{"as_of":"2026-08-17T19:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:812dfbb760994f8478025a1fb74069dc1b248e4a26f0944f37d13550caabca10","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-20T12:56:48.177386Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"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/2605.17997/citation-record","integrity":"/paper/2605.17997/integrity","json":"/paper/2605.17997/citation-record.json","paper":"/paper/2605.17997"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Llama 3 model card","venue":null,"work_id":"07ecd780-67f0-4775-9528-f2ea56a4f1b3","year":2024},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:e0ecc68544e756cc0de2161b5c4c21d3d480cc07873c2b0980ba464b6d8b2535","observation_id":"5e23fc2d-5212-4b40-8ae1-584000dc5beb","resolution":{"observed_at":"2026-05-20T12:58:18.428754Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A pid controller approach for stochastic optimization of deep networks","venue":null,"work_id":"94f0baf7-2ec6-4424-9cf6-d6f93c06c8a0","year":2018},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:ae160b7a870ba01e6e0db3153e90ec6c0409e23cb821c40820f07976083147f0","observation_id":"2314d70a-af98-4cb8-a855-191a77c93bd6","resolution":{"observed_at":"2026-05-20T12:58:18.430623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Quarot: Outlier-free 4-bit inference in rotated llms","venue":null,"work_id":"fd7ddeb4-51c5-45cc-8803-c7425090ea8c","year":2024},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:4800bc88708b0e4d0da183dd2fde11d0bf8f84ca3bc832d2f3dbb335e68ea257","observation_id":"b3a0eef5-718c-41e2-8242-d45f4b65cf6c","resolution":{"observed_at":"2026-05-20T12:58:18.427049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"10.1609/aaai.v34i05.6239","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"PIQA: Reasoning about physical commonsense in natural language","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","work_id":"d1a9f293-b596-42e3-b48c-112b9f9a06df","year":2020},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:7bc53a6ebae39548bbbf4c9c0d1e244057dcac595f3ef77162d2863dc5818a92","observation_id":"5eb3791e-8a8e-4040-bbce-71e4a464964c","resolution":{"observed_at":"2026-05-20T12:58:17.508926Z","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":"2026-08-01T09:08:05.075041+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-01T09:08:05.075041+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00828","last_updated":"2024-03-31T23:46:51Z","snapshot_observed_at":"2026-08-16T14:04:47.492805Z","submitted_at":"2024-03-31T23:46:51Z","title":"PID Control-Based Self-Healing to Improve the Robustness of Large Language Models","version":1},"cited_work":{"arxiv_id":"2404.00828","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.00828","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pid control-based self-healing to improve the robustness of large language models","venue":null,"work_id":"18275fcf-7267-4369-8413-ab1c3d4d4750","year":2024},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2404.00828","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:5b02c7c87c77ab1b786a406247f237d70da23a0ce3d996b342146e69a9a22a32","observation_id":"d42e02bb-3043-449b-82f9-ebe753fa80b8","resolution":{"observed_at":"2026-05-20T12:58:17.756074Z","resolver_source":"arxiv_id","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"b26c78d9-969c-4928-b6c1-b374417665b5","year":2024},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:8f88ee8a51322318a205b72dd1c93dd82c0c9e67c5bef06a6dfa6d0a0fe95034","observation_id":"5623fd9b-d973-4431-a404-c35a09d6a3a2","resolution":{"observed_at":"2026-05-20T12:58:18.454596Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"10.18653/v1/n19-1300","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"B ool Q : Exploring the Surprising Difficulty of Natural Yes/No Questions","venue":null,"work_id":"b0eff16f-bbcd-4d66-a41d-d89ff07a80e5","year":2019},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:4d7c26132f27a2b27e550a5c5f60428f6810804b9fdb1acdec86f08800729246","observation_id":"29262097-b4cf-47d6-92a3-1ba94498735b","resolution":{"observed_at":"2026-05-20T12:58:17.503138Z","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":"2026-08-14T20:38:13.539871+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-14T20:38:13.539871+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"1803.05457","doi":"10.1162/tacl_a_00448.https://aclanthology.org/2022.tacl-1.5","metadata_source":"pith","pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","venue":"cs.AI","work_id":"28ea1282-d657-4c61-a83c-f1249be6d6b1","year