{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BYAQDRMYD7P6P7TDQ2R54EUB4C","short_pith_number":"pith:BYAQDRMY","canonical_record":{"source":{"id":"2306.08162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T22:25:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c154aa421560b7f94812faf45db8f5ef1c90f265c0c9545f5dacbbb5293a7640","abstract_canon_sha256":"e8bd91a3637ef9d318dfc1d9bbb54abdcd64fec09f98948d21ea2c9cd21aae6c"},"schema_version":"1.0"},"canonical_sha256":"0e0101c5981fdfe7fe6386a3de1281e081e6ee04c9d9055a4ca50d0773ec4ba9","source":{"kind":"arxiv","id":"2306.08162","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08162","created_at":"2026-07-05T06:20:48Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08162v1","created_at":"2026-07-05T06:20:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08162","created_at":"2026-07-05T06:20:48Z"},{"alias_kind":"pith_short_12","alias_value":"BYAQDRMYD7P6","created_at":"2026-07-05T06:20:48Z"},{"alias_kind":"pith_short_16","alias_value":"BYAQDRMYD7P6P7TD","created_at":"2026-07-05T06:20:48Z"},{"alias_kind":"pith_short_8","alias_value":"BYAQDRMY","created_at":"2026-07-05T06:20:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BYAQDRMYD7P6P7TDQ2R54EUB4C","target":"record","payload":{"canonical_record":{"source":{"id":"2306.08162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T22:25:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c154aa421560b7f94812faf45db8f5ef1c90f265c0c9545f5dacbbb5293a7640","abstract_canon_sha256":"e8bd91a3637ef9d318dfc1d9bbb54abdcd64fec09f98948d21ea2c9cd21aae6c"},"schema_version":"1.0"},"canonical_sha256":"0e0101c5981fdfe7fe6386a3de1281e081e6ee04c9d9055a4ca50d0773ec4ba9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:48.851759Z","signature_b64":"+Krt8ujRIygiNmPFE7uEk+c2J8fxegTUJD6gIg2MCQRuZ2M/NC0nQ2PCkbSfP9WGcuvWYudKv96krtXZxdYwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e0101c5981fdfe7fe6386a3de1281e081e6ee04c9d9055a4ca50d0773ec4ba9","last_reissued_at":"2026-07-05T06:20:48.851362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:48.851362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.08162","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":"2026-07-05T06:20:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kvkSHudHHTI4XtsSPhOGXMQ90Xb4Bh3jlqhJynOZfYtE9BveyLeBWpGUKD9mqPY4yJdU3I1HBCirRnrSj3AzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:58:24.105235Z"},"content_sha256":"0ac485b7b5ff2147c6b37010048cc8166e9919dbfade8468c8b2e646b238f127","schema_version":"1.0","event_id":"sha256:0ac485b7b5ff2147c6b37010048cc8166e9919dbfade8468c8b2e646b238f127"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BYAQDRMYD7P6P7TDQ2R54EUB4C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Brooks, Glenn G. Ko, Gu-Yeon Wei, John Gkountouras, Yuji Chai","submitted_at":"2023-06-13T22:25:35Z","abstract_excerpt":"We introduce a method that dramatically reduces fine-tuning VRAM requirements and rectifies quantization errors in quantized Large Language Models. First, we develop an extremely memory-efficient fine-tuning (EMEF) method for quantized models using Low-Rank Adaptation (LoRA), and drawing upon it, we construct an error-correcting algorithm designed to minimize errors induced by the quantization process. Our method reduces the memory requirements by up to 5.6 times, which enables fine-tuning a 7 billion parameter Large Language Model (LLM) on consumer laptops. At the same time, we propose a Low-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08162","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/2306.08162/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":"2026-07-05T06:20:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gz/LvRena8baK0kzpm062Fo/H8cEhDV8wqp+230/1P7SLTHmUdARhGl4rHbxVniMjFGFyudccZnGFc/KGs9QBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:58:24.106147Z"},"content_sha256":"522d47b087538853bb8fbaaa1920f23df0537dd0f8de950707cb27861cfe5b47","schema_version":"1.0","event_id":"sha256:522d47b087538853bb8fbaaa1920f23df0537dd0f8de950707cb27861cfe5b47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYAQDRMYD7P6P7TDQ2R54EUB4C/bundle.json","state_url":"https://pith.science/pith/BYAQDRMYD