{"as_of":"2026-08-08T06:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6088ed110d6469ba4377e3cddb36b89a80ce8fea4fbada633e81d8f42a845a08","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:48:30.736528Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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":"2026-08-06T17:00:11.926420Z","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":"2026-05-20T20:59:01.882823Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.20932","snapshot_observed_at":"2026-08-06T17:00:11.926420Z","title":"Qwt-v2: Practical, effective and efficient post-training quantization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.12087","last_updated":"2025-07-20T15:16:24Z","snapshot_observed_at":"2026-08-06T20:41:34.598645Z","submitted_at":"2025-07-16T09:51:19Z","title":"YOLOv8-SMOT: An Efficient and Robust Framework for Real-Time Small Object Tracking via Slice-Assisted Training and Adaptive Association","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T17:00:11.926420Z"},"links":{"cited_paper":"/paper/2505.20932","citing_paper":"/paper/2507.12087"},"observation_digest":"sha256:f279ea4ba4ed120953bbe33a84d4bbc31508eac6df35d1bee5a9519761835606","observation_id":"865e6704-8ef8-4a51-9bf7-11c982512118","resolution":{"observed_at":"2026-08-06T17:00:11.926420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"cited_work":{"arxiv_id":"2505.20932","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.20932","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Qwt-v2: Practical, effective and efficient post-training quantization","venue":null,"work_id":"45e36532-6598-41e6-a489-fbafd1fc620a","year":2025},"citing_paper":{"arxiv_id":"2605.16423","last_updated":"2026-05-14T14:55:46Z","snapshot_observed_at":"2026-07-06T23:27:34.514541Z","submitted_at":"2026-05-14T14:55:46Z","title":"Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-20T20:55:10.360775Z"},"links":{"cited_paper":"/paper/2505.20932","citing_paper":"/paper/2605.16423"},"observation_digest":"sha256:4f859a33b326323810b1188ceefc407fd2ceaf2dc8aafae5d586c97f83de1aac","observation_id":"3089416c-90c4-4f02-a27e-80703dcc4c48","resolution":{"observed_at":"2026-05-20T20:59:01.884743Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.20932/citation-record","integrity":"/paper/2505.20932/integrity","json":"/paper/2505.20932/citation-record.json","paper":"/paper/2505.20932"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:48:26.074621Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.074621Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:301b5882b24a648bcff13d93fa033c1e40786ea3d160b268bf2778020552fd82","observation_id":"bdc3d67b-d6fb-4654-b35d-7d9a42be4973","resolution":{"observed_at":"2026-08-07T13:48:26.074621Z","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":"2026-08-07T13:48:39.319922Z","title":"BERT : Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":"99da2522-659c-4023-8bc0-2ed1101c003f","year":2019},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.182003Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:a22d1add7a7c15a58cad3a54861301093cdc9fca0b1a09f0c2cf33d9adf439c2","observation_id":"95fa9f49-3803-45c8-9f9b-064a10c6edcb","resolution":{"observed_at":"2026-08-07T13:48:39.460637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:39.006936Z","title":null,"venue":null,"work_id":"6c73dd11-0c84-4644-969a-496973a1b70a","year":2020},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.349992Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:e8491a6d719d380ac9440e0643c20eab3cfb35de5c1d7519e46efa123a04e111","observation_id":"533560de-9d54-4351-91f3-48ecbc8e1923","resolution":{"observed_at":"2026-08-07T13:48:39.164343Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:38.745742Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"428377fb-29ae-4118-af90-d197aeaf8c35","year":2021},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.509467Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:1e664b88d3bda99959102f13ed6f89ba78ae47500adb9d99e03df7ee7ad96128","observation_id":"a96d340c-dd55-43a3-9bdb-9fc153c47c93","resolution":{"observed_at":"2026-08-07T13:48:38.855065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:38.500403Z","title":"Mask