{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CHKKGIHJ3ZT5YTYLT6SNPIOREX","short_pith_number":"pith:CHKKGIHJ","schema_version":"1.0","canonical_sha256":"11d4a320e9de67dc4f0b9fa4d7a1d125f378b594a95909d0540a752b0dcf54a2","source":{"kind":"arxiv","id":"2607.14661","version":1},"attestation_state":"computed","paper":{"title":"SmartRAG: Native Graph-Based RAG for Mobile Device","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haipeng Dai, Keran Li, Meng Li, Ruiben Zhou, Shenghao Liu, Shuai Wang, Xianjun Deng, Zhihan Jiang","submitted_at":"2026-07-16T07:28:31Z","abstract_excerpt":"Deploying large language models (LLMs) as personal assistants on mobile devices demands privacy, low latency, and offline availability, yet the computational cost of giant models clashes with strict edge-hardware budgets. We argue that this tension cannot be resolved by model compression alone; it requires decomposing on-device intelligence into complementary functional roles. We present SmartRAG, a fully on-device framework that organizes an intelligent assistant around four coordinated modules -- Perception, Memory, Focus, and Thinking. At the core of SmartRAG is EvoNER, a continually learna"},"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":"2607.14661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-16T07:28:31Z","cross_cats_sorted":[],"title_canon_sha256":"5f8b0c2c4161666875528cb4e47f02ead96caf21c2ae28a6a15b98a711d5433d","abstract_canon_sha256":"df5ce623e74108af417ef871e4bb069facd794d9c51430c7a4c650e1a05bcb9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:23.736150Z","signature_b64":"uIxln/Ua9hBxUj5S6NVphlQrxu3M3ccGXlZ0eqenRsWYnyvOkKoh1PEL2d/AwiUruEQHMWjkydW1imUYk1RtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11d4a320e9de67dc4f0b9fa4d7a1d125f378b594a95909d0540a752b0dcf54a2","last_reissued_at":"2026-07-17T01:21:23.735259Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:23.735259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SmartRAG: Native Graph-Based RAG for Mobile Device","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haipeng Dai, Keran Li, Meng Li, Ruiben Zhou, Shenghao Liu, Shuai Wang, Xianjun Deng, Zhihan Jiang","submitted_at":"2026-07-16T07:28:31Z","abstract_excerpt":"Deploying large language models (LLMs) as personal assistants on mobile devices demands privacy, low latency, and offline availability, yet the computational cost of giant models clashes with strict edge-hardware budgets. We argue that this tension cannot be resolved by model compression alone; it requires decomposing on-device intelligence into complementary functional roles. We present SmartRAG, a fully on-device framework that organizes an intelligent assistant around four coordinated modules -- Perception, Memory, Focus, and Thinking. At the core of SmartRAG is EvoNER, a continually learna"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14661","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/2607.14661/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":"2607.14661","created_at":"2026-07-17T01:21:23.735718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14661v1","created_at":"2026-07-17T01:21:23.735718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14661","created_at":"2026-07-17T01:21:23.735718+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHKKGIHJ3ZT5","created_at":"2026-07-17T01:21:23.735718+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHKKGIHJ3ZT5YTYL","created_at":"2026-07-17T01:21:23.735718+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHKKGIHJ","created_at":"2026-07-17T01:21:23.735718+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/CHKKGIHJ3ZT5YTYLT6SNPIOREX","json":"https://pith.science/pith/CHKKGIHJ3ZT5YTYLT6SNPIOREX.json","graph_json":"https://pith.science/api/pith-number/CHKKGIHJ3ZT5YTYLT6SNPIOREX/graph.json","events_json":"https://pith.science/api/pith-number/CHKKGIHJ3ZT5YTYLT6SNPIOREX/events.json","paper":"https://pith.science/paper/CHKKGIHJ"},"agent_actions":{"view_html":"https://pith.science/pith/CHKKGIHJ3ZT5YTYLT6SNPIOREX","download_json":"https://pith.science/pith/CHKKGIHJ3ZT5YTYLT6SNPIOREX.json","view_paper":"https://pith.science/paper/CHKKGIHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14661&json=true","fetch_graph":"https://pith.science/api/pith-number/CHKKGIHJ3ZT5YTYLT6SNPIOREX/graph.json","fetch_events":"https://pith.science/api/pith-number/CHKKGIHJ3ZT5YTYLT6SNPIOREX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHKKGIHJ3ZT5YTYLT6SNPIOREX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHKKGIHJ3ZT5YTYLT6SNPIOREX/action/storage_attestation","attest_author":"https://pith.science/pith/CHKKGIHJ3ZT5YTYLT6SNPIOREX/action/author_attestation","sign_citation":"https://pith.science/pith/CHKKGIHJ3ZT5YTYLT6SNPIOREX/action/citation_signature","submit_replication":"https://pith.science/pith/CHKKGIHJ3ZT5YTYLT6SNPIOREX/action/replication_record"}},"created_at":"2026-07-17T01:21:23.735718+00:00","updated_at":"2026-07-17T01:21:23.735718+00:00"}