{"as_of":"2026-08-11T12:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0c12388afb3322242086abb817d26dd2b8e2ae5bb5f2c05cb759a5ff5288c08b","coverage":[{"denominator":25,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":25,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T01:35:44.824860Z","state":"measured"},{"denominator":25,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":25,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2607.14630/citation-record","integrity":"/paper/2607.14630/integrity","json":"/paper/2607.14630/citation-record.json","paper":"/paper/2607.14630"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2210.17323","last_updated":"2023-03-22T13:10:47Z","snapshot_observed_at":"2026-08-07T08:38:54.025062Z","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":"2026-08-02T01:35:42.139308Z","title":"Frantar, S","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":1,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:42.139308Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:06d85d92fd57583e6a5a0c38d2bef4f0ae122938584eea60b89ddb8a5a1389c4","observation_id":"8fdad455-67f5-42f6-a2bd-763dbf912e76","resolution":{"observed_at":"2026-08-02T01:35:42.139308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.05426","last_updated":"2021-07-25T09:34:39Z","snapshot_observed_at":"2026-08-10T19:57:21.389202Z","submitted_at":"2021-02-10T13:46:16Z","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.05426","snapshot_observed_at":"2026-08-02T01:35:42.201937Z","title":"Li et al","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":2,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:42.201937Z"},"links":{"cited_paper":"/paper/2102.05426","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:deabbc41a2901921d4ac1351291f5f52863c6256a80bdfc0070a6badd7aaf9d2","observation_id":"0c15cf56-3e34-4926-9c87-5a6d479e6562","resolution":{"observed_at":"2026-08-02T01:35:42.201937Z","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":"2026-08-08T12:31:54.022002Z","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":"2026-08-08T01:00:35.370812Z","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":"sha256:7bb94b9bf59c822adebc474427fc1bf49210697af515d00811727bbbff7729e1","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:35:42.475221Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":4,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:42.475221Z"},"links":{"citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:b86f4bfecbb0fdf3a7e8d40c8e5077e303822aa6f9043d6e4a7126e29d952bde","observation_id":"66ac6acf-9587-4ed4-8c7e-f6fc8f86cdf2","resolution":{"observed_at":"2026-08-02T01:35:42.475221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22988","last_updated":"2026-06-03T05:56:05Z","snapshot_observed_at":"2026-08-07T12:53:31.543703Z","submitted_at":"2025-05-29T01:53:00Z","title":"Model-Preserving Adaptive Rounding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.22988","snapshot_observed_at":"2026-08-02T01:35:42.511516Z","title":"Tseng, Z","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":5,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:42.511516Z"},"links":{"cited_paper":"/paper/2505.22988","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:605376e02dc4ca2abada1881ff1ef75141ed1e47861aca99dedd8defce247e71","observation_id":"65a9b4a5-5f7b-41bc-b16e-f4ad351355fe","resolution":{"observed_at":"2026-08-02T01:35:42.511516Z","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":"2026-08-02T01:35:42.620141Z","title":"Kim et al","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":6,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:42.620141Z"},"links":{"citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:8df13370a46402c8ee0e6ba7d52513acc33b795e312833a8f334e53a503b2ffb","observation_id":"f65bd00c-5c75-46d4-887e-696f4adce7a8","resolution":{"observed_at":"2026-08-02T01:35:42.620141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07955","last_updated":"2026-04-09T08:20:59Z","snapshot_observed_at":"2026-08-11T08:12:25.572641Z","submitted_at":"2026-04-09T08:20:59Z","title":"Rethinking Residual Errors in Compensation-based LLM Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.07955","snapshot_observed_at":"2026-08-02T01:35:42.742492Z","title":"arXiv:2604.07955, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":7,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:42.742492Z"},"links":{"cited_paper":"/paper/2604.07955","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:72a5f0886cfd648a70f4a31629c446227625109c95a4a4264423b39ffd9f3d8a","observation_id":"4e08ee3e-3c65-4757-a31f-f4681386b92b","resolution":{"observed_at":"2026-08-02T01:35:42.742492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.00363","last_updated":"2016-04-18T13:11:45Z","snapshot_observed_at":"2026-07-06T04:35:01.085808Z","submitted_at":"2015-11-02T02:50:05Z","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.00363","snapshot_observed_at":"2026-08-02T01:35:42.874126Z","title":"Courbariaux, Y","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":8,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:42.874126Z"},"links":{"cited_paper":"/paper/1511.00363","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:1d6feb8ed711766a4f682bbe2076a6957c508bb643d377e8f3d936c5ff0b0b5f","observation_id":"e4eb882a-a147-4cac-9d50-7907714d7f01","resolution":{"observed_at":"2026-08-02T01:35:42.874126Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1603.05279","last_updated":"2016-08-02T20:59:14Z","snapshot_observed_at":"2026-07-06T04:49:45.483208Z","submitted_at":"2016-03-16T20:56:21Z","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1603.05279","snapshot_observed_at":"2026-08-02T01:35:43.010828Z","title":"Rastegari, V","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":9,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.010828Z"},"links":{"cited_paper":"/paper/1603.05279","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:81afa11d2ce3bbd5c4b18d61964f4311b4fdab3e9578637413c28e1cbb5058c9","observation_id":"acdd4316-b7e3-4779-8521-733465d47e84","resolution":{"observed_at":"2026-08-02T01:35:43.010828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11453","last_updated":"2023-10-17T17:59:15Z","snapshot_observed_at":"2026-08-11T03:44:43.109946Z","submitted_at":"2023-10-17T17:59:15Z","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11453","snapshot_observed_at":"2026-08-02T01:35:43.133161Z","title":"Wang