":2018},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:42f0254c4d5df988e8e073acc569aa3e80679a513f1b4e8484e38bd725bc2eaa","observation_id":"e3b3c9ca-827e-4fe2-9394-8da7a27453a9","resolution":{"observed_at":"2026-05-20T12:58:17.759079Z","resolver_source":"local_arxiv","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":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":"2010.11929","doi":"10.1175/jcli-d-22-0357.1","metadata_source":"pith","pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","venue":"cs.CV","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","year":2020},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:118311d167195e9d268345f45e0d5f538ef2d5598a61281aeea4da3cf39758d0","observation_id":"e84ad82b-944e-4006-82c4-0ba1916ba47e","resolution":{"observed_at":"2026-05-20T12:58:17.751899Z","resolver_source":"local_arxiv","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Optimal brain compression: A framework for accurate post-training quantization and pruning.Advances in Neural Information Processing Systems, 35:4475–4488","venue":null,"work_id":"162882bd-7059-40a6-af79-7ca9d8297759","year":2022},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:2ee8ddb37ecba4e3dd13585d55967c3a2a0b2a481c4f408918f3c1ace7f23987","observation_id":"abf7c485-52df-4c68-8b36-bf1c0b65f993","resolution":{"observed_at":"2026-05-20T12:58:18.432784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"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":"2210.17323","doi":"10.48550/arxiv.2210.17323","metadata_source":"pith","pith_arxiv_id":"2210.17323","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","venue":"cs.LG","work_id":"19ed8c44-202a-48f6-8169-637d5a5f2408","year":2022},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:af7fd1cc4485ccc9f54d4a2852e1cc8e185224fce15bb589f2fbc7f3340342a8","observation_id":"6c5996bb-ba67-45bc-bdbd-621fe705e684","resolution":{"observed_at":"2026-05-20T12:58:17.768349Z","resolver_source":"local_arxiv","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":"2026-08-15T03:08:15.265514+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-15T03:08:15.265514+00:00","source":"openalex_status_cache"},{"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pushing the limit of post-training quantization.IEEE Transactions on Pattern Analysis and Machine Intelligence","venue":null,"work_id":"ed79bfae-7c1e-4e72-acc8-86f03cb90afa","year":2025},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:70d62ee2812a00dd94f89294d48b0465cdbdb58d18dff9a8385e6ae88babc27e","observation_id":"73775a1e-3e24-4c66-a7df-007700d5a8c9","resolution":{"observed_at":"2026-05-20T12:58:18.437162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-06T18:32:48.716398Z","title":"Knowledge distillation: A survey","venue":null,"work_id":"5107b3ea-e909-4621-b7e9-f9a1ec0e5134","year":2021},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:72aeb4f8d0cbdbbe1bd20a33b223b2d10eb88c59694f45791cd4585c73e8c026","observation_id":"34d22181-1ab6-4e48-ba6b-d1c5df953790","resolution":{"observed_at":"2026-05-20T12:58:18.439053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Optimal brain surgeon and general network pruning","venue":null,"work_id":"421d2920-c824-4b49-827c-ea4952abea53","year":1993},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:614f2dd07c3ecb053951ac274606042c4ad93a878e0c692cf80569c1488f9a67","observation_id":"3f247221-c1ed-48ba-8ca2-840e6aefba1a","resolution":{"observed_at":"2026-05-20T12:58:18.450717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-08T09:14:47.748213Z","title":"Mb-taylorformer v2: Improved multi-branch linear transformer expanded by taylor formula for image restoration.IEEE Transactions on Pattern Analysis and Machine Intelligence","venue":null,"work_id":"abb8b83e-e6c1-47bd-8d05-3b34e01ca9f2","year":2025},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:405676c8d5a8400839b85bf363bfc47c0052ef414a2fd565946e566931f9c26c","observation_id":"48179e1d-75e6-488f-b921-f7e7f901787b","resolution":{"observed_at":"2026-05-20T12:58:18.446857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Owq: Outlier-aware weight quantization for efficient fine-tuning and inference of large language models","venue":null,"work_id":"b626b647-2f28-4e27-a98d-e9cfa27ae8dd","year":2024},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:20b97ed281b0daf9bed2e4a4978f5118fe7c907f748caaf5937acf549cc27c60","observation_id":"5d0af67b-3a30-4807-8a54-3e4b8597e6cd","resolution":{"observed_at":"2026-05-20T12:58:18.452868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2604.07955","last_updated":"2026-04-09T08:20:59Z","snapshot_observed_at":"2026-08-11T08:12:25.572641Z","submitted_at":"2026-04-09T08:20:59Z","title":"Rethinking