R-CNN","venue":null,"work_id":"47a3963e-a3cb-4e87-98fd-4512f5148b5e","year":2017},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.675668Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:1f19abc9eb86a5a84bf703fa1cf3a2470d4142b238f5c387ddbc6ff6baaaf999","observation_id":"fb28f136-aa4c-49c9-a302-fb38ab977eaf","resolution":{"observed_at":"2026-08-07T13:48:38.633343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:38.270118Z","title":"S peech GPT : Empowering large language models with intrinsic cross-modal conversational abilities\"","venue":null,"work_id":"6ab2733f-0ac4-4785-bbaf-4a1f4b684a87","year":2023},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.789380Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:21467eb6c8dedde0eb819130b6c3c280d60026248f55f5f080e41d6b60b1ea49","observation_id":"48c1c222-d66a-4240-b85f-3ce654aa17d2","resolution":{"observed_at":"2026-08-07T13:48:38.393437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:37.966954Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":"6532ddbb-d32e-4717-8cae-0c6181072ddb","year":2021},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.866320Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:fd5c5d6af073e3d16d906cf15c3d4766347ed677328293bb3fe3fe5251eb9bba","observation_id":"8fc4ca32-4cff-4168-9edc-ecdd4f1e9595","resolution":{"observed_at":"2026-08-07T13:48:38.108535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:37.734461Z","title":"Visual instruction tuning","venue":null,"work_id":"4932763e-0b5b-4d88-8e8e-84fa02783aba","year":2023},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.875600Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:f61eb38ff8f4a99fcf5df0369a2ac2a264d407acd0b4ebed7210186f3ab7816d","observation_id":"e20ce6cc-076c-4eb6-a672-2dcbb989f692","resolution":{"observed_at":"2026-08-07T13:48:37.839310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:37.542071Z","title":"Pruning and quantization for deep neural network acceleration: A survey","venue":null,"work_id":"8dd2ac33-7efe-4dfd-808f-0eca9ec2f503","year":2021},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.884962Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:06f71eef461afb1ad8436195fc04237a7b488eecfd1b6736b4968b4d603dabfb","observation_id":"1cccac59-85d2-44cd-8e0e-d629ac562add","resolution":{"observed_at":"2026-08-07T13:48:37.622358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:37.345273Z","title":"BRECQ : Pushing the limit of post-training quantization by block reconstruction","venue":null,"work_id":"75be9cb9-7987-482e-8bca-e0c49ad8a2bc","year":2021},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.893061Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:53ad51405ddb585852d2cd76621f128d79866f8cfd54edcd7e1f290df5f1ba51","observation_id":"f182b4e1-0724-47d6-8111-d1d903a734c8","resolution":{"observed_at":"2026-08-07T13:48:37.428648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:37.167704Z","title":"Smoothquant: accurate and efficient post-training quantization for large language models","venue":null,"work_id":"ba172899-0c59-4fe5-8100-0af22e3fb0c3","year":2023},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.901867Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:d63009581b1f65d72ee967b604dc92f07e6081f1d360530878f18f76fd2d1cec","observation_id":"a1e5fa4c-5902-4852-8b84-aa43a0e2a663","resolution":{"observed_at":"2026-08-07T13:48:37.211136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:36.972410Z","title":"Learned step size quantization","venue":null,"work_id":"dd91e350-6ab4-463a-989d-99e48fe912ab","year":2020},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.911948Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:db60aa04f59a9c482cab2fe06c1d090eaf34b1e5d59b3a0b3bb2439215ec0425","observation_id":"a2bc934d-b893-4364-870c-29ba8d044c3b","resolution":{"observed_at":"2026-08-07T13:48:37.041203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:36.789916Z","title":"Quantized feature distillation for network