{"as_of":"2026-08-13T04:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f3d86b7fadd097d57bcd9bb8efc0491c8cffd34d1e9c36694b7584a615a5a19b","coverage":[{"denominator":119,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T04:46:24.499780Z","state":"measured"},{"denominator":101,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":101,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-08T17:37:51.790000Z","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":"2026-05-11T17:26:04.592292Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"cited_work":{"arxiv_id":"2412.01072","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.01072","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Bissyande, Haoye Tian, and Bach Le","venue":null,"work_id":"e56b038f-8845-49a8-87d8-0523ce2a9e71","year":2024},"citing_paper":{"arxiv_id":"2605.05267","last_updated":"2026-05-06T09:38:31Z","snapshot_observed_at":"2026-08-04T17:41:12.164736Z","submitted_at":"2026-05-06T09:38:31Z","title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-05-08T17:37:51.790000Z"},"links":{"cited_paper":"/paper/2412.01072","citing_paper":"/paper/2605.05267"},"observation_digest":"sha256:313df7e7b472fbbdc833532d6f02b73f035cd85e90ed68ef5321240b9a30b53e","observation_id":"ba77ba7d-22a7-4bd5-8763-5dad6d5774ec","resolution":{"observed_at":"2026-05-11T17:26:04.594444Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.01072/citation-record","integrity":"/paper/2412.01072/integrity","json":"/paper/2412.01072/citation-record.json","paper":"/paper/2412.01072"},"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":"2026-08-12T04:46:23.876705Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.876705Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:af06f0aa7e9ee9bf4baad47c3cbcd835dd0c3db349fc9282d6af7eab07d0be9b","observation_id":"b0304214-d5d8-4304-994c-6b6ad83efa0e","resolution":{"observed_at":"2026-08-12T04:46:23.876705Z","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":"2026-08-12T04:46:23.882793Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.882793Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:d488696a4a50a8f7501cd1d3d96d2ab5d34ffbc7e494b8fdf5bd631281c986c3","observation_id":"d1d5c2bb-1cfc-43c7-bf29-b94bfb76f2a3","resolution":{"observed_at":"2026-08-12T04:46:23.882793Z","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":"2026-08-12T04:46:23.887755Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.887755Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:5eebbb7aede0d5e130adec48f17e787745c7f8a9e6513f36d66d2bb6524826b3","observation_id":"e2b7a493-2981-477f-bfcd-ceab5acd6d56","resolution":{"observed_at":"2026-08-12T04:46:23.887755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07732","last_updated":"2021-08-16T03:57:30Z","snapshot_observed_at":"2026-08-02T19:23:53.535075Z","submitted_at":"2021-08-16T03:57:30Z","title":"Program Synthesis with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07732","snapshot_observed_at":"2026-08-12T04:46:23.892517Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.892517Z"},"links":{"cited_paper":"/paper/2108.07732","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:bd62b72395f5c88c44cff449eb016d276d806700cc5c344fd57918048ae3d1e6","observation_id":"8ea28afd-cc6f-459d-b2ec-19689423a1bb","resolution":{"observed_at":"2026-08-12T04:46:23.892517Z","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":"2026-08-12T04:46:23.897630Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.897630Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:d7fd46017e01d6f12962b047c8b529ea5feadfa3c63955a6e558b3ef79371781","observation_id":"f87e33c8-5d58-49f4-9075-2d00a5285c92","resolution":{"observed_at":"2026-08-12T04:46:23.897630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16609","last_updated":"2023-09-28T17:07:49Z","snapshot_observed_at":"2026-08-09T21:25:20.369782Z","submitted_at":"2023-09-28T17:07:49Z","title":"Qwen Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16609","snapshot_observed_at":"2026-08-12T04:46:23.902649Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.902649Z"},"links":{"cited_paper":"/paper/2309.16609","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:400678e83f0a797167ca29b131b0df535d6ee934f8507a63679e7ca4a096c5f2","observation_id":"c700eb2a-4b12-4be6-8214-6ae0f8676422","resolution":{"observed_at":"2026-08-12T04:46:23.902649Z","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":"2026-08-12T04:46:23.908203Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.908203Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:7e488486560d0fcee2a33c4649196d9a1d62e1de34b9a267484d53eb5d0a4787","observation_id":"c5f9239b-f57e-4391-9b1a-d260e5089cd9","resolution":{"observed_at":"2026-08-12T04:46:23.908203Z","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":"2026-08-12T04:46:23.916610Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.916610Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:7f1e82d5f8d4253fe02d3cb7b358e24b8dba8fed7e250a55d130bdd53700a811","observation_id":"12608904-7dfa-441e-b677-c16f62ea0fb4","resolution":{"observed_at":"2026-08-12T04:46:23.916610Z","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":"2026-08-12T04:46:23.922085Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.922085Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:9d10eb232e296bdead1cb392ae6f89420f64d27cde3034a2ae1225e442a6d834","observation_id":"56fcb1d2-1ae9-48bc-94df-dc40799de861","resolution":{"observed_at":"2026-08-12T04:46:23.922085Z","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":"2026-08-12T04:46:23.928158Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.928158Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:aa5f1e0d7c07ad938d25e10ffd27a112fbf4bd0e611f5e0f9ea245b8985c62ba","observation_id