{"as_of":"2026-08-08T09:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2420c7bec0806a85a1305abb4993b49e07d2e403c168cbc4dabe6c7a6330f083","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T19:03:04.952823Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2502.10202/citation-record","integrity":"/paper/2502.10202/integrity","json":"/paper/2502.10202/citation-record.json","paper":"/paper/2502.10202"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2308.12966","last_updated":"2023-10-13T02:41:28Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-24T17:59:17Z","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12966","snapshot_observed_at":"2026-08-07T19:03:04.783956Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.783956Z"},"links":{"cited_paper":"/paper/2308.12966","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:ef45f9c88d6c863dc54946ed680d811639ff64774060bdb9c09a95281ccd4004","observation_id":"b8fc4d71-1995-4814-9768-167912fde731","resolution":{"observed_at":"2026-08-07T19:03:04.783956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.04807","last_updated":"2020-03-10T15:33:54Z","snapshot_observed_at":"2026-08-06T01:22:03.305472Z","submitted_at":"2020-03-10T15:33:54Z","title":"Efficient Intent Detection with Dual Sentence Encoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.04807","snapshot_observed_at":"2026-08-07T19:03:04.790602Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.790602Z"},"links":{"cited_paper":"/paper/2003.04807","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:fb49b87e1e1699f5701a9b1bd6ab37217f99c821ca26f6cf7d98b45d572377fd","observation_id":"b001be23-2ee9-46fb-ac30-a1c246e9861c","resolution":{"observed_at":"2026-08-07T19:03:04.790602Z","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":"2026-08-07T19:03:04.795949Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.795949Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:465faeb01ad40d1c00ec5b1272abe69e0c1c49920d7ecb41c37aff63f30c664b","observation_id":"478cec03-2437-43ca-a72f-99f6f06010fa","resolution":{"observed_at":"2026-08-07T19:03:04.795949Z","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":"2026-08-07T19:03:05.539116Z","title":null,"venue":null,"work_id":"2b3f6bf5-78db-4eb7-b1a2-2a31ee5eb231","year":2024},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.803756Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:bf64f31d38095cf452a187f3ba96c44f31c5b99b9259d5bd0ea9aaf7f0424e9f","observation_id":"2a86c0fc-a129-4403-a53c-32f80bf719d7","resolution":{"observed_at":"2026-08-07T19:03:05.544649Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T19:03:04.809073Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.809073Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:62ead8683238da298bfceccab8b41f90c11bd1fe4d5372af70ea6da63d33df6a","observation_id":"4c4e017a-8a34-4ec9-aaac-6496d5935516","resolution":{"observed_at":"2026-08-07T19:03:04.809073Z","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":"2026-08-07T19:03:05.502664Z","title":null,"venue":null,"work_id":"85869c73-9b50-43f9-9150-b6ab09f98907","year":2023},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.814202Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:7e30cfaceda9a5f9b36844aad47d611c229a603460c0a9f404e6e32d2049a0ed","observation_id":"9ba65dab-8ce3-41ed-b955-eb89ea4691df","resolution":{"observed_at":"2026-08-07T19:03:05.507953Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T19:03:04.819711Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.819711Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:e7e7fac84d89509e00e49e76057ccf6c02aff4b6d3eaae6d8a59cc703edd3801","observation_id":"08eacbdc-a5f1-45d5-ba91-a8ad3cb60419","resolution":{"observed_at":"2026-08-07T19:03:04.819711Z","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":"2026-08-07T08:38:54.025062Z","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":"2026-08-07T19:03:04.824895Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.824895Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:aab530d5ec6e5795453d157a95367a8828d1007aea07babffdcc5d893e3350fe","observation_id":"c62a6ab0-8f4f-4642-a7cb-6c6ca9356536","resolution":{"observed_at":"2026-08-07T19:03:04.824895Z","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":"2026-08-07T19:03:05.483947Z","title":null,"venue":null,"work_id":"a1ea73c9-851d-46e9-adf6-99ba282c7625","year":2023},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.831444Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:c5e19afa6c083e5253eaf7d9117bda4cf26b4dbbfb43333331b3775a02606d97","observation_id":"ba15b062-6f1f-4f08-ae8b-f99cc97a44b3","resolution":{"observed_at":"2026-08-07T19:03:05.488851Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.13630","last_updated":"2021-06-21T21:01:12Z","snapshot_observed_at":"2026-07-06T10:53:11.986981Z","submitted_at":"2021-03-25T06:57:11Z","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.13630","snapshot_observed_at":"2026-08-07T19:03:04.836700Z","title":"Mahoney, and Kurt