{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I7EEFQHPZKN467RNZN3WDCL2P2","short_pith_number":"pith:I7EEFQHP","canonical_record":{"source":{"id":"2406.06385","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T15:44:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"92fc2f47ba16b0e955393e4dc674cb0f8767aac9d46b814d31c708a3cb2cf21f","abstract_canon_sha256":"61f15fa527e59f8cd9dd06b19406e17d83dd44c7544a29b0082a81c29f0364a6"},"schema_version":"1.0"},"canonical_sha256":"47c842c0efca9bcf7e2dcb7761897a7e8ba8312df8671701cd3dc2180b092ed1","source":{"kind":"arxiv","id":"2406.06385","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06385","created_at":"2026-07-05T09:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06385v3","created_at":"2026-07-05T09:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06385","created_at":"2026-07-05T09:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"I7EEFQHPZKN4","created_at":"2026-07-05T09:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"I7EEFQHPZKN467RN","created_at":"2026-07-05T09:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"I7EEFQHP","created_at":"2026-07-05T09:02:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I7EEFQHPZKN467RNZN3WDCL2P2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.06385","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T15:44:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"92fc2f47ba16b0e955393e4dc674cb0f8767aac9d46b814d31c708a3cb2cf21f","abstract_canon_sha256":"61f15fa527e59f8cd9dd06b19406e17d83dd44c7544a29b0082a81c29f0364a6"},"schema_version":"1.0"},"canonical_sha256":"47c842c0efca9bcf7e2dcb7761897a7e8ba8312df8671701cd3dc2180b092ed1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:21.073286Z","signature_b64":"p+Ct5sVxch3zEdrvWCkWqzJK5Wh/rygHCIJDZaAtMt9DMZMKEuPa+XKPBUawOF+NJNir3ratepWonjjadMcbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47c842c0efca9bcf7e2dcb7761897a7e8ba8312df8671701cd3dc2180b092ed1","last_reissued_at":"2026-07-05T09:02:21.072810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:21.072810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.06385","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"upG6BTVC+hhIQZkOjLaB9wz499uSucTrYCnNotiE/iVUlAhMng1w3EpqBOJHDDv6lJ6bJ1dLYaMjQHTIscSJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:40:26.242597Z"},"content_sha256":"d9e1c8b7b20cd91e2a7fcb35936389306057b75c04f61be73ba13e1bc7447e75","schema_version":"1.0","event_id":"sha256:d9e1c8b7b20cd91e2a7fcb35936389306057b75c04f61be73ba13e1bc7447e75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I7EEFQHPZKN467RNZN3WDCL2P2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Low-Rank Quantization-Aware Training for LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Markus Nagel, Riccardo Del Chiaro, Yelysei Bondarenko","submitted_at":"2024-06-10T15:44:22Z","abstract_excerpt":"Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and memory efficient. Quantization-aware training (QAT) methods, generally produce the best quantized performance, however it comes at the cost of potentially long training time and excessive memory usage, making it impractical when applying for LLMs. Inspired by parameter-efficient fine-tuning (PEFT) and low-rank adaptation (LoRA) literature, we propose LR-QAT -- a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06385","kind":"arxiv","version":3},"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/2406.06385/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":"2026-07-05T09:02:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WGrX7XvX18eQNSUkc3VV4SR5mW870H5fvMvVZmkqGtdB5WRPx5N1PLlMcxKydKeVp4n8BYKVEQJ0XFNRKLBCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:40:26.243142Z"},"content_sha256":"950901de621b522e7c029e2affda3476a99cf562cb3242039992ebe13b3f7b35","schema_version":"1.0","event_id":"sha256:950901de621b522e7c029e2affda3476a99cf562cb3242039992ebe13b3f7b35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I7EEFQHPZKN467RNZN3WDCL2P2/bundle.json","state_url":"https://pith.science/pith/I7EEFQHPZKN467RNZN3WDCL2P2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I7EEFQHPZKN467RNZN3WDCL2P2/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":"2026-08-08T14:40:26Z","links":{"resolver":"https://pith.science/pith/I7EEFQHPZKN467RNZN3WDCL2P2","bundle":"https://pith.science/pith/I7EEFQHPZKN467RNZN3WDCL2P2/bundle.json","state":"https://pith.science/pith/I7EEFQHPZKN467RNZN3WDCL2P2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I7EEFQHPZKN467RNZN3WDCL2P2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I7EEFQHPZKN467RNZN3WDCL2P2","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":"61f15fa527e59f8cd9dd06b19406e17d83dd44c7544a29b0082a81c29f0364a6","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T15:44:22Z","title_canon_sha256":"92fc2f47ba16b0e955393e4dc674cb0f8767aac9d46b814d31c708a3cb2cf21f"},"schema_version":"1.0","source":{"id":"2406.06385","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06385","created_at":"2026-07-05T09:02:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06385v3","created_at":"2026-07-05T09:02:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06385","created_at":"2026-07-05T09:02:21Z"},{"alias_kind":"pith_short_12","alias_value":"I7EEFQHPZKN4","created_at":"2026-07-05T09:02:21Z"},{"alias_kind":"pith_short_16","alias_value":"I7EEFQHPZKN467RN","created_at":"2026-07-05T09:02:21Z"},{"alias_kind":"pith_short_8","alias_value":"I7EEFQHP","created_at":"2026-07-05T09:02:21Z"}],"graph_snapshots":[{"event_id":"sha256:950901de621b522e7c029e2affda3476a99cf562cb3242039992ebe13b3f7b35","target":"graph","created_at":"2026-07-05T09:02:21Z","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/2406.06385/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and memory efficient. Quantization-aware training (QAT) methods, generally produce the best quantized performance, however it comes at the cost of potentially long training time and excessive memory usage, making it impractical when applying for LLMs. Inspired by parameter-efficient fine-tuning (PEFT) and low-rank adaptation (LoRA) literature, we propose LR-QAT -- a","authors_text":"Markus Nagel, Riccardo Del Chiaro, Yelysei Bondarenko","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T15:44:22Z","title":"Low-Rank Quantization-Aware Training for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06385","kind":"arxiv","version":3},"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:d9e1c8b7b20cd91e2a7fcb35936389306057b75c04f61be73ba13e1bc7447e75","target":"record","created_at":"2026-07-05T09:02:21Z","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":"61f15fa527e59f8cd9dd06b19406e17d83dd44c7544a29b0082a81c29f0364a6","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T15:44:22Z","title_canon_sha256":"92fc2f47ba16b0e955393e4dc674cb0f8767aac9d46b814d31c708a3cb2cf21f"},"schema_version":"1.0","source":{"id":"2406.06385","kind":"arxiv","version":3}},"canonical_sha256":"47c842c0efca9bcf7e2dcb7761897a7e8ba8312df8671701cd3dc2180b092ed1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47c842c0efca9bcf7e2dcb7761897a7e8ba8312df8671701cd3dc2180b092ed1","first_computed_at":"2026-07-05T09:02:21.072810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:02:21.072810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p+Ct5sVxch3zEdrvWCkWqzJK5Wh/rygHCIJDZaAtMt9DMZMKEuPa+XKPBUawOF+NJNir3ratepWonjjadMcbDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:02:21.073286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06385","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9e1c8b7b20cd91e2a7fcb35936389306057b75c04f61be73ba13e1bc7447e75","sha256:950901de621b522e7c029e2affda3476a99cf562cb3242039992ebe13b3f7b35"],"state_sha256":"45825f2339ef02703e1e31b79e14a409e335cf3f57a4ace6298533529ebddf18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zqZ4Ym1qXNZANcZCiXtzqlFbaWZbbwCNi+n/fQXR5l4nJSZcOSgYJVP/9RCWte5R63E4oN8e4iFE7+y3KV4HCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:40:26.247952Z","bundle_sha256":"a015a9d4fa2aa615a79b33d0d42769ee52f11dc2f19645bb6a772fbfc950561f"}}