{"as_of":"2026-08-21T12:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:02e144a2310ba88723ea4cfdbe294d14440b2873f1ddf8fd43dfe277dced8e69","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:42:38.782950Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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":"2026-08-02T05:40:34.750724Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.07440","snapshot_observed_at":"2026-08-02T05:40:34.750724Z","title":"Federated in-context learning: Iterative refinement for improved answer quality.arXiv preprint arXiv:2506.07440, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.13285","last_updated":"2026-07-14T21:39:55Z","snapshot_observed_at":"2026-08-14T19:05:46.825427Z","submitted_at":"2026-07-14T21:39:55Z","title":"Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T05:40:34.750724Z"},"links":{"cited_paper":"/paper/2506.07440","citing_paper":"/paper/2607.13285"},"observation_digest":"sha256:cd0f3ad1a1c7ec7d063d3f90df0c220b0e1fa8b26f54eabe9df6bfa40147e332","observation_id":"4aa0a6f1-ded3-4ce3-8e10-e8fba70ae4eb","resolution":{"observed_at":"2026-08-02T05:40:34.750724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.07440/citation-record","integrity":"/paper/2506.07440/integrity","json":"/paper/2506.07440/citation-record.json","paper":"/paper/2506.07440"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","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":"2026-08-07T05:42:38.641400Z","title":"L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.641400Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:8f27d4e0f0828d39ac4d8a5cbfc6927fe9184195d550dd69d4592f17e6d52ff3","observation_id":"f5bc6655-95ec-4399-9376-b6395f1c118d","resolution":{"observed_at":"2026-08-07T05:42:38.641400Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-07T05:42:38.654200Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.654200Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:552ccaf716f923e6cc1679944e3adc9c2170fe19297aa0426f1453f919fac61e","observation_id":"79e994c7-a3c1-4c4b-9b55-8d7d828bb80a","resolution":{"observed_at":"2026-08-07T05:42:38.654200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14325","last_updated":"2023-05-23T17:55:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-23T17:55:11Z","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14325","snapshot_observed_at":"2026-08-07T05:42:38.670653Z","title":"B., and Mor- datch, I","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.670653Z"},"links":{"cited_paper":"/paper/2305.14325","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:7560a473f5e31ca5d5d9b28c98701fd3ec1e746528c7b5943375b73650598ea7","observation_id":"25589031-cf85-4580-9279-061cc003f167","resolution":{"observed_at":"2026-08-07T05:42:38.670653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.10512","last_updated":"2024-11-15T17:11:42Z","snapshot_observed_at":"2026-08-14T20:41:04.637903Z","submitted_at":"2024-11-15T17:11:42Z","title":"On the Privacy Risk of In-context Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.10512","snapshot_observed_at":"2026-08-07T05:42:38.674222Z","title":"On the privacy risk of in-context learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.674222Z"},"links":{"cited_paper":"/paper/2411.10512","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:a76e9c82f7016af926320c284e75d4b3f94a59e0662e8f7b09654c0ccf177404","observation_id":"38570f64-697d-4f14-bb68-506e0dfa2e95","resolution":{"observed_at":"2026-08-07T05:42:38.674222Z","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":"2026-08-13T17:20:44.002518Z","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":"2026-08-07T05:42:38.678492Z","title":"The llama 3 herd of models.arXiv preprint arXiv:2407.21783,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.678492Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:fbaa6793c9b432379446ace5d76059fa2c6864b08354199206c4ed5eec20d2e8","observation_id":"50845e22-a601-4954-b7ae-ef13a6a5b5cd","resolution":{"observed_at":"2026-08-07T05:42:38.678492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10049","last_updated":"2023-10-16T04:17:13Z","snapshot_observed_at":"2026-08-16T14:51:55.351813Z","submitted_at":"2023-10-16T04:17:13Z","title":"FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10049","snapshot_observed_at":"2026-08-07T05:42:38.682227Z","title":"Fate-llm: A industrial grade federated learning framework for large language models.arXiv preprint