{"as_of":"2026-08-10T20:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fb315ad38688dcdc595a73e15a1c35f590cd86929d7c6f47819a8066862f1e95","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:45:45.917406Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.21591/citation-record","integrity":"/paper/2505.21591/integrity","json":"/paper/2505.21591/citation-record.json","paper":"/paper/2505.21591"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1308.3432","last_updated":"2013-08-15T15:19:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-08-15T15:19:34Z","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1308.3432","snapshot_observed_at":"2026-08-07T13:45:41.490029Z","title":"Estimating or propagating gradients through stochastic neurons for conditional computation","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:41.490029Z"},"links":{"cited_paper":"/paper/1308.3432","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:20abe1298f23d727bd009bb1092b01b102e33f996cf03190322237431476215b","observation_id":"6f93ce61-8844-4d86-a4ff-2c66e887704f","resolution":{"observed_at":"2026-08-07T13:45:41.490029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.06995","last_updated":"2024-08-13T15:56:20Z","snapshot_observed_at":"2026-08-10T04:55:17.511389Z","submitted_at":"2024-08-13T15:56:20Z","title":"Low-Bitwidth Floating Point Quantization for Efficient High-Quality Diffusion Models","version":1},"cited_work":{"arxiv_id":"2408.06995","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.06995","snapshot_observed_at":"2026-08-07T13:45:46.775419Z","title":"Low-Bitwidth Floating Point Quantization for Efficient High-Quality Diffusion Models","venue":"cs.CV","work_id":"515ef30e-6a11-4295-9894-994521f860b7","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:41.593727Z"},"links":{"cited_paper":"/paper/2408.06995","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:7d33abc9b36d35b874c44f1f7ef7cead8d421a6e1bcfcc39dd2daadfdb8a4a55","observation_id":"abd6ec1c-820d-4475-bed0-d95d5b1654cb","resolution":{"observed_at":"2026-08-07T13:45:46.851227Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:49.895555Z","title":"Qncd: Quantization noise correction for diffusion models","venue":null,"work_id":"54ab2723-c3e9-4320-ac1f-4ab2f27cc0df","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:41.697934Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:712e38c2ca17397ff49fd9cd9fa43712f0cbd1ad4e380171d089ec58174cbc5e","observation_id":"6eb53b47-b592-481b-873e-5d3d25383302","resolution":{"observed_at":"2026-08-07T13:45:49.970949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:49.760581Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":"59449a20-864e-43e9-812f-2b80b5661e7d","year":2009},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:41.750744Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:0f917da02d478595a5aa155a55863f41c6be483d37a68db22ca7496ac70c041b","observation_id":"b6e2753e-e51f-44dc-8e21-ec5243b8c0e8","resolution":{"observed_at":"2026-08-07T13:45:49.824682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14314","last_updated":"2023-05-23T17:50:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-23T17:50:33Z","title":"QLoRA: Efficient Finetuning of Quantized LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14314","snapshot_observed_at":"2026-08-07T13:45:41.759280Z","title":"Qlora: efficient finetuning of quantized llms (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:41.759280Z"},"links":{"cited_paper":"/paper/2305.14314","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:d8b9ef21eb06f007b02b9186df5da58c9bedab75a773bbff00e0986bd59df384","observation_id":"58c39e00-df00-4eb7-80a9-44b12f6e5c4c","resolution":{"observed_at":"2026-08-07T13:45:41.759280Z","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":"2026-08-07T13:45:49.596344Z","title":"Learned step size quantization","venue":null,"work_id":"24fc4897-8235-45f9-85c9-8bbff5f82ac7","year":2019},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:41.797583Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:137daa43768a3640340d0be0917a4453abb616a3575e47189c19179c0ba529c7","observation_id":"f83895c6-3d03-4311-a55d-cc190193ba27","resolution":{"observed_at":"2026-08-07T13:45:49.675480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:49.419887Z","title":"Mixture-of-loras: An efficient multitask tun- ing method for large language