":"bb1ea2a8-d174-4a21-889a-ef4c74b6f5d7","resolution":{"observed_at":"2026-08-12T04:46:23.928158Z","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":"2026-08-12T04:46:23.934913Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.934913Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:a2b87b9eda9e5d549de1787f630e9e502e639a51495f9c9bf5ece057b028431d","observation_id":"1305e2dc-242d-41f3-bd25-c5a593787f69","resolution":{"observed_at":"2026-08-12T04:46:23.934913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.15080","last_updated":"2024-02-11T11:59:52Z","snapshot_observed_at":"2026-08-10T12:41:27.810771Z","submitted_at":"2023-10-23T16:37:59Z","title":"Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.15080","snapshot_observed_at":"2026-08-12T04:46:23.943249Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.943249Z"},"links":{"cited_paper":"/paper/2310.15080","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:c3c1611466cd7e7f484cb93b4e67c59c53b3dc621d66d9757a2cd78f6042576e","observation_id":"f2f428d0-19de-4fd6-9d62-d03fec2a3f1b","resolution":{"observed_at":"2026-08-12T04:46:23.943249Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08925","last_updated":"2024-10-30T03:04:21Z","snapshot_observed_at":"2026-08-11T13:27:21.637180Z","submitted_at":"2023-07-18T02:09:14Z","title":"Integration of Large Language Models and Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08925","snapshot_observed_at":"2026-08-12T04:46:23.949100Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.949100Z"},"links":{"cited_paper":"/paper/2307.08925","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:14154ee3fb1f32b59327e98640c85d96bf8d2d874cfbbe9eedd29e46b6e697ea","observation_id":"4aa4f406-f5ba-4611-a286-8795ff82d864","resolution":{"observed_at":"2026-08-12T04:46:23.949100Z","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":"2026-08-12T04:46:23.955681Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.955681Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:1d831ceb7e288e69ae43ed5c17a0d0665a80709d858cfe29b7ded3ca2b8c5d59","observation_id":"e1ca3d04-1d34-45e4-9446-19cc15b573a3","resolution":{"observed_at":"2026-08-12T04:46:23.955681Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-12T04:46:23.962866Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.962866Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:46d2086aa5645920b717872364630d2ed5dd54850883c0f9c80c1b1d93747de4","observation_id":"48b13d4e-734c-4cb4-bbd8-572feb1c9fe4","resolution":{"observed_at":"2026-08-12T04:46:23.962866Z","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":"2026-08-12T04:46:23.968372Z","title":null,"venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.968372Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:623436ae3432b970c5b5e0e5caae7fa66c875baebf45bf883c38cd9ab7cbfcc2","observation_id":"3d96af16-e9b2-49d4-97ac-a710e92d7a10","resolution":{"observed_at":"2026-08-12T04:46:23.968372Z","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":"2026-08-12T04:46:23.974416Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.974416Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:a9af681abea29e8a9c42fed070dd56ac97740a396bbd0850816eff4d60292939","observation_id":"e0d8dd27-e02a-4a7a-b77e-24edb20cb9e6","resolution":{"observed_at":"2026-08-12T04:46:23.974416Z","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":"2026-08-12T04:46:23.981244Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.981244Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:b7bcf45191007bfa88c7d7e9c8e6daf90b4c504c778120f2bd05d10a4476aabd","observation_id":"2e10eaef-c85c-4deb-a3a5-37c640526832","resolution":{"observed_at":"2026-08-12T04:46:23.981244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.08155","last_updated":"2020-09-18T15:38:12Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-02-19T13:09:07Z","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.08155","snapshot_observed_at":"2026-08-12T04:46:23.986432Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.986432Z"},"links":{"cited_paper":"/paper/2002.08155","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:8d5ff56fd19e0c8cdbc13fa024b8c4caac8a34f064b14db1147495c55492179e","observation_id":"5348783a-5bf4-4d75-9315-d3228329bde6","resolution":{"observed_at":"2026-08-12T04:46:23.986432Z","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":"2026-08-12T04:46:23.991529Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.991529Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:adba888039696b8ad047d14e848cd0f231bc2d3eaad990de75806571c17e7a8e","observation_id":"5fadabe6-944f-4bbe-9e48-f26d20fd778b","resolution":{"observed_at":"2026-08-12T04:46:23.991529Z","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":"2026-08-12T04:46:23.996531Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:23.996531Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:f19b1eaeece5c16bf1f40e02961c99f3da26dbb5a98707907597b30c9156b01f","observation_id":"967c2698-ccb0-4c6b-89ad-4bdd22bc24e7","resolution":{"observed_at":"2026-08-12T04:46:23.996531Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-12T04:46:24.002309Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.002309Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:f34191dcb7cb0bb3cc8925060167cfacf9ffe58b3f9f6205fa3ca15d493d04f3","observation_id":"02591e05-b4a3-4c4a-ae41-101b80233b3b","resolution":{"observed_at":"2026-08-12T04:46:24.002309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14196","last_updated":"2024-01-26T09:23:11Z","snapshot_observed_at":"2026-08-06T22:40:28.707813Z","submitted_at":"2024-01-25T14:17:53Z","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14196","snapshot_observed_at":"2026-08-12T04:46:24.008377Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