et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":10,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.133161Z"},"links":{"cited_paper":"/paper/2310.11453","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:949a56a950e745bc782196eaa0c19771de45545342ce54104efaa990bb7f217e","observation_id":"e3d625a9-23ef-48cf-93ad-4ed24f282cd6","resolution":{"observed_at":"2026-08-02T01:35:43.133161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17764","last_updated":"2024-02-27T18:56:19Z","snapshot_observed_at":"2026-08-03T00:59:01.026576Z","submitted_at":"2024-02-27T18:56:19Z","title":"The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17764","snapshot_observed_at":"2026-08-02T01:35:43.203227Z","title":"Ma et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":11,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.203227Z"},"links":{"cited_paper":"/paper/2402.17764","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:09231ca77b03503d2b09347e770c26212c6c812638207496fefb1759620ffcfa","observation_id":"ba88d05a-0909-488b-aece-4d58cc9356ac","resolution":{"observed_at":"2026-08-02T01:35:43.203227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11295","last_updated":"2024-11-29T11:47:55Z","snapshot_observed_at":"2026-07-06T17:31:37.574049Z","submitted_at":"2024-02-17T14:26:57Z","title":"OneBit: Towards Extremely Low-bit Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11295","snapshot_observed_at":"2026-08-02T01:35:43.341032Z","title":"Xu et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":12,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.341032Z"},"links":{"cited_paper":"/paper/2402.11295","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:f7829d0236bf630f6e1c9926bcaf28d2fa1a921e02e560f4268ccb73bb460713","observation_id":"d615411e-6a98-4668-9e91-ff53a1bfa1f5","resolution":{"observed_at":"2026-08-02T01:35:43.341032Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04291","last_updated":"2024-05-15T13:55:12Z","snapshot_observed_at":"2026-08-10T07:01:56.653018Z","submitted_at":"2024-02-06T09:26:34Z","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04291","snapshot_observed_at":"2026-08-02T01:35:43.424174Z","title":"Huang et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":13,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.424174Z"},"links":{"cited_paper":"/paper/2402.04291","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:f30f04a76c46d90af22b659e48b89fe979b913270f9857658c715f5dafa0b91e","observation_id":"d39fd99e-8550-427d-bc25-842c1b824fa9","resolution":{"observed_at":"2026-08-02T01:35:43.424174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07093","last_updated":"2024-07-09T17:59:48Z","snapshot_observed_at":"2026-08-10T06:21:57.500242Z","submitted_at":"2024-07-09T17:59:48Z","title":"FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07093","snapshot_observed_at":"2026-08-02T01:35:43.528232Z","title":"Ma et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":14,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.528232Z"},"links":{"cited_paper":"/paper/2407.07093","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:7a15c0dde9a53b10c0c4eae2eb533b46585572fa635ea9fe2d4de58de1a3f6f6","observation_id":"c74d2b19-e863-46c6-89a3-37c4cf22ceef","resolution":{"observed_at":"2026-08-02T01:35:43.528232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00861","last_updated":"2019-03-05T00:28:48Z","snapshot_observed_at":"2026-08-09T18:10:01.425770Z","submitted_at":"2018-10-01T17:57:02Z","title":"ProxQuant: Quantized Neural Networks via Proximal Operators","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.00861","snapshot_observed_at":"2026-08-02T01:35:43.625592Z","title":"Bai, Y.-X","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":15,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.625592Z"},"links":{"cited_paper":"/paper/1810.00861","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:65cc24f55bc99e3b95640f1faa36793feb0b60f04079a8001cf1ae2931bf89ce","observation_id":"48c5bcc9-ee9b-4ad1-870c-73bfce890510","resolution":{"observed_at":"2026-08-02T01:35:43.625592Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.08237","last_updated":"2021-03-02T05:13:00Z","snapshot_observed_at":"2026-08-06T16:28:41.444776Z","submitted_at":"2019-10-18T03:19:21Z","title":"Mirror Descent View for Neural Network Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.08237","snapshot_observed_at":"2026-08-02T01:35:43.747800Z","title":"Ajanthan, K","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":16,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.747800Z"},"links":{"cited_paper":"/paper/1910.08237","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:19fa8b3033f7f9c3570573ad545061702f222bfcd8310b455f3e99a40c5b5655","observation_id":"e5d08d8d-0c72-40e0-bb01-9db0a45e781d","resolution":{"observed_at":"2026-08-02T01:35:43.747800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04396","last_updated":"2024-06-04T04:51:52Z","snapshot_observed_at":"2026-08-10T20:22:11.583524Z","submitted_at":"2024-02-06T20:52:12Z","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04396","snapshot_observed_at":"2026-08-02T01:35:43.851034Z","title":"Tseng, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":17,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.851034Z"},"links":{"cited_paper":"/paper/2402.04396","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:693d90d3d55bde5d15b571c182dbe55af23afc22292825d205f01013d677940d","observation_id":"6f7f2d25-95d6-4df6-a7d3-18d90b9d3ac6","resolution":{"observed_at":"2026-08-02T01:35:43.851034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16406","last_updated":"2025-02-20T06:07:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-05-26T02:15:49Z","title":"SpinQuant: LLM quantization with learned rotations","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.16406","snapshot_observed_at":"2026-08-02T01:35:43.971644Z","title":"Liu et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":18,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:43.971644Z"},"links":{"cited_paper":"/paper/2405.16406","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:009c0787dab3e4b154be2fe2fd59bdc8ea7e91e506a0c5fd8008283b54e2d643","observation_id":"7f521874-90f9-4496-bf3e-9c4d86c11ac7","resolution":{"observed_at":"2026-08-02T01:35:43.971644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.10899","last_updated":"2023-08-18T18:29:21Z","snapshot_observed_at":"2026-08-07T03:58:42.728383Z","submitted_at":"2023-02-10T01:00:49Z","title":"Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.10899","snapshot_observed_at":"2026-08-02T01:35:44.118863Z","title":"Li et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":19,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:44.118863Z"},"links":{"cited_paper":"/paper/2302.10899","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:2ec3c89ad370d9df12a1c43ae3be4d031c6e30e576b44ead190d0eb434193efb","observation_id":"c31bd8a8-aadd-4cbd-9b7c-93a9078cdd3d","resolution":{"observed_at":"2026-08-02T01:35:44.118863Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.00281","last_updated":"2020-01-01T23:58:26Z","snapshot_observed_at":"2026-08-09T08:03:19.750099Z","submitted_at":"2020-01-01T23:58:26Z","title":"ZeroQ: A Novel Zero Shot Quantization Framework","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.00281","snapshot_observed_at":"2026-08-02T01:35:44.239669Z","title":null,"venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":20,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:44.239669Z"},"links":{"cited_paper":"/paper/2001.00281","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:fecc5eb168384184e2982a8c941f636886c07464a5a13b4bdceca713485ac86e","observation_id":"e3a42f66-1f49-48d7-bd4a-7db214673753","resolution":{"observed_at":"2026-08-02T01:35:44.239669Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-02T01:35:44.360434Z","title":"Hinton, O","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":21,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:44.360434Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:b75fb83b68366ae76de850d823c7a7efc8b339a67348e9b4fc988dbd1d9bc20f","observation_id":"f163b451-23a7-40f2-9979-8ece2f811176","resolution":{"observed_at":"2026-08-02T01:35:44.360434Z","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":"2026-08-02T01:35:44.479317Z","title":"Kornblith, M","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":22,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:44.479317Z"},"links":{"citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:f4c01138ba533e8dc6f82dd43946bca598fdbdfe065682d2d34430b8d0b268ba","observation_id":"3e00ec65-69fb-4f5a-a5a2-5a563f07970f","resolution":{"observed_at":"2026-08-02T01:35:44.479317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-02T01:35:44.623653Z","title":"Qwen2.5 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":23,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:44.623653Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:99b3ac1ddc5c1451d00d50998a9cb60306307a95a13fdd601c078e7dd047c33f","observation_id":"3bd2d8a6-f640-4e9a-8eac-b50bb628f279","resolution":{"observed_at":"2026-08-02T01:35:44.623653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07843","last_updated":"2016-09-26T04:06:13Z","snapshot_observed_at":"2026-07-06T05:12:10.387914Z","submitted_at":"2016-09-26T04:06:13Z","title":"Pointer Sentinel Mixture Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.07843","snapshot_observed_at":"2026-08-02T01:35:44.731000Z","title":"Merity, C","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":24,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:44.731000Z"},"links":{"cited_paper":"/paper/1609.07843","citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:ddc2c4e131524d591e4c464eb197c5132bc03229f91addb50d14d0f73d2f53c2","observation_id":"b65a354e-9cbf-4c35-bb57-6a2f31440d4f","resolution":{"observed_at":"2026-08-02T01:35:44.731000Z","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":"2026-08-02T01:35:44.824860Z","title":"Raffel et al","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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":25,"source":"pdf_text","source_observed_at":"2026-08-02T01:35:44.824860Z"},"links":{"citing_paper":"/paper/2607.14630"},"observation_digest":"sha256:9114b51028b944e6547cdff481054e7267af86ffdca3ee9ba11abe43700a093c","observation_id":"2a8b0c6a-7cab-49b8-b673-dcdbaa84ec16","resolution":{"observed_at":"2026-08-02T01:35:44.824860Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.14630","last_updated":"2026-07-16T06:47:52Z","latest_version":1,"primary_category":"cs.NE","snapshot_observed_at":"2026-08-08T01:00:35.370812Z","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"},"reference_resolution":{"displayed":25,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":25,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":25},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2607.14630."}