arXiv:2310.10049,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.682227Z"},"links":{"cited_paper":"/paper/2310.10049","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:5fa69c8e0b9ec618c331590df7512d55b5bcec160d46c6eb19ae4e27864edb0a","observation_id":"31c8631f-bd0b-4a71-8c3e-a5934beca9a7","resolution":{"observed_at":"2026-08-07T05:42:38.682227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17086","last_updated":"2024-11-16T08:20:24Z","snapshot_observed_at":"2026-08-18T20:28:19.527178Z","submitted_at":"2023-10-26T01:08:47Z","title":"Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.17086","snapshot_observed_at":"2026-08-07T05:42:38.685820Z","title":"Transformers learn higher-order optimization methods for in-context learning: A study with linear models.arXiv preprint arXiv:2310.17086,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.685820Z"},"links":{"cited_paper":"/paper/2310.17086","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:90c92f60f63a6750c57139c859ed72e9d2e0524190cf35ae26ef1726c4182ac2","observation_id":"9294d641-9d0f-49ff-96f0-362a3c9ebb28","resolution":{"observed_at":"2026-08-07T05:42:38.685820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06335","last_updated":"2019-09-13T17:26:20Z","snapshot_observed_at":"2026-08-16T05:00:17.345539Z","submitted_at":"2019-09-13T17:26:20Z","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.06335","snapshot_observed_at":"2026-08-07T05:42:38.693232Z","title":"H., Qi, H., and Brown, M","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.693232Z"},"links":{"cited_paper":"/paper/1909.06335","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:1636543ce6664b01c49e8d806dad0924d0e7b45f5028f521cdc1773216d3a327","observation_id":"d824dadb-2a95-461b-bf23-c6228b114bf9","resolution":{"observed_at":"2026-08-07T05:42:38.693232Z","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":"2026-08-20T11:47:17.477107Z","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":"2026-08-07T05:42:38.700333Z","title":"Huang, Y ., Cheng, Y ., and Liang, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.700333Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:d6e337fce5814afa0cf03b576bdfa9f4bd05213e7ac02b729a2effaf0d40d3e9","observation_id":"46b3b904-4548-4d39-abc2-34926757163c","resolution":{"observed_at":"2026-08-07T05:42:38.700333Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.15530","last_updated":"2024-01-28T00:36:44Z","snapshot_observed_at":"2026-08-19T05:30:37.113182Z","submitted_at":"2024-01-28T00:36:44Z","title":"An Information-Theoretic Analysis of In-Context Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.15530","snapshot_observed_at":"2026-08-07T05:42:38.703423Z","title":"J., Lee, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.703423Z"},"links":{"cited_paper":"/paper/2401.15530","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:25d27169d7cf9006aa88eca9b821e04c12bdacb6643dd19ffb83b0a697125d3d","observation_id":"3f57021e-b374-4e2c-8f0b-35a68f237fe2","resolution":{"observed_at":"2026-08-07T05:42:38.703423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-18T18:36:22.935192Z","submitted_at":"2023-06-05T03:32:26Z","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T05:42:38.707387Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.707387Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:70b893f16bb518414daafb5149a6b0b651bc07821de2e4499e4d52da27c3f196","observation_id":"a5d7070e-ea2d-45b0-9f0f-1f8dc7e67019","resolution":{"observed_at":"2026-08-07T05:42:38.707387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01258","last_updated":"2024-06-02T06:31:43Z","snapshot_observed_at":"2026-08-20T15:42:09.979675Z","submitted_at":"2024-02-02T09:29:40Z","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","version":2},"cited_work":{"arxiv_id":"2402.01258","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.01258","snapshot_observed_at":"2026-08-07T05:42:38.977619Z","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","venue":"stat.ML","work_id":"a89c4844-4ef1-4dfd-813e-20a2d860125f","year":2024},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.710826Z"},"links":{"cited_paper":"/paper/2402.01258","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:f211637a264419e338c4dfa28337c1655d289c760a39971b1924d5b5c5578d39","observation_id":"81a63fef-d273-4049-bbc4-1f307019bc24","resolution":{"observed_at":"2026-08-07T05:42:38.981686Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.13461","last_updated":"2019-10-29T18:01:00Z","snapshot_observed_at":"2026-07-06T08:33:12.534026Z","submitted_at":"2019-10-29T18:01:00Z","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.13461","snapshot_observed_at":"2026-08-07T05:42:38.714386Z","title":"Bart: Denoising