{"as_of":"2026-08-08T04:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9dfd80cacf9bd1c8c12700cb92f43da34ce202fbdfa523a75bba181d8545edb2","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:16:23.379721Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T16:12:12.064235Z","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":"2026-05-10T08:48:01.010080Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"cited_work":{"arxiv_id":"2506.03337","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.03337","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mitigating non-iid drift in zeroth-order federated llm fine-tuning with transferable sparsity","venue":null,"work_id":"2a0c703d-4db5-4f1f-8518-45817502546a","year":2025},"citing_paper":{"arxiv_id":"2604.16197","last_updated":"2026-07-19T20:58:40Z","snapshot_observed_at":"2026-08-07T01:48:38.832815Z","submitted_at":"2026-04-17T16:07:11Z","title":"Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-10T08:47:36.122054Z"},"links":{"cited_paper":"/paper/2506.03337","citing_paper":"/paper/2604.16197"},"observation_digest":"sha256:02f60ba08dd07c519f1dad4b8af480ef1e078653c7e287a8865cc6c2cea3b306","observation_id":"52365066-34db-4900-b12d-44fe023fded1","resolution":{"observed_at":"2026-05-10T08:48:01.011965Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.03337","snapshot_observed_at":"2026-08-02T16:12:12.064235Z","title":"Mitigating non-iid drift in zeroth-order federated llm fine-tuning with transferable sparsity, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.16197","last_updated":"2026-07-19T20:58:40Z","snapshot_observed_at":"2026-08-07T01:48:38.832815Z","submitted_at":"2026-04-17T16:07:11Z","title":"Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T16:12:12.064235Z"},"links":{"cited_paper":"/paper/2506.03337","citing_paper":"/paper/2604.16197"},"observation_digest":"sha256:579ba4aaa05d61ef20d41ccb5fa3d739237f5161b252a49f15b151c35fbd2e70","observation_id":"725f1724-5409-46c4-b804-e576c963f7af","resolution":{"observed_at":"2026-08-02T16:12:12.064235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.03337/citation-record","integrity":"/paper/2506.03337/integrity","json":"/paper/2506.03337/citation-record.json","paper":"/paper/2506.03337"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:16:19.749113Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:19.749113Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:8bdd4c9a6e0b3f5f8bd5a2e9ddc88b091de779acfa73bd2d156602661d9d31a2","observation_id":"fdb4c744-4f00-4fae-abaa-8e92880ae167","resolution":{"observed_at":"2026-08-07T11:16:19.749113Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.04263","last_updated":"2021-11-09T16:37:10Z","snapshot_observed_at":"2026-08-06T07:03:02.521207Z","submitted_at":"2021-11-08T03:58:28Z","title":"Federated Learning Based on Dynamic Regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.04263","snapshot_observed_at":"2026-08-07T11:16:19.831388Z","title":"What- mough, and Venkatesh Saligrama","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:19.831388Z"},"links":{"cited_paper":"/paper/2111.04263","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:19f76e1b4c143d40b9578a85f158667ab1bd995f85d35ea629491d60fa3dbe59","observation_id":"e0f3bf3d-0882-4b8c-a40d-bcd12b99ecdb","resolution":{"observed_at":"2026-08-07T11:16:19.831388Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.04838","last_updated":"2018-02-08T20:40:22Z","snapshot_observed_at":"2026-07-06T05:00:05.796040Z","submitted_at":"2016-06-15T16:15:53Z","title":"Optimization Methods for Large-Scale Machine Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.04838","snapshot_observed_at":"2026-08-07T11:16:19.941903Z","title":"Curtis, and Jorge Nocedal","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:19.941903Z"},"links":{"cited_paper":"/paper/1606.04838","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:a1834a28b898f0b656db3c0741a912014e933b32b827fcc65f9788817f2ee92f","observation_id":"cf45c2db-c37a-47ef-bb49-0c7a2350fd75","resolution":{"observed_at":"2026-08-07T11:16:19.941903Z","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":"2026-08-07T11:16:20.034105Z","title":"Languagemodels are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.034105Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:e72c6bb1af991598ea84dc2eca45ee348e256291895fca032da169c849e38df8","observation_id":"b94b8ca7-58fe-44a9-8d33-785666b5329a","resolution":{"observed_at":"2026-08-07T11:16:20.034105Z","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":"2026-08-07T11:16:27.022753Z","title":"Fine-grained theoretical analysis of federated zeroth-order optimization.