models","venue":null,"work_id":"93cbe855-6711-4d9e-9494-60fa8c0fc792","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:41.891172Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:34f47bee268fc01edb17cce934f0b7df06e523e20af705d79ddb6ffca20c47d3","observation_id":"906c7a53-24c7-45f9-bfb5-947b6de6c62f","resolution":{"observed_at":"2026-08-07T13:45:49.496867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03270","last_updated":"2024-04-13T07:33:57Z","snapshot_observed_at":"2026-08-09T06:00:18.288366Z","submitted_at":"2023-10-05T02:51:53Z","title":"EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03270","snapshot_observed_at":"2026-08-07T13:45:42.006346Z","title":"Efficientdm: Efficient quantization-aware fine-tuning of low-bit diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:42.006346Z"},"links":{"cited_paper":"/paper/2310.03270","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:57b4591351047c01184ed75ae3beec4c83c2de8b017a399bf415b4aa9ae59b2b","observation_id":"7a9088ae-67f6-4441-ab1a-0f7f6c80430e","resolution":{"observed_at":"2026-08-07T13:45:42.006346Z","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":"2026-08-07T13:45:49.287558Z","title":"Ptqd: Accurate post-training quantization for diffusion models","venue":null,"work_id":"2a6a7b90-d065-4586-ab8f-effe8b8ca07e","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:42.104535Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:8e338f2dc38e6d163cf819179373d494bdf08ec9eb42f1bffa311f575dbb339c","observation_id":"8efcae50-56d1-467e-87bf-fb15a184767a","resolution":{"observed_at":"2026-08-07T13:45:49.349184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:42.246674Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilib- rium","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:42.246674Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:be95fc225ba406c4892c576820a272fe7c587cd088c4e554b16b7ad1e26d549c","observation_id":"7809432a-485e-40ca-a6c8-20f407850f8f","resolution":{"observed_at":"2026-08-07T13:45:42.246674Z","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":"2026-08-07T13:45:42.344992Z","title":"Denoising dif- fusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:42.344992Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:ae24ac9fa90abf985d281a53c3feed16486d3758b740c988db7c0bb03ededc46","observation_id":"38315edd-342a-4a22-aaf7-565764645859","resolution":{"observed_at":"2026-08-07T13:45:42.344992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-07T13:45:42.482498Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:42.482498Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:e781524c494fc85c48895983e591114d3cde0f4381e4d2f6b6513e6abedb25dd","observation_id":"6115ffc0-7785-455e-b382-8917fe2954ab","resolution":{"observed_at":"2026-08-07T13:45:42.482498Z","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":"2026-08-07T13:45:49.068591Z","title":"An empirical study of llama3 quantization: From llms to mllms","venue":null,"work_id":"afe83e39-5a3d-44b8-a893-6b3bc1e81959","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:42.674839Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:47232319ecb0c2edadbdd66ce48064ff3c1fbdc8b962dd94892b9a48a58c5ebf","observation_id":"8660d64c-a6c3-4ad1-b896-0a16cb61ac02","resolution":{"observed_at":"2026-08-07T13:45:49.142400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:48.952598Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","venue":null,"work_id":"2557b418-5347-47e4-afb3-15f706f3e0c0","year":2018},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:42.803405Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:18d13f1dc418b38499439422d5ad2fc486ae0f536dcb9544763627c1d6dc9102","observation_id":"0e4802fd-af62-4a47-add4-235b5ab0758f","resolution":{"observed_at":"2026-08-07T13:45:48.985665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08342","last_updated":"2018-06-21T17:32:46Z","snapshot_observed_at":"2026-07-06T06:46:08.396066Z","submitted_at":"2018-06-21T17:32:46Z","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08342","snapshot_observed_at":"2026-08-07T13:45:42.907533Z","title":"Quantizing deep convolu- tional networks for efficient inference: A whitepaper","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:42.907533Z"},"links":{"cited_paper":"/paper/1806.08342","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:7e4f37aec472069ba9218a473685f69b950a3ddf52ea9ed6b17e74f6f49262ec","observation_id":"f93e198e-4668-45bc-9b8d-e4077c6ff20c","resolution":{"observed_at":"2026-08-07T13:45:42.907533Z","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":"2026-08-07T13:45:42.979931Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:42.979931Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:e32aad9c6e7ace34999c9c252b7b05196ea343db905465c8321656356b19e74b","observation_id":"dc81b4b7-da52-48ad-9f03-476fa0cfa81c","resolution":{"observed_at":"2026-08-07T13:45:42.979931Z","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":"2026-08-07T13:45:48.814890Z","title":"Fp8 