{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RUHKNKAKTD6OPV63IXWCV42RXL","short_pith_number":"pith:RUHKNKAK","schema_version":"1.0","canonical_sha256":"8d0ea6a80a98fce7d7db45ec2af351baeea1836267dc112908b00827265e2102","source":{"kind":"arxiv","id":"2605.18763","version":1},"attestation_state":"computed","paper":{"title":"Query-Conditioned Graph Retrieval for Contextualized LLM Reasoning in Personalized Wearable Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Amir M. Rahmani, Mahyar Abbasian, Zhenyu Lu","submitted_at":"2026-04-10T13:13:17Z","abstract_excerpt":"Large language models (LLMs) are increasingly applied to analyzing wearable sensing data, which are long-term, multimodal, and highly personalized. A key challenge is context selection: providing insufficient context limits reasoning, while including all available data leads to inefficiency and degraded generation quality. We propose Wearable As Graph (WAG), a graph-based context retrieval framework that enables query-adaptive reasoning over wearable data with LLMs. WAG organizes wearable metrics and user-specific signals into a personalized knowledge graph, and retrieves a query-conditioned s"},"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":"2605.18763","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-04-10T13:13:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80be2ee7d247fb7dda8d242935b9e9343cc91ebff321650f2bfcee96c39c4304","abstract_canon_sha256":"e5fbed5a65f8e795eed544d7f6d3a67d78be1180b52480b1e69492191e9346ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:20.627563Z","signature_b64":"ifr606NUgTxrK5sOrpNmm9n2tUJyzvQm6P39atgpjEd9C259wpuKrJApIqdJVAP0tTt9NeHO6KyI5LbT16wxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d0ea6a80a98fce7d7db45ec2af351baeea1836267dc112908b00827265e2102","last_reissued_at":"2026-05-20T00:06:20.626738Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:20.626738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query-Conditioned Graph Retrieval for Contextualized LLM Reasoning in Personalized Wearable Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Amir M. Rahmani, Mahyar Abbasian, Zhenyu Lu","submitted_at":"2026-04-10T13:13:17Z","abstract_excerpt":"Large language models (LLMs) are increasingly applied to analyzing wearable sensing data, which are long-term, multimodal, and highly personalized. A key challenge is context selection: providing insufficient context limits reasoning, while including all available data leads to inefficiency and degraded generation quality. We propose Wearable As Graph (WAG), a graph-based context retrieval framework that enables query-adaptive reasoning over wearable data with LLMs. WAG organizes wearable metrics and user-specific signals into a personalized knowledge graph, and retrieves a query-conditioned s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18763","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/2605.18763/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":"2605.18763","created_at":"2026-05-20T00:06:20.626847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18763v1","created_at":"2026-05-20T00:06:20.626847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18763","created_at":"2026-05-20T00:06:20.626847+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUHKNKAKTD6O","created_at":"2026-05-20T00:06:20.626847+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUHKNKAKTD6OPV63","created_at":"2026-05-20T00:06:20.626847+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUHKNKAK","created_at":"2026-05-20T00:06:20.626847+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUHKNKAKTD6OPV63IXWCV42RXL","json":"https://pith.science/pith/RUHKNKAKTD6OPV63IXWCV42RXL.json","graph_json":"https://pith.science/api/pith-number/RUHKNKAKTD6OPV63IXWCV42RXL/graph.json","events_json":"https://pith.science/api/pith-number/RUHKNKAKTD6OPV63IXWCV42RXL/events.json","paper":"https://pith.science/paper/RUHKNKAK"},"agent_actions":{"view_html":"https://pith.science/pith/RUHKNKAKTD6OPV63IXWCV42RXL","download_json":"https://pith.science/pith/RUHKNKAKTD6OPV63IXWCV42RXL.json","view_paper":"https://pith.science/paper/RUHKNKAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18763&json=true","fetch_graph":"https://pith.science/api/pith-number/RUHKNKAKTD6OPV63IXWCV42RXL/graph.json","fetch_events":"https://pith.science/api/pith-number/RUHKNKAKTD6OPV63IXWCV42RXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUHKNKAKTD6OPV63IXWCV42RXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUHKNKAKTD6OPV63IXWCV42RXL/action/storage_attestation","attest_author":"https://pith.science/pith/RUHKNKAKTD6OPV63IXWCV42RXL/action/author_attestation","sign_citation":"https://pith.science/pith/RUHKNKAKTD6OPV63IXWCV42RXL/action/citation_signature","submit_replication":"https://pith.science/pith/RUHKNKAKTD6OPV63IXWCV42RXL/action/replication_record"}},"created_at":"2026-05-20T00:06:20.626847+00:00","updated_at":"2026-05-20T00:06:20.626847+00:00"}