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"b337ab46-1aaa-4c1c-b8af-e7d3d23fe3d3","year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.115793Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:e9fe036f3928ac6de769c2d448526bc8ee36c1a6004a373ac42de17898009ed4","observation_id":"9a3dd913-5ea5-429b-a167-62519923b2f6","resolution":{"observed_at":"2026-08-07T11:16:27.080591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.10044","last_updated":"2019-05-24T05:48:49Z","snapshot_observed_at":"2026-07-06T07:55:12.121264Z","submitted_at":"2019-05-24T05:48:49Z","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.10044","snapshot_observed_at":"2026-08-07T11:16:20.207736Z","title":"Boolq: Exploring the surprising difficulty of natural yes/no questions","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.207736Z"},"links":{"cited_paper":"/paper/1905.10044","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:1a4749045e15d4426308ce20d0f4310edb77720240bc2acda139bee9832e512c","observation_id":"c72ef9fd-1a01-4ef4-84bc-4321e8d03df6","resolution":{"observed_at":"2026-08-07T11:16:20.207736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T11:16:20.272607Z","title":"The llama 3 herd of models.arXiv preprint arXiv:2407.21783, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.272607Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:9953e463318be48901b76cd9acf2e40dd87e2c78051a5a544a7068b6fa02d89e","observation_id":"bf7bf74c-f27a-4e11-9765-b2f53d81d56d","resolution":{"observed_at":"2026-08-07T11:16:20.272607Z","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":"2026-08-07T11:16:26.864069Z","title":"Communication-efficient stochastic zeroth-order optimization for federated learning.IEEE Transactions on Signal Processing, 70:5058–5073, 2022","venue":null,"work_id":"5ff9d5f7-705a-4de0-ad26-8b9d301003c2","year":2022},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.352609Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:de6fb32682629b6184dcbd9159a6cf49940626df5160b70bcae66b8e786ccc6f","observation_id":"d3f21eaa-b62e-47b6-931e-a1279517c1e7","resolution":{"observed_at":"2026-08-07T11:16:26.937303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02913","last_updated":"2024-06-05T04:07:35Z","snapshot_observed_at":"2026-07-06T18:25:40.229186Z","submitted_at":"2024-06-05T04:07:35Z","title":"Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02913","snapshot_observed_at":"2026-08-07T11:16:20.416022Z","title":"Gardner, Osbert Bastani, Christopher De Sa, Xiaodong Yu, Beidi Chen, and Zhaozhuo Xu","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.416022Z"},"links":{"cited_paper":"/paper/2406.02913","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:f37ac668d624b01e4809947b6b054b591c0123e7c90f32df2cdc4134f7a7dbb6","observation_id":"f169995d-d57c-4451-bb56-f256717cd7a8","resolution":{"observed_at":"2026-08-07T11:16:20.416022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.20584","last_updated":"2024-12-18T07:14:33Z","snapshot_observed_at":"2026-08-08T01:30:48.726185Z","submitted_at":"2024-07-30T06:33:44Z","title":"Pruning Large Language Models with Semi-Structural Adaptive Sparse Training","version":3},"cited_work":{"arxiv_id":"2407.20584","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.20584","snapshot_observed_at":"2026-08-07T11:16:24.349651Z","title":"Pruning Large Language Models with Semi-Structural Adaptive Sparse Training","venue":"cs.CL","work_id":"83a19808-8376-4ece-9d51-d51814a61f75","year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.505689Z"},"links":{"cited_paper":"/paper/2407.20584","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:70cedba1ef9e9e348c9adb421299ae63f586b063edc8a95995272efa78b64bf6","observation_id":"beeb33f7-77e1-4298-a91a-79e4c1d01dec","resolution":{"observed_at":"2026-08-07T11:16:24.436227Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:26.715599Z","title":"Reddi, Sebastian U","venue":null,"work_id":"c4e4437b-bbfd-404f-9e07-b7650a1e8484","year":null},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.563096Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:2ef5a404e0caa8a5de0ce7e57754b83c006cd9e7e52c4b5913d2f67da4229bb0","observation_id":"27768946-2fd8-41cb-9bd1-b05064344234","resolution":{"observed_at":"2026-08-07T11:16:26.768995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:20.686847Z","title":"The winograd schema challenge","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.686847Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:e356fdb0da05c215414dd6442a769ce678f5751d00b68baf16cbb45c4c8f618d","observation_id":"aa169567-cbe5-40dc-a2cd-f8a852830efd","resolution":{"observed_at":"2026-08-07T11:16:20.686847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.02079","last_updated":"2021-10-28T15:22:21Z","snapshot_observed_at":"2026-08-05T23:24:43.659689Z","submitted_at":"2021-02-03T14:29:09Z","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.02079","snapshot_observed_at":"2026-08-07T11:16:20.795118Z","title":"Federated