Residual Errors in Compensation-based LLM Quantization","version":1},"cited_work":{"arxiv_id":"2604.07955","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07955","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Rethinking Residual Errors in Compensation-based LLM Quantization","venue":"cs.LG","work_id":"d1bba1f2-92e3-4c67-b60e-7f4a8f472c33","year":2026},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2604.07955","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:09d6d408ae27bb76d93a4a26650484196014841365b31a873ac5c1dd1f752094","observation_id":"5116b8df-976d-46e2-93ff-3125cb07332f","resolution":{"observed_at":"2026-05-20T12:58:17.774104Z","resolver_source":"local_arxiv","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":{"arxiv_id":"2102.05426","last_updated":"2021-07-25T09:34:39Z","snapshot_observed_at":"2026-08-16T18:46:30.310486Z","submitted_at":"2021-02-10T13:46:16Z","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","version":2},"cited_work":{"arxiv_id":"2102.05426","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2102.05426","snapshot_observed_at":"2026-07-02T08:16:48.283550Z","title":"Brecq: Pushing the limit of post-training quantization by block reconstruction.arXiv preprint arXiv:2102.05426","venue":null,"work_id":"ddb603e2-b7ab-4904-8a08-89b0622424f7","year":2021},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2102.05426","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:3b2aaf6f8521b5caa13ce5e2408e31bad6a24fcccca3e434d31086a0086ef8eb","observation_id":"ed23cfc9-80c5-4b50-b812-3cf219f8499c","resolution":{"observed_at":"2026-05-20T12:58:17.793673Z","resolver_source":"arxiv_id","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":{"arxiv_id":"2504.02692","last_updated":"2025-05-13T17:54:56Z","snapshot_observed_at":"2026-08-16T12:44:13.286364Z","submitted_at":"2025-04-03T15:30:43Z","title":"GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration","version":3},"cited_work":{"arxiv_id":"2504.02692","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.02692","snapshot_observed_at":"2026-07-10T14:47:14.597664Z","title":"Gptaq: Efficient finetuning- free quantization for asymmetric calibration","venue":"cs.LG","work_id":"9d8a601e-0c17-4f52-b63b-9e3e219c1078","year":2025},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2504.02692","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:a5e8f5277fd61dfa95b25f235351f28fafc1cc8624a1c00b009eb17a2662797d","observation_id":"2b0a8e15-181d-486d-9aff-68e278f833b0","resolution":{"observed_at":"2026-05-20T12:58:17.782611Z","resolver_source":"arxiv_id","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Repq-vit: Scale reparameterization for post- training quantization of vision transformers","venue":null,"work_id":"f3f05eef-d33d-4269-bcaa-41f826c20008","year":2023},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:1ae5e17495e7d22ff7fb45b1853187ef7909cde1f2b44f48e0536e0883e81a20","observation_id":"e29c620b-4519-4a39-99f9-a4bff840fc21","resolution":{"observed_at":"2026-05-20T12:58:18.471625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lightweight deep learning for resource-constrained environments: A survey.ACM Computing Surveys, 56(10):1–42","venue":null,"work_id":"5813e482-4449-4ee9-b24a-43a215c199d1","year":2024},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:79cfc14e61c0ccc2199975023556c0b6a5d3254925cbea1c798ec9e0f499117a","observation_id":"94bce6eb-38bb-4225-9c2b-653bb845995e","resolution":{"observed_at":"2026-05-20T12:58:18.473506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2505.05530","last_updated":"2025-05-08T13:26:19Z","snapshot_observed_at":"2026-08-17T13:34:18.858488Z","submitted_at":"2025-05-08T13:26:19Z","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","version":1},"cited_work":{"arxiv_id":"2505.05530","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.05530","snapshot_observed_at":"2026-07-01T15:45:48.761436Z","title":"arXiv preprint arXiv:2505.05530 , year=","venue":null,"work_id":"1e774860-eac0-4be9-981e-1b6fd9fa75fb","year":2025},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2505.05530","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:45e869ed5129de6cb0e0bc4e3534a8be7c4fd9826e1d508fa7d17e8713268039","observation_id":"d241124c-6c77-482f-a11a-e77cc63a4737","resolution":{"observed_at":"2026-05-20T12:58:17.777018Z","resolver_source":"arxiv_id","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-07T23:54:19.119275Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":"d577574a-ec23-4a36-89fc-494c4f56328e","year":2021},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:9fd18d4b50c4a780644b8f527fb562aebe4081ce31d46010276f2cef19d4df83","observation_id":"a154513e-13b7-4b59-b26a-e50e45ae674d","resolution":{"observed_at":"2026-05-20T12:58:18.467803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2405.16406","last_updated":"2025-02-20T06:07:00Z","snapshot_observed_at":"2026-08-16T17:18:05.876361Z","submitted_at":"2024-05-26T02:15:49Z","title":"SpinQuant: LLM quantization with learned rotations","version":4},"cited_work":{"arxiv_id":"2405.16406","doi":"10.48550/arxiv.2405.16406","metadata_source":"pith","pith_arxiv_id":"2405.16406","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"SpinQuant: LLM quantization with learned rotations","venue":"cs.LG","work_id":"489855f8-bd1c-4c87-a334-f6ab27d6707d","year":2024},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2405.16406","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:69a2dfc32af9b01d447e98c6892ff5f9ad704e7a1f4d09ea31465edb6d309509","observation_id":"6dcb3097-e125-4c1b-9c8c-0ad798ae27bc","resolution":{"observed_at":"2026-05-20T12:58:17.764929Z","resolver_source":"local_arxiv","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"cd38e4ae-1783-443b-9716-5e1a965f0c0e","year":2021},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:3dd7471eeb8070895feacef6cd9b434f4ebcc640d0cf1a64fcb2920755a6ee8a","observation_id":"526e03ff-6925-4153-a669-2c49b631071e","resolution":{"observed_at":"2026-05-20T12:58:18.460011Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Meta pid attention network for flexible and efficient real-world noisy image denoising.IEEE Transactions on Image Processing, 31:2053–2066","venue":null,"work_id":"57e28aee-b1ff-49cc-8877-2e16510553af","year":2053},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:e666eaf0ac7a30260fa944a4b031f013ad44c0a535b52433f60acbdc44d63ef2","observation_id":"2317e166-c1d2-4f14-8751-0a3d3e8924b2","resolution":{"observed_at":"2026-05-20T12:58:18.469742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"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":"1609.07843","doi":"10.1007/978-3-030-62077-6","metadata_source":"pith","pith_arxiv_id":"1609.07843","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Pointer Sentinel Mixture Models","venue":"cs.CL","work_id":"fef3833e-dc80-42a3-a1e0-ffbfafee6fff","year":2016},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/1609.07843","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:6f79e03cbc5162140b98a3350b497d33550cbab5605a58c25579b3d75c222434","observation_id":"42b0cbb7-d798-40c1-9e71-dfe5f3d8f928","resolution":{"observed_at":"2026-05-20T12:58:17.790762Z","resolver_source":"local_arxiv","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Up or down? adaptive rounding for post-training quantization","venue":null,"work_id":"9c2c6f4a-72be-4eae-960b-6f42a756897d","year":2020},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:f69a9ffd3ce109b84335b41c90bb427a449294eebf2250171bdf82bf1419c616","observation_id":"5025ebf4-dd69-473d-9672-16c1806de925","resolution":{"observed_at":"2026-05-20T12:58:18.442799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mb-taylorformer: Multi-branch efficient transformer expanded by taylor formula for image dehazing","venue":null,"work_id":"758c8551-9e8f-4203-a570-955d951367d5","year":2023},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:31f202aebc5a12cc478098c2adca7bc833d33dd4b09ebe63cc158e857eef3353","observation_id":"f0d27acc-5663-4c71-83c8-470004c4800d","resolution":{"observed_at":"2026-05-20T12:58:18.444848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer","venue":null,"work_id":"eb47c630-8bcd-4f31-bc25-f7c73903d972","year":2020},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:cb6a8af1168117149f55f663b8e4bbdb0df747dae2e95284be2370907ca625f7","observation_id":"6449b9e5-bc47-484e-b246-3da6dc2f796a","resolution":{"observed_at":"2026-05-20T12:58:18.479584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Imagenet large scale visual recognition challenge","venue":null,"work_id":"128c0a22-7ab8-40e6-9620-0faacd140bc4","year":2015},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:eff24e679f43a0739e80895818defdfed8806b113a65bbb13384e72ee4a05802","observation_id":"1af070ae-20eb-47e5-b381-386491c62a11","resolution":{"observed_at":"2026-05-20T12:58:18.481442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"WinoGrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 