{"as_of":"2026-08-16T10:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1a4b12adfa0bdc7822948007fd08116644cb8309917971fa74d721206214d6ef","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T20:08:46.997688Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.06858/citation-record","integrity":"/paper/2412.06858/integrity","json":"/paper/2412.06858/citation-record.json","paper":"/paper/2412.06858"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:48.347071Z","title":"Randomized algorithms for estimating the trace of an implicit symmetric positive semi-definite matrix","venue":null,"work_id":"32b28c4a-0142-4a12-85f1-16ae3a30e47d","year":2011},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.466185Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:a5f1ed205cbe197174f30704e9d23a6058195e3caf61674ae51c84cd5f22f335","observation_id":"2a526b3a-3500-4868-8d49-e035f6d06bf2","resolution":{"observed_at":"2026-08-11T20:08:48.351933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.11062","last_updated":"2025-05-19T06:20:01Z","snapshot_observed_at":"2026-08-13T19:22:45.524352Z","submitted_at":"2024-07-10T17:53:30Z","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.11062","snapshot_observed_at":"2026-08-11T20:08:46.495869Z","title":"Efficientqat: Efficient quantization-aware training for large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.495869Z"},"links":{"cited_paper":"/paper/2407.11062","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:713da18e8ebd47a4fa189e16aee20f7c3a7753cc64e51526d3c8655630ec0d39","observation_id":"4a9f2c71-0722-4369-9645-28bda3cb6cfc","resolution":{"observed_at":"2026-08-11T20:08:46.495869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:48.331679Z","title":"Palm: Scaling language modeling with pathways","venue":null,"work_id":"b0db2830-7bd0-40fd-9a0b-40e77d4f9ca8","year":2023},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.518154Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:4292312b196035ec7385a940cc8eade581eedd71b1e42c2d4e59a2c192825791","observation_id":"3a3a10fd-8c3f-4aa1-b006-cc925dfd3ed3","resolution":{"observed_at":"2026-08-11T20:08:48.337276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:48.127984Z","title":null,"venue":null,"work_id":"bbed8686-aee1-4bab-b7dc-0b33c6f55f4a","year":2022},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.523255Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:12d03d66ed9133e448e84dbab0180989c60b6d3bbe036bbe85e5c330f08e4ce2","observation_id":"58eadb53-94f2-441d-aa35-c24ac91c7b03","resolution":{"observed_at":"2026-08-11T20:08:48.233554Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:48.109136Z","title":"Qlora: Efficient finetuning of quantized llms","venue":null,"work_id":"73abbbe8-5468-4027-82b9-3410568c8dcf","year":2024},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.527951Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:47046bb9327628deed41f8280eb5c73cc93dad9979716830aeda61c5b9d59b77","observation_id":"80d256e7-c182-4b8f-9e6c-b52da9f94639","resolution":{"observed_at":"2026-08-11T20:08:48.114965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03078","last_updated":"2023-06-05T17:53:28Z","snapshot_observed_at":"2026-08-13T11:24:04.469181Z","submitted_at":"2023-06-05T17:53:28Z","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.03078","snapshot_observed_at":"2026-08-11T20:08:46.533253Z","title":"Spqr: A sparse-quantized representation for near-lossless llm weight compression","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.533253Z"},"links":{"cited_paper":"/paper/2306.03078","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:49dc01ef90f4e5fa21e1f95d2748fe6dfdf854351e887b32a630c755c6fdf2cb","observation_id":"08846aa6-8fbe-4506-b235-386758d2b3a4","resolution":{"observed_at":"2026-08-11T20:08:46.533253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:48.092827Z","title":"Hawq-v2: Hessian aware trace-weighted quantization of neural networks","venue":null,"work_id":"17198d2c-299e-4d50-9f19-f4c883c6db12","year":2020},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.537555Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:12cf6b72c1bae6e84abf4b1f1e0c6c70f1b60fdaf817931c9eaa7fa5c1f32cdb","observation_id":"bab8d1ba-3755-4dc5-9975-6abaeb4c3042","resolution":{"observed_at":"2026-08-11T20:08:48.098313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:47.952873Z","title":"Hawq: Hessian aware quantization of neural networks with mixed-precision","venue":null,"work_id":"742f21e5-8156-4df5-9c8d-a2e670f2aef4","year":2019},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.542485Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:0ed8afaad8642d042adb47e00f5817d14b91b4021e4417432f262bb654c98e16","observation_id":"42263eb2-4dbf-4a41-8ed7-9c5f5de4af89","resolution":{"observed_at":"2026-08-11T20:08:48.019653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10631","last_updated":"2024-02-16T12:27:15Z","snapshot_observed_at":"2026-08-13T04:17:38.154945Z","submitted_at":"2024-02-16T12:27:15Z","title":"BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.10631","snapshot_observed_at":"2026-08-11T20:08:46.548503Z","title":"Bitdistiller: Unleashing the potential of sub-4-bit llms via