{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:APEUIO7KERA7QI6KETHDBSG7PG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"206675ea5466bbc53114fd921373a1cf2f9c685a2a656bca4697848b74d6ecc9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-22T11:07:50Z","title_canon_sha256":"abbfc27828e4645993eee55e963cc2ba42e476eabf42094228462acdad3626c7"},"schema_version":"1.0","source":{"id":"2509.25214","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.25214","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"2509.25214v4","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.25214","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"APEUIO7KERA7","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"APEUIO7KERA7QI6K","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"APEUIO7K","created_at":"2026-06-23T02:13:17Z"}],"graph_snapshots":[{"event_id":"sha256:246d21efca166d0019c65548cccf5bc929748f53bca0c929dd24bdde3caa2c3e","target":"graph","created_at":"2026-06-23T02:13:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CoA-LoRA dynamically adjusts the LoRA adapter to arbitrary quantization configurations without requiring repeated fine-tuning and achieves comparable or superior performance to state-of-the-art methods that fine-tune a separate LoRA adapter for each configuration."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The configuration-aware model can accurately predict low-rank adjustments for unseen quantization configurations when trained only on a Pareto-selected subset of configurations that cover different total bit-width budgets."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CoA-LoRA trains a single configuration-aware model on a Pareto-optimized set of quantization configurations to enable dynamic LoRA adaptation to arbitrary bit-width assignments without per-configuration fine-tuning."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single configuration-aware model generates effective LoRA adjustments for any quantization setting of an LLM without retraining per configuration."}],"snapshot_sha256":"feac72112f5f4f2b596bfb1a9ff5e67f9fa16e4eb4d458372db1fcb8c227d842"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d5a6c1ab72ef4a06457ff43482d5ad8e5646e8a7a417f930a2881632d3ba2ca1"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.25214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As increasingly large pre-trained models are released, deploying them on edge devices for privacy-preserving applications requires effective compression. Recent works combine quantization with the fine-tuning of high-precision LoRA adapters, which can substantially reduce model size while mitigating the accuracy loss from quantization. However, edge devices have inherently heterogeneous capabilities, while performing configuration-wise fine-tuning for every quantization setting is computationally prohibitive. In this paper, we propose CoA-LoRA, a method that dynamically adjusts the LoRA adapte","authors_text":"Edith C. H. Ngai, Ming Tang, Rongguang Ye","cross_cats":["cs.AI"],"headline":"A single configuration-aware model generates effective LoRA adjustments for any quantization setting of an LLM without retraining per configuration.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-22T11:07:50Z","title":"On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.25214","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-18T13:49:52.475415Z","id":"005bcfd4-597f-4294-9493-a6a2f653299c","model_set":{"reader":"grok-4.3"},"one_line_summary":"CoA-LoRA trains a single configuration-aware model on a Pareto-optimized set of quantization configurations to enable dynamic LoRA adaptation to arbitrary bit-width assignments without per-configuration fine-tuning.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single configuration-aware model generates effective LoRA adjustments for any quantization setting of an LLM without retraining per configuration.","strongest_claim":"CoA-LoRA dynamically adjusts the LoRA adapter to arbitrary quantization configurations without requiring repeated fine-tuning and achieves comparable or superior performance to state-of-the-art methods that fine-tune a separate LoRA adapter for each configuration.","weakest_assumption":"The configuration-aware model can accurately predict low-rank adjustments for unseen quantization configurations when trained only on a Pareto-selected subset of configurations that cover different total bit-width budgets."}},"verdict_id":"005bcfd4-597f-4294-9493-a6a2f653299c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1ff85eda6a18a7487e01acf2adad010f5dea67fd0f18cef49c780796585d7d54","target":"record","created_at":"2026-06-23T02:13:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"206675ea5466bbc53114fd921373a1cf2f9c685a2a656bca4697848b74d6ecc9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-22T11:07:50Z","title_canon_sha256":"abbfc27828e4645993eee55e963cc2ba42e476eabf42094228462acdad3626c7"},"schema_version":"1.0","source":{"id":"2509.25214","kind":"arxiv","version":4}},"canonical_sha256":"03c9443bea2441f823ca24ce30c8df799aa0bf2c6c6c0e9893e7f142c1c48b75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03c9443bea2441f823ca24ce30c8df799aa0bf2c6c6c0e9893e7f142c1c48b75","first_computed_at":"2026-06-23T02:13:17.155161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:17.155161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"didfKrpQmYS20G/x7yRH2vGsR/Poh9Gkzcv5Ujr4Vwb0qE0NCtzCZlZCRRWK5x0Qnj74aU4Jk0l73+qo8BWtAA==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:17.155681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.25214","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ff85eda6a18a7487e01acf2adad010f5dea67fd0f18cef49c780796585d7d54","sha256:246d21efca166d0019c65548cccf5bc929748f53bca0c929dd24bdde3caa2c3e"],"state_sha256":"5f385b47c845fd57c463b125a675266497182e8851aafa2c3d60c810c775982e"}