64(9):99–106","venue":null,"work_id":"88994fe4-dc6a-4f19-b5cd-61c4be019f0f","year":2021},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:a4c76913f43d1c1550dc36bff7bae10f5b97b121db9c01e37b977316506b0f8b","observation_id":"b960424b-52f1-4d50-a7da-2eb77c5d7207","resolution":{"observed_at":"2026-05-20T12:58:18.440933Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Globally optimal policy gradient algorithms for reinforcement learning with pid control policies","venue":null,"work_id":"4b8f45a0-881e-44b2-98fd-b6fb51dd41de","year":null},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:40348b486ff2794b40e5e834ad746bf89240c46fa0a662721e0f96c9fd1db795","observation_id":"8168c6ff-68bd-480f-aa48-cd9e9a9dd439","resolution":{"observed_at":"2026-05-20T12:58:18.477236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A simple and effective pruning approach for large language models","venue":null,"work_id":"9e932dd7-4c46-40fa-b14f-6a41bb06f09b","year":2024},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:d51042ced1e1b3c614ef1e3ab062d90f0ebe648a8ee36eab936aed44e063afbd","observation_id":"12e3f5fd-ff5e-4919-abba-ee6264253070","resolution":{"observed_at":"2026-05-20T12:58:18.448915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Training data-efficient image transformers & distillation through attention","venue":null,"work_id":"692f8513-6eba-4c5b-b9e9-ec03f978b69d","year":2021},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:78b3dfa868e22b421111f471941d15c598b4f55eb975bdbd195baa500b4fdfd9","observation_id":"b96b17fe-c99e-411d-b7a6-c40b18cbc28b","resolution":{"observed_at":"2026-05-20T12:58:18.435193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":"2307.09288","doi":"10.24963/ijcai.2025/706","metadata_source":"pith","pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","venue":"cs.CL","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","year":2023},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:8243d87efab8b92e8c1fbee3f7a88ddae50eb074095b5a9916baef2cf136c0b9","observation_id":"70cc7d35-0d01-48d6-b353-0af6e31efe63","resolution":{"observed_at":"2026-05-20T12:58:17.788002Z","resolver_source":"local_arxiv","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":{"arxiv_id":"2203.05740","last_updated":"2023-02-21T11:24:41Z","snapshot_observed_at":"2026-08-16T17:15:24.808674Z","submitted_at":"2022-03-11T04:01:53Z","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","version":2},"cited_work":{"arxiv_id":"2203.05740","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.05740","snapshot_observed_at":"2026-07-02T08:16:48.290504Z","title":"Qdrop: Randomly dropping quantization for extremely low-bit post-training quantization","venue":null,"work_id":"7ec52667-7b82-4b3c-b5ef-7f45a81015f9","year":2022},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2203.05740","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:1f10ff2a797edc7ae1bfe854a5b1a779ccbe375626d4b2b8e33fee79dc258ec8","observation_id":"391be1b4-f984-48d2-b99c-d145c673b518","resolution":{"observed_at":"2026-05-20T12:58:17.771436Z","resolver_source":"arxiv_id","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Adalog: Post-training quantization for vision transformers with adaptive logarithm quantizer","venue":null,"work_id":"39d26341-c04e-417f-982d-c5e4be17e411","year":2024},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:342f2b270a9783c0523f6662b7b592061b567611567e585ca41cec7ac70c9946","observation_id":"2497c24e-cf05-4225-b5af-6a8a2c98398d","resolution":{"observed_at":"2026-05-20T12:58:18.456481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fima-q: Post-training quantization for vision transformers by fisher information matrix approximation","venue":null,"work_id":"8bb8a619-6214-4acd-8542-76877db3a3c0","year":2025},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:3344a1dd4c5ac285df4ed4bc342a9de77123b7fe67efefb1462dbe0c4ae0bc7d","observation_id":"a6f44942-7f71-423c-b022-59e7cb148ef3","resolution":{"observed_at":"2026-05-20T12:58:18.475291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Smoothquant: Accurate and efficient post-training quantization for large language models","venue":null,"work_id":"77fc2260-e069-4a67-902b-18c51bfc7a29","year":2023},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:ddcff2b3381414760458bdab47980e52c7e54e2078636f1629e5dcbed970ed37","observation_id":"5c8f891c-1472-45e6-8984-c3828a776e03","resolution":{"observed_at":"2026-05-20T12:58:18.486677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":"2505.09388","doi":"10.1016/j.aiopen.2022.12","metadata_source":"pith","pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Qwen3 Technical