{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WGGUTYKMS5MERJ2J467CGKHVFG","short_pith_number":"pith:WGGUTYKM","schema_version":"1.0","canonical_sha256":"b18d49e14c975848a749e7be2328f529a42a9b3ba3d88d308edcf85589c52f61","source":{"kind":"arxiv","id":"2410.09407","version":1},"attestation_state":"computed","paper":{"title":"CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jianpeng Cheng, Raviteja Anantha, Yicheng Fu","submitted_at":"2024-10-12T07:28:10Z","abstract_excerpt":"While server-side Large Language Models (LLMs) demonstrate proficiency in function calling and complex reasoning, deploying Small Language Models (SLMs) directly on devices brings opportunities to improve latency and privacy but also introduces unique challenges for accuracy and memory. We introduce CAMPHOR, an innovative on-device SLM multi-agent framework designed to handle multiple user inputs and reason over personal context locally, ensuring privacy is maintained. CAMPHOR employs a hierarchical architecture where a high-order reasoning agent decomposes complex tasks and coordinates expert"},"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":"2410.09407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T07:28:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"48fdf1a6739d0d2955fdeb310d3518795c2ab80ba10796f9d336d6334362fe24","abstract_canon_sha256":"490f8d8557520b9054b45c7130c0ec38a6d733598d67b502ea213bd8839167d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:38.908497Z","signature_b64":"//B7COJod6ImXkCzM0O3tP5caAMJphi6EwGPybh0C/tYtZrkbv9p+MWlL/IgGT9jfP4ZQ9PwnM+yBdeDyC5xAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b18d49e14c975848a749e7be2328f529a42a9b3ba3d88d308edcf85589c52f61","last_reissued_at":"2026-07-05T09:19:38.908045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:38.908045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jianpeng Cheng, Raviteja Anantha, Yicheng Fu","submitted_at":"2024-10-12T07:28:10Z","abstract_excerpt":"While server-side Large Language Models (LLMs) demonstrate proficiency in function calling and complex reasoning, deploying Small Language Models (SLMs) directly on devices brings opportunities to improve latency and privacy but also introduces unique challenges for accuracy and memory. We introduce CAMPHOR, an innovative on-device SLM multi-agent framework designed to handle multiple user inputs and reason over personal context locally, ensuring privacy is maintained. CAMPHOR employs a hierarchical architecture where a high-order reasoning agent decomposes complex tasks and coordinates expert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09407","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/2410.09407/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":"2410.09407","created_at":"2026-07-05T09:19:38.908102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09407v1","created_at":"2026-07-05T09:19:38.908102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09407","created_at":"2026-07-05T09:19:38.908102+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGGUTYKMS5ME","created_at":"2026-07-05T09:19:38.908102+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGGUTYKMS5MERJ2J","created_at":"2026-07-05T09:19:38.908102+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGGUTYKM","created_at":"2026-07-05T09:19:38.908102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25602","citing_title":"OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03804","citing_title":"ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGGUTYKMS5MERJ2J467CGKHVFG","json":"https://pith.science/pith/WGGUTYKMS5MERJ2J467CGKHVFG.json","graph_json":"https://pith.science/api/pith-number/WGGUTYKMS5MERJ2J467CGKHVFG/graph.json","events_json":"https://pith.science/api/pith-number/WGGUTYKMS5MERJ2J467CGKHVFG/events.json","paper":"https://pith.science/paper/WGGUTYKM"},"agent_actions":{"view_html":"https://pith.science/pith/WGGUTYKMS5MERJ2J467CGKHVFG","download_json":"https://pith.science/pith/WGGUTYKMS5MERJ2J467CGKHVFG.json","view_paper":"https://pith.science/paper/WGGUTYKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09407&json=true","fetch_graph":"https://pith.science/api/pith-number/WGGUTYKMS5MERJ2J467CGKHVFG/graph.json","fetch_events":"https://pith.science/api/pith-number/WGGUTYKMS5MERJ2J467CGKHVFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGGUTYKMS5MERJ2J467CGKHVFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGGUTYKMS5MERJ2J467CGKHVFG/action/storage_attestation","attest_author":"https://pith.science/pith/WGGUTYKMS5MERJ2J467CGKHVFG/action/author_attestation","sign_citation":"https://pith.science/pith/WGGUTYKMS5MERJ2J467CGKHVFG/action/citation_signature","submit_replication":"https://pith.science/pith/WGGUTYKMS5MERJ2J467CGKHVFG/action/replication_record"}},"created_at":"2026-07-05T09:19:38.908102+00:00","updated_at":"2026-07-05T09:19:38.908102+00:00"}