{"as_of":"2026-08-18T02:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b99ee29cb75d6d81bc77aeaea400b35c611db2c9b1c4bea325b91a17ec1a9e73","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T22:41:17.578542Z","state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.07222/citation-record","integrity":"/paper/2509.07222/integrity","json":"/paper/2509.07222/citation-record.json","paper":"/paper/2509.07222"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T22:41:17.869659Z","title":"Un- covering and mitigating algorithmic bias through learned latent structure","venue":null,"work_id":"7d9eb990-2daa-4371-8c80-45cd77c303a9","year":2019},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.187188Z"},"links":{"citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:3536f74b13eaf4b02a1d1c6625100401f3c6b4a9e9fc8c458f267482efa16c27","observation_id":"5f384917-85c9-4a98-a53a-d05f7833dd26","resolution":{"observed_at":"2026-08-04T22:41:17.905826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-04T22:41:17.277620Z","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding.arXiv preprint arXiv:1510.00149, 2015a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.277620Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:7c611ec455e98fc2aad1658fadad9a89f9400e7fc9c9965c05bfa6ab0862eb57","observation_id":"16223b5f-abe9-4dcb-9d2a-ab0e00d61238","resolution":{"observed_at":"2026-08-04T22:41:17.277620Z","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":"2026-08-04T22:41:17.796461Z","title":"On large-batch training for deep learning: Generalization gap and sharp minima","venue":null,"work_id":"34641ebd-2410-4baa-9b82-6cb1abdee53e","year":2017},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.370202Z"},"links":{"citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:34aabf491dd54661f96a7ea30c8d49969eccb4894039822ede011a1faeb91d5f","observation_id":"4b49f2f4-77c5-4abc-bcd6-bf59447a9fa5","resolution":{"observed_at":"2026-08-04T22:41:17.829553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08295","last_updated":"2021-06-15T17:12:42Z","snapshot_observed_at":"2026-08-02T11:19:40.664702Z","submitted_at":"2021-06-15T17:12:42Z","title":"A White Paper on Neural Network Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08295","snapshot_observed_at":"2026-08-04T22:41:17.459798Z","title":"A white paper on neural network quantization.arXiv preprint arXiv:2106.08295,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.459798Z"},"links":{"cited_paper":"/paper/2106.08295","citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:5bfe7871c02710fedb08fbd3a5410f53f0eb68287cfc78e646a5a8292e562551","observation_id":"1f624ef5-dd75-4002-a990-92776cc5a6d2","resolution":{"observed_at":"2026-08-04T22:41:17.459798Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.01878","last_updated":"2017-11-13T18:40:16Z","snapshot_observed_at":"2026-08-15T03:14:52.303459Z","submitted_at":"2017-10-05T04:26:49Z","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.01878","snapshot_observed_at":"2026-08-04T22:41:17.578542Z","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression.arXiv preprint arXiv:1710.01878,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.578542Z"},"links":{"cited_paper":"/paper/1710.01878","citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:52f4f0dbb9b948c162337515d7c2a515e399022ca8abefd7be60de0bdec698bf","observation_id":"284ce55a-b07f-483a-b7f0-5d15a632bd2f","resolution":{"observed_at":"2026-08-04T22:41:17.578542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.00199","last_updated":"2018-06-30T16:43:23Z","snapshot_observed_at":"2026-08-14T18:57:12.973744Z","submitted_at":"2018-06-30T16:43:23Z","title":"Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.00199","snapshot_observed_at":"2026-08-04T22:41:17.507653Z","title":"ISBN 1558602224","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":1991,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.507653Z"},"links":{"cited_paper":"/paper/1807.00199","citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:cd86774ec1484fbf3aef01b380f7f6d8eaff8507aa20fceca3dde825c968f722","observation_id":"38df0666-0d2b-4379-837d-5fb119133533","resolution":{"observed_at":"2026-08-04T22:41:17.507653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.05248","last_updated":"2021-09-06T00:47:17Z","snapshot_observed_at":"2026-08-11T03:53:11.067950Z","submitted_at":"2019-11-13T02:02:19Z","title":"What Do Compressed Deep Neural Networks Forget?