Report","venue":"cs.CL","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","year":2025},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:692a551ccf50b43126dea0bdb9074052b68b54dd4369feb73cb263cbe82a4925","observation_id":"082e53a2-1a6e-46f1-8d68-74048a375594","resolution":{"observed_at":"2026-05-20T12:58:17.779815Z","resolver_source":"local_arxiv","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Self-supervised graph neural networks via low-rank decomposition.Advances in Neural Information Processing Systems, 36:34295–34307","venue":null,"work_id":"8b2e6bdf-9cff-4619-a7fb-bc38a5993884","year":2023},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:c0e0dd27c8ed3e3a7630b2ada0227c0e0725ad82666ab2e707d4df588f26b22d","observation_id":"3988bb82-32d0-4ce5-b050-a9e4da11b075","resolution":{"observed_at":"2026-05-20T12:58:18.461913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ptq4vit: Post-training quantization for vision transformers with twin uniform quantization","venue":null,"work_id":"01973771-1015-4e8b-944d-9a58c7000669","year":2022},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:27ac208a7c0959841c703f9ffa7d79649d9878fa1e1d36fa41fdd44a35abffa3","observation_id":"6b88339a-32df-478a-8720-9154d0569373","resolution":{"observed_at":"2026-05-20T12:58:18.465642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"10.18653/v1/p19-1472","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T12:07:03.406813Z","title":"URL https:// doi.org/10.18653/v1/p19-1472","venue":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","work_id":"11bfc949-547c-40f3-a86d-953eb9b2154c","year":2019},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:fbe9b7c02d58e4dccba1cc3b8ed8e32a7a67248c083a7a1eadb6e7caf8614830","observation_id":"49ad8247-3a57-4366-880b-b5ab0fd5e807","resolution":{"observed_at":"2026-05-20T12:58:17.506077Z","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":"2026-08-14T20:38:10.937946+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-14T20:38:10.937946+00:00","source":"openalex_status_cache"},{"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Decoupled knowledge distillation","venue":null,"work_id":"59384485-6f49-4ef2-853a-309d477179ae","year":2022},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:c2df38ba4e3ec31bdb152727295ceba6844160cb7e2d36d07d8f00718456538a","observation_id":"880b6185-d326-4001-ba20-ec3d344a0ed8","resolution":{"observed_at":"2026-05-20T12:58:18.458270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"First-order error matters: Accurate compensation for quantized large language models","venue":null,"work_id":"0d463cfb-36b3-455a-ad1e-6dfa26d85d78","year":2026},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:e21c8321b78a6523e15e88b53bfbb2f52e139f848059e6f01fec3cdc59313367","observation_id":"3da51741-7bf4-4666-aeb6-754beeffc9a6","resolution":{"observed_at":"2026-05-20T12:58:18.463771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2311.10126","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T08:09:41.098765Z","title":"I&s-vit: An inclusive & stable method for pushing the limit of post-training vits quantization","venue":null,"work_id":"ae2ce5e1-c043-424a-a66b-19563e834c22","year":2023},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:95f664bef0cff823ef084f2747767fe97af8a402890ca5602bad6eb1583d9505","observation_id":"ae691778-6fca-41da-99c4-3cfcc6e8bcc0","resolution":{"observed_at":"2026-05-20T12:58:17.762173Z","resolver_source":"arxiv_id","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":"6043.3071","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards accurate post-training quantization of vision transformers via error reduction.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4):2676–2692","venue":null,"work_id":"9909dfff-df8f-4050-bd54-6edb9159e2ea","year":2025},"citing_paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-20T12:56:48.177386Z"},"links":{"citing_paper":"/paper/2605.17997"},"observation_digest":"sha256:12a6b09e535b1c0c05ea569473c0161ba9314daa025cbab21adb8c3ad07e9b69","observation_id":"6f0022de-fc24-470f-8eb1-20ce931a7e95","resolution":{"observed_at":"2026-05-20T12:58:17.785413Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"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"}}],"paper":{"arxiv_id":"2605.17997","last_updated":"2026-05-18T07:51:49Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T20:09:44.271449Z","submitted_at":"2026-05-18T07:51:49Z","title":"MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":2,"verified_exact":17,"verified_fuzzy":27},"total_outbound_references":48},"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 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2605.17997."}