.008377Z"},"links":{"cited_paper":"/paper/2401.14196","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:607be202debd9b0401e446552e3ac2ba487bab3a69191e6962b4df6c62cd9d23","observation_id":"021ef58f-4951-4615-af47-f83d540aa311","resolution":{"observed_at":"2026-08-12T04:46:24.008377Z","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":"2026-08-12T04:46:24.014392Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.014392Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:6efda73acc000c92acfdeb933a8c46a4ed0a9cd16c4fd956b9e6a11468f3e129","observation_id":"f12b1b1b-314b-4030-8c75-206a5bebb576","resolution":{"observed_at":"2026-08-12T04:46:24.014392Z","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":"2026-08-12T04:46:24.022307Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.022307Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:619b4f4dd855fca1efbcd1fac87fd1b815ff653b2b6b971619a684eaef8ba3b3","observation_id":"b7f4e968-ad10-42f8-8d4a-cd3334630858","resolution":{"observed_at":"2026-08-12T04:46:24.022307Z","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":"2026-08-12T04:46:24.028152Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.028152Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:c8b957b2b4d17ca6f6d6f1288b9336f28ebd62d1d907ea74c5a20caa09fe659f","observation_id":"e6ad137f-16dd-4ef6-ad33-90c2b848a0ba","resolution":{"observed_at":"2026-08-12T04:46:24.028152Z","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":"2026-08-12T04:46:24.042264Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.042264Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:e963daf07c112536d33788ac0dd1869503681ff2ee47a8617b96a33df872a95e","observation_id":"8da0d974-bd5c-4de2-ab5d-965ec7e3e916","resolution":{"observed_at":"2026-08-12T04:46:24.042264Z","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":"2026-08-12T04:46:24.048771Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.048771Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:81e73a7c77f9f296f7e6acdc595b190c91940cf1119791cbca11b9f2e8295327","observation_id":"5c4ef182-25f6-4494-9ba8-04f8a72dd905","resolution":{"observed_at":"2026-08-12T04:46:24.048771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-12T04:46:24.053816Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.053816Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:007e68fd043b4aabb74f85669db59db8f1edbffc557c91fe4996e6d83efdc6b4","observation_id":"86a6f00e-d824-4870-9d30-f71d6f0c4b2b","resolution":{"observed_at":"2026-08-12T04:46:24.053816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13896","last_updated":"2023-07-26T01:44:02Z","snapshot_observed_at":"2026-08-10T11:31:44.866211Z","submitted_at":"2023-07-26T01:44:02Z","title":"Low-Parameter Federated Learning with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13896","snapshot_observed_at":"2026-08-12T04:46:24.059805Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.059805Z"},"links":{"cited_paper":"/paper/2307.13896","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:a2a7828ffdfcc61c9d47a1376c32247764c28fdb1595def48d57f2cb1f3fb259","observation_id":"b5a42924-bba5-42f9-9905-8263329c9160","resolution":{"observed_at":"2026-08-12T04:46:24.059805Z","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":"2026-08-12T04:46:24.065778Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.065778Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:68293f1d8f9bb6de07b6058a5aaba268bec2c5552bbe12aad4af40339065b7b4","observation_id":"b0283ca3-8c0c-4162-8d4e-4a698195b47c","resolution":{"observed_at":"2026-08-12T04:46:24.065778Z","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":"2026-08-12T04:46:24.071476Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.071476Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:8486ed614589b853048482be1a96d9f0b05592522d9c5abc94b9c29cb5c9f20e","observation_id":"2140768c-db8a-484a-8e63-5a737ebf6507","resolution":{"observed_at":"2026-08-12T04:46:24.071476Z","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":"2026-08-12T04:46:24.079268Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.079268Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:7345c9850bc33cd2d00f2b92fa1626bad86ecb2a5551854b8e28afe8d2980557","observation_id":"ac97e858-4c6d-4c35-bdc1-da927146852a","resolution":{"observed_at":"2026-08-12T04:46:24.079268Z","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":"2026-08-12T04:46:24.084718Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.084718Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:aa903f903ed1d2835b8da50b2eb779c1203254568ccf5be41e1146446602c570","observation_id":"17482709-12a4-4e35-a26c-13c349748cbb","resolution":{"observed_at":"2026-08-12T04:46:24.084718Z","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":"2026-08-12T04:46:24.091894Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.091894Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:791b6ff396ef86732ab203be27f7666edc19cd6a26a964ad458f8594117f235c","observation_id":"5afea110-05e6-4b25-bb08-8cc25d963cbd","resolution":{"observed_at":"2026-08-12T04:46:24.091894Z","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":"2026-08-12T04:46:24.098707Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.098707Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:018c4f124ead2d83579d4af4d31f7e4093b0367c0e6a0ca0eedbb6b66a3b916f","observation_id":"b62d5132-f33b-41dd-ab4c-7ac568358762","resolution":{"observed_at":"2026-08-12T04:46:24.098707Z","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":"2026-08-12T04:46:24.103823Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.103823Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:f509ca05cbfce1b10153b97716e8c7cb0377c73f669271c0f6e658ea96835fe2","observation_id":"862a21f6-e091-49cd-b38a-0f1ab