learning on non-iid data silos: An experimental study, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.795118Z"},"links":{"cited_paper":"/paper/2102.02079","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:6ae48baf16c87eec75de5a08856ee55826ff65eed0e4d313af171be4a6f8b9cb","observation_id":"8d84fb4a-c071-4788-ae19-6cf762a36e35","resolution":{"observed_at":"2026-08-07T11:16:20.795118Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.06127","last_updated":"2020-04-21T18:58:23Z","snapshot_observed_at":"2026-08-06T22:59:35.729012Z","submitted_at":"2018-12-14T19:28:29Z","title":"Federated Optimization in Heterogeneous Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.06127","snapshot_observed_at":"2026-08-07T11:16:20.859882Z","title":"Federated optimization in heterogeneous networks, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.859882Z"},"links":{"cited_paper":"/paper/1812.06127","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:36e967491efe46c3167aaf087e2accc103108f097f3a561e9b1ea5e47bcf9419","observation_id":"1825b4f4-56e6-4597-af4d-ef34599f65a7","resolution":{"observed_at":"2026-08-07T11:16:20.859882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02189","last_updated":"2020-06-25T06:45:52Z","snapshot_observed_at":"2026-08-06T15:26:37.394053Z","submitted_at":"2019-07-04T02:04:56Z","title":"On the Convergence of FedAvg on Non-IID Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02189","snapshot_observed_at":"2026-08-07T11:16:20.939212Z","title":"Ontheconvergence of fedavg on non-iid data, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.939212Z"},"links":{"cited_paper":"/paper/1907.02189","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:efe7dd601bd032ebd423d111bf7b348679ea16911f5bdf5792a2076bc950df00","observation_id":"b5508f8c-5a14-4e94-aed4-369ef51b8e41","resolution":{"observed_at":"2026-08-07T11:16:20.939212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15861","last_updated":"2025-06-02T23:58:41Z","snapshot_observed_at":"2026-07-06T18:19:33.945119Z","submitted_at":"2024-05-24T18:07:05Z","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","version":5},"cited_work":{"arxiv_id":"2405.15861","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.15861","snapshot_observed_at":"2026-08-07T11:16:24.057695Z","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","venue":"cs.LG","work_id":"602c3352-f051-4e03-8334-c38aa617108c","year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.024460Z"},"links":{"cited_paper":"/paper/2405.15861","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:eadefcb928cd0b384760cd9881485f749a6a664b0378e2ecc93fe169881fbdb3","observation_id":"dbba13a1-ff0a-480d-8cde-c5492d8a8492","resolution":{"observed_at":"2026-08-07T11:16:24.165987Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:26.513081Z","title":"On the convergence of zeroth-order federated tuning for large language models","venue":null,"work_id":"0744b445-da8c-4337-96bd-beafb350fa31","year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.110778Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:6386ff138e2f3a0c2dd03f9c83bf0d075ac898d41b0aca03fe8740f06e81e78c","observation_id":"1c471dd2-bf25-425d-aaff-1c277b839ead","resolution":{"observed_at":"2026-08-07T11:16:26.582590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:21.196321Z","title":"Sparse mezo: Less parameters for better performance in zeroth-order llm fine-tuning, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.196321Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:8f4cfb4892d97c83ffb7504842445adb18fce6d8a2fef4b6ceb666d3e4773dac","observation_id":"5cbc0f52-33b6-4d07-bbee-77b2a551c631","resolution":{"observed_at":"2026-08-07T11:16:21.196321Z","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":"2026-08-07T11:16:26.297968Z","title":"Scissorhands: Exploiting the persistence of importance hypothesis for LLM KV cache compression at test time","venue":null,"work_id":"9f615a44-b596-40b5-86f1-fec2f99c4495","year":2023},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.268200Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:b2337de0eb4a62609f7dfdc0802b524aec3e1488be04554b3492bee02d9ac444","observation_id":"1e149a59-7893-45b4-b69b-7ec3d714f960","resolution":{"observed_at":"2026-08-07T11:16:26.429789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:26.076398Z","title":"Deja vu: Contextual sparsity for efficient llms at inference time","venue":null,"work_id":"dcb092a5-3274-41ca-8390-7614f73f56e6","year":2023},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.346669Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:a91cd920d066a6a83760749e69964255e90c7d7ffe7b1de45dee2a1ed99e1ec2","observation_id":"0d8b6117-a07f-47c1-acf9-9ace8c14d5ba","resolution":{"observed_at":"2026-08-07T11:16:26.180492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:25.921695Z","title":"SPP: