{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:37OXJOHNJ4UUW2LCHJGLZ3KAHU","short_pith_number":"pith:37OXJOHN","schema_version":"1.0","canonical_sha256":"dfdd74b8ed4f294b69623a4cbced403d3cc2cef8a47846d757aaf076d3da6876","source":{"kind":"arxiv","id":"2604.16400","version":2},"attestation_state":"computed","paper":{"title":"CoLLM: Continuous Adaptation for SLO-Aware LLM Serving on Shared GPU Clusters","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DC","authors_text":"Na Yan, Shaoyuan Huang, Tiancheng Zhang, Wenyu Wang, Xiaofei Wang, Xiaokai Wang, Yansha Deng, Yunfeng Zhao","submitted_at":"2026-03-31T09:49:47Z","abstract_excerpt":"As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domain-specific applications and personalized services, the quality and efficiency of the LLM post-training phase-including fine-tuning and inference, have become critical due to constrained resources. Although recent advances in federated parameter-efficient fine-tuning (FL PEFT) and low-latency inference have improved individual task performance, fine-tuning and inference are still handled as isolated workloads, which overlooks their interdependence and results in redundant deployments and delayed improvem"},"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":"2604.16400","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-03-31T09:49:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3fe01046848d74d05da32219038fe0fcbef897e177ccf8bf58660806f9a9ba46","abstract_canon_sha256":"e139ad95cfc1865f9c91c09719816564215cec5599db475de3cdbbe6518c34f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:11.594105Z","signature_b64":"VnepsDuvhDqR6atCmMxWKTPgRJGiFOiZrhW9aZIgVlW7BR2hCqdatBjn3OQyXaF5f9oSreUOXoTj4beE0xiWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfdd74b8ed4f294b69623a4cbced403d3cc2cef8a47846d757aaf076d3da6876","last_reissued_at":"2026-05-20T00:02:11.593432Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:11.593432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoLLM: Continuous Adaptation for SLO-Aware LLM Serving on Shared GPU Clusters","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DC","authors_text":"Na Yan, Shaoyuan Huang, Tiancheng Zhang, Wenyu Wang, Xiaofei Wang, Xiaokai Wang, Yansha Deng, Yunfeng Zhao","submitted_at":"2026-03-31T09:49:47Z","abstract_excerpt":"As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domain-specific applications and personalized services, the quality and efficiency of the LLM post-training phase-including fine-tuning and inference, have become critical due to constrained resources. Although recent advances in federated parameter-efficient fine-tuning (FL PEFT) and low-latency inference have improved individual task performance, fine-tuning and inference are still handled as isolated workloads, which overlooks their interdependence and results in redundant deployments and delayed improvem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.16400","kind":"arxiv","version":2},"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/2604.16400/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":"2604.16400","created_at":"2026-05-20T00:02:11.593530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.16400v2","created_at":"2026-05-20T00:02:11.593530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.16400","created_at":"2026-05-20T00:02:11.593530+00:00"},{"alias_kind":"pith_short_12","alias_value":"37OXJOHNJ4UU","created_at":"2026-05-20T00:02:11.593530+00:00"},{"alias_kind":"pith_short_16","alias_value":"37OXJOHNJ4UUW2LC","created_at":"2026-05-20T00:02:11.593530+00:00"},{"alias_kind":"pith_short_8","alias_value":"37OXJOHN","created_at":"2026-05-20T00:02:11.593530+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/37OXJOHNJ4UUW2LCHJGLZ3KAHU","json":"https://pith.science/pith/37OXJOHNJ4UUW2LCHJGLZ3KAHU.json","graph_json":"https://pith.science/api/pith-number/37OXJOHNJ4UUW2LCHJGLZ3KAHU/graph.json","events_json":"https://pith.science/api/pith-number/37OXJOHNJ4UUW2LCHJGLZ3KAHU/events.json","paper":"https://pith.science/paper/37OXJOHN"},"agent_actions":{"view_html":"https://pith.science/pith/37OXJOHNJ4UUW2LCHJGLZ3KAHU","download_json":"https://pith.science/pith/37OXJOHNJ4UUW2LCHJGLZ3KAHU.json","view_paper":"https://pith.science/paper/37OXJOHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.16400&json=true","fetch_graph":"https://pith.science/api/pith-number/37OXJOHNJ4UUW2LCHJGLZ3KAHU/graph.json","fetch_events":"https://pith.science/api/pith-number/37OXJOHNJ4UUW2LCHJGLZ3KAHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37OXJOHNJ4UUW2LCHJGLZ3KAHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37OXJOHNJ4UUW2LCHJGLZ3KAHU/action/storage_attestation","attest_author":"https://pith.science/pith/37OXJOHNJ4UUW2LCHJGLZ3KAHU/action/author_attestation","sign_citation":"https://pith.science/pith/37OXJOHNJ4UUW2LCHJGLZ3KAHU/action/citation_signature","submit_replication":"https://pith.science/pith/37OXJOHNJ4UUW2LCHJGLZ3KAHU/action/replication_record"}},"created_at":"2026-05-20T00:02:11.593530+00:00","updated_at":"2026-05-20T00:02:11.593530+00:00"}