self-distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.548503Z"},"links":{"cited_paper":"/paper/2402.10631","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:e7ebebc034dd7c0d8275bc635e543cf5801730593319c5d3a3cf08206021a7f2","observation_id":"0bee0ec6-1ed2-4e86-999d-400f46f30a90","resolution":{"observed_at":"2026-08-11T20:08:46.548503Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:47.869010Z","title":"Glam: Efficient scaling of language models with mixture-of-experts","venue":null,"work_id":"f42305eb-fe5a-40a4-9956-e5c76fb60de4","year":2022},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.603373Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:6c84db1b4b1091476387da9ddd622d6dd6f22996b91b1b2cc15bf6bb8a663c48","observation_id":"5a41970a-da90-4c41-a5ae-69b80e401c11","resolution":{"observed_at":"2026-08-11T20:08:47.874327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:47.854742Z","title":"Gpt-3: Its nature, scope, limits, and consequences","venue":null,"work_id":"a6612997-3c84-4d3a-b0a3-d9d30f5a6b9e","year":2020},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.608177Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:468f25ce2c4eb1a20561d259adb65a2aaebf700dd89d9dd12da9a8b9ba8f956d","observation_id":"e596bede-f1c0-4153-8d47-0d4c9d829032","resolution":{"observed_at":"2026-08-11T20:08:47.859164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17323","last_updated":"2023-03-22T13:10:47Z","snapshot_observed_at":"2026-08-16T07:57:19.216626Z","submitted_at":"2022-10-31T13:42:40Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.17323","snapshot_observed_at":"2026-08-11T20:08:46.613246Z","title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.613246Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:85547c4dd9b62c7a3dd7c690387164c456f7babfba1074bae9bbd76daee79e64","observation_id":"5c99e64a-f436-491f-841d-4541fe62a5f2","resolution":{"observed_at":"2026-08-11T20:08:46.613246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-11T08:20:29.798517Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-11T20:08:46.618543Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.618543Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:be2bb98d407b9b8a01c39a1a56fc9d17c7584357200493352485a7ca0658a76f","observation_id":"7ee47ec4-2c98-4e3b-b342-31f0d9b3f26f","resolution":{"observed_at":"2026-08-11T20:08:46.618543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-08-13T17:41:53.092611Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-11T20:08:46.623021Z","title":"Scaling laws for neural language models","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.623021Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:c56cea23a7676688439362fd7809b68622b4e0d158668cb5af1f435a75f8e41d","observation_id":"d057e549-ff21-4087-b82d-779ce0d7bf02","resolution":{"observed_at":"2026-08-11T20:08:46.623021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07629","last_updated":"2024-06-05T03:57:41Z","snapshot_observed_at":"2026-08-13T11:18:21.844753Z","submitted_at":"2023-06-13T08:57:54Z","title":"SqueezeLLM: Dense-and-Sparse Quantization","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07629","snapshot_observed_at":"2026-08-11T20:08:46.631080Z","title":"Squeezellm: Dense-and-sparse quantization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.631080Z"},"links":{"cited_paper":"/paper/2306.07629","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:f9b444c95a8c0ae6f3d73050719db894ea89c9234241daa70c48f86ac4929d9a","observation_id":"04f5fb6c-f226-4659-bf54-4ba5affb2bb7","resolution":{"observed_at":"2026-08-11T20:08:46.631080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:47.795562Z","title":"Awq: Activation-aware weight quantization for on-device llm compression and acceleration","venue":null,"work_id":"12315ee5-58d4-4c39-99f1-5eed1b739922","year":2024},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.636198Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:ef19612d23d8804de1a9ff793f4a8893ebc7acd15e20e25055fee4a558bf367e","observation_id":"98080bb7-ab6b-4e0e-b1bc-6a1ad05638b1","resolution":{"observed_at":"2026-08-11T20:08:47.844795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.17888","last_updated":"2023-05-29T05:22:11Z","snapshot_observed_at":"2026-08-13T11:30:33.812255Z","submitted_at":"2023-05-29T05:22:11Z","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.17888","snapshot_observed_at":"2026-08-11T20:08:46.640538Z","title":"Llm-qat: Data-free quan- tization aware training for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.640538Z"},"links":{"cited_paper":"/paper/2305.17888","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:7c4324facc63b3a63fa183ea977c459822f3c6dc3c0ee812bf0d8f5b7dcde924","observation_id":"6db3ee7a-ba31-4cb4-a21d-02ead5086f58","resolution":{"observed_at":"2026-08-11T20:08:46.640538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07843","last_updated":"2016-09-26T04:06:13Z","snapshot_observed_at":"2026-07-06T05:12:10.387914Z","submitted_at":"2016-09-26T04:06:13Z","title":"Pointer Sentinel Mixture Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.07843","snapshot_observed_at":"2026-08-11T20:08:46.681916Z","title":"Pointer sentinel mixture models","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.681916Z"},"links":{"cited_paper":"/paper/1609.07843","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:8b7fb8cf7ac29531fdbc16bcd83800f1adf0c0b512002c4df532d4c21b8f39ba","observation_id":"2cd7b284-004d-4b75-9720-a410207d62f8","resolution":{"observed_at":"2026-08-11T20:08:46.681916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:47.557839Z","title":"Mixed-Precision