{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AG62CRRJLGW227W6W6A27WHDRC","short_pith_number":"pith:AG62CRRJ","canonical_record":{"source":{"id":"2410.08661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T09:39:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a17beb8910dc9e7221c44daeb88661ca25e2071a72133098a9c3ee6a9a90f56","abstract_canon_sha256":"adfbb96f9652d8ce876fe501486fdd5b48df8e28098f6e2ae153d4b83678be64"},"schema_version":"1.0"},"canonical_sha256":"01bda1462959adad7edeb781afd8e388bd73128515e5b5eedc3fb1e7aae1dfe0","source":{"kind":"arxiv","id":"2410.08661","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08661","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08661v1","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08661","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"AG62CRRJLGW2","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"AG62CRRJLGW227W6","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"AG62CRRJ","created_at":"2026-07-05T09:19:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AG62CRRJLGW227W6W6A27WHDRC","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T09:39:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a17beb8910dc9e7221c44daeb88661ca25e2071a72133098a9c3ee6a9a90f56","abstract_canon_sha256":"adfbb96f9652d8ce876fe501486fdd5b48df8e28098f6e2ae153d4b83678be64"},"schema_version":"1.0"},"canonical_sha256":"01bda1462959adad7edeb781afd8e388bd73128515e5b5eedc3fb1e7aae1dfe0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:15.811312Z","signature_b64":"G+RZZRNTdLY8zp+zXWRyunq8ffK4HjmImR3lMOKXgYSF2wRHgJaKxUzs94LKC04gOPY9TUEujpn5IwfdmdKmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01bda1462959adad7edeb781afd8e388bd73128515e5b5eedc3fb1e7aae1dfe0","last_reissued_at":"2026-07-05T09:19:15.810896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:15.810896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08661","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5P9IkMjzIB7siqfsoVDy3t3aj4ZpW6uQDG2ZYtOJ7+84bBdEDeQLa4pnExYWWgqfZxdRb7zVtKfUAIUa5bAkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T16:59:34.434697Z"},"content_sha256":"86588796a7cc8b09481f43907cb2485c74ec863b8a745653db6309f980751096","schema_version":"1.0","event_id":"sha256:86588796a7cc8b09481f43907cb2485c74ec863b8a745653db6309f980751096"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AG62CRRJLGW227W6W6A27WHDRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QEFT: Quantization for Efficient Fine-Tuning of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Changhun Lee, Eunhyeok Park, Jun-gyu Jin, Younghyun Cho","submitted_at":"2024-10-11T09:39:33Z","abstract_excerpt":"With the rapid growth in the use of fine-tuning for large language models (LLMs), optimizing fine-tuning while keeping inference efficient has become highly important. However, this is a challenging task as it requires improvements in all aspects, including inference speed, fine-tuning speed, memory consumption, and, most importantly, model quality. Previous studies have attempted to achieve this by combining quantization with fine-tuning, but they have failed to enhance all four aspects simultaneously. In this study, we propose a new lightweight technique called Quantization for Efficient Fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08661","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/2410.08661/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kiM9kqQFeQid9GW/79dk2NbBC7cEHjGF5CPfNSh6oISncuOziIEcu41UV5qY5cBYpJx/apm5zFm2c/FpCO20Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T16:59:34.435294Z"},"content_sha256":"51d12b986377814b34cd3739d12f60c96b12b36802d04a37bf46aa9c83d17d84","schema_version":"1.0","event_id":"sha256:51d12b986377814b34cd3739d12f60c96b12b36802d04a37bf46aa9c83d17d84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AG62CRRJLGW227W6W6A27WHDRC/bundle.json","state_url":"https://pith.science/pith/AG62CRRJLGW227W6W6A27WHDRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AG62CRRJLGW227W6W6A27WHDRC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T16:59:34Z","links":{"resolver":"https://pith.science/pith/AG62CRRJLGW227W6W6A27WHDRC","bundle":"https://pith.science/pith/AG62CRRJLGW227W6W6A27WHDRC/bundle.json","state":"https://pith.science/pith/AG62CRRJLGW227W6W6A27WHDRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AG62CRRJLGW227W6W6A27WHDRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AG62CRRJLGW227W6W6A27WHDRC","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":"adfbb96f9652d8ce876fe501486fdd5b48df8e28098f6e2ae153d4b83678be64","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T09:39:33Z","title_canon_sha256":"4a17beb8910dc9e7221c44daeb88661ca25e2071a72133098a9c3ee6a9a90f56"},"schema_version":"1.0","source":{"id":"2410.08661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08661","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08661v1","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08661","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"AG62CRRJLGW2","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"AG62CRRJLGW227W6","created_at":"2026-07-05T09:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"AG62CRRJ","created_at":"2026-07-05T09:19:15Z"}],"graph_snapshots":[{"event_id":"sha256:51d12b986377814b34cd3739d12f60c96b12b36802d04a37bf46aa9c83d17d84","target":"graph","created_at":"2026-07-05T09:19:15Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.08661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid growth in the use of fine-tuning for large language models (LLMs), optimizing fine-tuning while keeping inference efficient has become highly important. However, this is a challenging task as it requires improvements in all aspects, including inference speed, fine-tuning speed, memory consumption, and, most importantly, model quality. Previous studies have attempted to achieve this by combining quantization with fine-tuning, but they have failed to enhance all four aspects simultaneously. In this study, we propose a new lightweight technique called Quantization for Efficient Fin","authors_text":"Changhun Lee, Eunhyeok Park, Jun-gyu Jin, Younghyun Cho","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T09:39:33Z","title":"QEFT: Quantization for Efficient Fine-Tuning of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08661","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:86588796a7cc8b09481f43907cb2485c74ec863b8a745653db6309f980751096","target":"record","created_at":"2026-07-05T09:19:15Z","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":"adfbb96f9652d8ce876fe501486fdd5b48df8e28098f6e2ae153d4b83678be64","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T09:39:33Z","title_canon_sha256":"4a17beb8910dc9e7221c44daeb88661ca25e2071a72133098a9c3ee6a9a90f56"},"schema_version":"1.0","source":{"id":"2410.08661","kind":"arxiv","version":1}},"canonical_sha256":"01bda1462959adad7edeb781afd8e388bd73128515e5b5eedc3fb1e7aae1dfe0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01bda1462959adad7edeb781afd8e388bd73128515e5b5eedc3fb1e7aae1dfe0","first_computed_at":"2026-07-05T09:19:15.810896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:15.810896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G+RZZRNTdLY8zp+zXWRyunq8ffK4HjmImR3lMOKXgYSF2wRHgJaKxUzs94LKC04gOPY9TUEujpn5IwfdmdKmDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:15.811312Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86588796a7cc8b09481f43907cb2485c74ec863b8a745653db6309f980751096","sha256:51d12b986377814b34cd3739d12f60c96b12b36802d04a37bf46aa9c83d17d84"],"state_sha256":"d39be6802f025aa2604a20149709c6a17c1493a10db2ae28fcbf51a69b7013e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wo0tOCeyy7sVQPNpPlevIl9bzIWIAg/C1Hj7cfrm+iBtwpnXmxMfHrhKbIYkgfVLBASC/D2AkUzBMCTS0ly5CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T16:59:34.440102Z","bundle_sha256":"8b12a18a19d3857a618c4a98487f1a1b4634aa8fc871abe603c2e3dee443032b"}}