine modeling and occupancy tracking, require high-level reasoning abilities to comprehend concepts and make inferences based on long-term sensor traces. Existing machine learning-based approaches for handling such complex tasks struggle to generalize due to the limited training samples and the high dimensionality of sensor traces, necessitating the integration of human knowledge for designing fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19857","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/2403.19857/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":"2403.19857","created_at":"2026-07-05T08:02:09.902112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19857v1","created_at":"2026-07-05T08:02:09.902112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19857","created_at":"2026-07-05T08:02:09.902112+00:00"},{"alias_kind":"pith_short_12","alias_value":"PI3GNZP6T47Z","created_at":"2026-07-05T08:02:09.902112+00:00"},{"alias_kind":"pith_short_16","alias_value":"PI3GNZP6T47ZZO7F","created_at":"2026-07-05T08:02:09.902112+00:00"},{"alias_kind":"pith_short_8","alias_value":"PI3GNZP6","created_at":"2026-07-05T08:02:09.902112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03876","citing_title":"From 'What' to 'How' and 'Why': Sharing LLM-Generated Retrospective Summaries of Older Adults' Passive Tracking Data with Remote Family Members","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":203,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06204","citing_title":"SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams","ref_index":33,"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":114,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PI3GNZP6T47ZZO7FOEY7VJAYV3","json":"https://pith.science/pith/PI3GNZP6T47ZZO7FOEY7VJAYV3.json","graph_json":"https://pith.science/api/pith-number/PI3GNZP6T47ZZO7FOEY7VJAYV3/graph.json","events_json":"https://pith.science/api/pith-number/PI3GNZP6T47ZZO7FOEY7VJAYV3/events.json","paper":"https://pith.science/paper/PI3GNZP6"},"agent_actions":{"view_html":"https://pith.science/pith/PI3GNZP6T47ZZO7FOEY7VJAYV3","download_json":"https://pith.science/pith/PI3GNZP6T47ZZO7FOEY7VJAYV3.json","view_paper":"https://pith.science/paper/PI3GNZP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19857&json=true","fetch_graph":"https://pith.science/api/pith-number/PI3GNZP6T47ZZO7FOEY7VJAYV3/graph.json","fetch_events":"https://pith.science/api/pith-number/PI3GNZP6T47ZZO7FOEY7VJAYV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PI3GNZP6T47ZZO7FOEY7VJAYV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PI3GNZP6T47ZZO7FOEY7VJAYV3/action/storage_attestation","attest_author":"https://pith.science/pith/PI3GNZP6T47ZZO7FOEY7VJAYV3/action/author_attestation","sign_citation":"https://pith.science/pith/PI3GNZP6T47ZZO7FOEY7VJAYV3/action/citation_signature","submit_replication":"https://pith.science/pith/PI3GNZP6T47ZZO7FOEY7VJAYV3/action/replication_record"}},"created_at":"2026-07-05T08:02:09.902112+00:00","updated_at":"2026-07-05T08:02:09.902112+00:00"}