4c88809","resolution":{"observed_at":"2026-08-12T04:46:24.103823Z","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":"2026-08-12T04:46:24.112117Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.112117Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:7a6d6d76c7e275a8ee71c637b98b405950a110bf093e33acebb8f659ff917bf5","observation_id":"843c1c73-0646-46c4-85f3-5f295fc03f97","resolution":{"observed_at":"2026-08-12T04:46:24.112117Z","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":"2026-08-12T04:46:24.121043Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.121043Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:6633ceb8ef24b72a0117213c0f961f546a77081f0021fcb6795ab871fc799430","observation_id":"8990aa0f-5fe7-48b3-97c2-5178b2e9ce04","resolution":{"observed_at":"2026-08-12T04:46:24.121043Z","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":"2026-08-12T04:46:24.131336Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.131336Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:a276036412e831ae9c28d90a78006d473c85a26edc5cfbbc1f3248bb0b295e66","observation_id":"816abf3d-152a-42ee-8ac1-b620a4eefbcc","resolution":{"observed_at":"2026-08-12T04:46:24.131336Z","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":"2026-08-12T04:46:24.138551Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.138551Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:d4c9b848aefbb48a10d8225d657e364c0ee02517fb38236ecf89b1d6059f0b1f","observation_id":"00516440-3334-48f7-a835-367768676fab","resolution":{"observed_at":"2026-08-12T04:46:24.138551Z","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":"2026-08-12T04:46:24.145859Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.145859Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:cea7bf11c0abecee782aabd5b03d2af9f149ac555803908dc61fa3476a993485","observation_id":"99ee6794-a35d-4324-8c8f-958aa1982329","resolution":{"observed_at":"2026-08-12T04:46:24.145859Z","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":"2026-08-12T04:46:24.151493Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.151493Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:c75712a98340af575dad1c8c85f070af7371806aa22a5eaca0e13067f79be044","observation_id":"20ba5d17-e251-478c-8a22-f17da63e154a","resolution":{"observed_at":"2026-08-12T04:46:24.151493Z","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":"2026-08-12T04:46:24.157436Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.157436Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:0c4246f09680e5ce42fcf4b15e4df89f5dd60a39a9e8620616bebd1d73633c45","observation_id":"b3697113-dc46-4809-a0e9-cc4502585c4a","resolution":{"observed_at":"2026-08-12T04:46:24.157436Z","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":"2026-08-12T04:46:24.165289Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.165289Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:c54775d3b93b3316fe8c4d805eed9bcf2dd4aaed02079356ab055a42e9d08b70","observation_id":"3db4ffbb-3fcc-4c3b-b002-62d381fd7394","resolution":{"observed_at":"2026-08-12T04:46:24.165289Z","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":"2026-08-12T04:46:24.171071Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.171071Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:c548f44bcffc8795dfdfc872fba2d4e0def8545c316dc787e52067f971e6c451","observation_id":"70bc763c-0cc8-4183-aec1-4523ba30a398","resolution":{"observed_at":"2026-08-12T04:46:24.171071Z","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":"2026-08-12T04:46:24.176726Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.176726Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:c0f5ee9f8257081b226ab9546ec686db1ccc3458a7bd76d9b7cda22503458a12","observation_id":"179b437d-1c43-43d0-b266-e009b79f8aec","resolution":{"observed_at":"2026-08-12T04:46:24.176726Z","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":"2026-08-12T04:46:24.182653Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.182653Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:747fcfee52d92ab14d6b02137385c4a952b914443913308818333077ba89cb5f","observation_id":"747d871a-a1ab-4711-b23c-817548ad71a9","resolution":{"observed_at":"2026-08-12T04:46:24.182653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.07623","last_updated":"2021-05-11T14:21:00Z","snapshot_observed_at":"2026-08-09T15:59:31.104495Z","submitted_at":"2021-02-15T16:04:10Z","title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.07623","snapshot_observed_at":"2026-08-12T04:46:24.188267Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.188267Z"},"links":{"cited_paper":"/paper/2102.07623","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:925018f9648f6260222899e25cc09f79c4a5fa60f138e996bf26dd496ee153bb","observation_id":"4a3356ea-79ac-4d93-8947-73466256f858","resolution":{"observed_at":"2026-08-12T04:46:24.188267Z","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":"2026-08-12T04:46:24.194886Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.194886Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:886529c7a8e73a901369b77bc7b0630f5ed4bb93cc76a45c2d3f32ae9b55b80d","observation_id":"09509d57-81b9-4148-a6f8-58c97a6cc74a","resolution":{"observed_at":"2026-08-12T04:46:24.194886Z","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":"2026-08-12T04:46:24.200603Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.200603Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:b92e73ac378ecedfbe55b3d5c26a1305a88c830756f3b7b67fd2cd10c8709fe3","observation_id":"a6786459-7960-49f6-b9c0-6b08bee8a155","resolution":{"observed_at":"2026-08-12T04:46:24.200603Z","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":"2026-08-12T04:46:26.280083Z","title":null,"venue":null,"work_id":"857c7e19-1b8d-45c6-b1cc-926d4fcb0bf0","year