quantization","venue":null,"work_id":"3ed6bfaf-bb37-4773-8fed-006d16dc607a","year":2023},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.922233Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:0acef7639adac7b6caf6643883879a68ad11b62778b3e1ebd8e1309b5e1b6777","observation_id":"aee14e9f-67ca-4176-9fa9-9e7caa4647aa","resolution":{"observed_at":"2026-08-07T13:48:36.899103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:36.605127Z","title":"Q-ViT : Accurate and fully quantized low-bit Vision Transformer","venue":null,"work_id":"786d4d47-dce2-4ff7-8087-4d22e4d23ee7","year":2024},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.932290Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:e9f763ee1874d4bf07a32096dfd5ecef9cf56bb192c29cf18cf13f0a8630a80d","observation_id":"43e2e41f-e694-4e35-84ce-397a659c12df","resolution":{"observed_at":"2026-08-07T13:48:36.690453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:36.432921Z","title":"Quantization without tears","venue":null,"work_id":"1d6ae870-ce56-4340-a302-194bc348ab1d","year":2025},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.940840Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:5df77e32d02a71affb9f2f8e16a947dc3e191feea05f5dba318b84331cf3b075","observation_id":"30d08ca3-248d-42a7-99db-3250d404afb1","resolution":{"observed_at":"2026-08-07T13:48:36.520229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:26.945336Z","title":"Gonzalez, Hao Zhang, and Ion Stoica","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.945336Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:ffb22eec4b8b8d1866d705839648748b99e63ab657183565240b1cf9b96faccb","observation_id":"c2059587-3998-45f4-a800-a57abcff2a68","resolution":{"observed_at":"2026-08-07T13:48:26.945336Z","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":"2026-08-07T13:48:36.254606Z","title":"ReActNet : Towards precise binary neural network with generalized activation functions","venue":null,"work_id":"2b6b42a6-12d9-458c-a4dd-b2883abe0d40","year":2020},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.950033Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:0c085c6024b7fe5b58b9dd047b21c2f44feb5e5d37249f2b6a5eaae9a7e0ba3f","observation_id":"6e197e0b-d06b-422f-aeed-f85aa2c2caf7","resolution":{"observed_at":"2026-08-07T13:48:36.335290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:36.074314Z","title":"Network quantization with element-wise gradient scaling","venue":null,"work_id":"ae4838dc-f7b5-4761-a5aa-11201c895f67","year":2021},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:26.960366Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:d7f1293a35b163849c895d971e38c9bcbd09b2302593e7388e684f6455df2c45","observation_id":"69445254-0874-48c1-90ce-a2958cc16f86","resolution":{"observed_at":"2026-08-07T13:48:36.159674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:35.911806Z","title":"Lsq+: Improving low-bit quantization through learnable offsets and better initialization","venue":null,"work_id":"8b1a5346-e0b4-4aad-b7b4-d40f007dc86d","year":2020},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:27.017418Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:942a869d1f90544b741d5d6e9bf66899c6055906a072178afc56f93096dbe973","observation_id":"1e376c2c-b290-4128-a595-83c64bb3555f","resolution":{"observed_at":"2026-08-07T13:48:36.012992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:35.763348Z","title":"PTQ4ViT : Post-training quantization for Vision Transformers with twin uniform quantization","venue":null,"work_id":"b3762b3a-1db9-4d22-b02b-15c07d8cae77","year":2022},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:27.116476Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:de0766762ea4a919ee790fa4ca48bae269f0c6201b5c2fdd704359d22374c1c3","observation_id":"2571cfb3-c535-4fcd-9681-b178f046b461","resolution":{"observed_at":"2026-08-07T13:48:35.843247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:35.586512Z","title":"GPTQ : Accurate post-training quantization for generative pre-trained Transformers","venue":null,"work_id":"2509e54f-eaf0-4a01-a7dc-7786bf46e10e","year":2023},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:27.268785Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:83a93feb673488e1cb3b4ae57a0594e89d6b4593f001de254d5c3ccf55836da7","observation_id":"97888d78-2694-4975-9f84-60a7432d6cad","resolution":{"observed_at":"2026-08-07T13:48:35.647849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:35.368660Z","title":"Up