quanti- zation: The power of the exponent","venue":null,"work_id":"425fbee7-f0ac-4983-8fcc-8c8476bdb2a1","year":2022},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:43.059103Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:ee4920151175a7d5af6a62c528273b3e50c8e5979b4ddf7d0d563de10aed8b07","observation_id":"073ed858-c9ec-422f-889f-9e0245090852","resolution":{"observed_at":"2026-08-07T13:45:48.860831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:48.668068Z","title":"Contemporary ad- vances in neural network quantization: A survey","venue":null,"work_id":"3f133fe8-0b89-4004-81d0-cc6310a4b03e","year":null},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:43.129486Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:b8c29c1f450255fb7fca4a78a9cfb9fb623fac43054994fd8c5dbb9a263f26d0","observation_id":"0b40b56f-a1cb-457b-a895-9637b4d0ee42","resolution":{"observed_at":"2026-08-07T13:45:48.710508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:48.545256Z","title":"Q-diffusion: Quantizing diffusion models","venue":null,"work_id":"93ab71aa-5cbd-4dde-a584-542867175562","year":2023},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:43.203856Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:570e4789fd108f105dddd595c4a63add03b537d89ca656da9b35a61005ecfbce","observation_id":"22e27283-26c0-4600-9310-8252d8576c49","resolution":{"observed_at":"2026-08-07T13:45:48.602057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:48.421861Z","title":"Q-dm: An efficient low-bit quantized dif- fusion model","venue":null,"work_id":"c4705f50-9dd1-4417-b549-215505c030cb","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:43.309194Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:09a3fb0d34d3b653926dbfc186ef93360091cee2b7e6d70c703d6607e83a2ae4","observation_id":"50415437-cc34-4be8-882f-1872fbd244cf","resolution":{"observed_at":"2026-08-07T13:45:48.478796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:48.274681Z","title":"Pruning and quantization for deep neural network acceleration: A survey","venue":null,"work_id":"315940e6-aee6-42cc-8cd8-658ba13ceb95","year":2021},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:43.418760Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:11b02566e415a786f89159e77404dfc7146772c5bd78b99784be84e421b638a9","observation_id":"c077dcff-522a-4910-80e2-6d044885c616","resolution":{"observed_at":"2026-08-07T13:45:48.339910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:43.496996Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:43.496996Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:0a8f7263dc400ae1a829d7c849cdb19d34e1716980ddeacdd8343e9d3874be38","observation_id":"e917de86-2536-4f59-9143-7fffe2520c02","resolution":{"observed_at":"2026-08-07T13:45:43.496996Z","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":"2026-08-07T13:45:48.110629Z","title":"Improving neural network efficiency via post-training quan- tization with adaptive floating-point","venue":null,"work_id":"dc789bac-74cb-457b-8f5f-4bfd5704245c","year":2021},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:43.603456Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:750ba035e87c10d9e93955bf1ccc8a21a5ed656f02d5c4b5eabd266dd2ad38e8","observation_id":"d40cb4a9-cf58-4a83-8188-605e4bad4589","resolution":{"observed_at":"2026-08-07T13:45:48.186433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.09778","last_updated":"2022-10-31T09:05:25Z","snapshot_observed_at":"2026-08-10T13:42:46.496202Z","submitted_at":"2022-02-20T10:37:52Z","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.09778","snapshot_observed_at":"2026-08-07T13:45:43.707572Z","title":"Pseudo numerical methods for diffusion models on manifolds.arXiv preprint arXiv:2202.09778, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:43.707572Z"},"links":{"cited_paper":"/paper/2202.09778","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:3aa29217fedb329a5a4d5b1914cfb684b3eeab81914eeda9e5edae4e169c01eb","observation_id":"7b790076-e84d-4182-9018-14a9e938279f","resolution":{"observed_at":"2026-08-07T13:45:43.707572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16836","last_updated":"2023-10-25T17:59:32Z","snapshot_observed_at":"2026-08-07T20:37:03.856800Z","submitted_at":"2023-10-25T17:59:32Z","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.16836","snapshot_observed_at":"2026-08-07T13:45:43.829649Z","title":"Llm-fp4: 