{"as_of":"2026-08-10T03:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d3b5c17c98a1e41c7d847eb67f369daf7000deea5904e121dbca56b50c4ff382","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:35:20.206546Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T18:51:18.466788Z","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":"2026-05-10T23:50:52.675006Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"cited_work":{"arxiv_id":"2506.07587","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.07587","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Available: https://arxiv.org/abs/2506.07587","venue":null,"work_id":"6cfba3a8-cec9-4804-ae87-ca506d5727ad","year":null},"citing_paper":{"arxiv_id":"2604.05807","last_updated":"2026-04-07T12:44:19Z","snapshot_observed_at":"2026-08-03T02:37:09.804633Z","submitted_at":"2026-04-07T12:44:19Z","title":"Constraint-Driven Warm-Freeze for Efficient Transfer Learning in Photovoltaic Systems","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T18:51:18.466788Z"},"links":{"cited_paper":"/paper/2506.07587","citing_paper":"/paper/2604.05807"},"observation_digest":"sha256:38ac7200ee1166a70f074a262293343a2585d41dcf9255cf90fe71016ffe725e","observation_id":"8ece6cc0-cd04-46b6-93d0-d8cf91c4f667","resolution":{"observed_at":"2026-05-10T23:50:52.707893Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.07587/citation-record","integrity":"/paper/2506.07587/integrity","json":"/paper/2506.07587/citation-record.json","paper":"/paper/2506.07587"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.10512","last_updated":"2023-12-20T20:56:14Z","snapshot_observed_at":"2026-07-06T15:05:16.471478Z","submitted_at":"2023-03-18T22:36:25Z","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.10512","snapshot_observed_at":"2026-08-07T05:35:20.143648Z","title":"Adalora: Adaptive budget allocation for parameter-efficient fine- tuning.arXiv preprint arXiv:2303.10512,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.143648Z"},"links":{"cited_paper":"/paper/2303.10512","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:8551e77418cf490252970620dd78a7c6844e919670e32af24502db64117dd900","observation_id":"9114de08-f057-4f7e-b8c8-c69548095bee","resolution":{"observed_at":"2026-08-07T05:35:20.143648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00247","last_updated":"2021-01-26T12:54:33Z","snapshot_observed_at":"2026-08-09T18:48:57.194984Z","submitted_at":"2020-05-01T07:03:42Z","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.00247","snapshot_observed_at":"2026-08-07T05:35:20.151362Z","title":"Adapter- fusion: Non-destructive task composition for transfer learning.arXiv preprint arXiv:2005.00247, 2020a","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.151362Z"},"links":{"cited_paper":"/paper/2005.00247","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:babc935d4de89658157dac29b4338b04921c22fd6f0bf8461d66636e7b6a0ebb","observation_id":"bd17ceb5-dfe2-49d4-866c-1845ea576a5d","resolution":{"observed_at":"2026-08-07T05:35:20.151362Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16597","last_updated":"2023-05-26T03:01:07Z","snapshot_observed_at":"2026-08-05T13:15:12.433866Z","submitted_at":"2023-05-26T03:01:07Z","title":"Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.16597","snapshot_observed_at":"2026-08-07T05:35:20.155261Z","title":"Neural architecture search for parameter-efficient fine-tuning of large pre-trained language models.arXiv preprint arXiv:2305.16597,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.155261Z"},"links":{"cited_paper":"/paper/2305.16597","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:13ce54eafe2796cff541b6186db9efc16b5ef1a020562d9ed202b625eb19efce","observation_id":"893469f6-6f61-445a-b117-77ab73870ae6","resolution":{"observed_at":"2026-08-07T05:35:20.155261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.06440","last_updated":"2017-06-08T19:53:26Z","snapshot_observed_at":"2026-08-07T07:29:29.524604Z","submitted_at":"2016-11-19T22:48:30Z","title":"Pruning Convolutional Neural Networks for Resource Efficient Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.06440","snapshot_observed_at":"2026-08-07T05:35:20.159227Z","title":"Pruning convolutional neural networks for resource efficient inference.arXiv preprint arXiv:1611.06440,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.159227Z"},"links":{"cited_paper":"/paper/1611.06440","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:88618a14f36507635f580b23cb38de797617e72d67b58616bd5ea91b3c44d078","observation_id":"a362526e-a552-4b43-975d-7867b651620c","resolution":{"observed_at":"2026-08-07T05:35:20.159227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00052","last_updated":"2020-10-06T10:17:45Z","snapshot_observed_at":"2026-07-06T09:16:43.105433Z","submitted_at":"2020-04-30T18:54:43Z","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","version":3},"cited_work":{"arxiv_id":"2005.00052","doi":null,"metadata_source":"pith","pith_arxiv_id":"2005.00052","snapshot_observed_at":"2026-08-07T05:35:20.329270Z","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","venue":"cs.CL","work_id":"496bf2f1-a9fb-43ab-9b12-b82058a90bd0","year":2020},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.166702Z"},"links":{"cited_paper":"/paper/2005.00052","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:1000544fbab0da3c38c653d6647043d46784ef141fb505f6598bc3a8c1c3be8b","observation_id":"79b4c205-0cc0-43f2-a3bb-f55588cd6450","resolution":{"observed_at":"2026-08-07T05:35:20.333309Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12410","last_updated":"2022-11-02T02:47:17Z","snapshot_observed_at":"2026-08-09T21:04:05.676909Z","submitted_at":"2022-05-24T23:41:22Z","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.12410","snapshot_observed_at":"2026-08-07T05:35:20.170246Z","title":"Adamix: Mixture-of-adaptations for parameter-efficient model tuning.arXiv preprint arXiv:2205.12410,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.170246Z"},"links":{"cited_paper":"/paper/2205.12410","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:ad4be4d581e99972040fa3d562d8d1c444c7cef8eee56875df6b2ca34e0f311f","observation_id":"da7fc3c7-e972-4460-a171-a32463387dcb","resolution":{"observed_at":"2026-08-07T05:35:20.170246Z","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":"2026-08-07T05:35:20.463542Z","title":"Dora: Weight-decomposed low-rank adaptation.ICML 2024,","venue":null,"work_id":"94f86599-bd80-4972-8582-d4ec2f93e4d7","year":2024},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.173875Z"},"links":{"citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:ff935ab0f9c7b3d6ac7f2076032b6790cfacb882a4032479faf5e8eef9df4e39","observation_id":"315b20f0-4cc1-472b-b85b-dfceb9c29e36","resolution":{"observed_at":"2026-08-07T05:35:20.467487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.03844","last_updated":"2022-08-13T18:54:33Z","snapshot_observed_at":"2026-08-09T23:32:35.704157Z","submitted_at":"2020-04-08T07:09:59Z","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","version":3},"cited_work":{"arxiv_id":"2004.03844","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.03844","snapshot_observed_at":"2026-08-07T05:35:20.293046Z","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","venue":"cs.CL","work_id":"b800f98a-7ca2-49be-9872-9f61c747ea9f","year":2020},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.181064Z"},"links":{"cited_paper":"/paper/2004.03844","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:23c607217164afd32d72d1e7df20d36f25b82d9d473ab6deb2ebef9c366132ef","observation_id":"99d0d9cd-d21c-46c6-ae39-3b72deb90d6f","resolution":{"observed_at":"2026-08-07T05:35:20.298704Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:35:20.452868Z","title":"Probing pretrained language models for lexical semantics","venue":null,"work_id":"5d61ae15-13fb-437e-9dc3-663a0475d224","year":2020},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.188263Z"},"links":{"citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:3f92108459d862029acae20a32b02f8a65c1a683d904a28eff02d913bb33fe92","observation_id":"4c3b3d44-8668-4304-bc2c-384561bc8660","resolution":{"observed_at":"2026-08-07T05:35:20.456586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.01821","last_updated":"2023-01-04T21:00:18Z","snapshot_observed_at":"2026-07-06T14:37:32.503892Z","submitted_at":"2023-01-04T21:00:18Z","title":"Parameter-Efficient Fine-Tuning Design Spaces","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.01821","snapshot_observed_at":"2026-08-07T05:35:20.195445Z","title":"Parameter-efficient fine-tuning design spaces.arXiv preprint arXiv:2301.01821,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.195445Z"},"links":{"cited_paper":"/paper/2301.01821","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:275a92f3b5617e7e4ee5f3ba048f7f8c4b4062c3386e79d3cba0a93434e509e3","observation_id":"d594b4ae-c5e1-42c0-8dd7-f5156b0b6694","resolution":{"observed_at":"2026-08-07T05:35:20.195445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.02846","last_updated":"2021-09-07T03:59:22Z","snapshot_observed_at":"2026-08-06T08:08:54.702382Z","submitted_at":"2021-09-07T03:59:22Z","title":"Datasets: A Community Library for Natural Language Processing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.02846","snapshot_observed_at":"2026-08-07T05:35:20.199005Z","title":"Blending pruning criteria for convolutional neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.199005Z"},"links":{"cited_paper":"/paper/2109.02846","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:969eb07411cdae4e51fd29fb03b82a1f004d53851cafa219a5b884e6d5f0fcaf","observation_id":"e26d6800-9d60-4262-b3b4-ef343fb65ceb","resolution":{"observed_at":"2026-08-07T05:35:20.199005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.07779","last_updated":"2020-10-06T10:16:39Z","snapshot_observed_at":"2026-07-06T09:38:29.271727Z","submitted_at":"2020-07-15T15:56:05Z","title":"AdapterHub: A Framework for Adapting Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.07779","snapshot_observed_at":"2026-08-07T05:35:20.202596Z","title":"Adapterhub: A framework for adapting transformers.arXiv preprint arXiv:2007.07779, 