or down? adaptive rounding for post-training quantization","venue":null,"work_id":"818bb0e5-a661-4e86-9067-e9d229008395","year":2020},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:27.367341Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:6200e3212f8946c53d5545ff452c520b955518b72a8f20d72c41af6f4b81aac4","observation_id":"6d8f1073-51c7-42e1-96d8-e8c0da60b90e","resolution":{"observed_at":"2026-08-07T13:48:35.486397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:35.149133Z","title":"QDROP : Randomly dropping quantization for extremely low-bit post-training quantization","venue":null,"work_id":"a1c1d55e-35ac-422f-b518-426cc871e194","year":2022},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:27.502449Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:a95773d29624e663816983bc12b6878a844736370b4711acffaff1538747ef93","observation_id":"a3c2b4c7-3ad5-40ab-a82e-dcc2da767388","resolution":{"observed_at":"2026-08-07T13:48:35.246530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:34.925467Z","title":"RepQ-ViT : Scale reparameterization for post-training quantization of Vision Transformers","venue":null,"work_id":"cf0f1d25-7981-4a16-bfd4-37ffde837256","year":2023},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:27.716428Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:92cd87ae0f400b72b47352c219a75f405dc94c3585db69d3b8a73ed2d94ac062","observation_id":"864558e2-d857-4e03-889b-2bfaf9ebc329","resolution":{"observed_at":"2026-08-07T13:48:35.031648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:34.782978Z","title":"FQ-ViT : Post-training quantization for fully quantized Vision Transformer","venue":null,"work_id":"34d19023-5c3c-4986-8b91-fc864a5e8f08","year":2022},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:27.889310Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:d90e24b1c4e2b803f47670f51202b6a7cbb7d7b79c1f6fa32e5ada4879222171","observation_id":"5d5659da-5a99-44be-a505-53863fac6dec","resolution":{"observed_at":"2026-08-07T13:48:34.831029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:34.546241Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","venue":null,"work_id":"7b967283-91ee-44b8-b5aa-98139f26dcc2","year":2018},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:28.003767Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:4cca1a606888755b217dcb3bb6559ea7c88ea839fc72563863c94d0201c5668d","observation_id":"db53855a-a38a-4e7e-91ef-9b48a43761dc","resolution":{"observed_at":"2026-08-07T13:48:34.680721Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:34.326929Z","title":"TensorFlow Lite , 2024","venue":null,"work_id":"007eced2-3081-4882-8332-05d84fbae7bb","year":2024},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:28.154485Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:76a22a623ebec76128ade99674ce5e1a76cadf8d50b3ef4217e5c6f1f0b1a7c0","observation_id":"9515ccd6-cdb4-42eb-b009-dce72f1668ec","resolution":{"observed_at":"2026-08-07T13:48:34.424066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:34.206973Z","title":"Fully quantized network for object detection","venue":null,"work_id":"636e3a9e-aeba-4736-b45d-2b2b22f3ed41","year":2019},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:28.271214Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:cb7a3a16eb1aa13df7b45aba853b1fef891eeb30ee6f7303c0fa7959896a399b","observation_id":"8f6cc431-7cb6-4552-9ae2-08d726a52278","resolution":{"observed_at":"2026-08-07T13:48:34.254252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:34.036453Z","title":"ImageNet : A large-scale hierarchical image database","venue":null,"work_id":"92d54d86-d564-489a-a996-8a029706a0fc","year":2009},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:28.414660Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:528900966d32a4c38528dbdf89f6801997a11a20ebdcdb868b605f8891c82cb8","observation_id":"5bb2d7e5-5ac2-486e-9677-1d02f1727e3a","resolution":{"observed_at":"2026-08-07T13:48:34.103714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:33.964153Z","title":"Swin Transformer : Hierarchical Vision Transformer using shifted