Sparsity-preserved parameter-efficient fine-tuning for large language models","venue":null,"work_id":"7fb1ec1e-a32c-4db6-96c8-2c7e2190d512","year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.440717Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:a62543f18e9589d76f5e5bfa06fbdcea991c0f07e291df9627ce81726a1da845","observation_id":"3a1e1a05-4941-4126-8c7e-e818c71566b1","resolution":{"observed_at":"2026-08-07T11:16:25.997769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:21.519960Z","title":"Fine-tuning language models with just forward passes.Advances in Neural Information Processing Systems, 36:53038–53075, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.519960Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:9d9016303add45ab4e0579c6c02684340798350b05b3174b7d5c41737f817b7f","observation_id":"21995090-b69d-4105-ac2a-d01798f70c7e","resolution":{"observed_at":"2026-08-07T11:16:21.519960Z","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":"2026-08-07T11:16:25.692087Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":"36f2ad2b-8417-43c1-ad7e-52950aa54fab","year":2017},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.586701Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:d8b60f67dfd34a0725257ba8144a4b2dce523dc1c3d4065cfd0c8b85017839e3","observation_id":"32eb43a7-ea7b-45c6-bba3-c375b973e081","resolution":{"observed_at":"2026-08-07T11:16:25.782947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:21.665441Z","title":"Local learning matters: Rethinking data heterogeneity in federated learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.665441Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:589255cecd0afbd0c2965ccb84e1d542a4f916602137cc84e68fb4f3632beacb","observation_id":"cc09178b-c527-442b-920e-b8d254987796","resolution":{"observed_at":"2026-08-07T11:16:21.665441Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.09121","last_updated":"2019-04-27T09:31:59Z","snapshot_observed_at":"2026-07-06T06:57:46.546190Z","submitted_at":"2018-08-28T05:16:35Z","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.09121","snapshot_observed_at":"2026-08-07T11:16:21.769514Z","title":"Wic: the word-in-context dataset for evaluating context-sensitive meaning representations.arXiv preprint arXiv:1808.09121, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.769514Z"},"links":{"cited_paper":"/paper/1808.09121","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:af85aca65632a317713809863630919f38a324bdce2375f0a4932e527b336aad","observation_id":"dae2ce05-9d3e-4f1f-9580-82bfacc80c1c","resolution":{"observed_at":"2026-08-07T11:16:21.769514Z","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":"2026-08-07T11:16:21.849827Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.849827Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:f3c5c7e11febf056ab43e39004d7227295ad834c1c937279afac46ade6c511f8","observation_id":"7e3bd07f-b15e-4f41-9630-7a3e341fb34a","resolution":{"observed_at":"2026-08-07T11:16:21.849827Z","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":"2026-08-07T11:16:25.467497Z","title":"One-shot sensitivity-aware mixed sparsity pruning for large language models","venue":null,"work_id":"57bd16f8-a962-4948-b160-c156523193b5","year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.914393Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:c3fefe8f8831ed17eff304bb9298f5b75dab3aae5c9a77f5d06fd064067f34b6","observation_id":"9da1562d-6f92-4542-abe6-ecfc80a6e32b","resolution":{"observed_at":"2026-08-07T11:16:25.552043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:25.290543Z","title":"Recursive deep models for semantic compositionality over a senti- ment treebank","venue":null,"work_id":"1744feb1-38a6-4b7d-ba3c-984f242eb222","year":2013},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.988500Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:56969ff2f0ac06f20e3bab12fcd833862e145d5dafd5260f9457c12ae8c2e32c","observation_id":"664f0862-f9b3-4c56-b673-f2c5faba6b9b","resolution":{"observed_at":"2026-08-07T11:16:25.362296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:22.078410Z","title":"In defense of structural sparse adapters for concurrent llm