4-bit floating-point quan- tized transformers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:43.829649Z"},"links":{"cited_paper":"/paper/2310.16836","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:23725b8edc4fbcdc01eccd15c1e72fd37fdb168b5f5caf27a4b43bacbf7e4f8a","observation_id":"2e530c43-7315-46f0-a0eb-0ae3f8e057a2","resolution":{"observed_at":"2026-08-07T13:45:43.829649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.14307","last_updated":"2025-07-09T04:40:14Z","snapshot_observed_at":"2026-08-05T16:14:04.341230Z","submitted_at":"2024-09-22T04:21:29Z","title":"DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation","version":3},"cited_work":{"arxiv_id":"2409.14307","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.14307","snapshot_observed_at":"2026-08-07T13:45:46.426735Z","title":"DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation","venue":"cs.CV","work_id":"708fb60f-e61b-4eae-a860-06b1bdbc4d05","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:43.910644Z"},"links":{"cited_paper":"/paper/2409.14307","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:040b1d6da756416aa61f09b299b17774f270365295bba4f7edcd35382a0c8877","observation_id":"5f0c8e01-a53d-40a3-93f8-1e1a6bf099c6","resolution":{"observed_at":"2026-08-07T13:45:46.486663Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04585","last_updated":"2025-06-22T12:05:22Z","snapshot_observed_at":"2026-08-05T00:01:10.603482Z","submitted_at":"2024-01-09T14:42:49Z","title":"EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.04585","snapshot_observed_at":"2026-08-07T13:45:44.006590Z","title":"En- hanced distribution alignment for post-training quantization of diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.006590Z"},"links":{"cited_paper":"/paper/2401.04585","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:bf1126cbcdf3e25a124e81073892711f61527e75430a0cc44186461cb560c322","observation_id":"08defcd2-ad34-4e7b-b271-99570aa61761","resolution":{"observed_at":"2026-08-07T13:45:44.006590Z","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":"2026-08-07T13:45:47.952464Z","title":"Deep learning face attributes in the wild","venue":null,"work_id":"f19b6791-8f01-44f7-a5a0-a31971aa2fc0","year":2015},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.082098Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:50380a4468edb7ef442b3e2eabf5da09cb8a76e6d10306a5fe8cc6d2c16014db","observation_id":"98373f25-4fdb-42ef-982a-74f7f76d113e","resolution":{"observed_at":"2026-08-07T13:45:48.029051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:44.180696Z","title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.180696Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:56ef671df5b61b7d3b42f1dcfae25ff87b46a27ee131453c61132e7c5e5360f6","observation_id":"5598c3e5-9367-40e9-9e18-5d55ce2602b4","resolution":{"observed_at":"2026-08-07T13:45:44.180696Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.05433","last_updated":"2022-09-29T20:47:07Z","snapshot_observed_at":"2026-08-10T16:19:00.326414Z","submitted_at":"2022-09-12T17:39:55Z","title":"FP8 Formats for Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.05433","snapshot_observed_at":"2026-08-07T13:45:44.294486Z","title":"Fp8 formats for deep learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.294486Z"},"links":{"cited_paper":"/paper/2209.05433","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:f84e312339385d15a9f9b23066895986ccb7edf9c800c3306346da1bbd5a0dc8","observation_id":"89a617d2-de96-42d7-95cd-84dfe4618626","resolution":{"observed_at":"2026-08-07T13:45:44.294486Z","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":"2026-08-07T13:45:44.443376Z","title":"Up or down? adap- tive rounding for post-training quantization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.443376Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:8c698703fc82569bd59174d6581e9dc860b3fe871a0d223170382c84a429d977","observation_id":"4a2f7bbf-2b2c-4577-bec0-4cd03d496398","resolution":{"observed_at":"2026-08-07T13:45:44.443376Z","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":"2026-08-07T13:45:47.781602Z","title":"Blackwell platform sets new llm inference records in mlperf inference v4.1, 