{"as_of":"2026-08-17T17:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8d3722e7279a376c13a25e819b718ac3c84c6d16a49fb303bddd5a7613c91239","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T16:19:29.246452Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2509.15206/citation-record","integrity":"/paper/2509.15206/integrity","json":"/paper/2509.15206/citation-record.json","paper":"/paper/2509.15206"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T16:19:22.259898Z","title":"Pi QA : Reasoning about physical commonsense in natural language","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:22.259898Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:1ee8b89a1a86cdf6b5911e0fb7a118277489e12ba944e660095e9f7f5be73310","observation_id":"cdff50ef-6be9-4be0-8bb9-06dbf511ca97","resolution":{"observed_at":"2026-08-04T16:19:22.259898Z","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":"2026-08-04T16:19:22.411939Z","title":"Man is to computer programmer as woman is to homemaker? debiasing word embeddings","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:22.411939Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:469303fc35c000d508ee09bcef6f198aa28cd01055ca33d1b65292e45f8e000a","observation_id":"20a13242-b5b1-4ef2-86ef-85f002439188","resolution":{"observed_at":"2026-08-04T16:19:22.411939Z","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":"2026-08-04T16:19:22.608703Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:22.608703Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:71d3184f188a8762d446dc94af7a4b065fdb5204989b2ec7a7b4115175ce4723","observation_id":"a81ac765-9d57-4d20-883f-02c6dce2890a","resolution":{"observed_at":"2026-08-04T16:19:22.608703Z","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":"2026-08-04T16:19:22.781051Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:22.781051Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:223df5913d1068785b1006e248f3aa99a6b75d7d49da9ac4758f230622dba33c","observation_id":"911d6221-05d1-4053-a308-9d745ef825e3","resolution":{"observed_at":"2026-08-04T16:19:22.781051Z","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":"2026-08-04T16:19:22.901718Z","title":"Semantics derived automatically from language corpora contain human-like biases","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:22.901718Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:95c36bfeeaef765636f8f598c60fd4e926d87ec058db9b0896a93c8801c0bc5a","observation_id":"3635a8b4-3881-4dff-bd36-6b91d47301e2","resolution":{"observed_at":"2026-08-04T16:19:22.901718Z","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":"2026-08-04T16:19:23.025853Z","title":"Quip: 2-bit quantization of large language models with guarantees","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:23.025853Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:bac9f0a423d39fb8e3b7c79bde4c677c53f8aa58988360854333d4b40e25439d","observation_id":"281ccdeb-be24-4c42-90c5-05470c3d6d4d","resolution":{"observed_at":"2026-08-04T16:19:23.025853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-08-14T19:36:07.505691Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-08-04T16:19:23.180826Z","title":"Think you have solved question answering? T ry ARC , the AI2 reasoning challenge","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:23.180826Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:91ca7b9baff0114b21c3dbb163e51d7a3f8ab469a90c52865293f25e25e63fc5","observation_id":"0c1dc487-5038-49b9-b3e3-52d3379318e2","resolution":{"observed_at":"2026-08-04T16:19:23.180826Z","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":"2026-08-04T16:19:23.293538Z","title":"Racial bias in hate speech and abusive language detection datasets","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:23.293538Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:c152b550ada54fe6a95a60b81e1e9337ea84296d90bb1975c585abb46e152828","observation_id":"d5edca8b-87fc-4be4-bf9d-71ccbde90129","resolution":{"observed_at":"2026-08-04T16:19:23.293538Z","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":"2026-08-04T16:19:23.446596Z","title":"Gpt3.int8(): 8-bit matrix multiplication for transformers at scale","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:23.446596Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:923f7b892b8568b746cd9094a716fd369dc262a9f05e074c74ebdff008d7dedc","observation_id":"d05eff68-87b9-4abc-9591-7a6196d2f0b3","resolution":{"observed_at":"2026-08-04T16:19:23.446596Z","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":"2026-08-04T16:19:23.535896Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:23.535896Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:6e6a84560305009e658e186b8380392cc1aab8540c8a65096417bb8307f248d0","observation_id":"84b3f5ae-6c62-4c00-b2ee-203f5881accb","resolution":{"observed_at":"2026-08-04T16:19:23.535896Z","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":"2026-08-04T16:19:23.681875Z","title":"A