{"as_of":"2026-08-21T15:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:72ef97d78cf049a7e632e000a0b56df265dfb61fffcd1b99ef4e0d915365c02d","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:25:30.186633Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T04:38:43.942401Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T16:59:58.450016Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"cited_work":{"arxiv_id":"2505.04877","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.04877","snapshot_observed_at":"2026-07-04T16:59:58.450016Z","title":"arXiv preprint arXiv:2505.04877 (2025)","venue":null,"work_id":"cae329ef-bc0c-48bb-8105-0420532c3520","year":2025},"citing_paper":{"arxiv_id":"2606.25087","last_updated":"2026-06-23T18:48:45Z","snapshot_observed_at":"2026-08-16T11:00:44.828781Z","submitted_at":"2026-06-23T18:48:45Z","title":"Neural Network Quantization by Learning Low-Loss Subspaces","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-26T00:05:03.762579Z"},"links":{"cited_paper":"/paper/2505.04877","citing_paper":"/paper/2606.25087"},"observation_digest":"sha256:b74ec0857ecd25fc322cb6b06f808e0022bd4b2ea2cfd6e991806f6ca697cb1e","observation_id":"62642afe-89ba-4a24-a73e-461589a752d7","resolution":{"observed_at":"2026-07-04T16:59:58.451661Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.04877","snapshot_observed_at":"2026-08-14T04:38:43.942401Z","title":"arXiv preprint arXiv:2505.04877 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.08506","last_updated":"2026-08-09T06:03:48Z","snapshot_observed_at":"2026-08-20T01:43:54.976595Z","submitted_at":"2026-08-09T06:03:48Z","title":"Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs","version":1},"reference_index":111,"source":"arxiv_source","source_observed_at":"2026-08-14T04:38:43.942401Z"},"links":{"cited_paper":"/paper/2505.04877","citing_paper":"/paper/2608.08506"},"observation_digest":"sha256:5fae70aac297094a6eacd3c9f4e30657b3133e5b4bb62c7fa41c7915ce45de4d","observation_id":"f722e321-f99a-449a-aa68-11fb7378dbdc","resolution":{"observed_at":"2026-08-14T04:38:43.942401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.04877/citation-record","integrity":"/paper/2505.04877/integrity","json":"/paper/2505.04877/citation-record.json","paper":"/paper/2505.04877"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:25:30.093506Z","title":"Food-101– mining discriminative components with random forests","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.093506Z"},"links":{"citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:a0f12e5899f22e35225af7d1d41f8211e1861899b5ff34d8d98867ee2da334a5","observation_id":"0a1cd589-c158-452d-9e52-169edae8b995","resolution":{"observed_at":"2026-08-15T23:25:30.093506Z","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":"2026-08-15T23:25:30.118168Z","title":"Single path one-shot neural architecture search with uniform sampling","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.118168Z"},"links":{"citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:a72f5a01d24858c1eef41aeee4f582f6672cc0dbe156934417e7f96207f9e220","observation_id":"34e2ed55-b545-479c-93d6-ad2603aa3c85","resolution":{"observed_at":"2026-08-15T23:25:30.118168Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:25:30.465791Z","title":"V ., Jennings, R","venue":null,"work_id":"ce87e8f8-3b92-4de4-a53a-6051190ea2d5","year":2020},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.122935Z"},"links":{"citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:d57898e03f930098fd72acb42494832aa20c3e0b29559329186e8bd9e190d06b","observation_id":"c43b80b5-ebbc-4078-b9e2-bc8cd073fcff","resolution":{"observed_at":"2026-08-15T23:25:30.470377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:25:30.449714Z","title":"Simplified pac-bayesian margin bounds","venue":null,"work_id":"cbd0a7d1-0ff2-4bc9-a45c-d8e67aa02c9d","year":2003},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.137313Z"},"links":{"citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:5344e680171531c27c0641509cfd5dc0684730f0dec863389db23b4683e7d285","observation_id":"467484c6-f878-46e7-843e-72a7a505d889","resolution":{"observed_at":"2026-08-15T23:25:30.454547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11452","last_updated":"2020-05-22T17:02:41Z","snapshot_observed_at":"2026-08-15T23:55:48.282700Z","submitted_at":"2019-05-27T19:03:40Z","title":"Mixed Precision DNNs: All you need is a good parametrization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11452","snapshot_observed_at":"2026-08-15T23:25:30.152432Z","title":"A., Tiedemann, S., Kemp, T., and