{"as_of":"2026-08-08T14:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c94b6e6a16bf581a85dddcf99ac86a8446c4990cafc8417eedcc82dd415ad87f","coverage":[{"denominator":16,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:43:12.324753Z","state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.16600/citation-record","integrity":"/paper/2506.16600/integrity","json":"/paper/2506.16600/citation-record.json","paper":"/paper/2506.16600"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-06T23:43:10.394745Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:10.394745Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:a98cbecde2c625656cb47bfdb95c4458cfe178a5529ef40b9f4136b03af20de9","observation_id":"0a014456-dca8-4eeb-bca0-e9c72a570349","resolution":{"observed_at":"2026-08-06T23:43:10.394745Z","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":"2026-08-06T23:43:10.484750Z","title":"Fine-tuning large language models for specialized use cases","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:10.484750Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:4649b0e6e9376f63fa0c19c7cd497669683260ea2ea302295c1725a4af014a03","observation_id":"0c2110db-3637-4971-a364-cf210e0d6294","resolution":{"observed_at":"2026-08-06T23:43:10.484750Z","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":"2026-08-06T23:43:10.594752Z","title":"Federated fine-tuning of large language models under heterogeneous tasks and client resources","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:10.594752Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:7504a3617e2ab7031a568311375d422c9a3f1d4d950e9078db8c1aad1a825102","observation_id":"0436d0c6-75af-4b8c-ba50-f0f6885ff3a3","resolution":{"observed_at":"2026-08-06T23:43:10.594752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.10162","last_updated":"2023-05-08T19:50:56Z","snapshot_observed_at":"2026-07-06T13:12:05.091944Z","submitted_at":"2022-05-20T13:10:43Z","title":"FedAdapter: Efficient Federated Learning for Modern NLP","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.10162","snapshot_observed_at":"2026-08-06T23:43:10.734745Z","title":"Fedadapter: Efficient federated learning for modern nlp","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:10.734745Z"},"links":{"cited_paper":"/paper/2205.10162","citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:2b709f33fd083244f35e807b0b269df28d8470f58699a242f79c634da5a914ec","observation_id":"3717be6b-0776-42b3-b5ab-db9df47284fd","resolution":{"observed_at":"2026-08-06T23:43:10.734745Z","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":"2026-08-06T23:43:10.847588Z","title":"A survey on mixture of experts in large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:10.847588Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:a9a54ed28c1b22d6b49509dee14fbadf38860aceef0da02b7c1409f6da931269","observation_id":"3851ab99-5fcd-43c2-ada6-36ef73274420","resolution":{"observed_at":"2026-08-06T23:43:10.847588Z","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":"2026-08-06T23:43:10.974756Z","title":"Improved training of mixture-of-experts language gans","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:10.974756Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:7dc47090984e9926e8a75e783150feb2f9f456d7fb16763b42d9e97ccd5b46fc","observation_id":"9bcdafde-a193-4679-912b-03e61ce98ed1","resolution":{"observed_at":"2026-08-06T23:43:10.974756Z","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":"2026-08-06T23:43:11.035546Z","title":"Federated learning of large language models with parameter-efficient prompt tuning and adaptive optimization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:11.035546Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:cc751eae3c3859b5680dad8ddde2810c29b69cb1d79ef0f4b71c65d6b9513d3b","observation_id":"22c4735f-05a5-492b-bb01-4ae23bb39f5d","resolution":{"observed_at":"2026-08-06T23:43:11.035546Z","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":"2026-08-06T23:43:11.174888Z","title":"Alpagasus: Training a better alpaca with fewer data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:11.174888Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:73af2fefb39fbe755b4c38980259d9b97e7e3ba2aca705606d7e3781b010005b","observation_id":"43fbb149-fcc2-4be3-84fd-0106681701d2","resolution":{"observed_at":"2026-08-06T23:43:11.174888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16160","last_updated":"2024-01-30T15:44:58Z","snapshot_observed_at":"2026-07-06T17:21:51.054477Z","submitted_at":"2024-01-29T13:48:36Z","title":"LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.16160","snapshot_observed_at":"2026-08-06T23:43:11.344752Z","title":"Llava-mole: Sparse mixture of lora