mathematical framework for transformer circuits","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:23.681875Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:7a653f95477c6c7efb373f5ed7782734d2e448f43ba499321ef49fb7d989ab1e","observation_id":"834c5515-338d-4903-86f4-a7b64fbd0636","resolution":{"observed_at":"2026-08-04T16:19:23.681875Z","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":"2026-08-04T16:19:23.796588Z","title":"From pretraining data to language models to downstream tasks: Tracking the trails of political biases leading to unfair NLP models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:23.796588Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:587cf747986bfb82bac6a000c8f0d5251b23d52517056e5093e568e105e45d14","observation_id":"c9213451-c47e-4886-beda-b379af7f9967","resolution":{"observed_at":"2026-08-04T16:19:23.796588Z","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":"2026-08-04T16:19:23.902989Z","title":"Optimal brain compression: A framework for accurate post-training quantization and pruning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:23.902989Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:ff54a5b11696d391a9087dae16fe6e10fa53a461f1916f87369297346b2f5bb1","observation_id":"89b7b0df-828f-40b7-b027-af8546e52202","resolution":{"observed_at":"2026-08-04T16:19:23.902989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-04T16:19:24.001390Z","title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:24.001390Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:952097cb6ce959e20de728c924525035034932afa980a43800aa07e33b5942c7","observation_id":"fa0a9989-db1a-4e1f-a483-ad77e3b6cf09","resolution":{"observed_at":"2026-08-04T16:19:24.001390Z","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":"2026-08-04T16:19:24.086937Z","title":"Marlin: Mixed-precision auto-regressive parallel inference on large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:24.086937Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:f45aa695cec733fed18021f393c76f361f6036354fab4d60cdae88275a59bcb6","observation_id":"8691e94a-613c-43b3-8991-679b2a1b7593","resolution":{"observed_at":"2026-08-04T16:19:24.086937Z","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":"2026-08-04T16:19:24.173399Z","title":"Transformer feed-forward layers are key-value memories","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:24.173399Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:ab7fa7391d16984309473701bf8b1e38844e4ac658c68f811b934929e92c6e7b","observation_id":"647ba264-73fe-40ca-87b7-95584239e5d6","resolution":{"observed_at":"2026-08-04T16:19:24.173399Z","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":"2026-08-04T16:19:24.309338Z","title":"Understanding the effect of model compression on social bias in large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:24.309338Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:0d949e528832556f45153205b1ea03c416232c1af85868a83a66cf93dee7df2a","observation_id":"71bae433-12ee-4362-bef6-83c3b5e2561d","resolution":{"observed_at":"2026-08-04T16:19:24.309338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-04T16:19:24.466940Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:24.466940Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:be4bf156033600674577e483c820fe5f654613fc416cf9f691b564d1532a680e","observation_id":"cb21918b-d06e-4fa5-b641-3b1e826417b2","resolution":{"observed_at":"2026-08-04T16:19:24.466940Z","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":"2026-08-04T16:19:24.653115Z","title":"Accelerate: Training and inference at scale made simple, efficient and adaptable","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:24.653115Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:ec05a29bb47accb36789ef246273d454d35d88f79e7108115c3800acbcd8e5a4","observation_id":"a22724fc-5d60-4a1a-8460-63672d9cd09d","resolution":{"observed_at":"2026-08-04T16:19:24.653115Z","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":"2026-08-04T16:19:24.824274Z","title":"Optimal brain surgeon and general network pruning","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:24.824274Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:0b14344e82ab2fc4b4348707cb188f6c5dd2d6f3968a3098bf0a9ce79647429d","observation_id":"1ac4bced-8d76-41a3-9d5b-1f0856ca4bb2","resolution":{"observed_at":"2026-08-04T16:19:24.824274Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15531","last_updated":"2025-04-14T01:25:53Z","snapshot_observed_at":"2026-08-16T14:57:15.236543Z","submitted_at":"2023-09-27T09:48:31Z","title":"Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15531","snapshot_observed_at":"2026-08-04T16:19:24.990979Z","title":"Rethinking