{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RTEINFSR3LG3HCREO6RGRRUW3P","short_pith_number":"pith:RTEINFSR","schema_version":"1.0","canonical_sha256":"8cc8869651dacdb38a2477a268c696dbdb3c613d174cb0b679164d66bf9c0e67","source":{"kind":"arxiv","id":"2606.22496","version":1},"attestation_state":"computed","paper":{"title":"Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.PF","authors_text":"Ayg\\\"un Varol, Johanna Virkki, Katarzyna Ko{\\l}odziej, {\\L}ukasz Sobczak, Micha{\\l} Romaszewski, Mirka Leino, Naser Hossein Motlagh, Przemys{\\l}aw G{\\l}omb","submitted_at":"2026-06-21T13:35:57Z","abstract_excerpt":"Large language models (LLMs) offer a natural-language interface for interpreting Internet of Things (IoT) sensor data in smart environments; however, cloud deployment introduces latency, privacy, and connectivity concerns. Local LLMs can reduce these limitations, but compact edge-deployable models often show weaker numerical reasoning when raw sensor readings are provided directly. This paper investigates whether prompt-side preprocessing can improve the accuracy-latency trade-off of local LLMs for environmental monitoring. We propose a structured prompt construction framework that transforms "},"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":"2606.22496","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.PF","submitted_at":"2026-06-21T13:35:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"40683124471462190ca069d0c1bdd72b1c1a27abcc0adb9e9a99cb240c605d06","abstract_canon_sha256":"5ad154acb633d87eb965f375702c3133129307627893a849fe86b27b393a1fa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:40.140202Z","signature_b64":"etWf/PmnLoo8UGuIwMFfUzc26dirxiiJ+bD3LSsxkWPS1GhdAAWLraxTlBnP4VA7XcnjTLJGpD2IRXI7579DDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cc8869651dacdb38a2477a268c696dbdb3c613d174cb0b679164d66bf9c0e67","last_reissued_at":"2026-06-23T02:13:40.139781Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:40.139781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.PF","authors_text":"Ayg\\\"un Varol, Johanna Virkki, Katarzyna Ko{\\l}odziej, {\\L}ukasz Sobczak, Micha{\\l} Romaszewski, Mirka Leino, Naser Hossein Motlagh, Przemys{\\l}aw G{\\l}omb","submitted_at":"2026-06-21T13:35:57Z","abstract_excerpt":"Large language models (LLMs) offer a natural-language interface for interpreting Internet of Things (IoT) sensor data in smart environments; however, cloud deployment introduces latency, privacy, and connectivity concerns. Local LLMs can reduce these limitations, but compact edge-deployable models often show weaker numerical reasoning when raw sensor readings are provided directly. This paper investigates whether prompt-side preprocessing can improve the accuracy-latency trade-off of local LLMs for environmental monitoring. We propose a structured prompt construction framework that transforms "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22496","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/2606.22496/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":"2606.22496","created_at":"2026-06-23T02:13:40.139848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22496v1","created_at":"2026-06-23T02:13:40.139848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22496","created_at":"2026-06-23T02:13:40.139848+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTEINFSR3LG3","created_at":"2026-06-23T02:13:40.139848+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTEINFSR3LG3HCRE","created_at":"2026-06-23T02:13:40.139848+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTEINFSR","created_at":"2026-06-23T02:13:40.139848+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/RTEINFSR3LG3HCREO6RGRRUW3P","json":"https://pith.science/pith/RTEINFSR3LG3HCREO6RGRRUW3P.json","graph_json":"https://pith.science/api/pith-number/RTEINFSR3LG3HCREO6RGRRUW3P/graph.json","events_json":"https://pith.science/api/pith-number/RTEINFSR3LG3HCREO6RGRRUW3P/events.json","paper":"https://pith.science/paper/RTEINFSR"},"agent_actions":{"view_html":"https://pith.science/pith/RTEINFSR3LG3HCREO6RGRRUW3P","download_json":"https://pith.science/pith/RTEINFSR3LG3HCREO6RGRRUW3P.json","view_paper":"https://pith.science/paper/RTEINFSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22496&json=true","fetch_graph":"https://pith.science/api/pith-number/RTEINFSR3LG3HCREO6RGRRUW3P/graph.json","fetch_events":"https://pith.science/api/pith-number/RTEINFSR3LG3HCREO6RGRRUW3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTEINFSR3LG3HCREO6RGRRUW3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTEINFSR3LG3HCREO6RGRRUW3P/action/storage_attestation","attest_author":"https://pith.science/pith/RTEINFSR3LG3HCREO6RGRRUW3P/action/author_attestation","sign_citation":"https://pith.science/pith/RTEINFSR3LG3HCREO6RGRRUW3P/action/citation_signature","submit_replication":"https://pith.science/pith/RTEINFSR3LG3HCREO6RGRRUW3P/action/replication_record"}},"created_at":"2026-06-23T02:13:40.139848+00:00","updated_at":"2026-06-23T02:13:40.139848+00:00"}