experts for mitigating data conflicts in instruction finetuning mllms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:11.344752Z"},"links":{"cited_paper":"/paper/2401.16160","citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:6cf91dc913354aa5f95105de90431858ec8ce71a9d0f020a1d3352c4bc78ddfc","observation_id":"ecc81d5d-252c-4c36-856a-e5fbf090c530","resolution":{"observed_at":"2026-08-06T23:43:11.344752Z","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":"2026-08-06T23:43:11.474749Z","title":"Robust federated finetuning of llms via alternating optimization of lora","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:11.474749Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:ef0b4112ebc30d14f7e4b55335b75973a89cc6082b7bf0090134f888ee32e89f","observation_id":"0cfd8835-fe78-445e-a9e5-be536f650d9a","resolution":{"observed_at":"2026-08-06T23:43:11.474749Z","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":"2026-08-06T23:43:11.597726Z","title":"Heterogeneous LoRA for federated fine-tuning of on-device foundation models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:11.597726Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:6e281d31a66eb7fb10339c3a6eeff7015bf7a6cb30ecaeffb7f66a46bd204fef","observation_id":"aeefbf24-e315-4ee6-b8a4-9f3c50a0bb63","resolution":{"observed_at":"2026-08-06T23:43:11.597726Z","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":"2026-08-06T23:43:11.734757Z","title":"Free dolly: Introducing the world’s first truly open instruction-tuned llm, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:11.734757Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:dd490aeda3f116e3dd928ffc7d73fce60d943f8245f40330019fe19998d9538c","observation_id":"5f869d02-ab42-4021-b1ff-ffe482f0cdb7","resolution":{"observed_at":"2026-08-06T23:43:11.734757Z","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":"2026-08-06T23:43:11.894755Z","title":"Towards next-generation intelligent assistants leveraging llm techniques","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:11.894755Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:f77cc95332e0cddf53ae1497c0897cc45319c408524691f870aa2f972fa7a700","observation_id":"37687138-a24b-4f14-96c9-e67fa9c3b59a","resolution":{"observed_at":"2026-08-06T23:43:11.894755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.19389","last_updated":"2026-05-23T21:24:55Z","snapshot_observed_at":"2026-07-06T20:29:11.710285Z","submitted_at":"2025-01-31T18:44:35Z","title":"Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.19389","snapshot_observed_at":"2026-08-06T23:43:12.006331Z","title":"Federated sketching lora: On-device collaborative fine-tuning of large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:12.006331Z"},"links":{"cited_paper":"/paper/2501.19389","citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:20a26f398722fc8d64aea0ef96162c6fbf0093463553267fa2da2d66abf51cd8","observation_id":"12f15a85-fa72-43ac-b219-05cfc7fea3fc","resolution":{"observed_at":"2026-08-06T23:43:12.006331Z","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":"2026-08-06T23:43:12.138413Z","title":"Pm-moe: Mixture of experts on private model parameters for personalized federated learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:12.138413Z"},"links":{"citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:d1f147cd33f9deb542e6ca5e3ba263fef873abb401aec5eabd53b88f32fe21c1","observation_id":"463c25d6-b11d-4cee-84fe-f9b38f9a3c7d","resolution":{"observed_at":"2026-08-06T23:43:12.138413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16795","last_updated":"2023-10-25T17:24:53Z","snapshot_observed_at":"2026-08-07T00:00:13.606144Z","submitted_at":"2023-10-25T17:24:53Z","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.16795","snapshot_observed_at":"2026-08-06T23:43:12.324753Z","title":"Qmoe: Practical sub-1-bit compression of trillion-parameter models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T23:43:12.324753Z"},"links":{"cited_paper":"/paper/2310.16795","citing_paper":"/paper/2506.16600"},"observation_digest":"sha256:54ac0e1be27cdf6d61bfd2cce548e3b68c214dfc1850ae9add3bea586a996638","observation_id":"58426aa9-67d3-48b5-9f44-d4264f6dac2f","resolution":{"observed_at":"2026-08-06T23:43:12.324753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.16600","last_updated":"2025-07-14T21:49:53Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T00:00:39.120705Z","submitted_at":"2025-06-19T21:02:19Z","title":"FLAME: Towards Federated Fine-Tuning Large Language Models Through Adaptive SMoE"},"reference_resolution":{"displayed":16,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":16},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2506.16600."}