{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NRJKRC3HMM37JUYJTAHHXVLUPF","short_pith_number":"pith:NRJKRC3H","schema_version":"1.0","canonical_sha256":"6c52a88b676337f4d309980e7bd574796c91aaa0a35e6979a0e3d0eb2bc88e68","source":{"kind":"arxiv","id":"2402.04902","version":6},"attestation_state":"computed","paper":{"title":"L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hyesung Jeon, Jae-Joon Kim, Yulhwa Kim","submitted_at":"2024-02-07T14:35:05Z","abstract_excerpt":"Due to the high memory and computational costs associated with large language models (LLMs), model compression techniques such as quantization, which reduces inference costs, and parameter-efficient fine-tuning (PEFT) methods like Low-Rank Adaptation (LoRA), which reduce training costs, have gained significant popularity. This trend has spurred active research into quantization-aware PEFT techniques, aimed at maintaining model accuracy while minimizing memory overhead during both inference and training. Previous quantization-aware PEFT methods typically apply post-training quantization (PTQ) t"},"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":"2402.04902","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T14:35:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"436d52076513d8ff2ae6498714b62f593df1555ebebe44af005363fb1ff371b0","abstract_canon_sha256":"3e4ec7df0f2ce9d96ca73833c594164e50fbe8103373a22c3d9d6031cafb00a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:47.650627Z","signature_b64":"VF2G42GAfMF9xOES/+uNGXrEjFXYljnGiVkgySEG8oVKG35XtLFtvhOeMz3L76KgMhv6LG7CvLGwml5qXkyqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c52a88b676337f4d309980e7bd574796c91aaa0a35e6979a0e3d0eb2bc88e68","last_reissued_at":"2026-07-05T11:40:47.650074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:47.650074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hyesung Jeon, Jae-Joon Kim, Yulhwa Kim","submitted_at":"2024-02-07T14:35:05Z","abstract_excerpt":"Due to the high memory and computational costs associated with large language models (LLMs), model compression techniques such as quantization, which reduces inference costs, and parameter-efficient fine-tuning (PEFT) methods like Low-Rank Adaptation (LoRA), which reduce training costs, have gained significant popularity. This trend has spurred active research into quantization-aware PEFT techniques, aimed at maintaining model accuracy while minimizing memory overhead during both inference and training. Previous quantization-aware PEFT methods typically apply post-training quantization (PTQ) t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04902","kind":"arxiv","version":6},"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/2402.04902/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":"2402.04902","created_at":"2026-07-05T11:40:47.650140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04902v6","created_at":"2026-07-05T11:40:47.650140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04902","created_at":"2026-07-05T11:40:47.650140+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRJKRC3HMM37","created_at":"2026-07-05T11:40:47.650140+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRJKRC3HMM37JUYJ","created_at":"2026-07-05T11:40:47.650140+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRJKRC3H","created_at":"2026-07-05T11:40:47.650140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04063","citing_title":"LLM Compression with Jointly Optimizing Architectural and Quantization choices","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NRJKRC3HMM37JUYJTAHHXVLUPF","json":"https://pith.science/pith/NRJKRC3HMM37JUYJTAHHXVLUPF.json","graph_json":"https://pith.science/api/pith-number/NRJKRC3HMM37JUYJTAHHXVLUPF/graph.json","events_json":"https://pith.science/api/pith-number/NRJKRC3HMM37JUYJTAHHXVLUPF/events.json","paper":"https://pith.science/paper/NRJKRC3H"},"agent_actions":{"view_html":"https://pith.science/pith/NRJKRC3HMM37JUYJTAHHXVLUPF","download_json":"https://pith.science/pith/NRJKRC3HMM37JUYJTAHHXVLUPF.json","view_paper":"https://pith.science/paper/NRJKRC3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04902&json=true","fetch_graph":"https://pith.science/api/pith-number/NRJKRC3HMM37JUYJTAHHXVLUPF/graph.json","fetch_events":"https://pith.science/api/pith-number/NRJKRC3HMM37JUYJTAHHXVLUPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRJKRC3HMM37JUYJTAHHXVLUPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRJKRC3HMM37JUYJTAHHXVLUPF/action/storage_attestation","attest_author":"https://pith.science/pith/NRJKRC3HMM37JUYJTAHHXVLUPF/action/author_attestation","sign_citation":"https://pith.science/pith/NRJKRC3HMM37JUYJTAHHXVLUPF/action/citation_signature","submit_replication":"https://pith.science/pith/NRJKRC3HMM37JUYJTAHHXVLUPF/action/replication_record"}},"created_at":"2026-07-05T11:40:47.650140+00:00","updated_at":"2026-07-05T11:40:47.650140+00:00"}