sequence-to-sequence pre- training for natural language generation, translation, and comprehension.arXiv preprint arXiv:1910.13461,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.714386Z"},"links":{"cited_paper":"/paper/1910.13461","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:58f50b7c836e3f23c046fb36af0e2d16780cc378d69c8dc0cad20912ce4125a5","observation_id":"13372f7c-8688-4d7b-8d4a-9823a5b3bd76","resolution":{"observed_at":"2026-08-07T05:42:38.714386Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.07958","last_updated":"2022-05-08T02:43:02Z","snapshot_observed_at":"2026-08-03T16:26:48.747700Z","submitted_at":"2021-09-08T17:15:27Z","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.07958","snapshot_observed_at":"2026-08-07T05:42:38.718406Z","title":"Truthfulqa: Measuring how models mimic human falsehoods.arXiv preprint arXiv:2109.07958,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.718406Z"},"links":{"cited_paper":"/paper/2109.07958","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:bdab077d7b2be43aac9e354312167aae665b71cb95bcbddb14126a6c5685dbae","observation_id":"fc0d77c3-a524-4bb5-bd59-fac010b6caf6","resolution":{"observed_at":"2026-08-07T05:42:38.718406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.06804","last_updated":"2021-01-17T23:38:40Z","snapshot_observed_at":"2026-08-16T18:51:47.106761Z","submitted_at":"2021-01-17T23:38:40Z","title":"What Makes Good In-Context Examples for GPT-$3$?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.06804","snapshot_observed_at":"2026-08-07T05:42:38.721998Z","title":"What makes good in-context examples for gpt- 3? arXiv preprint arXiv:2101.06804,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.721998Z"},"links":{"cited_paper":"/paper/2101.06804","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:bda473e9b35a34ca0504dc59d95db7600398a656b09b912c118e40cb891db757","observation_id":"a470171f-cece-4e1a-a69c-1cfc6c1bf2de","resolution":{"observed_at":"2026-08-07T05:42:38.721998Z","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":"2026-08-07T05:42:39.168081Z","title":"4o mini: Advancing cost-efficient intelli- gence, 2024.URL: https://openai","venue":null,"work_id":"25610c52-9db4-4078-a65c-0d15507de16f","year":2024},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.725449Z"},"links":{"citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:4483382d31e926b287371b3e8c9654d5bea67a9797797a864f91f72d6bc59cd3","observation_id":"413b9181-4904-4483-a1b7-0666b1aac967","resolution":{"observed_at":"2026-08-07T05:42:39.172546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06123","last_updated":"2023-10-09T19:57:24Z","snapshot_observed_at":"2026-08-20T20:10:05.807488Z","submitted_at":"2023-10-09T19:57:24Z","title":"Text-driven Prompt Generation for Vision-Language Models in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06123","snapshot_observed_at":"2026-08-07T05:42:38.728689Z","title":"K., Ganesh, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.728689Z"},"links":{"cited_paper":"/paper/2310.06123","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:2fd2691667182d84553b0d6885012b25d3a35d8e9c53b23e3f025c7c31a2a970","observation_id":"06b32a4c-4437-438a-9a54-db84f8052717","resolution":{"observed_at":"2026-08-07T05:42:38.728689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10084","last_updated":"2019-08-27T08:50:17Z","snapshot_observed_at":"2026-08-14T05:02:11.716316Z","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10084","snapshot_observed_at":"2026-08-07T05:42:38.732285Z","title":"Sentence-bert: Sentence embeddings using siamese bert-networks.arXiv preprint arXiv:1908.10084,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.732285Z"},"links":{"cited_paper":"/paper/1908.10084","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:dc2efcf7bf8cbfaf365f32d9a3160b166f144191a6a486ae6b907e3d6fda6e34","observation_id":"a84d1513-dc57-4c88-88e2-b1670d6c7871","resolution":{"observed_at":"2026-08-07T05:42:38.732285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.10853","last_updated":"2024-10-14T16:37:29Z","snapshot_observed_at":"2026-08-18T11:12:59.020087Z","submitted_at":"2024-05-17T15:27:52Z","title":"The Future of Large Language Model Pre-training is Federated","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.10853","snapshot_observed_at":"2026-08-07T05:42:38.736432Z","title":"F., Aleksandrov, P., Qiu, X., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.736432Z"},"links":{"cited_paper":"/paper/2405.10853","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:22943f903878e617d21113c1ae325db877d28a2686cac31e4799ff9d4d4f295b","observation_id":"1f314605-7427-41c9-af25-912dc3203d5c","resolution":{"observed_at":"2026-08-07T05:42:38.736432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.04696","last_updated":"2020-05-21T16:53:47Z","snapshot_observed_at":"2026-08-18T19:40:05.706404Z","submitted_at":"2020-04-09T17:26:52Z","title":"BLEURT: Learning Robust Metrics for Text Generation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.04696","snapshot_observed_at":"2026-08-07T05:42:38.740034Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.740034Z"},"links":{"cited_paper":"/paper/2004.04696","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:7b474b9840b511cd73b595c36bd8b590fc409b14783ad4fdb58773f740d88eb5","observation_id":"15cac342-1ad2-4f07-87aa-8ba3e0230c58","resolution":{"observed_at":"2026-08-07T05:42:38.740034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-08-20T18:27:04.837880Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-07T05:42:38.743665Z","title":"M., Hauth, A., Millican, K., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.743665Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:de0be02991dfc54b71e267f8a39f0371b5e537b40b0fcbb861f34bd60f100091","observation_id":"297b2111-33a4-4abc-b683-d64ca366582b","resolution":{"observed_at":"2026-08-07T05:42:38.743665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03953","last_updated":"2024-10-04T22:31:15Z","snapshot_observed_at":"2026-08-18T15:12:40.273243Z","submitted_at":"2024-10-04T22:31:15Z","title":"LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.03953","snapshot_observed_at":"2026-08-07T05:42:38.746830Z","title":"F., Ilhan, F., Huang, T., Hu, S., and Liu, L","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.746830Z"},"links":{"cited_paper":"/paper/2410.03953","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:1620a0e93e252a7a677007ec2de5a0be85f8f9847be61ade234a691d08e885ce","observation_id":"27b31bab-f56f-4d77-a145-824554729d9c","resolution":{"observed_at":"2026-08-07T05:42:38.746830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-07T05:42:38.750325Z","title":"Llama 2: Open foundation and fine- tuned chat models.arXiv preprint arXiv:2307.09288,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.750325Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:8b6a6a5674e4cb47f26718e0846a6555f4e1c6513fc5cac682fbee3afa7e127f","observation_id":"d300cb87-caae-4cb2-bb78-907d9b6ab5cc","resolution":{"observed_at":"2026-08-07T05:42:38.750325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04692","last_updated":"2024-06-07T07:04:10Z","snapshot_observed_at":"2026-08-13T12:11:51.471762Z","submitted_at":"2024-06-07T07:04:10Z","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04692","snapshot_observed_at":"2026-08-07T05:42:38.753851Z","title":"Mixture-of-agents enhances large language model capabilities.arXiv preprint arXiv:2406.04692,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.753851Z"},"links":{"cited_paper":"/paper/2406.04692","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:35a641b2504077af851a569573ad6d98b8541b4585e1c1bfa8bae8e3892e7aef","observation_id":"8c6088b5-51a6-4435-ad9b-9199fb47c91c","resolution":{"observed_at":"2026-08-07T05:42:38.753851Z","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":"2026-08-07T05:42:39.157606Z","title":"Transformers: State-of-the-art natural language processing","venue":null,"work_id":"5fdaa1ef-f333-4d00-9a4e-f4963e989b4e","year":2020},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.757420Z"},"links":{"citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:505730c56dc3011799032350dcec4b68b9a36c2f307dd198e08a675cb1fffbc7","observation_id":"3e8d0b3f-4bbb-4562-8647-52258ec79de6","resolution":{"observed_at":"2026-08-07T05:42:39.161233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.08054","last_updated":"2024-12-11T03:00:24Z","snapshot_observed_at":"2026-08-17T19:47:57.295315Z","submitted_at":"2024-12-11T03:00:24Z","title":"Federated In-Context LLM Agent Learning","version":1},"cited_work":{"arxiv_id":"2412.08054","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.08054","snapshot_observed_at":"2026-08-07T05:42:38.860234Z","title":"Federated In-Context LLM Agent Learning","venue":"cs.LG","work_id":"68695220-2628-4ab5-b2b6-5fd803083064","year":2024},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.760856Z"},"links":{"cited_paper":"/paper/2412.08054","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:0321e6d0f162e4b05974c6fe1423591fa06c67f67bf2e7f8181278e6abf5a1b5","observation_id":"4bc713b8-ab39-4e32-b1a0-ee44190aebc3","resolution":{"observed_at":"2026-08-07T05:42:38.866255Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.02080","last_updated":"2022-07-21T07:44:13Z","snapshot_observed_at":"2026-08-10T22:45:29.185791Z","submitted_at":"2021-11-03T09:12:33Z","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.02080","snapshot_observed_at":"2026-08-07T05:42:38.764691Z","title":"M., Raghunathan, A., Liang, P., and