windows","venue":null,"work_id":"10b9b5d5-350c-452e-9196-b1225759104a","year":2021},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:28.574447Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:9b6c5696aaa727f5e5dd71e6caf9c8e08057e0093ba5834949df9b9379c35dd6","observation_id":"f32411ab-91dc-4140-995e-3346f0398c18","resolution":{"observed_at":"2026-08-07T13:48:33.992167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:33.779852Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"f25c594a-4379-4c61-b9c6-1817801ec33b","year":2016},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:28.719589Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:299f79db299693646922f22ca7f215ae52e9257cf0ba84f7e3a7727db48a198f","observation_id":"2ea925b2-c59d-49d2-9708-3d372d45a928","resolution":{"observed_at":"2026-08-07T13:48:33.861109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:33.528212Z","title":"Microsoft COCO : Common objects in context","venue":null,"work_id":"5814ec32-d67b-46f9-9ee0-9b5864b50bf1","year":2014},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:28.856009Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:7207e89be6c9a587677ac0429b1c9a2174e6a7f908cb5e12cf802447e18ef36d","observation_id":"261e7f1a-20c0-445c-9395-f0875f975633","resolution":{"observed_at":"2026-08-07T13:48:33.670528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:33.280530Z","title":"Cascade R-CNN : Delving into high quality object detection","venue":null,"work_id":"cfb99b1f-fc22-423e-8dd3-7808e4164616","year":2018},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:28.988777Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:366ea3d218f45da461ae1833a98a4d4fe3bfb6c3b7ee70cc9025df72608c9c88","observation_id":"020581cb-d1bd-4fed-a4f6-1a1b5633e7d9","resolution":{"observed_at":"2026-08-07T13:48:33.404125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T13:48:29.119170Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:29.119170Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:a97664276125caa555989d8c8b074ec20e394a0192b830be02c7f0e8f75b5463","observation_id":"0b6d8fbe-cf64-4620-9248-fb7cad2dc972","resolution":{"observed_at":"2026-08-07T13:48:29.119170Z","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":"2026-08-07T13:48:33.075139Z","title":"Pointer sentinel mixture models","venue":null,"work_id":"bc5b54f2-814c-4a3b-b06b-d2091a1ac43d","year":2017},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:29.260287Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:eb037e05a5b6cb7a3368f38f8425741357df899cfd100e9fa5434c64385b86f9","observation_id":"b37936e4-6a91-4322-b4fd-75024189ecc4","resolution":{"observed_at":"2026-08-07T13:48:33.133171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:32.827051Z","title":"Exploring the limits of transfer learning with a unified text-to-text Transformer","venue":null,"work_id":"d59f6c9c-8d1f-4e54-94ff-42e0da903ad7","year":2020},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:29.396806Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:13acc3474216796c315fc2a51891f590f34704fdaad565b01cd90b435119ac32","observation_id":"9e1f3eb1-e906-4bd8-a798-e14637eaf4f0","resolution":{"observed_at":"2026-08-07T13:48:32.959648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:32.597972Z","title":"Social IQ a: Commonsense reasoning about social interactions","venue":null,"work_id":"f5127107-eee4-4f32-8b6b-c22573fbdabf","year":2019},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:29.541961Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:dd9b96bf3a6fb683a59b3dd6cd289bcf108996ae8234813387e48a7b72fe0647","observation_id":"65ee4725-d53b-41e9-ade1-34afd2461b48","resolution":{"observed_at":"2026-08-07T13:48:32.719330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:32.392651Z","title":"HellaSwag : Can a machine really finish your sentence? In Annual Meeting of the Association for Computational Linguistics, page 4791–4800, 2019","venue":null,"work_id":"a892f6db-a2ef-40d1-8fb1-011cf3d62175","year":2019},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:29.703384Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:7bd322d60d4f5cba5a50a90a94949d44f93f85510c6802ef737e9f279193526b","observation_id":"1558af1f-35ec-4d13-ac48-5c7bca839732","resolution":{"observed_at":"2026-08-07T13:48:32.494230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:32.094762Z","title":"Piqa: Reasoning about physical commonsense in natural language","venue":null,"work_id":"042d5146-3294-4c67-8bb2-ee64c8b867de","year":2020},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:29.830121Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:8df3a89695a7acb2be490beffeda2e59de54e0a3d14b70da987fe356ce85b5d0","observation_id":"034d7b00-0d5d-400c-94bd-17149f188d0d","resolution":{"observed_at":"2026-08-07T13:48:32.236253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:31.770234Z","title":"WinoGrande : an adversarial winograd schema challenge at scale","venue":null,"work_id":"19938bb9-70b8-4058-b073-c3a85a28c833","year":2021},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:29.926504Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:96afabdd7422603092a7101b615e0b6751be9fb2ddf2673099318e54580bc45d","observation_id":"9d0dd65c-e781-48d0-98c5-f96a9011ec6e","resolution":{"observed_at":"2026-08-07T13:48:31.951343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-08-07T13:48:30.079925Z","title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:30.079925Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:7e5e2f5b692c1a6d8a0a55c12e5ecf12ca7537561c6dab05c87730d714fa0d12","observation_id":"90169922-b5a9-4bd4-89f4-4e1b005d052e","resolution":{"observed_at":"2026-08-07T13:48:30.079925Z","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":"2026-08-07T13:48:31.475644Z","title":"Boolq: Exploring the surprising difficulty of natural yes/no questions","venue":null,"work_id":"fbfe071a-593f-477e-a306-2020c3333fe9","year":2019},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:30.215612Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:65160591b3a1fc4d622c897536eb3041c275655eaf7d35dfd34d2b6a48d811ef","observation_id":"1acd8557-3bdb-4b21-957e-4e2eeeb4f4f1","resolution":{"observed_at":"2026-08-07T13:48:31.614777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:31.201794Z","title":"Can a suit of armor conduct electricity? a new dataset for open book question answering","venue":null,"work_id":"c88d67a9-9883-4eed-b0d0-addbb0d36619","year":2018},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:30.398856Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:aa086e24ad981579aeacecf8ddfd1262a33ebd683aaa3a65a4029b0fca99d635","observation_id":"e477a98a-fe91-463a-95e5-454336a50bda","resolution":{"observed_at":"2026-08-07T13:48:31.326005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:48:30.974890Z","title":"Decoupled weight decay regularization","venue":null,"work_id":"7c5c2d95-2351-47ee-a210-d2c58b61d879","year":2019},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:30.555404Z"},"links":{"citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:cc4ef2e021c3a3cd5f8adb8dc6958f903c5c7e11613126e47975d65c5a922a94","observation_id":"e69ee5ae-43d8-4ce4-aea0-e9b5cf9cc67f","resolution":{"observed_at":"2026-08-07T13:48:31.078741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.17343","last_updated":"2024-11-19T09:58:07Z","snapshot_observed_at":"2026-07-06T18:36:34.369503Z","submitted_at":"2024-06-25T07:57:27Z","title":"Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.17343","snapshot_observed_at":"2026-08-07T13:48:30.736528Z","title":"Q-DiT : Accurate post-training quantization for diffusion Transformers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T13:48:30.736528Z"},"links":{"cited_paper":"/paper/2406.17343","citing_paper":"/paper/2505.20932"},"observation_digest":"sha256:0cb81b94955ad04447f6be4ee5802d52feafe90a4eb81c132f8e11467f1df658","observation_id":"e1633e1d-d337-422c-abc5-40a05b7c6ee3","resolution":{"observed_at":"2026-08-07T13:48:30.736528Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.20932","last_updated":"2025-05-27T09:21:36Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T20:39:03.419810Z","submitted_at":"2025-05-27T09:21:36Z","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":39},"total_outbound_references":45},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 2 inbound Pith citation observations for arXiv:2505.20932."}