channel dimensions to isolate outliers for low-bit weight quantization of large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:24.990979Z"},"links":{"cited_paper":"/paper/2309.15531","citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:f0d2b5a704e5e4493a8b8f3bd8787cacf07a406180744f65dc43161bf3d1caf1","observation_id":"b5f99710-f5e1-4302-a878-360e2e730e73","resolution":{"observed_at":"2026-08-04T16:19:24.990979Z","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":"2026-08-04T16:19:25.111926Z","title":"Accurate post training quantization with small calibration sets","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:25.111926Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:3c048649dbac41c46061b5475e0b3e45c9943832eabf907e10f9b961ec4abe53","observation_id":"24db4675-4f2e-4e1a-a0c2-9ce204123253","resolution":{"observed_at":"2026-08-04T16:19:25.111926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01382","last_updated":"2024-03-17T00:38:59Z","snapshot_observed_at":"2026-08-16T14:55:46.888335Z","submitted_at":"2023-10-02T17:42:37Z","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01382","snapshot_observed_at":"2026-08-04T16:19:25.244046Z","title":"Compressing llms: The truth is rarely pure and never simple","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:25.244046Z"},"links":{"cited_paper":"/paper/2310.01382","citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:73295ea7eaef289e1545142f25bc383ba1b0cc9c9ce7a95819cef832919c527a","observation_id":"7635ee2f-f159-473c-9459-a4a3901a698e","resolution":{"observed_at":"2026-08-04T16:19:25.244046Z","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":"2026-08-04T16:19:25.365161Z","title":"Perplexity—a measure of the difficulty of speech recognition tasks","venue":null,"work_id":null,"year":1977},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:25.365161Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:faf378e177ce58a77acd2d012abade22f439cca4cff129ed394edaf4380b141d","observation_id":"de7a2549-29ff-4954-945d-c60546f2e01d","resolution":{"observed_at":"2026-08-04T16:19:25.365161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-08-17T02:13:39.510069Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-04T16:19:25.488134Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:25.488134Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:36b309e18176f9c4ebdb723c9e6d912e9cb86f1b920c14227588caf583ff6788","observation_id":"2570fede-775a-479c-82ac-443bf8dfe7e4","resolution":{"observed_at":"2026-08-04T16:19:25.488134Z","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":"2026-08-04T16:19:25.614265Z","title":"Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeff Wu, and Dario Amodei","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:25.614265Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:f0866aae0d36180bbbbeb366b21aa819658fad049acc8a85c36b3451ae81e53a","observation_id":"e10f657e-fa68-4de1-bdf0-a6a8879bcc33","resolution":{"observed_at":"2026-08-04T16:19:25.614265Z","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":"2026-08-04T16:19:25.734201Z","title":"Optimal brain damage","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:25.734201Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:a5f973b539c8a3e5333e438438302860a10942509d824e12aed064229f1d9b1e","observation_id":"a10f14ce-6b2d-4e0b-a003-3c60a44c02d7","resolution":{"observed_at":"2026-08-04T16:19:25.734201Z","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":"2026-08-04T16:19:25.813923Z","title":"Owq: Outlier-aware weight quantization for efficient fine-tuning and inference of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:25.813923Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:da3c1edd65779bea2119c5fd0d83b2201cbed174b1792fa4380fed3375ab8a91","observation_id":"c460dcd2-72db-4a31-804c-dd8b421cbe84","resolution":{"observed_at":"2026-08-04T16:19:25.813923Z","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":"2026-08-04T16:19:25.900053Z","title":"Towards debiasing sentence representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:25.900053Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:2a46642b66428a13d0e0449adbee57504699e325053fef41c3bf44207e7f5222","observation_id":"a8c15fe1-7b7c-4750-a671-5ea98807534c","resolution":{"observed_at":"2026-08-04T16:19:25.900053Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08072","last_updated":"2023-07-26T04:15:48Z","snapshot_observed_at":"2026-08-16T15:15:53.424986Z","submitted_at":"2023-07-16T15:11:01Z","title":"Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08072","snapshot_observed_at":"2026-08-04T16:19:26.042135Z","title":"Do