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.206773Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:41427aead6e1ac58d7a89bbf00515260d211e271288af85b71ce6862c61acdcc","observation_id":"18de59eb-6427-486a-916b-c5365aafca3e","resolution":{"observed_at":"2026-08-12T04:46:26.285720Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:26.260858Z","title":null,"venue":null,"work_id":"0110da85-ecaf-47ee-b523-6e009546d3b3","year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.213247Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:03515bae701cf0593f43bc4e2e6007f5f542435d04932b84655fb569eaac3aa8","observation_id":"a2672ed8-8451-47e6-a009-78affcc87ee9","resolution":{"observed_at":"2026-08-12T04:46:26.266095Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08815","last_updated":"2022-05-06T10:05:52Z","snapshot_observed_at":"2026-07-06T11:01:05.577957Z","submitted_at":"2021-04-18T11:04:49Z","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08815","snapshot_observed_at":"2026-08-12T04:46:24.222010Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.222010Z"},"links":{"cited_paper":"/paper/2104.08815","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:77ef11adf6516c4705ef804ddcc453c2a887fcd012eca7bdef7dbe3812a477ef","observation_id":"933be542-28eb-4151-83f9-bf31bf53ef1d","resolution":{"observed_at":"2026-08-12T04:46:24.222010Z","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":"2026-08-12T04:46:24.229726Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.229726Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:debe86a3a7a08f45a825f6f6cb86c1b48ca45954edd76f4f83e7f41b2d570d6b","observation_id":"ff03874e-1d04-4617-b4a3-7a00b1ab10a3","resolution":{"observed_at":"2026-08-12T04:46:24.229726Z","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":"2026-08-12T04:46:26.233645Z","title":null,"venue":null,"work_id":"8588a50b-e065-42cf-9451-9a50bb7e4710","year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.236257Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:3e32148a6f21d49fa2ccc9fe06c30689b2b2f4ead1a6d8a0ca31d9cbf153e924","observation_id":"7b3bb740-6523-4ffc-a19f-127916458c5d","resolution":{"observed_at":"2026-08-12T04:46:26.239134Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-12T04:46:24.241529Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.241529Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:bac470638dcba4724196cd88cc8d6df1324b77ecce2ccc48442e8e657af1f613","observation_id":"6ac4396c-a262-48a3-ad7c-cd08421bac73","resolution":{"observed_at":"2026-08-12T04:46:24.241529Z","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":"2026-08-12T04:46:24.250292Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.250292Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:cd7606572f7f3f83342ae9114a4d1f32a6dd56580ebb14e2c04003cd08913f9b","observation_id":"a359b759-b69e-44e7-9705-df935b64179e","resolution":{"observed_at":"2026-08-12T04:46:24.250292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08568","last_updated":"2025-05-27T07:40:36Z","snapshot_observed_at":"2026-08-04T15:08:40.203853Z","submitted_at":"2023-06-14T15:18:48Z","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08568","snapshot_observed_at":"2026-08-12T04:46:24.255758Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.255758Z"},"links":{"cited_paper":"/paper/2306.08568","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:ae008b5170b483636e15415603205ebbff3300f71e930eb115823bccadc57447","observation_id":"3f916895-0546-4384-bf60-3c24fa51705d","resolution":{"observed_at":"2026-08-12T04:46:24.255758Z","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":"2026-08-12T04:46:26.204133Z","title":null,"venue":null,"work_id":"54227540-1a9a-4d0b-b3be-495ff4e6f7c6","year":2020},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.261111Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:3fadd8b2e2a4fe33bc851e14c1f075c40068424f2603c2640acabf76d618417d","observation_id":"b1c2d8e2-8334-426d-8257-fe65d723f0bd","resolution":{"observed_at":"2026-08-12T04:46:26.209543Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:26.186403Z","title":null,"venue":null,"work_id":"156ee0c7-6626-4335-9e87-75ff989a875d","year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.266587Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:b56f0fc253de511b1e6cacbe1932674d53d79ef693aa6e18fe67fd55e7d801c1","observation_id":"607132d9-43b7-4b06-b5e3-b9574f1e6689","resolution":{"observed_at":"2026-08-12T04:46:26.191750Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:26.169766Z","title":null,"venue":null,"work_id":"7ffa4c37-71d8-4e9d-9709-da1d8e010154","year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.272908Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:21e51d1399ed5c8249cbe3181ce7064294311680a98f3a4e4e72f1b602afe440","observation_id":"02435cff-1216-40c3-a131-1f9b28b059cc","resolution":{"observed_at":"2026-08-12T04:46:26.174800Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:24.279397Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.279397Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:7cc770cbf962e46423523503539b6f473973471f0795f9f99598e9b6c3e9639a","observation_id":"d03faed9-8d21-4481-9b5e-f2531acdef97","resolution":{"observed_at":"2026-08-12T04:46:24.279397Z","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":"2026-08-12T04:46:26.140687Z","title":null,"venue":null,"work_id":"f9c38e8a-d48c-4a14-b988-f90812d14e2c","year":2000},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.285410Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:188eeda91d494d6f4aa366ed6842b354034f922693c6de2f91599728c7f447c8","observation_id":"26a6bc95-9724-43e4-a886-f211c83ce8a7","resolution":{"observed_at":"2026-08-12T04:46:26.146076Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:26