Keutzer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.836700Z"},"links":{"cited_paper":"/paper/2103.13630","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:cc6e2fd8d1831bfb086984bf2f0cba137c8a628e9f84c222031c255b2b5401bf","observation_id":"be0c3fb5-8441-4c69-9787-a111ff43e423","resolution":{"observed_at":"2026-08-07T19:03:04.836700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.00751","last_updated":"2019-06-13T17:48:30Z","snapshot_observed_at":"2026-07-06T07:30:44.870185Z","submitted_at":"2019-02-02T16:29:47Z","title":"Parameter-Efficient Transfer Learning for NLP","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.00751","snapshot_observed_at":"2026-08-07T19:03:04.842154Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.842154Z"},"links":{"cited_paper":"/paper/1902.00751","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:e829254828739caeeb01102734466bef18d99913b048e8c6ad38932e3e56247b","observation_id":"849cea46-4e56-4e4d-9d99-31babb59e85a","resolution":{"observed_at":"2026-08-07T19:03:04.842154Z","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":"2026-08-07T19:03:05.466796Z","title":null,"venue":null,"work_id":"e243b171-fac0-4793-8436-2d66e14b04b5","year":2022},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.847099Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:dbeecee063c8c1f3ae2ed06138629a7586a10f9bed86f18010dc31cbdc8be3a1","observation_id":"280796a5-b564-47fc-b041-9dcdc695c225","resolution":{"observed_at":"2026-08-07T19:03:05.471875Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T19:03:05.447679Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen - Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":"0152b893-0a98-4c25-b20c-9575c2ac3964","year":2022},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.851839Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:5034f03999da8db08e865bcfa612a556306e7670ed36a5ad2c39392196feedb8","observation_id":"efdac8ed-8a5d-453c-8c98-e8919c548821","resolution":{"observed_at":"2026-08-07T19:03:05.454151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T19:03:05.428234Z","title":null,"venue":null,"work_id":"5ad4465b-a726-4891-aaed-3afd92b96c01","year":2018},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.855994Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:84e4d25683ff42e1446a33b3ca55fd510cccb01ae574ec5d2e93b8fceffffaf4","observation_id":"9692f89c-8f4a-4f9f-8842-5465d9cf0c23","resolution":{"observed_at":"2026-08-07T19:03:05.434395Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-07T19:03:04.860679Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.860679Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:a41a40cbaa05ff93718acc931f9a7e4b3e4e5ad2c23bc1d1d40942261beb0511","observation_id":"f259af1e-2281-4c7f-a1ac-dca7fdfa2024","resolution":{"observed_at":"2026-08-07T19:03:04.860679Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11055","last_updated":"2025-06-04T01:15:49Z","snapshot_observed_at":"2026-08-06T14:52:52.028018Z","submitted_at":"2024-09-17T10:31:37Z","title":"Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11055","snapshot_observed_at":"2026-08-07T19:03:04.865990Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.865990Z"},"links":{"cited_paper":"/paper/2409.11055","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:e675ed0aa0ac2fdb64005e1e562f15dc34021ddd265070b2184a9ddb72a8f12c","observation_id":"1ba30fcc-a5e0-469a-a5c1-42f00d72f477","resolution":{"observed_at":"2026-08-07T19:03:04.865990Z","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":"2026-08-04T09:21:27.169501Z","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":"2026-08-07T19:03:04.871376Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.871376Z"},"links":{"cited_paper":"/paper/2102.05426","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:70b408ec26ea1561b3b28792e38c2320d239e05094c61b047bd41ee249a37a85","observation_id":"3dfdb429-e723-4e75-a4bb-51d0e5dac7f0","resolution":{"observed_at":"2026-08-07T19:03:04.871376Z","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":"2026-08-07T19:03:05.404885Z","title":null,"venue":null,"work_id":"781a5eae-21c5-433c-a3e8-36d4225e6700","year":2024},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.876851Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:7cd301512c0288636593afbbe1b453e575b7f56bb452d3aba3dfc35eddc7f95d","observation_id":"52a1e0e5-d7bc-4f83-937b-316a46c593ad","resolution":{"observed_at":"2026-08-07T19:03:05.410906Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T19:03:05.385789Z","title":null,"venue":null,"work_id":"c0029459-319a-4161-ac31-753e71256de9","year":2024},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.882502Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:4a6955e48688d8e304acc2e230487a59574901aa2dba4fc439bd4cad429fbabb","observation_id":"59634723-225c-45b9-a7d4-632ad0ec4466","resolution":{"observed_at":"2026-08-07T19:03:05.390339Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-07T19:03:04.887338Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.887338Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:85cd5569db2f57aa36697f62f69e93ac26d509ec65c664629ef34687d968614d","observation_id":"5df8c8fb-2ca8-4e20-9fed-1609a0470700","resolution":{"observed_at":"2026-08-07T19:03:04.887338Z","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":"2026-08-07T19:03:05.368660Z","title":null,"venue":null,"work_id":"7b287808-d605-4330-a618-5a37374be8de","year":2020},