Ma, T","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.764691Z"},"links":{"cited_paper":"/paper/2111.02080","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:721414980b07ca8efe62fb144363a0a8450388498fbc467776ea947d9936b88b","observation_id":"0647accc-120d-4a2b-80ae-436591b35651","resolution":{"observed_at":"2026-08-07T05:42:38.764691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07496","last_updated":"2024-06-11T17:32:21Z","snapshot_observed_at":"2026-08-13T02:15:58.634561Z","submitted_at":"2024-06-11T17:32:21Z","title":"TextGrad: Automatic \"Differentiation\" via Text","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07496","snapshot_observed_at":"2026-08-07T05:42:38.768387Z","title":"Textgrad: Automatic” dif- ferentiation” via text.arXiv preprint arXiv:2406.07496,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.768387Z"},"links":{"cited_paper":"/paper/2406.07496","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:fe53ded1f28dce2789036fec02cd8689607d87bdf45b69cbb7b795ed04c1d6db","observation_id":"99e419c8-f8e4-4618-ad39-29a35cf8c725","resolution":{"observed_at":"2026-08-07T05:42:38.768387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15012","last_updated":"2024-10-08T16:30:11Z","snapshot_observed_at":"2026-08-16T13:50:00.576249Z","submitted_at":"2024-05-23T19:35:03Z","title":"Extracting Prompts by Inverting LLM Outputs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15012","snapshot_observed_at":"2026-08-07T05:42:38.771942Z","title":"X., and Shmatikov, V","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.771942Z"},"links":{"cited_paper":"/paper/2405.15012","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:2ae3683c58b24848c63e05160ac8a76c71447fa9bc4ba8eeb55a3bf9fabf796d","observation_id":"91d52439-3faf-4ea9-a56d-1d0f3c782851","resolution":{"observed_at":"2026-08-07T05:42:38.771942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.14852","last_updated":"2024-04-01T03:51:06Z","snapshot_observed_at":"2026-08-16T16:17:34.586575Z","submitted_at":"2022-12-30T17:59:01Z","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.14852","snapshot_observed_at":"2026-08-07T05:42:38.775781Z","title":"An analysis of attention via the lens of exchangeability and latent variable models.arXiv preprint arXiv:2212.14852,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.775781Z"},"links":{"cited_paper":"/paper/2212.14852","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:81ea02fc646c181e0d9cb3b5bdb9dbb14d6ee6293589910b066f50f0c8b88df3","observation_id":"45937a89-d280-46e5-9f4e-0a22770602bb","resolution":{"observed_at":"2026-08-07T05:42:38.775781Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.06865","last_updated":"2024-08-07T22:05:01Z","snapshot_observed_at":"2026-08-18T18:38:20.525162Z","submitted_at":"2023-07-13T16:15:08Z","title":"Effective Prompt Extraction from Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.06865","snapshot_observed_at":"2026-08-07T05:42:38.779335Z","title":"Effective prompt extraction from language models.arXiv preprint arXiv:2307.06865, 2023b","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.779335Z"},"links":{"cited_paper":"/paper/2307.06865","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:afb829c0cd443ba9fb0d68c950c774adc4ec231d830f3308c6bcd336fe0c4f47","observation_id":"56c55de3-6bd7-488f-9404-b8f277e4f2f1","resolution":{"observed_at":"2026-08-07T05:42:38.779335Z","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":"2026-08-07T05:42:39.147441Z","title":"prompts","venue":null,"work_id":"2177b05d-cfda-49da-a7c5-8bd2f0c084e1","year":2022},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.782950Z"},"links":{"citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:58764e19cd6d377908ea5fd981ee6209a3bd7f28b02bdbf2443e9cff08115e22","observation_id":"4326537b-afec-42d8-8323-40b4b0f54d79","resolution":{"observed_at":"2026-08-07T05:42:39.150864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09783","last_updated":"2024-04-03T23:29:03Z","snapshot_observed_at":"2026-08-21T06:01:46.441373Z","submitted_at":"2023-11-16T11:03:04Z","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09783","snapshot_observed_at":"2026-08-07T05:42:38.666546Z","title":"Investigating data contamination in modern benchmarks for large language models.arXiv preprint arXiv:2311.09783,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.666546Z"},"links":{"cited_paper":"/paper/2311.09783","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:af1754b92673f4f972fc55b367dab711d5c4c4490b503399379380da823698d9","observation_id":"ebacc265-7c29-422e-9e7c-1ed6523700ef","resolution":{"observed_at":"2026-08-07T05:42:38.666546Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.19980","last_updated":"2025-02-27T11:03:24Z","snapshot_observed_at":"2026-08-20T08:38:00.446997Z","submitted_at":"2025-02-27T11:03:24Z","title":"Can Textual Gradient Work in Federated Learning?