{"as_of":"2026-08-22T18:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:826cb1e0b5d8fe5bf07b9a8a361d6b5fc9d20d582c2e39c5c80b4deec1cbc35b","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":10,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":10,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":10,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T00:26:51.626399Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T10:19:47.784742Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10568","snapshot_observed_at":"2026-08-11T12:53:58.546181Z","title":"Up or down? adaptive rounding for post-training quantization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.13737","last_updated":"2024-12-18T11:14:30Z","snapshot_observed_at":"2026-08-17T13:41:07.551546Z","submitted_at":"2024-12-18T11:14:30Z","title":"On the Compression of Language Models for Code: An Empirical Study on CodeBERT","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T12:53:58.546181Z"},"links":{"cited_paper":"/paper/2004.10568","citing_paper":"/paper/2412.13737"},"observation_digest":"sha256:5d990ff19e0012f9214009ee2840a00f198ef23475f79a769ad45afbcc67363e","observation_id":"99ab9e81-96ba-4f37-a426-b725beea7989","resolution":{"observed_at":"2026-08-11T12:53:58.546181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10568","snapshot_observed_at":"2026-08-10T14:44:36.234576Z","title":"Up or down? adaptive rounding for post-training quan- tization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.16385","last_updated":"2025-05-23T05:33:23Z","snapshot_observed_at":"2026-08-15T10:44:44.326322Z","submitted_at":"2025-01-25T06:04:07Z","title":"FBQuant: FeedBack Quantization for Large Language Models","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-10T14:44:36.234576Z"},"links":{"cited_paper":"/paper/2004.10568","citing_paper":"/paper/2501.16385"},"observation_digest":"sha256:d2dcb5c00cfd12ff83d5a31019249ff16417c2aa967ec31e5850966bfce38e37","observation_id":"b60d753e-85d4-4e8b-8e27-d397cf333dfe","resolution":{"observed_at":"2026-08-10T14:44:36.234576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10568","snapshot_observed_at":"2026-08-07T10:43:44.852414Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization, April 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04985","last_updated":"2026-07-08T07:56:27Z","snapshot_observed_at":"2026-08-19T02:08:39.348290Z","submitted_at":"2025-06-05T12:56:12Z","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:44.852414Z"},"links":{"cited_paper":"/paper/2004.10568","citing_paper":"/paper/2506.04985"},"observation_digest":"sha256:c8308315b1b3964db27ddd691873f74d9c26e08c3eca47f5f575082776272ae0","observation_id":"b210edd9-11bb-41f6-af73-0a1ab55e1632","resolution":{"observed_at":"2026-08-07T10:43:44.852414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10568","snapshot_observed_at":"2026-08-07T14:06:23.724826Z","title":"Up or down? adaptive rounding for post-training quantization","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.15689","last_updated":"2025-08-29T12:03:45Z","snapshot_observed_at":"2026-08-18T02:46:12.498670Z","submitted_at":"2025-05-26T14:22:21Z","title":"BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:23.724826Z"},"links":{"cited_paper":"/paper/2004.10568","citing_paper":"/paper/2506.15689"},"observation_digest":"sha256:404587c8eccaa334681da156a6dca1198df517d22509aeeaccbd9df26c4b0edf","observation_id":"ee549646-d103-4bea-8b68-47d41e8179a3","resolution":{"observed_at":"2026-08-07T14:06:23.724826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10568","snapshot_observed_at":"2026-08-06T17:55:14.246829Z","title":"Up or down? adaptive round- ing for post-training quantization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.09687","last_updated":"2025-07-13T15:48:16Z","snapshot_observed_at":"2026-08-16T17:19:44.963723Z","submitted_at":"2025-07-13T15:48:16Z","title":"Post-Training Quantization of Generative and Discriminative LSTM Text Classifiers: A Study of Calibration, Class Balance, and Robustness","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T17:55:14.246829Z"},"links":{"cited_paper":"/paper/2004.10568","citing_paper":"/paper/2507.09687"},"observation_digest":"sha256:ef198b682020c3c0acbac75ec05311b6b362d1cff78ace1ff48ccbe00a19ee7a","observation_id":"e7f21b11-fa44-4318-a874-3ac1e9ad4786","resolution":{"observed_at":"2026-08-06T17:55:14.246829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10568","snapshot_observed_at":"2026-08-05T10:50:16.934268Z","title":"Markus