.121195Z","title":null,"venue":null,"work_id":"a1bcef19-cc20-4411-a859-437c346112ad","year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.290759Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:9bf161b745657a8142f9a019b7eb0bd0b628ace6143e7a6c5f2e26d5938bef95","observation_id":"2f010a98-456c-4e3a-aa63-d7cc960cf6dc","resolution":{"observed_at":"2026-08-12T04:46:26.126410Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:26.103405Z","title":null,"venue":null,"work_id":"3b3b38c2-fe4a-42b8-a77a-ac0f0715692a","year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.296271Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:94738b5c2ca62b2f27d92a891115509acd03af6d34d69aebe62dd377099c9cb6","observation_id":"ce375aa1-12c4-41c5-b758-81ff0ec9a4cd","resolution":{"observed_at":"2026-08-12T04:46:26.109011Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07840","last_updated":"2023-07-21T20:56:41Z","snapshot_observed_at":"2026-08-05T14:58:00.577616Z","submitted_at":"2023-04-16T17:29:51Z","title":"Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07840","snapshot_observed_at":"2026-08-12T04:46:24.302775Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.302775Z"},"links":{"cited_paper":"/paper/2304.07840","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:9276e28c1b7c13953fcc0c8c27664292a8ca2d4a40e99d671a0c7a37534b6cb8","observation_id":"48e561f3-a926-441e-8e2a-8ed320739e42","resolution":{"observed_at":"2026-08-12T04:46:24.302775Z","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":"2026-08-12T04:46:24.308602Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.308602Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:997f10d59dbb9ea97f3d1b9f97f4a5e3fe639560c6c7832a238ad21db02b020e","observation_id":"99a4d946-7999-4ca5-bb25-6ab61a2d8475","resolution":{"observed_at":"2026-08-12T04:46:24.308602Z","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":"2026-08-12T04:46:26.075056Z","title":null,"venue":null,"work_id":"504055f2-a1a0-4498-8c30-2979e36d917a","year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.315181Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:4f344b5f054be9e58f02940b154b4d5ef4a5df99f018b11aea3caa2cf1f95feb","observation_id":"f8fdc496-a600-4baa-ac84-1980cf35c2d6","resolution":{"observed_at":"2026-08-12T04:46:26.080974Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:26.055545Z","title":"Reddi, Zachary Charles, Manzil Zaheer, Zachary Garrett, Keith Rush, Jakub Konečný, Sanjiv Kumar, and Hugh Brendan McMahan","venue":null,"work_id":"265a547f-902f-4063-976b-8ae50a1a1c7d","year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.320147Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:2c33951f0391aad592d427d3f9fb4c06e46950d58c9b6d1ae63f6eeeb0bcd7fd","observation_id":"c7c45516-6d98-4ebf-afcb-9201cf7bf903","resolution":{"observed_at":"2026-08-12T04:46:26.061769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:26.035943Z","title":null,"venue":null,"work_id":"78b067b5-f5c6-46b7-a2f1-2f725f582860","year":2019},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.326773Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:b72c89b07d8eea84accfe8abe4be6261f6193a9445625334a1ab62393e0b5a86","observation_id":"3670dbc3-5bf5-4e68-aa90-e9082430539b","resolution":{"observed_at":"2026-08-12T04:46:26.042891Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12950","last_updated":"2024-01-31T19:47:26Z","snapshot_observed_at":"2026-07-06T16:10:07.931347Z","submitted_at":"2023-08-24T17:39:13Z","title":"Code Llama: Open Foundation Models for Code","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12950","snapshot_observed_at":"2026-08-12T04:46:24.332029Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.332029Z"},"links":{"cited_paper":"/paper/2308.12950","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:91dd2d52cd7c186df408abe52329c7d7e6ff22b65c0cdeadf2047849bed5f460","observation_id":"dac24738-44ca-40ff-aa02-0dedbaff6e79","resolution":{"observed_at":"2026-08-12T04:46:24.332029Z","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":"2026-08-12T04:46:24.337136Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.337136Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:1e468434ff215ec8d79af9525069d3f7d6893d7bcd94d2afaea74889097f2442","observation_id":"74af7687-e175-44ef-bdbe-8bfcbf0815f4","resolution":{"observed_at":"2026-08-12T04:46:24.337136Z","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":"2026-08-12T04:46:24.341833Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.341833Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:deca346526453d148e8e45e6e417168edecc4b003bca2f0e0e13442874f0b78e","observation_id":"ade39b8a-6fe0-469f-8e6c-aab58a07b71c","resolution":{"observed_at":"2026-08-12T04:46:24.341833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.15698","last_updated":"2025-09-03T01:34:48Z","snapshot_observed_at":"2026-08-10T13:10:47.015768Z","submitted_at":"2023-12-25T11:39:46Z","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.15698","snapshot_observed_at":"2026-08-12T04:46:24.346643Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.346643Z"},"links":{"cited_paper":"/paper/2312.15698","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:1c2c3840c26d32c94f127dfe0b460a0d8098de326c2eccfc4a3754dd51b271df","observation_id":"1df4a806-77d5-42d4-bfb8-bb28c32adad0","resolution":{"observed_at":"2026-08-12T04:46:24.346643Z","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":"2026-08-11T21:12:03.445934Z","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":"2026-08-12T04:46:24.351899Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.351899Z"},"links":{"cited_paper":"/paper/2310.01467","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:9b83927b7a4de4a9b78db31f38dc87d76c740b64d1fa39da49762fed551ce4a5","