{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L2AXAXIYPTCTLUDDHHM3XLYQQ5","short_pith_number":"pith:L2AXAXIY","schema_version":"1.0","canonical_sha256":"5e81705d187cc535d06339d9bbaf10876b64c9a86d85efd4dcc1ae5e4fdd4265","source":{"kind":"arxiv","id":"2507.16731","version":1},"attestation_state":"computed","paper":{"title":"Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Haozhao Wang, Jingling Yuan, Ruixuan Li, Rui Zhang, Senyao Li, Song Guo, Tianwei Zhang, Wenchao Xu, Xian Zhong","submitted_at":"2025-07-22T16:13:43Z","abstract_excerpt":"As large language models (LLMs) evolve, deploying them solely in the cloud or compressing them for edge devices has become inadequate due to concerns about latency, privacy, cost, and personalization. This survey explores a collaborative paradigm in which cloud-based LLMs and edge-deployed small language models (SLMs) cooperate across both inference and training. We present a unified taxonomy of edge-cloud collaboration strategies. For inference, we categorize approaches into task assignment, task division, and mixture-based collaboration at both task and token granularity, encompassing adapti"},"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":"2507.16731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-07-22T16:13:43Z","cross_cats_sorted":[],"title_canon_sha256":"9b519c1ba24dab241b066f8c242b8144d885ee237646946d04c0da8ffc13a5c2","abstract_canon_sha256":"cb2c70c36dc9f954c056d72f2d26147142a6686a37dc5def8fe9c8693466c576"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:30.042278Z","signature_b64":"bhGMo+KutTL0q8oOHe19FHvoQcaTPFVn1dUDotMggZz7jJ0Wh1XSUL97SM1/5PH/kzRuiG62YCkMpW9ihkwZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e81705d187cc535d06339d9bbaf10876b64c9a86d85efd4dcc1ae5e4fdd4265","last_reissued_at":"2026-07-05T11:41:30.041779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:30.041779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Haozhao Wang, Jingling Yuan, Ruixuan Li, Rui Zhang, Senyao Li, Song Guo, Tianwei Zhang, Wenchao Xu, Xian Zhong","submitted_at":"2025-07-22T16:13:43Z","abstract_excerpt":"As large language models (LLMs) evolve, deploying them solely in the cloud or compressing them for edge devices has become inadequate due to concerns about latency, privacy, cost, and personalization. This survey explores a collaborative paradigm in which cloud-based LLMs and edge-deployed small language models (SLMs) cooperate across both inference and training. We present a unified taxonomy of edge-cloud collaboration strategies. For inference, we categorize approaches into task assignment, task division, and mixture-based collaboration at both task and token granularity, encompassing adapti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16731","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/2507.16731/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":"2507.16731","created_at":"2026-07-05T11:41:30.041846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16731v1","created_at":"2026-07-05T11:41:30.041846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16731","created_at":"2026-07-05T11:41:30.041846+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2AXAXIYPTCT","created_at":"2026-07-05T11:41:30.041846+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2AXAXIYPTCTLUDD","created_at":"2026-07-05T11:41:30.041846+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2AXAXIY","created_at":"2026-07-05T11:41:30.041846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25716","citing_title":"An Efficient and Privacy-Preserving Architecture for Cross-Institutional Collaborative RAG","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16630","citing_title":"PrivScope: Task-scoped Disclosure Control for Hybrid Agentic Systems","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27112","citing_title":"RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07767","citing_title":"Administrative Decentralization in Edge-Cloud Multi-Agent for Mobile Automation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17227","citing_title":"Cloud-native and Distributed Systems for Efficient and Scalable Large Language Models -- A Research Agenda","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2AXAXIYPTCTLUDDHHM3XLYQQ5","json":"https://pith.science/pith/L2AXAXIYPTCTLUDDHHM3XLYQQ5.json","graph_json":"https://pith.science/api/pith-number/L2AXAXIYPTCTLUDDHHM3XLYQQ5/graph.json","events_json":"https://pith.science/api/pith-number/L2AXAXIYPTCTLUDDHHM3XLYQQ5/events.json","paper":"https://pith.science/paper/L2AXAXIY"},"agent_actions":{"view_html":"https://pith.science/pith/L2AXAXIYPTCTLUDDHHM3XLYQQ5","download_json":"https://pith.science/pith/L2AXAXIYPTCTLUDDHHM3XLYQQ5.json","view_paper":"https://pith.science/paper/L2AXAXIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16731&json=true","fetch_graph":"https://pith.science/api/pith-number/L2AXAXIYPTCTLUDDHHM3XLYQQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/L2AXAXIYPTCTLUDDHHM3XLYQQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2AXAXIYPTCTLUDDHHM3XLYQQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2AXAXIYPTCTLUDDHHM3XLYQQ5/action/storage_attestation","attest_author":"https://pith.science/pith/L2AXAXIYPTCTLUDDHHM3XLYQQ5/action/author_attestation","sign_citation":"https://pith.science/pith/L2AXAXIYPTCTLUDDHHM3XLYQQ5/action/citation_signature","submit_replication":"https://pith.science/pith/L2AXAXIYPTCTLUDDHHM3XLYQQ5/action/replication_record"}},"created_at":"2026-07-05T11:41:30.041846+00:00","updated_at":"2026-07-05T11:41:30.041846+00:00"}