emergent abilities exist in quantized large language models: An empirical study","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:26.042135Z"},"links":{"cited_paper":"/paper/2307.08072","citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:be45a39a10633ef88e7dc8bb469aad9a5fa710580cb13d68a5769b4e9320a749","observation_id":"efc6503c-f37f-48bd-89d6-4e29339a8ccc","resolution":{"observed_at":"2026-08-04T16:19:26.042135Z","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":"2026-08-04T16:19:26.158112Z","title":"B lack is to criminal as C aucasian is to police: Detecting and removing multiclass bias in word embeddings","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:26.158112Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:a632354a7b80ef86701c621b8a4f232cfb212707e3d276f46d7e7da237a79bba","observation_id":"59e4acc1-a1c5-4961-8010-834bd3dcdac5","resolution":{"observed_at":"2026-08-04T16:19:26.158112Z","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":"10.18653/v1/2024.emnlp-main.812","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Social bias probing: Fairness benchmarking for language models","venue":null,"work_id":"d3c03bfb-e960-4580-85df-f40407fbd446","year":2024},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:26.264840Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:e0273ced407812f84f9cfbdb0e754402d33fc23908097ec16dccb7a0ce86be80","observation_id":"41c799cf-f9e5-41bc-8c9e-25057732afd0","resolution":{"observed_at":"2026-08-04T16:23:39.434748Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-04T16:19:26.422250Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:26.422250Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:7956cd3b4d887da34e9aa91eae6aab17f967a3966c31fe56b09ea71a8de9b744","observation_id":"c67fc6b8-2f3f-47b0-8bfb-9d884ef33f15","resolution":{"observed_at":"2026-08-04T16:19:26.422250Z","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":"2026-08-04T16:19:26.571098Z","title":"An empirical survey of the effectiveness of debiasing techniques for pre-trained language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:26.571098Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:82239de106460fc3b2df3f1f08edde983df1a3ff8324470adfbd024f896590fa","observation_id":"db78471e-74ac-41da-a9f9-723a3beb1daa","resolution":{"observed_at":"2026-08-04T16:19:26.571098Z","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":"2026-08-17T01:46:43.513643Z","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":"2026-08-04T16:19:26.680977Z","title":"Pointer sentinel mixture models","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:26.680977Z"},"links":{"cited_paper":"/paper/1609.07843","citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:72c0ed711bd1a4c95670fbf0955d78c9893c8313b1fcbd2d3efdaa590bfefdd6","observation_id":"a12fcddf-911d-433c-b7ff-a7ea002afbe7","resolution":{"observed_at":"2026-08-04T16:19:26.680977Z","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":"2026-08-04T16:19:26.789462Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:26.789462Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:e05d01130550c3ddc88a665d085ac5b956b21a34d5f7524c04435fce5f6c6111","observation_id":"42f4ab4d-b66c-4004-b68d-4e0b212410b7","resolution":{"observed_at":"2026-08-04T16:19:26.789462Z","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":"2026-08-04T16:19:26.942330Z","title":"LSDS em 2017 shared task: The story cloze test","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:26.942330Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:c3a11935108466daee6b042fa8122ff6635f86762c8ca2976c1a3f7d6706ff34","observation_id":"063e8982-5a58-4be8-b622-aba0895dc980","resolution":{"observed_at":"2026-08-04T16:19:26.942330Z","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":"2026-08-04T16:19:27.002705Z","title":"S tereo S et: Measuring stereotypical bias in pretrained language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:27.002705Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:be3a99c091f865a75d3199aedbd73f03e8c97d8202a941728ec142c3c83e474f","observation_id":"e246c039-a104-430e-89d9-e32ca47c7e75","resolution":{"observed_at":"2026-08-04T16:19:27.002705Z","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":"2026-08-04T16:19:27.065645Z","title":"Up or down? adaptive rounding for post-training