observation_id":"d9bbc918-1a20-443f-9ea3-487616ec0399","resolution":{"observed_at":"2026-08-12T04:46:24.351899Z","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":"2026-08-12T04:46:25.993844Z","title":null,"venue":null,"work_id":"9329253d-cdb5-4faf-8b48-15d8ec787278","year":2020},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.357286Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:f453b00c3b20cabfe0683c612fe2949b672cce3fe66297690f403843f86597bb","observation_id":"ad952edb-c7ec-426c-93ed-10696d565e3c","resolution":{"observed_at":"2026-08-12T04:46:25.998882Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:25.975846Z","title":null,"venue":null,"work_id":"08d1dcf0-9a56-44b6-9cc2-752e11aa26c0","year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.362873Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:69afb9a26d11a31d935ebbcd30ee4c69dfe7c766112a542fd06c95df16664b49","observation_id":"64b6875b-1736-4711-b723-3cf52f3749e3","resolution":{"observed_at":"2026-08-12T04:46:25.981965Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.13044","last_updated":"2022-05-01T08:19:28Z","snapshot_observed_at":"2026-07-06T11:22:32.341852Z","submitted_at":"2021-06-24T14:17:00Z","title":"Personalized Federated Learning with Contextualized Generalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.13044","snapshot_observed_at":"2026-08-12T04:46:24.368800Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.368800Z"},"links":{"cited_paper":"/paper/2106.13044","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:0cd045d203c1faf6c3e8ef77251e7c84a3427c636fa12bb9d2769671bcf712fd","observation_id":"4b017b53-8b80-43bf-b168-0dd8a61662ed","resolution":{"observed_at":"2026-08-12T04:46:24.368800Z","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":"2026-08-12T04:46:24.374641Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.374641Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:00b55c28be7535dfc46f35ebf95789d00956566d6fa08e99684cc7620c7976d0","observation_id":"06d5fd69-e218-4a61-a07a-8c57f73d80f1","resolution":{"observed_at":"2026-08-12T04:46:24.374641Z","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":"2026-08-12T04:46:25.945947Z","title":null,"venue":null,"work_id":"76a997cb-c43a-4007-8bfb-95c60b5c3de0","year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.380893Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:0f0498ec5ba6cbc7996776926032c780f7c7febefafb0a026f7d3f6140b438d0","observation_id":"be3e8f5b-edcb-4ea5-a196-5650ad71d722","resolution":{"observed_at":"2026-08-12T04:46:25.950989Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-12T04:46:24.386650Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.386650Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:24e22c3d9fb68fa4b27674cfbcd40889eed920c1f466156b4921b1628622d908","observation_id":"a3aa23a6-d97d-47db-9ab3-6710128590a6","resolution":{"observed_at":"2026-08-12T04:46:24.386650Z","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":"2026-08-12T04:46:25.924215Z","title":null,"venue":null,"work_id":"9ed72f64-c2a3-41f1-863a-1629132a47e2","year":2019},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.391923Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:a8e6d1af51d9c9377175d9039648ef31b5b59a689fa71c750c1d7e931ff6e630","observation_id":"23fe050e-c4b7-403f-8f4a-4db50113763d","resolution":{"observed_at":"2026-08-12T04:46:25.929495Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:25.907394Z","title":null,"venue":null,"work_id":"9c24a199-a86d-4f1c-8e24-42ca08de64c7","year":2024},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.397986Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:e82182024b00d8c9007630f3173614a41b31e0f07ae880392da1a30d33b7968b","observation_id":"0c5d077c-744d-44db-b26d-5b5029a9a661","resolution":{"observed_at":"2026-08-12T04:46:25.912731Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12132","last_updated":"2024-04-12T21:01:12Z","snapshot_observed_at":"2026-08-09T16:50:43.749067Z","submitted_at":"2023-05-20T07:55:58Z","title":"Can Public Large Language Models Help Private Cross-device Federated Learning?","version":2},"cited_work":{"arxiv_id":"2305.12132","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.12132","snapshot_observed_at":"2026-08-12T04:46:25.027069Z","title":"Can Public Large Language Models Help Private Cross-device Federated Learning?","venue":"cs.LG","work_id":"07fb2a74-deda-435f-bd20-85fbcab79cc2","year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.403345Z"},"links":{"cited_paper":"/paper/2305.12132","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:c3ba84e773c3ec3e43797e92a9a4111f3204b41dded3959fe5e0cd55bef98317","observation_id":"ac16d328-48f3-4a5a-881d-52d925945202","resolution":{"observed_at":"2026-08-12T04:46:25.035252Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:25.884372Z","title":null,"venue":null,"work_id":"b148eebf-709f-4299-b40b-ea7516cc34fb","year":2020},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.408916Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:da01e39c65ee25f2bdb1b685f35e07d53ea23802ee38946399305ebecb230aa4","observation_id":"153a0b6a-c99c-4b40-bc16-afa606362499","resolution":{"observed_at":"2026-08-12T04:46:25.893601Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:24.416676Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.416676Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:f264f097be25652b6df9e305622ba3748e4a4e3db094a04c6705c391d15c3d43","observation_id":"11736988-78d2-4bc4-8411-42a1e78fd1b5","resolution":{"observed_at":"2026-08-12T04:46:24.416676Z","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":"2026-08-12T04:46:25.849527Z","title":null,"venue":null,"work_id":"4fd7bf5b-38b4-453c-b6b0-02a406586e6c","year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