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.892668Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:b092da4e3560b89c16b67fd4db8cc29086822908c68be32430faf3d43ff5f6e6","observation_id":"84f0cab1-ee13-4463-a783-62b6ce8a871b","resolution":{"observed_at":"2026-08-07T19:03:05.374538Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"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":"2026-08-07T19:03:04.899119Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.899119Z"},"links":{"cited_paper":"/paper/2106.08295","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:5bc5f169937b323aa2eb67d5e7f6748401be1654317885f71457df35517aa7c3","observation_id":"38e9f7c6-a4ca-4f9b-80a6-3cbc5368a6c2","resolution":{"observed_at":"2026-08-07T19:03:04.899119Z","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":"2026-08-07T19:03:04.904192Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.904192Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:7eb23a752b6c5a1c13a69e41cbbf506a9a5244bdfa91da0cf1880dcd6d48177d","observation_id":"e0e7553a-9311-4693-9a29-229204ca3ffb","resolution":{"observed_at":"2026-08-07T19:03:04.904192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.10683","last_updated":"2023-09-19T15:14:48Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2019-10-23T17:37:36Z","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.10683","snapshot_observed_at":"2026-08-07T19:03:04.909191Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.909191Z"},"links":{"cited_paper":"/paper/1910.10683","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:1f975be45688c9a850d445a678ba00b2a3954c545e2e4ad928f2e901095fe3c2","observation_id":"cce01f86-fdb0-49bc-94a7-56f2809cb184","resolution":{"observed_at":"2026-08-07T19:03:04.909191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-07T19:03:04.914838Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.914838Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:33bc9f483a3dc53f1fdb0f8eae5dba1f2b06244074988a65d838a9a13bf79f76","observation_id":"0f56160b-4c24-4c59-86e2-2736592306c1","resolution":{"observed_at":"2026-08-07T19:03:04.914838Z","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":"2026-08-07T19:03:04.921739Z","title":"Smith, Daniel Khashabi, and Hannaneh Hajishirzi","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.921739Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:a7e4f0f201ba1b404fdf9ded6cbe041041dcb92c492adca4be3e799c58aed015","observation_id":"2c5bcfe7-7558-4f49-aa0d-c3c5519629f4","resolution":{"observed_at":"2026-08-07T19:03:04.921739Z","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":"2026-08-07T19:03:04.927820Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.927820Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:5528b9f530b88e65c6e772fe671df75fc68c08ae5c332608a0e7dcc9baad06d9","observation_id":"6194d3b9-a5c9-4c1f-bcb9-16d84940719b","resolution":{"observed_at":"2026-08-07T19:03:04.927820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10671","last_updated":"2024-09-10T13:25:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-15T12:35:42Z","title":"Qwen2 Technical Report","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10671","snapshot_observed_at":"2026-08-07T19:03:04.935180Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.935180Z"},"links":{"cited_paper":"/paper/2407.10671","citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:ffe8d98f95120213684059536c759589795fdde31d913a885a160045b8328134","observation_id":"7d0d3486-75ed-4b5c-87a8-ff7e59931247","resolution":{"observed_at":"2026-08-07T19:03:04.935180Z","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":"2026-08-07T19:03:04.940997Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.940997Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:11cc254a2287a4fd6a9bb7b3cec7cbb86094e69c199ae8b83b396539e2f861bd","observation_id":"09373e4b-cbaa-43b4-a5da-96b915ba79fe","resolution":{"observed_at":"2026-08-07T19:03:04.940997Z","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":"2026-08-07T19:03:04.947234Z","title":"online\" 'onlinestring :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.947234Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:d23fb04d29f464ce83710529cb9e53a770aec7da5e1cd953ea0e14491d3eeeca","observation_id":"6739deae-6ac4-48f6-ae1b-fa46dcaf5382","resolution":{"observed_at":"2026-08-07T19:03:04.947234Z","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":"2026-08-07T19:03:04.952823Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T19:03:04.952823Z"},"links":{"citing_paper":"/paper/2502.10202"},"observation_digest":"sha256:51f8aed64a127291d291c80e3baf789062542c1ed6ddbd9babb4aa26e1093bd6","observation_id":"5c42d01f-63ca-4c55-98d1-01e8a4abc59e","resolution":{"observed_at":"2026-08-07T19:03:04.952823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.10202","last_updated":"2025-02-14T14:56:19Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T23:43:07.586371Z","submitted_at":"2025-02-14T14:56:19Z","title":"Can Post-Training Quantization Benefit from an Additional QLoRA Integration?"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":0,"verified_fuzzy":1},"total_outbound_references":31},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2502.10202."}