Nakamura, A","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.152432Z"},"links":{"cited_paper":"/paper/1905.11452","citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:e33d98c66d9a472b66455f365b7fa5512e8b041ad0d08d07b05c6f2936cbd787","observation_id":"9ad7c615-c3c3-463e-bcc5-0877934bf831","resolution":{"observed_at":"2026-08-15T23:25:30.152432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00090","last_updated":"2018-11-30T23:15:45Z","snapshot_observed_at":"2026-08-14T17:50:18.985454Z","submitted_at":"2018-11-30T23:15:45Z","title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00090","snapshot_observed_at":"2026-08-15T23:25:30.157791Z","title":"Mixed precision quantization of convnets via dif- ferentiable neural architecture search","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.157791Z"},"links":{"cited_paper":"/paper/1812.00090","citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:ef8707ca10a4e6ca4d82540d494c0323638b86a164b999161cc3fe04d60c8e48","observation_id":"c42b3453-f93a-4c35-a3d8-ad486b6da0be","resolution":{"observed_at":"2026-08-15T23:25:30.157791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:25:30.423861Z","title":"Search what you want: Barrier panelty nas for mixed precision quantization","venue":null,"work_id":"f5462cfb-6afb-4b21-99d6-0ac9ebff77bf","year":2020},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.162804Z"},"links":{"citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:422d9f16811cdde2e726b578aca82da828fa2da56ac0c30528d8f6ea9b404795","observation_id":"f68e3b0d-a77d-4574-bd55-86cd6fc0ebe0","resolution":{"observed_at":"2026-08-15T23:25:30.428887Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.08065","last_updated":"2022-03-19T15:56:32Z","snapshot_observed_at":"2026-08-16T17:14:21.841080Z","submitted_at":"2022-03-15T16:57:59Z","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.08065","snapshot_observed_at":"2026-08-15T23:25:30.172502Z","title":"Surrogate gap minimization improves sharpness-aware training","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.172502Z"},"links":{"cited_paper":"/paper/2203.08065","citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:facd567d740c76557a199b4c6a07c381423703eb94a96580e8d104398705a0a2","observation_id":"35aad018-5cbe-41e1-89cd-d7dae2ef0216","resolution":{"observed_at":"2026-08-15T23:25:30.172502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:25:30.408323Z","title":null,"venue":null,"work_id":"ec0a20d5-deb0-4dbd-b8ba-b6e8dc28d13c","year":2023},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.177335Z"},"links":{"citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:a63c1051968bac85742d9e0f718480ed4e002c4ba96295c771d43188b97bcba0","observation_id":"0b0a3854-7a53-4e46-949f-38b3534a039f","resolution":{"observed_at":"2026-08-15T23:25:30.413181Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:25:30.392776Z","title":"This shows that ASGA effectively reduces the upper bound of the generalization error during the MPQ process","venue":null,"work_id":"5e774536-951c-4ccb-884b-771a0b26d8bb","year":2003},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.181893Z"},"links":{"citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:6a215ca4485956ca323d6e808f8a8394d39745c97bac3decf34ae098b6a17545","observation_id":"e56d02e5-1600-466f-8e86-9561182fe9a2","resolution":{"observed_at":"2026-08-15T23:25:30.397694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:25:30.375536Z","title":"14 Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning Details of models","venue":null,"work_id":"ec49c716-dea1-4db3-8a5b-fed9d2118d56","year":2016},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.186633Z"},"links":{"citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:e9518323649852b2cff503de103d0045f0f283f5e77e3f4e3964e7a62fdeccfc","observation_id":"b49eba51-1ed6-4089-b224-c5b83bbab535","resolution":{"observed_at":"2026-08-15T23:25:30.382492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T23:25:30.141692Z","title":"and Zisserman, A","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":2003,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.141692Z"},"links":{"citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:3a552fb300bb7437d992fdffe5816d24c5f48a11f532a52a05cee9c82b5b9c2a","observation_id":"3d1c0207-8807-4573-807d-ef7f542fbb62","resolution":{"observed_at":"2026-08-15T23:25:30.141692Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01412","last_updated":"2021-04-29T16:44:25Z","snapshot_observed_at":"2026-08-20T01:10:01.850538Z","submitted_at":"2020-10-03T19:02:10Z","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01412","snapshot_observed_at":"2026-08-15T23:25:30.113568Z","title":"Sharpness-aware minimization for efficiently improving