Training Guide, 2023","venue":null,"work_id":"bae070d6-0ce9-44da-818c-ccdf0fa8462c","year":2023},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.767320Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:754662ca68a533b3d635e56b68eb64dff011b7552e147aa86b649f3fca854d21","observation_id":"d8795a43-f225-4e0f-b23c-2d6493c87f87","resolution":{"observed_at":"2026-08-11T20:08:47.672988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:46.860105Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.860105Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:0c7b77c3973d950a5fc463d1437d65a6c6a75b85ebe56585ef664947906766f4","observation_id":"8cf13f8a-dfcc-40a8-905d-4037862a1393","resolution":{"observed_at":"2026-08-11T20:08:46.860105Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11990","last_updated":"2022-02-04T18:02:23Z","snapshot_observed_at":"2026-08-09T17:07:26.804289Z","submitted_at":"2022-01-28T08:59:57Z","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11990","snapshot_observed_at":"2026-08-11T20:08:46.864896Z","title":"Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.864896Z"},"links":{"cited_paper":"/paper/2201.11990","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:a061a6567c56b44721d5559d572a24df8e204e0bfc1ed11e2e838d95200a0388","observation_id":"743047ae-22e0-4716-b5d8-73bd468cb879","resolution":{"observed_at":"2026-08-11T20:08:46.864896Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:46.869237Z","title":"Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.869237Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:04a6fa3a6aa10411199094138fda8a2aba6ceed611b93642ff13f1548d6de520","observation_id":"b901b2b4-a946-474b-a381-d3ef804264c6","resolution":{"observed_at":"2026-08-11T20:08:46.869237Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:47.533025Z","title":"Outlier suppression: Pushing the limit of low-bit transformer language models","venue":null,"work_id":"f6794e6b-4650-4250-81fa-e2d80bd4f945","year":2022},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.873606Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:c1fe5ee4085e1067f03a0f3e22b50fddf289bbd77fa1a30068ca436af8b3b21c","observation_id":"ce8544ab-bc0a-48a4-b183-f24caffdd3ee","resolution":{"observed_at":"2026-08-11T20:08:47.537701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.05100","last_updated":"2023-06-27T09:57:58Z","snapshot_observed_at":"2026-08-04T18:56:03.233715Z","submitted_at":"2022-11-09T18:48:09Z","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.05100","snapshot_observed_at":"2026-08-11T20:08:46.877482Z","title":"Bloom: A 176b-parameter open-access multilingual language model","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.877482Z"},"links":{"cited_paper":"/paper/2211.05100","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:6298f2532986985aed1c29f180b47e78d9658334aa2698877b9c799f1d8de71a","observation_id":"3118e128-a998-4bdb-a45e-19a50c848867","resolution":{"observed_at":"2026-08-11T20:08:46.877482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:47.517903Z","title":"Hero: Hessian-enhanced robust optimization for unifying and improving generalization and quantization performance","venue":null,"work_id":"432f0d1e-6fc3-43ff-b2bc-2544cae64433","year":2022},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.882490Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:4195fa3b45df188846210d32d66e693b1392c4762efb906655d3fb0d6134a620","observation_id":"f8732d66-24e1-4a55-99c4-e0b334d27a80","resolution":{"observed_at":"2026-08-11T20:08:47.523298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.01068","last_updated":"2022-06-21T17:04:40Z","snapshot_observed_at":"2026-08-06T03:13:37.403059Z","submitted_at":"2022-05-02T17:49:50Z","title":"OPT: Open Pre-trained Transformer Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.01068","snapshot_observed_at":"2026-08-11T20:08:46.886544Z","title":"Opt: Open pre-trained transformer language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.886544Z"},"links":{"cited_paper":"/paper/2205.01068","citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:ef2560eee5902bb74918c4d088c5d03281b3c5035c597ea13c3c4530adf700d3","observation_id":"af19ebc8-7d21-49ce-bc27-703578ab6070","resolution":{"observed_at":"2026-08-11T20:08:46.886544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:08:47.327855Z","title":"Table 10: OPT-1.3B-4bit latency(s) for generating different lengths of tokens","venue":null,"work_id":"c72c58c1-28f7-4f30-9358-2d3a424c6834","year":null},"citing_paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T20:08:46.997688Z"},"links":{"citing_paper":"/paper/2412.06858"},"observation_digest":"sha256:19f067fd277008090f7b22fa0299293f1f3896ed78d11078731712ca981c7038","observation_id":"adbc729f-9b7b-4ad5-aa0c-3d49ba55ff20","resolution":{"observed_at":"2026-08-11T20:08:47.485547Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.06858","last_updated":"2025-03-15T19:35:05Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T00:04:37.270299Z","submitted_at":"2024-12-08T21:46:22Z","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":11},"total_outbound_references":27},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2412.06858."}