quantization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:27.065645Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:f1fc73d48bde48cec97d7768c9f71114fdfa6a4b9e7cbb55655f65ef077706db","observation_id":"373d1acd-2e01-4a8a-8bce-609dccf0494c","resolution":{"observed_at":"2026-08-04T16:19:27.065645Z","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":"2026-08-04T16:19:27.178802Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:27.178802Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:27ece64f43d3e425e026dd49f5d44a25cb1751d55e21be946255a8c8670bf11a","observation_id":"4b8c688c-306b-4b1b-9627-fba5454aa139","resolution":{"observed_at":"2026-08-04T16:19:27.178802Z","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":"2026-08-04T16:19:27.277119Z","title":"Social-group-agnostic bias mitigation via the stereotype content model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:27.277119Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:e18d6c3b379c7535cbb0149fd176f73d3fd05075b50a92e2125f21ad79eb70a4","observation_id":"eaa3466a-30ac-43bb-992a-5185fff18940","resolution":{"observed_at":"2026-08-04T16:19:27.277119Z","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":"2026-08-04T16:19:27.367200Z","title":"BBQ : A hand-built bias benchmark for question answering","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:27.367200Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:12ad8e72cc225ce7282678b71054c9768bd60602e313d8fd7cb29093f4a0cca6","observation_id":"64abe1b3-0ba8-41d0-b351-a8baa148e2f6","resolution":{"observed_at":"2026-08-04T16:19:27.367200Z","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":"2026-08-04T16:19:27.471402Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:27.471402Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:619a7af0a6164d62bbb592dcba1fd3d09bc2c7291b73e80ced3189d7d4415154","observation_id":"86e84b32-823e-4bd8-b7af-dc8445816b34","resolution":{"observed_at":"2026-08-04T16:19:27.471402Z","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":"10.18653/v1/2023.blackboxnlp-1.22","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Layered bias: Interpreting bias in pretrained large language models","venue":null,"work_id":"9cefb8b4-497e-46e1-b860-259b99998770","year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:27.562087Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:6e3a1f449acdb67746bdcf93bc9613de8279081f401b3948c85785929b5ab53d","observation_id":"c5edbd96-0750-4513-9066-067fab44f24f","resolution":{"observed_at":"2026-08-04T16:23:38.724747Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-04T16:19:27.669594Z","title":"Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:27.669594Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:aec39e3e3ac5200ce55c97b4b698748b17c0d4e2c2a232bf25cbc46c2744d1c3","observation_id":"771c667e-dd8a-4069-9e5a-6873cb8ad334","resolution":{"observed_at":"2026-08-04T16:19:27.669594Z","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":"2026-08-04T16:19:27.767685Z","title":"A comparative study on the impact of model compression techniques on fairness in language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:27.767685Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:3a4069b4da4f5a03c28d4ed2b711161e802a48f1e3581bc93179f02ca62bb7e9","observation_id":"aac319e3-e1f3-4361-8434-d24cae6e2dfd","resolution":{"observed_at":"2026-08-04T16:19:27.767685Z","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":"2026-08-04T16:19:27.875161Z","title":"Null it out: Guarding protected attributes by iterative nullspace projection","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:27.875161Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:24813bcefc898b8b9b92feea2e624b9d263c42b443ac94e3a644ebae63372ce4","observation_id":"55815cef-32d4-47f2-88bc-fef2bc955de0","resolution":{"observed_at":"2026-08-04T16:19:27.875161Z","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":"2026-08-04T16:19:28.011674Z","title":"Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in NLP","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:28.011674Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:de45363e7ab1eb4586790fa8f87f22d7f386feaaca2cabfbae42005fee54c425","observation_id":"f24e5f6c-7518-4b7a-bf87-f87f5e7b61a8","resolution":{"observed_at":"2026-08-04T16:19:28.011674Z","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":"2026-08-04T16:19:28.112127Z","title":"Upstream mitigation is not all you need: Testing the bias transfer hypothesis in pre-trained language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:28.112127Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:f1c0779d66684e62bba059717495b2db733d97c83b91d4de8f3d2a9f3a1242dd","observation_id":"13fb7ae3-5acd-4c0b-bd6b-2493252bad38","resolution":{"observed_at":"2026-08-04T16:19:28.112127Z","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":"2026-08-04T16:19:28.203309Z","title":"Transformers: State-of-the-art natural language processing","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:28.203309Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:91626fbea0ab88d0182f747f0f7e4070e43e7ec0730603e7b871eac4ff9b653b","observation_id":"4f43f112-0dca-4f46-b9e3-5ebac171cbf6","resolution":{"observed_at":"2026-08-04T16:19:28.203309Z","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":"2026-08-04T16:19:28.312253Z","title":"Smoothquant: Accurate and efficient post-training quantization for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:28.312253Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:b830dcb3674b04feea6c01542214889ac0af10a7e522333ad50f9ef3e1f11abc","observation_id":"c6a1c1b6-b4fd-49d6-82ca-bd7ff82f6122","resolution":{"observed_at":"2026-08-04T16:19:28.312253Z","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":"2026-08-04T16:19:28.383550Z","title":"Beyond perplexity: Multi-dimensional safety evaluation of LLM compression","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:28.383550Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:7c0528f2b8e1603b043a63c39473c9a3e140a1ea302d72000958017c6dd27e05","observation_id":"a8caafdb-d518-4c02-9c0b-de6c5b4556a6","resolution":{"observed_at":"2026-08-04T16:19:28.383550Z","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":"2026-08-04T16:19:28.510608Z","title":"Zeroquant: Efficient and affordable post-training quantization for large-scale transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:28.510608Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:74624d2a2d5fae3febdf55b8af5747db9361f86b188117579368c7838a454d11","observation_id":"2ff11535-f2bf-46e3-9c70-fe230c344d52","resolution":{"observed_at":"2026-08-04T16:19:28.510608Z","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":"2026-08-04T16:19:28.617157Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:28.617157Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:2e9e9e51ab965d33db360cc08a765923aacbf86def92dc9b8bf1227dea945c04","observation_id":"cf6539ab-2f1a-43fa-b066-821a1596dcd4","resolution":{"observed_at":"2026-08-04T16:19:28.617157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-04T16:19:28.752954Z","title":"Opt: Open pre-trained transformer language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:28.752954Z"},"links":{"cited_paper":"/paper/2205.01068","citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:1a5724cc491bb42af2d8199937a34617136eb845732ba28f524d282a2475ff01","observation_id":"6e5466e9-b605-43fa-9b92-ceabc06d8cd4","resolution":{"observed_at":"2026-08-04T16:19:28.752954Z","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":"2026-08-04T16:19:28.883427Z","title":"Unibias: Unveiling and mitigating llm bias through internal attention and ffn manipulation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:28.883427Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:809b922982310b0a5186e57cbf300abe6add030c3dc896817d9b57c46bf83bde","observation_id":"0ce1f265-3339-4678-be54-3916b49426d7","resolution":{"observed_at":"2026-08-04T16:19:28.883427Z","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":"2026-08-04T16:19:29.045216Z","title":"A survey on model compression for large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:29.045216Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:2a62445cc932d372cb991477ff59b302a23c50ea32f76cfb5374adf5df76151c","observation_id":"51e30214-c7b7-4ed4-86c5-ba3675682962","resolution":{"observed_at":"2026-08-04T16:19:29.045216Z","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":"2026-08-04T16:19:29.246452Z","title":"Mielke, Hanna Wallach, and Ryan Cotterell","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","version":3},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-04T16:19:29.246452Z"},"links":{"citing_paper":"/paper/2509.15206"},"observation_digest":"sha256:ca545b3e8074c337cb97ca835e724029460a89741457e333ac3c85c259965d52","observation_id":"c5477a84-c659-496f-8a61-6a94560e97fb","resolution":{"observed_at":"2026-08-04T16:19:29.246452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.15206","last_updated":"2026-07-06T11:20:29Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-12T12:55:58.504974Z","submitted_at":"2025-09-18T17:56:16Z","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":56,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":58},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 0 inbound Pith citation observations for arXiv:2509.15206."}