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.05248","snapshot_observed_at":"2026-08-04T22:41:17.308780Z","title":"What do com- pressed deep neural networks forget?arXiv preprint arXiv:1911.05248,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.308780Z"},"links":{"cited_paper":"/paper/1911.05248","citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:000c86aad02235d6b323f06cf8009ee0c1c3a51595121adadf99a54c249a5e16","observation_id":"96659789-0933-43bf-b38f-47269ae135d2","resolution":{"observed_at":"2026-08-04T22:41:17.308780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14152","last_updated":"2023-10-28T11:53:52Z","snapshot_observed_at":"2026-08-16T15:30:35.307563Z","submitted_at":"2023-05-23T15:20:01Z","title":"Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14152","snapshot_observed_at":"2026-08-04T22:41:17.395343Z","title":"Memory-efficient fine-tuning of compressed large language models via sub-4-bit integer quantization.arXiv preprint arXiv:2305.14152,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.395343Z"},"links":{"cited_paper":"/paper/2305.14152","citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:bd7dd1060fa14e5e7e9943880675ff38c1a90451e38c4822e76209539221fe3d","observation_id":"a23ff971-4c8d-4fe3-8aab-1f592a335631","resolution":{"observed_at":"2026-08-04T22:41:17.395343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07215","last_updated":"2024-08-20T16:37:12Z","snapshot_observed_at":"2026-08-16T15:24:32.631660Z","submitted_at":"2023-06-12T16:20:36Z","title":"Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection","version":3},"cited_work":{"arxiv_id":"2306.07215","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.07215","snapshot_observed_at":"2026-08-04T22:41:17.664337Z","title":"Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection","venue":"cs.LG","work_id":"27a71022-ec94-4cbc-8f67-09f91f4ae900","year":2023},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.339803Z"},"links":{"cited_paper":"/paper/2306.07215","citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:68ba19ce9511aac3802e83807422ef2c59d3dad18a547dd1fa2967d33064e5c0","observation_id":"062f522e-cca3-4ee2-b4ea-613acaf57a90","resolution":{"observed_at":"2026-08-04T22:41:17.699800Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00090","last_updated":"2018-11-30T23:15:45Z","snapshot_observed_at":"2026-08-14T17:50:18.985454Z","submitted_at":"2018-11-30T23:15:45Z","title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00090","snapshot_observed_at":"2026-08-04T22:41:17.547175Z","title":"mlr.press/v119/wang20c.html","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.547175Z"},"links":{"cited_paper":"/paper/1812.00090","citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:9792d08d129576ca5c4d0a151b95eb5a7a54d46d280539a8e8d9d166ba595875","observation_id":"f706f310-9207-4042-bbeb-09670ad286f7","resolution":{"observed_at":"2026-08-04T22:41:17.547175Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17323","last_updated":"2023-03-22T13:10:47Z","snapshot_observed_at":"2026-08-16T07:57:19.216626Z","submitted_at":"2022-10-31T13:42:40Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.17323","snapshot_observed_at":"2026-08-04T22:41:17.246666Z","title":"Gptq: Accurate post-training quantization for generative pre-trained transformers.arXiv preprint arXiv:2210.17323,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.246666Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:c0973f89cc7c4d80ae58d209179393d9c131a03b0ec526e85f47553d80e701be","observation_id":"d12c40e4-9993-43a0-b820-cfb1636c84f2","resolution":{"observed_at":"2026-08-04T22:41:17.246666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.02973","last_updated":"2024-02-16T09:52:58Z","snapshot_observed_at":"2026-08-16T15:18:15.446196Z","submitted_at":"2023-07-06T13:18:44Z","title":"Pruning vs Quantization: Which is Better?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.02973","snapshot_observed_at":"2026-08-04T22:41:17.422775Z","title":"Prun- ing vs quantization: Which is better?arXiv preprint arXiv:2307.02973,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-04T22:41:17.422775Z"},"links":{"cited_paper":"/paper/2307.02973","citing_paper":"/paper/2509.07222"},"observation_digest":"sha256:af11c7fd4abd07b7b74dfc76edaff55e2774a151bfc5199ed6c149c35c9f1766","observation_id":"3d2c7a5f-74bd-4e8d-b462-927597d79998","resolution":{"observed_at":"2026-08-04T22:41:17.422775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.07222","last_updated":"2025-09-08T21:04:16Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T03:54:15.832631Z","submitted_at":"2025-09-08T21:04:16Z","title":"Explaining How Quantization Disparately Skews a Model"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":1,"verified_fuzzy":2},"total_outbound_references":12},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2509.07222."}