2024","venue":null,"work_id":"792b1902-a708-4f36-9d65-17e3490a06c8","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.549717Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:2dbd639ab620a759ea901f449f51d0455157355a2ad3104df612109d0bedd5ef","observation_id":"9a4eb73b-f4f5-4cce-8218-31aa538ea4e5","resolution":{"observed_at":"2026-08-07T13:45:47.834094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:44.665743Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.665743Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:ae3f3eff0bd998f1a9f14ac28e9c24391a9cf39c97da1faa111def11f6189949","observation_id":"d8a4ad47-0e1a-41f7-9d9d-96e8afdb5529","resolution":{"observed_at":"2026-08-07T13:45:44.665743Z","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":"2026-08-07T13:45:44.741058Z","title":"Improved techniques for training gans","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.741058Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:8e5ae0313424715aba5e41e32923b3de27a56c5ff6f1342b99e196a048131fdf","observation_id":"9041568c-faf3-472e-837a-b180eafc7d81","resolution":{"observed_at":"2026-08-07T13:45:44.741058Z","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":"2026-08-07T13:45:47.577282Z","title":"Post-training quantization on diffusion models","venue":null,"work_id":"b8c1ff08-6c5b-44c7-a423-604e4dfc30c4","year":1972},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.813613Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:ca76b9dde01e58bf7a279ea77cb6ad2436b0418713cc0072451920ea120fe774","observation_id":"2cb5dd0e-8c85-4d55-8014-0bc00fc92612","resolution":{"observed_at":"2026-08-07T13:45:47.661402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:47.401948Z","title":"Temporal dynamic quantization for dif- fusion models","venue":null,"work_id":"7edff069-1498-4506-b891-d3ca484d38e3","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.885768Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:b7378e98f10e688c59436de098138daf76f788467e7ac325307138c552823421","observation_id":"44d3f7f7-e769-4b4b-bf8f-d297afb8ff0d","resolution":{"observed_at":"2026-08-07T13:45:47.475291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-07-06T10:01:50.133383Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-07T13:45:44.988836Z","title":"Denoising diffusion implicit models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:44.988836Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:e87ba37c90f15aded6a7783458be766533ecbf7aaa5c78b25b501cc94df49ba2","observation_id":"17dc49a3-e5c7-41e1-9848-a43d5be4d749","resolution":{"observed_at":"2026-08-07T13:45:44.988836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.09532","last_updated":"2024-04-15T07:51:40Z","snapshot_observed_at":"2026-08-10T08:45:18.028847Z","submitted_at":"2024-04-15T07:51:40Z","title":"TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models","version":1},"cited_work":{"arxiv_id":"2404.09532","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.09532","snapshot_observed_at":"2026-08-07T13:45:46.170096Z","title":"TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models","venue":"cs.CV","work_id":"3bd7e54c-a9ca-4ded-b2a4-37ddfb73529f","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:45.095753Z"},"links":{"cited_paper":"/paper/2404.09532","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:1273285347152853673591d27f2a783963d4b7a187ecb25492d4c45fd231b2fe","observation_id":"f4bbe5a2-8139-4b8a-90f4-76942fd62b64","resolution":{"observed_at":"2026-08-07T13:45:46.234877Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.17951","last_updated":"2023-06-15T08:14:02Z","snapshot_observed_at":"2026-08-10T09:51:19.547404Z","submitted_at":"2023-03-31T10:29:17Z","title":"FP8 versus INT8 for efficient deep learning inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.17951","snapshot_observed_at":"2026-08-07T13:45:45.220121Z","title":"Fp8 ver- sus int8 for efficient deep learning inference","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:45.220121Z"},"links":{"cited_paper":"/paper/2303.17951","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:d3b3998166e37c4ceadab1107353eb6774460b29a5bf499b52d424091fcacfa6","observation_id":"e5530f14-8c65-472e-b013-bfafdf5d73b6","resolution":{"observed_at":"2026-08-07T13:45:45.220121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02490","last_updated":"2024-03-26T03:41:26Z","snapshot_observed_at":"2026-08-06T14:43:08.775092Z","submitted_at":"2023-03-04T20:08:57Z","title":"Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.02490","snapshot_observed_at":"2026-08-07T13:45:45.289305Z","title":"Diffusion models gener- ate images like painters: an analytical theory of outline first, details