{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WYCZPCTLQF6EV3DG2PY6NRCQGB","short_pith_number":"pith:WYCZPCTL","schema_version":"1.0","canonical_sha256":"b605978a6b817c4aec66d3f1e6c4503050f3f8e783ff7176bc22c075f7c8b36f","source":{"kind":"arxiv","id":"2501.09367","version":1},"attestation_state":"computed","paper":{"title":"PICE: A Semantic-Driven Progressive Inference System for LLM Serving in Cloud-Edge Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Dongping Yong, Haisheng Tan, Han Tian, Huiyou Zhan, Junyang Zhang, Xiang-Yang Li, Xuan Zhang","submitted_at":"2025-01-16T08:25:07Z","abstract_excerpt":"Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a progressive inference paradigm over cloud and edge, i.e., firstly generating the sketch of the answer by LLMs at cloud, and then conducting parallel extension to fill in details by small models (SLMs) at edge. Progressive inference offers potential benefits to improve throughput and reduce inference latency while facing key implementation challenges, includi"},"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":"2501.09367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-16T08:25:07Z","cross_cats_sorted":[],"title_canon_sha256":"e0e95b039ac1a3fe81b0d96d67d78c0ba659ca3a9134b3879390a9927f0299f1","abstract_canon_sha256":"c069dcab8064abadac3da197b7d66bd907bb14ba66871fd03291ff82ea4ff5d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:45.868301Z","signature_b64":"nmNnn4+qYsKrlhMebvx0JBJduwdBDdoGLnBFvRXbv6bBXUWzrGnJ8QvY72xrtzIun+In4lE8I1Ay3+Ck4U5kAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b605978a6b817c4aec66d3f1e6c4503050f3f8e783ff7176bc22c075f7c8b36f","last_reissued_at":"2026-07-05T10:01:45.867800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:45.867800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PICE: A Semantic-Driven Progressive Inference System for LLM Serving in Cloud-Edge Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Dongping Yong, Haisheng Tan, Han Tian, Huiyou Zhan, Junyang Zhang, Xiang-Yang Li, Xuan Zhang","submitted_at":"2025-01-16T08:25:07Z","abstract_excerpt":"Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a progressive inference paradigm over cloud and edge, i.e., firstly generating the sketch of the answer by LLMs at cloud, and then conducting parallel extension to fill in details by small models (SLMs) at edge. Progressive inference offers potential benefits to improve throughput and reduce inference latency while facing key implementation challenges, includi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09367","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/2501.09367/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":"2501.09367","created_at":"2026-07-05T10:01:45.867868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09367v1","created_at":"2026-07-05T10:01:45.867868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09367","created_at":"2026-07-05T10:01:45.867868+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYCZPCTLQF6E","created_at":"2026-07-05T10:01:45.867868+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYCZPCTLQF6EV3DG","created_at":"2026-07-05T10:01:45.867868+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYCZPCTL","created_at":"2026-07-05T10:01:45.867868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16731","citing_title":"Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYCZPCTLQF6EV3DG2PY6NRCQGB","json":"https://pith.science/pith/WYCZPCTLQF6EV3DG2PY6NRCQGB.json","graph_json":"https://pith.science/api/pith-number/WYCZPCTLQF6EV3DG2PY6NRCQGB/graph.json","events_json":"https://pith.science/api/pith-number/WYCZPCTLQF6EV3DG2PY6NRCQGB/events.json","paper":"https://pith.science/paper/WYCZPCTL"},"agent_actions":{"view_html":"https://pith.science/pith/WYCZPCTLQF6EV3DG2PY6NRCQGB","download_json":"https://pith.science/pith/WYCZPCTLQF6EV3DG2PY6NRCQGB.json","view_paper":"https://pith.science/paper/WYCZPCTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09367&json=true","fetch_graph":"https://pith.science/api/pith-number/WYCZPCTLQF6EV3DG2PY6NRCQGB/graph.json","fetch_events":"https://pith.science/api/pith-number/WYCZPCTLQF6EV3DG2PY6NRCQGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYCZPCTLQF6EV3DG2PY6NRCQGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYCZPCTLQF6EV3DG2PY6NRCQGB/action/storage_attestation","attest_author":"https://pith.science/pith/WYCZPCTLQF6EV3DG2PY6NRCQGB/action/author_attestation","sign_citation":"https://pith.science/pith/WYCZPCTLQF6EV3DG2PY6NRCQGB/action/citation_signature","submit_replication":"https://pith.science/pith/WYCZPCTLQF6EV3DG2PY6NRCQGB/action/replication_record"}},"created_at":"2026-07-05T10:01:45.867868+00:00","updated_at":"2026-07-05T10:01:45.867868+00:00"}