7P6P7TDQ2R54EUB4C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYAQDRMYD7P6P7TDQ2R54EUB4C/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":"2026-08-06T06:58:24Z","links":{"resolver":"https://pith.science/pith/BYAQDRMYD7P6P7TDQ2R54EUB4C","bundle":"https://pith.science/pith/BYAQDRMYD7P6P7TDQ2R54EUB4C/bundle.json","state":"https://pith.science/pith/BYAQDRMYD7P6P7TDQ2R54EUB4C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYAQDRMYD7P6P7TDQ2R54EUB4C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BYAQDRMYD7P6P7TDQ2R54EUB4C","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":"e8bd91a3637ef9d318dfc1d9bbb54abdcd64fec09f98948d21ea2c9cd21aae6c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T22:25:35Z","title_canon_sha256":"c154aa421560b7f94812faf45db8f5ef1c90f265c0c9545f5dacbbb5293a7640"},"schema_version":"1.0","source":{"id":"2306.08162","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08162","created_at":"2026-07-05T06:20:48Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08162v1","created_at":"2026-07-05T06:20:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08162","created_at":"2026-07-05T06:20:48Z"},{"alias_kind":"pith_short_12","alias_value":"BYAQDRMYD7P6","created_at":"2026-07-05T06:20:48Z"},{"alias_kind":"pith_short_16","alias_value":"BYAQDRMYD7P6P7TD","created_at":"2026-07-05T06:20:48Z"},{"alias_kind":"pith_short_8","alias_value":"BYAQDRMY","created_at":"2026-07-05T06:20:48Z"}],"graph_snapshots":[{"event_id":"sha256:522d47b087538853bb8fbaaa1920f23df0537dd0f8de950707cb27861cfe5b47","target":"graph","created_at":"2026-07-05T06:20:48Z","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/2306.08162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a method that dramatically reduces fine-tuning VRAM requirements and rectifies quantization errors in quantized Large Language Models. First, we develop an extremely memory-efficient fine-tuning (EMEF) method for quantized models using Low-Rank Adaptation (LoRA), and drawing upon it, we construct an error-correcting algorithm designed to minimize errors induced by the quantization process. Our method reduces the memory requirements by up to 5.6 times, which enables fine-tuning a 7 billion parameter Large Language Model (LLM) on consumer laptops. At the same time, we propose a Low-","authors_text":"David Brooks, Glenn G. Ko, Gu-Yeon Wei, John Gkountouras, Yuji Chai","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T22:25:35Z","title":"INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08162","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":"sha256:0ac485b7b5ff2147c6b37010048cc8166e9919dbfade8468c8b2e646b238f127","target":"record","created_at":"2026-07-05T06:20:48Z","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":"e8bd91a3637ef9d318dfc1d9bbb54abdcd64fec09f98948d21ea2c9cd21aae6c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T22:25:35Z","title_canon_sha256":"c154aa421560b7f94812faf45db8f5ef1c90f265c0c9545f5dacbbb5293a7640"},"schema_version":"1.0","source":{"id":"2306.08162","kind":"arxiv","version":1}},"canonical_sha256":"0e0101c5981fdfe7fe6386a3de1281e081e6ee04c9d9055a4ca50d0773ec4ba9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e0101c5981fdfe7fe6386a3de1281e081e6ee04c9d9055a4ca50d0773ec4ba9","first_computed_at":"2026-07-05T06:20:48.851362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:48.851362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Krt8ujRIygiNmPFE7uEk+c2J8fxegTUJD6gIg2MCQRuZ2M/NC0nQ2PCkbSfP9WGcuvWYudKv96krtXZxdYwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:48.851759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08162","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ac485b7b5ff2147c6b37010048cc8166e9919dbfade8468c8b2e646b238f127","sha256:522d47b087538853bb8fbaaa1920f23df0537dd0f8de950707cb27861cfe5b47"],"state_sha256":"bd777a0e2ed688ee984cf4674542c9bc16ce6609f6c1a01d5ad35e05c01baa4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"so//Hk02TtMp/2Jd6fT3N3aixpaaOmjvYOGDRBZW1b69qoDvYhr1gHbI5eMN/3lKc4gCDwZ5L/a7xZFkxW02CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:58:24.111341Z","bundle_sha256":"3d38a077b7473687fdddc46071ca9f6f2e2cd220f932ac3ea26741902680b8c4"}}