serving","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.078410Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:3e9eb6eb5e38bda82afe0ec8101c25f7b338ec7b0b39dec01e3569322b7cd412","observation_id":"02f30a04-9317-409d-9e59-87d44676bc60","resolution":{"observed_at":"2026-08-07T11:16:22.078410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01467","last_updated":"2023-10-02T16:43:14Z","snapshot_observed_at":"2026-07-06T16:26:42.253705Z","submitted_at":"2023-10-02T16:43:14Z","title":"FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01467","snapshot_observed_at":"2026-08-07T11:16:22.169338Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.169338Z"},"links":{"cited_paper":"/paper/2310.01467","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:f81d5c26f2830e9b60f7514229ad988570f6955c47f1f1382124b65fe3ad95fa","observation_id":"ccf9532c-57d1-427c-9ff6-c6021dbbece6","resolution":{"observed_at":"2026-08-07T11:16:22.169338Z","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":"2026-08-07T11:16:22.271292Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.271292Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:dcaaecea3a4af70fc346f158cc89f7c1efa7d224b55aa12c9621cb9a0aa75dbe","observation_id":"9afa0859-ff63-4820-93bc-12ef388e9583","resolution":{"observed_at":"2026-08-07T11:16:22.271292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.07461","last_updated":"2019-02-22T23:53:34Z","snapshot_observed_at":"2026-07-06T06:34:26.609892Z","submitted_at":"2018-04-20T06:35:04Z","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.07461","snapshot_observed_at":"2026-08-07T11:16:22.350214Z","title":"Glue: A multi-task benchmark and analysis platform for natural language under- standing.arXiv preprint arXiv:1804.07461, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.350214Z"},"links":{"cited_paper":"/paper/1804.07461","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:5a34d8b76da3c2b058da0fadbfd752d181d2b726779e3c7475fa0eeb64487ffc","observation_id":"daa39695-925f-4f07-b280-1fdaa68f274d","resolution":{"observed_at":"2026-08-07T11:16:22.350214Z","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":"2021.31061","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:16:23.714759Z","title":"Vincent Poor","venue":null,"work_id":"cfddf79c-3963-44d1-b17d-643cdb5aefcc","year":2021},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.447638Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:c945786ac1cf39e1d5ea3d00c90bf4426b363678361dd47273c7adeca5776317","observation_id":"29e08bd5-e933-446c-8ceb-080c29de42ed","resolution":{"observed_at":"2026-08-07T11:16:23.790364Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.04732","last_updated":"2021-03-28T19:04:25Z","snapshot_observed_at":"2026-08-06T01:26:31.344805Z","submitted_at":"2019-10-10T17:44:18Z","title":"Structured Pruning of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.04732","snapshot_observed_at":"2026-08-07T11:16:22.539186Z","title":"Structured pruning of large language models","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.539186Z"},"links":{"cited_paper":"/paper/1910.04732","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:b00199ce8b9eb8056f2cc7235dfcd22d92a3d5237ec41f550694e6b09540320d","observation_id":"467e8493-f8ec-4550-b95f-021b981257c9","resolution":{"observed_at":"2026-08-07T11:16:22.539186Z","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":"2026-08-07T11:16:25.064939Z","title":"Soft prompt recovers compressed llms, transferably","venue":null,"work_id":"0c5e1d45-fd21-4ead-9753-7d5a857e31d8","year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.603600Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:c5a421b1b0e622958e79285f3379d5b69bb892b777b5a456d9f90751ea702ce6","observation_id":"53dd072e-406a-482e-b01c-0ee56dd90230","resolution":{"observed_at":"2026-08-07T11:16:25.170043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:24.852515Z","title":"Fedfed: Feature distillation against data heterogeneity in federated learning.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"b1203344-5f33-4002-bc48-ff369b12a750","year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.679380Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:bdab8bf000ebb35a3a3825b50b94333f09bd85296d966ed7cbe724ce045a1336","observation_id":"021ac5b4-a9b4-490a-a173-5d20ad8d3229","resolution":{"observed_at":"2026-08-07T11:16:24.940068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:24.682380Z","title":"Desirable companion for vertical federated learning: New zeroth-order gradient based algorithm","venue":null,"work_id":"acb80825-c238-4a83-9239-0237adfc237c","year":2021},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.779279Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:b0b027d5db7213ab6afee0a93c96d6af51a81f4e958d8d9990d5e4d8b819fe30","observation_id":"4ccf140a-8a0e-4587-bea0-afa0d36b11f1","resolution":{"observed_at":"2026-08-07T11:16:24.744223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:16:22.866923Z","title":"Character-level convolutional networks for text classification.Advances in neural information processing systems, 28, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.866923Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:f51beb5c6e4d0ce752087a72931a926203995ff8adaf10bb6c3c3bc2fee725b2","observation_id":"3937d818-489e-417f-ba42-08ed29534dd3","resolution":{"observed_at":"2026-08-07T11:16:22.866923Z","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":"2026-08-07T11:16:22.962538Z","title":"Lee, Wotao Yin, Mingyi Hong, Zhangyang Wang, Sijia Liu, and Tianlong Chen","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:22.962538Z"},"links":{"citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:e056d8947d8dae306c491b8d897bc0acd0805e836efe6d90d30166f725b94acc","observation_id":"6d1bafca-1759-4089-8835-1a31d9a7976b","resolution":{"observed_at":"2026-08-07T11:16:22.962538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08915","last_updated":"2024-02-26T02:51:30Z","snapshot_observed_at":"2026-07-06T16:32:23.448967Z","submitted_at":"2023-10-13T07:38:52Z","title":"Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08915","snapshot_observed_at":"2026-08-07T11:16:23.075668Z","title":"Dynamic sparse no training: Training-free fine-tuning for sparse llms, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:23.075668Z"},"links":{"cited_paper":"/paper/2310.08915","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:ebaaf1683f432257a46dca8f84fdfa8a83b90ae592a9f069f8ef02f9bffd4da4","observation_id":"4ca45ddc-6dd6-4a4b-aa4d-3f385f7fd442","resolution":{"observed_at":"2026-08-07T11:16:23.075668Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00582","last_updated":"2022-07-21T12:33:15Z","snapshot_observed_at":"2026-07-06T06:42:35.645776Z","submitted_at":"2018-06-02T04:45:58Z","title":"Federated Learning with Non-IID Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00582","snapshot_observed_at":"2026-08-07T11:16:23.173208Z","title":"Federated learning with non-iid data","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:23.173208Z"},"links":{"cited_paper":"/paper/1806.00582","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:2857270ae960002b32b8c4a251cce8c4e8b1a37c1b8f40dc69c9216d46d1b970","observation_id":"fc9dae28-6f94-4597-90eb-0f96c4b79c6a","resolution":{"observed_at":"2026-08-07T11:16:23.173208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06126","last_updated":"2024-12-12T05:28:56Z","snapshot_observed_at":"2026-08-04T09:21:16.695218Z","submitted_at":"2024-02-09T01:18:16Z","title":"Learn To be Efficient: Build Structured Sparsity in Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06126","snapshot_observed_at":"2026-08-07T11:16:23.297275Z","title":"Learn to be efficient: Build structured sparsity in large language models.arXiv preprint arXiv:2402.06126, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:23.297275Z"},"links":{"cited_paper":"/paper/2402.06126","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:e21f0ae7b872f70b795bf3337247c7650204486b5059ee835e768ab3934be757","observation_id":"40562781-a13f-4706-ac95-8103b211d093","resolution":{"observed_at":"2026-08-07T11:16:23.297275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.03856","last_updated":"2024-09-05T18:38:07Z","snapshot_observed_at":"2026-07-06T19:11:14.114279Z","submitted_at":"2024-09-05T18:38:07Z","title":"Sirius: Contextual Sparsity with Correction for Efficient LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.03856","snapshot_observed_at":"2026-08-07T11:16:23.379721Z","title":"sensitive","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:23.379721Z"},"links":{"cited_paper":"/paper/2409.03856","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:dda95968f8f12b5c23ed3419cb2b6924133b0836ff5868adccae222c15059f88","observation_id":"0d4ac30f-5025-4671-8c50-3799667ecd85","resolution":{"observed_at":"2026-08-07T11:16:23.379721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.06378","last_updated":"2021-04-09T16:21:59Z","snapshot_observed_at":"2026-07-06T08:29:27.968839Z","submitted_at":"2019-10-14T18:49:20Z","title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.06378","snapshot_observed_at":"2026-08-07T11:16:20.624757Z","title":null,"venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:20.624757Z"},"links":{"cited_paper":"/paper/1910.06378","citing_paper":"/paper/2506.03337"},"observation_digest":"sha256:cf6423b320a7bbefcbd4d993e907da197028efa32915e038a02c3b3cd4345b92","observation_id":"bd4cba08-1588-458d-8758-3fff890f09d6","resolution":{"observed_at":"2026-08-07T11:16:20.624757Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.03337","last_updated":"2025-06-03T19:29:50Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T11:03:19.477293Z","submitted_at":"2025-06-03T19:29:50Z","title":"Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":28,"verified_exact":2,"verified_fuzzy":13},"total_outbound_references":44},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2506.03337."}