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.19980","snapshot_observed_at":"2026-08-07T05:42:38.658400Z","title":"Can textual gradient work in federated learning?arXiv preprint arXiv:2502.19980,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.658400Z"},"links":{"cited_paper":"/paper/2502.19980","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:89947ff721b88ccfe76364578c10d67643d473f2f5fbfa78921978e56c5e1c28","observation_id":"65da570e-5ff2-4cda-a79e-25af64ceb459","resolution":{"observed_at":"2026-08-07T05:42:38.658400Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.03300","last_updated":"2021-01-12T18:57:11Z","snapshot_observed_at":"2026-08-13T20:44:28.824685Z","submitted_at":"2020-09-07T17:59:25Z","title":"Measuring Massive Multitask Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.03300","snapshot_observed_at":"2026-08-07T05:42:38.689540Z","title":"Measuring mas- sive multitask language understanding.arXiv preprint arXiv:2009.03300,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.689540Z"},"links":{"cited_paper":"/paper/2009.03300","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:b2af2ca77cab422dd4891f61cead433ce77132bcd22eb19638b09b97fc7c176f","observation_id":"54a1454b-cb31-4fe8-99a1-97acd9b26357","resolution":{"observed_at":"2026-08-07T05:42:38.689540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04571","last_updated":"2025-07-23T01:08:36Z","snapshot_observed_at":"2026-08-16T13:12:08.585627Z","submitted_at":"2024-10-06T18:06:42Z","title":"EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04571","snapshot_observed_at":"2026-08-07T05:42:38.645861Z","title":"Ensemw2s: Can an ensemble of llms be leveraged to obtain a stronger llm?arXiv preprint arXiv:2410.04571,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.645861Z"},"links":{"cited_paper":"/paper/2410.04571","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:db69979bddb109320377afdc6b54e5378fdac8de8691783384097c16caf23892","observation_id":"9fbe78b5-2160-47d0-a62c-25b5479d6bd8","resolution":{"observed_at":"2026-08-07T05:42:38.645861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.15661","last_updated":"2023-05-17T21:08:32Z","snapshot_observed_at":"2026-08-15T11:54:11.033052Z","submitted_at":"2022-11-28T18:59:51Z","title":"What learning algorithm is in-context learning? Investigations with linear models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.15661","snapshot_observed_at":"2026-08-07T05:42:38.650283Z","title":"What learning algorithm is in-context learn- ing? investigations with linear models.arXiv preprint arXiv:2211.15661,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.650283Z"},"links":{"cited_paper":"/paper/2211.15661","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:3c7f9865cddfac4e7cfb1ae1b579c4861232f8738bd02b2cabd94d346e26b904","observation_id":"4b7fd676-4c38-4a70-ac16-4f92ebb0e83f","resolution":{"observed_at":"2026-08-07T05:42:38.650283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.19442","last_updated":"2024-06-10T17:18:07Z","snapshot_observed_at":"2026-08-19T20:57:26.412894Z","submitted_at":"2024-02-29T18:43:52Z","title":"Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.19442","snapshot_observed_at":"2026-08-07T05:42:38.662534Z","title":"Training dynamics of multi-head softmax attention for in-context learning: Emergence, convergence, and optimality.arXiv preprint arXiv:2402.19442,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.662534Z"},"links":{"cited_paper":"/paper/2402.19442","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:5fb1b9861ff4336fcad061eb774949b5b7d02d5ad671ecc05c5d68381f8e4dc5","observation_id":"9de3bf8a-670e-4ffd-8d13-05f02c5f9db0","resolution":{"observed_at":"2026-08-07T05:42:38.662534Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":33,"verified_exact":1,"verified_fuzzy":3},"total_outbound_references":38},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2506.07440."}