Nagel, Raoul Amjad, Mart Van Baalen, Christos Louizos, and Tijmen Blankevoort","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2509.03704","last_updated":"2026-06-25T20:51:47Z","snapshot_observed_at":"2026-08-19T23:27:03.356363Z","submitted_at":"2025-09-03T20:39:03Z","title":"QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-05T10:50:16.934268Z"},"links":{"cited_paper":"/paper/2004.10568","citing_paper":"/paper/2509.03704"},"observation_digest":"sha256:222c8dacb4118ed1c5b388643146c3c33814f412688896a19f79be23f025c000","observation_id":"5c7fb40d-2bc1-4e8e-9c71-610114543e80","resolution":{"observed_at":"2026-08-05T10:50:16.934268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","version":2},"cited_work":{"arxiv_id":"2004.10568","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2004.10568","snapshot_observed_at":"2026-07-04T10:19:47.784742Z","title":"arXiv preprint arXiv:2004.10568 (2020)","venue":null,"work_id":"07ded62e-2974-41e6-9e44-10482478a2dd","year":2004},"citing_paper":{"arxiv_id":"2606.22935","last_updated":"2026-06-22T07:11:52Z","snapshot_observed_at":"2026-08-08T05:55:33.888268Z","submitted_at":"2026-06-22T07:11:52Z","title":"Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-26T08:55:52.174148Z"},"links":{"cited_paper":"/paper/2004.10568","citing_paper":"/paper/2606.22935"},"observation_digest":"sha256:9e5432696028705d06091e3b6d7b92493cc8ea46f872e4119f105c184d4da918","observation_id":"00070c34-0463-42cd-b5d8-682087ec819a","resolution":{"observed_at":"2026-07-04T10:19:47.786087Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10568","snapshot_observed_at":"2026-08-02T01:35:42.260594Z","title":"Nagel, R","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-19T16:53:38.710419Z","submitted_at":"2026-07-16T06:47:52Z","title":"Cross-Layer Error Compensation and Finite-Sample Feature-Statistics Matching for Extreme Low-Bit Quantization of Large Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:42.260594Z"},"links":{"cited_paper":"/paper/2004.10568","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:c0d4c7dfebfce49da7ad8c2ad3bb6aeb6a6ffbac876280bfbe8a5dce988c8655","observation_id":"0a30f443-eb52-41a4-9ed9-093397107d49","resolution":{"observed_at":"2026-08-02T01:35:42.260594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10568","snapshot_observed_at":"2026-08-01T08:38:51.443601Z","title":"International Conference on Machine Learning (ICML) , year =","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.21063","last_updated":"2026-07-23T08:56:11Z","snapshot_observed_at":"2026-08-07T01:50:19.863208Z","submitted_at":"2026-07-23T08:56:11Z","title":"QuantiBias: Benchmarking Quantization-Induced Bias in LLMs","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-01T08:38:51.443601Z"},"links":{"cited_paper":"/paper/2004.10568","citing_paper":"/paper/2607.21063"},"observation_digest":"sha256:433ea49dc09c9228ac6673becf2e7cf663136dee0e33368bd560c8e6e5f76392","observation_id":"960741bd-d7b9-4354-a140-3f5a453f9ddf","resolution":{"observed_at":"2026-08-01T08:38:51.443601Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10568","snapshot_observed_at":"2026-08-16T00:26:51.626399Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2608.12026","last_updated":"2026-08-12T13:06:50Z","snapshot_observed_at":"2026-08-19T01:47:20.297286Z","submitted_at":"2026-08-12T13:06:50Z","title":"SoftWater: Class-Aware Rate Allocation for Softmax Quantization","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-16T00:26:51.626399Z"},"links":{"cited_paper":"/paper/2004.10568","citing_paper":"/paper/2608.12026"},"observation_digest":"sha256:1552472a7ba77bd8cb51af61b45a36f6530ff78fe2fb847c4060ef97a1015b8b","observation_id":"2e73f742-8acc-4034-aea7-93e1458efc6e","resolution":{"observed_at":"2026-08-16T00:26:51.626399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2004.10568/citation-record","integrity":"/paper/2004.10568/integrity","json":"/paper/2004.10568/citation-record.json","paper":"/paper/2004.10568"},"outbound":[],"paper":{"arxiv_id":"2004.10568","last_updated":"2020-06-30T09:51:23Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T19:59:54.746291Z","submitted_at":"2020-04-22T13:44:28Z","title":"Up or Down? Adaptive Rounding for Post-Training Quantization"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2004.10568."}