2020c","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.202596Z"},"links":{"cited_paper":"/paper/2007.07779","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:8ebb7227e07b9c4bb43e34ec90684c7e161098b2b486bc91b62f51796b59fc95","observation_id":"7605fc6d-826f-4505-b753-4adb3b0bb590","resolution":{"observed_at":"2026-08-07T05:35:20.202596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-07T05:35:20.206546Z","title":null,"venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.206546Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:45e7b201d4eaa8287626f688171741335f135818e788f71683386bee8992d3d6","observation_id":"60630552-b47d-43ed-a219-dc3aee264f25","resolution":{"observed_at":"2026-08-07T05:35:20.206546Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.03250","last_updated":"2016-07-12T07:43:01Z","snapshot_observed_at":"2026-07-06T05:03:13.994105Z","submitted_at":"2016-07-12T07:43:01Z","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.03250","snapshot_observed_at":"2026-08-07T05:35:20.184803Z","title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.184803Z"},"links":{"cited_paper":"/paper/1607.03250","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:007e45a17201e5e71f4b15e9c5d017718cdd7ebf699225c8cfea076dcc29fb82","observation_id":"c4b00561-cae5-4e44-a113-a287d818e1f3","resolution":{"observed_at":"2026-08-07T05:35:20.184803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.03635","last_updated":"2019-03-04T15:51:11Z","snapshot_observed_at":"2026-08-05T23:54:27.386622Z","submitted_at":"2018-03-09T18:51:28Z","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.03635","snapshot_observed_at":"2026-08-07T05:35:20.177613Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks.arXiv preprint arXiv:1803.03635,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.177613Z"},"links":{"cited_paper":"/paper/1803.03635","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:322a59e489fe3bc018eb2abf22e2040629c0b4a90803acd424683c47e975bd9f","observation_id":"18103730-bff9-407b-b741-fadd7058c342","resolution":{"observed_at":"2026-08-07T05:35:20.177613Z","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":"2026-08-07T05:35:20.474234Z","title":"Auto-keras: An efficient neural architecture search system","venue":null,"work_id":"bf923589-4511-4880-bb73-b94a13c53b9e","year":1946},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.163347Z"},"links":{"citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:e88c00aadff947e154c2784df5f1111353018f3429be271018acf4c0d9171dc2","observation_id":"e7b57d7e-27d3-47dd-a5e6-8a3c759f9b58","resolution":{"observed_at":"2026-08-07T05:35:20.477914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.05950","last_updated":"2019-08-09T15:51:47Z","snapshot_observed_at":"2026-07-06T07:53:03.268985Z","submitted_at":"2019-05-15T05:47:23Z","title":"BERT Rediscovers the Classical NLP Pipeline","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.05950","snapshot_observed_at":"2026-08-07T05:35:20.191800Z","title":"Bert rediscovers the classical nlp pipeline.arXiv preprint arXiv:1905.05950,","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.191800Z"},"links":{"cited_paper":"/paper/1905.05950","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:6adc629baace2cc2328f56ba0e1a2adcf6b7e186b5588b8c33695206a00d2e54","observation_id":"94577200-2b90-490b-a9b3-8bd5d796387e","resolution":{"observed_at":"2026-08-07T05:35:20.191800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-07T05:35:20.139893Z","title":"Lora: Low-rank adaptation of large language models.arXiv preprint arXiv:2106.09685,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.139893Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:487508bf3a96fdba008b687c90f93599f3e69705cce53ab17e13c4e304d23c72","observation_id":"153a104c-87aa-4d72-8785-3835d1aa3e91","resolution":{"observed_at":"2026-08-07T05:35:20.139893Z","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":"2026-08-07T05:35:20.135969Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models.arXiv preprint arXiv:2106.10199,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.135969Z"},"links":{"citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:e442c0dcaefbb712fe0d94b18a82dc7c331566c6f99f6529fdfae3955a7578e5","observation_id":"c3ff001d-7415-4c3c-a478-95bd87511714","resolution":{"observed_at":"2026-08-07T05:35:20.135969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04366","last_updated":"2022-02-02T16:39:23Z","snapshot_observed_at":"2026-08-09T04:45:04.547249Z","submitted_at":"2021-10-08T20:22:26Z","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04366","snapshot_observed_at":"2026-08-07T05:35:20.147596Z","title":"Towards a unified view of parameter-efficient transfer learning.arXiv preprint arXiv:2110.04366, 2021a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T05:35:20.147596Z"},"links":{"cited_paper":"/paper/2110.04366","citing_paper":"/paper/2506.07587"},"observation_digest":"sha256:4eacf2f9104e7ba1d3c6cd50feab86ee07b5236dcff713ca99355d5121e6df17","observation_id":"fdf6c6db-7c5b-48b9-a443-307acc0c4f4e","resolution":{"observed_at":"2026-08-07T05:35:20.147596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.07587","last_updated":"2025-06-09T09:32:58Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T04:44:05.253698Z","submitted_at":"2025-06-09T09:32:58Z","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":15,"verified_exact":1,"verified_fuzzy":3},"total_outbound_references":20},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 1 inbound Pith citation observation for arXiv:2506.07587."}