later","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:45.289305Z"},"links":{"cited_paper":"/paper/2303.02490","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:8c4c7b2bce3f0676cbc40b6d7d39ee4116fffbd0f71a1eb4d1c1f716ac5a5261","observation_id":"e42cd56e-114d-4645-88fe-a4b0dcc34f40","resolution":{"observed_at":"2026-08-07T13:45:45.289305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18723","last_updated":"2024-04-30T08:53:45Z","snapshot_observed_at":"2026-07-06T15:35:11.938380Z","submitted_at":"2023-05-30T04:00:35Z","title":"Towards Accurate Post-training Quantization for Diffusion Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18723","snapshot_observed_at":"2026-08-07T13:45:45.420073Z","title":"Towards accurate data- free quantization for diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:45.420073Z"},"links":{"cited_paper":"/paper/2305.18723","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:dde3694247c2f6953e7296ecae21d2c4af66e682bdcbdcd5f2492fee825b1545","observation_id":"aac9255e-eaa7-42b1-a752-7f44eac9991b","resolution":{"observed_at":"2026-08-07T13:45:45.420073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03666","last_updated":"2025-07-15T15:33:13Z","snapshot_observed_at":"2026-08-09T03:33:46.844193Z","submitted_at":"2024-02-06T03:39:44Z","title":"QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03666","snapshot_observed_at":"2026-08-07T13:45:45.526470Z","title":"Quest: Low-bit diffusion model quantization via efficient selective finetuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:45.526470Z"},"links":{"cited_paper":"/paper/2402.03666","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:bc9e98128aa3b17efc1b1b3bb4709d53e4c0e90bde9567185e6ec3e4af8a6a7d","observation_id":"af1f11a9-b088-4d26-ac4c-4aee88a864e3","resolution":{"observed_at":"2026-08-07T13:45:45.526470Z","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":"2026-08-07T13:45:47.240045Z","title":"Fp4-quantization: Lossless 4bit quantization for large lan- guage models","venue":null,"work_id":"42a7ea1d-1e7f-41ca-9f24-90a48b517444","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:45.597015Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:0a76f94349c430bf37f5f1819aedea1522a49db4f434d1bf638f6086aff1693c","observation_id":"ec952f8b-3394-455c-b16d-1cb3227d9bc8","resolution":{"observed_at":"2026-08-07T13:45:47.318492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1506.03365","last_updated":"2016-06-04T09:51:30Z","snapshot_observed_at":"2026-08-08T13:26:17.517503Z","submitted_at":"2015-06-10T15:38:47Z","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.03365","snapshot_observed_at":"2026-08-07T13:45:45.722601Z","title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:45.722601Z"},"links":{"cited_paper":"/paper/1506.03365","citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:18d6a33f8a84d2ff121cb40f657be2a6a56c5434cdad336efe1f0725aa9602bd","observation_id":"8bcc5734-8f52-42df-bf25-6076174cb8a3","resolution":{"observed_at":"2026-08-07T13:45:45.722601Z","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":"2026-08-07T13:45:47.108569Z","title":"Integer or floating point? new outlooks for low-bit quantization on large language models","venue":null,"work_id":"d6d3a6e6-07b0-405c-bac8-355c610a6186","year":2024},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:45.823570Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:d6789c165ec9f49e724f4432f75695f45d48fba5f08b1afa0c4645ba3b5a31a7","observation_id":"d9c634a9-a520-439b-8047-72b50e9ff91f","resolution":{"observed_at":"2026-08-07T13:45:47.156253Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T13:45:46.938656Z","title":"The input channels of the router match the channel count of the timestep embedding in the diffusion model","venue":null,"work_id":"a7ad3c4e-a9b8-4e80-9f3b-e16edc1dacc2","year":null},"citing_paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:45:45.917406Z"},"links":{"citing_paper":"/paper/2505.21591"},"observation_digest":"sha256:e503f1b7607639a19f6f736791943066d58304b5ab46403674aff62162c3ef18","observation_id":"8185a844-fda6-4497-8e90-9d5ae0455569","resolution":{"observed_at":"2026-08-07T13:45:47.022404Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.21591","last_updated":"2025-05-27T13:40:47Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T06:00:35.478274Z","submitted_at":"2025-05-27T13:40:47Z","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":3,"verified_fuzzy":18},"total_outbound_references":46},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2505.21591."}