generalization","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":2010,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.113568Z"},"links":{"cited_paper":"/paper/2010.01412","citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:79d88b54d8739296e959796932bebb66d23e629d36385402b1555cd6ff2c3065","observation_id":"5bff0267-8237-48ee-b53d-2267c762ad18","resolution":{"observed_at":"2026-08-15T23:25:30.113568Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.14647","last_updated":"2023-04-28T06:23:32Z","snapshot_observed_at":"2026-08-16T15:37:04.134239Z","submitted_at":"2023-04-28T06:23:32Z","title":"An Adaptive Policy to Employ Sharpness-Aware Minimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.14647","snapshot_observed_at":"2026-08-15T23:25:30.127668Z","title":"An adaptive policy to employ sharpness-aware minimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.127668Z"},"links":{"cited_paper":"/paper/2304.14647","citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:5f6355aa447dba5e2ec287ea47ee7dd168e92e56de87a548240613d26a987f05","observation_id":"1cbee745-a14f-4b9d-8f06-698807ca2d60","resolution":{"observed_at":"2026-08-15T23:25:30.127668Z","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":"2026-08-15T23:25:30.104116Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.104116Z"},"links":{"citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:4a9a6141c8be56d816305e1da601da965bf1f1252770084f84afc6a9afba9361","observation_id":"76fb5c4c-ebfa-4c9c-a1b4-e9539adeb18c","resolution":{"observed_at":"2026-08-15T23:25:30.104116Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-18T09:17:55.370547Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-15T23:25:30.108649Z","title":"K., McKinstry, J","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.108649Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:2fdfd09f804ea8d3d99480baccb89e803a3ef216ba33593fefa17ff6142f1640","observation_id":"6f016767-6db1-44a6-b060-7655cb905541","resolution":{"observed_at":"2026-08-15T23:25:30.108649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06085","last_updated":"2018-07-17T07:33:19Z","snapshot_observed_at":"2026-08-17T06:12:39.940205Z","submitted_at":"2018-05-16T01:19:43Z","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.06085","snapshot_observed_at":"2026-08-15T23:25:30.098821Z","title":"I.-J., Srini- vasan, V ., and Gopalakrishnan, K","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.098821Z"},"links":{"cited_paper":"/paper/1805.06085","citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:53b41a69652d3eb85285a5f6d6bcd07e20345dc833dae6fb31728971843abbfa","observation_id":"8456f338-05fa-4043-b994-88fa7db67f01","resolution":{"observed_at":"2026-08-15T23:25:30.098821Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-17T19:17:06.411141Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-15T23:25:30.147509Z","title":"and Zisserman, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.147509Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:648e33214cbdccc8ae08ae2ca62c58796c5962a7eda940f00ab3e06f88fd7093","observation_id":"2f4369b3-2a7a-43f3-a3c3-d8a6a56acaff","resolution":{"observed_at":"2026-08-15T23:25:30.147509Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.04836","last_updated":"2017-02-09T20:38:16Z","snapshot_observed_at":"2026-08-15T20:45:29.277746Z","submitted_at":"2016-09-15T20:03:06Z","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.04836","snapshot_observed_at":"2026-08-15T23:25:30.132499Z","title":"S., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.132499Z"},"links":{"cited_paper":"/paper/1609.04836","citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:de9b557f23d4d4a285f38da5703c2e9520eb8c094edfcf8ece537bbedcd80b74","observation_id":"be27764b-c930-4614-9b60-6a2b6ffa1033","resolution":{"observed_at":"2026-08-15T23:25:30.132499Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.06160","last_updated":"2018-02-02T01:43:54Z","snapshot_observed_at":"2026-08-15T08:38:24.917341Z","submitted_at":"2016-06-20T15:02:31Z","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.06160","snapshot_observed_at":"2026-08-15T23:25:30.167198Z","title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T23:25:30.167198Z"},"links":{"cited_paper":"/paper/1606.06160","citing_paper":"/paper/2505.04877"},"observation_digest":"sha256:e6f8b5fd0345145e5451a8d58b5598633fbe23c8e08fee0be18be83423683351","observation_id":"86c40bd2-f783-4fd8-ba39-70db70f9b903","resolution":{"observed_at":"2026-08-15T23:25:30.167198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.04877","last_updated":"2025-05-08T01:20:24Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T09:18:47.334330Z","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":0,"verified_fuzzy":5},"total_outbound_references":20},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 2 inbound Pith citation observations for arXiv:2505.04877."}