.422277Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:4189a44e3b625e39e39e2433423d3026874867d01ee76dd2436db1e738babd6b","observation_id":"fd395317-b771-40c0-a6b0-a21dd4d31654","resolution":{"observed_at":"2026-08-12T04:46:25.855865Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:25.829443Z","title":null,"venue":null,"work_id":"c4f35175-41df-4ee6-a592-589c91b3a878","year":2007},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.427655Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:412390f26249e9c0e21fa0b99fd1c5c3372e3350519aba7f6558c78b07c2d194","observation_id":"1e3e62f6-3631-4009-9630-930c30e5ee93","resolution":{"observed_at":"2026-08-12T04:46:25.836506Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:25.811386Z","title":null,"venue":null,"work_id":"48a2b7ee-0bd8-4668-a4e8-2714baa277a0","year":2019},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.433110Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:23b7aa36dcf07cc14b4240fd118ff624a6b7d8fc3dd72274be7b6fe9e23f7426","observation_id":"5a6b302d-adea-45d9-8bc6-3ab468dcedd5","resolution":{"observed_at":"2026-08-12T04:46:25.816792Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:25.793173Z","title":null,"venue":null,"work_id":"2116f066-3b9f-4699-8f22-31661c49145f","year":1992},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.438443Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:404fadea755a351775a61f2c9778a0eaedd27789a2fc320c6e6d71012b17c0af","observation_id":"2dff79ff-a16a-423d-9c70-6f1677ddbad8","resolution":{"observed_at":"2026-08-12T04:46:25.798585Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:25.775106Z","title":null,"venue":null,"work_id":"fb2d7feb-97f1-408d-8baa-109011d3f5c3","year":2024},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.444063Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:db60fa327df7b6fc1a6f4cb120f661715c9d8c7f89b558acb8ecf861140ec7ea","observation_id":"f207eefb-839a-49a1-b5c9-6c99f7917219","resolution":{"observed_at":"2026-08-12T04:46:25.780405Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:25.757776Z","title":null,"venue":null,"work_id":"180ba84c-9e36-4341-bc42-5f820f3988e7","year":2024},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.450322Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:658a821a5f97d165564623c1214926ee5f492ad54836fdb714b01ac5a6359638","observation_id":"4e3dbda9-8134-440c-abe3-932819e9d8f5","resolution":{"observed_at":"2026-08-12T04:46:25.763612Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:25.741321Z","title":null,"venue":null,"work_id":"66d1f98a-da1d-46a3-a15f-27e39425dafe","year":null},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.456023Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:df62ff0666d1c4100cb221ec5286f62711191c18712bd42d310f75739b484176","observation_id":"81878c23-b3b9-4d58-922e-ca00e240df6f","resolution":{"observed_at":"2026-08-12T04:46:25.746743Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.14179","last_updated":"2024-12-09T20:42:29Z","snapshot_observed_at":"2026-08-10T19:39:55.850235Z","submitted_at":"2022-10-25T17:18:02Z","title":"Practical Program Repair in the Era of Large Pre-trained Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.14179","snapshot_observed_at":"2026-08-12T04:46:24.466950Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.466950Z"},"links":{"cited_paper":"/paper/2210.14179","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:dca24e62f8a183ff1e8cba53a2bc767e4f320e0b3acce2fee3b0a9ac59e1fda2","observation_id":"cf1afebc-5bca-4095-91af-f68ac5b1ad26","resolution":{"observed_at":"2026-08-12T04:46:24.466950Z","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":"2026-08-12T04:46:24.473295Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.473295Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:f0cdba98450fc79ade79df3d98f56a7511a156d7934f357348b8698d88092ff7","observation_id":"7abb9475-0acf-4769-b4f7-58812ff79105","resolution":{"observed_at":"2026-08-12T04:46:24.473295Z","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":"2026-08-12T04:46:24.479882Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.479882Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:3cdbf3ff211fe48de14aa4519a744f0f8b10fa416c35f3fcd50623f5d644e8fb","observation_id":"9ab99db0-dee7-43e3-af3e-453852519125","resolution":{"observed_at":"2026-08-12T04:46:24.479882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.12244","last_updated":"2025-05-27T06:49:09Z","snapshot_observed_at":"2026-08-13T02:06:18.586697Z","submitted_at":"2023-04-24T16:31:06Z","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.12244","snapshot_observed_at":"2026-08-12T04:46:24.486009Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.486009Z"},"links":{"cited_paper":"/paper/2304.12244","citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:e00351382d88b9ff759e223ef6f2da75c8a904b9382177fc543a45d0f6220907","observation_id":"3fe8e78d-0f03-442b-8296-1dded6e2d717","resolution":{"observed_at":"2026-08-12T04:46:24.486009Z","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":"2026-08-12T04:46:25.675708Z","title":null,"venue":null,"work_id":"60cbfdff-5d66-4918-a772-2df179e76458","year":2019},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.492579Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:4aa20e4e643f4a31c2a5aec9167e56a9c1814c66c6e79d1e459a63516d338f9c","observation_id":"7611e121-4e62-474e-8014-e831097eb923","resolution":{"observed_at":"2026-08-12T04:46:25.685344Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T04:46:25.654790Z","title":null,"venue":null,"work_id":"20ca660d-af81-43c1-b8a5-39b0359053ea","year":2024},"citing_paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-12T04:46:24.499780Z"},"links":{"citing_paper":"/paper/2412.01072"},"observation_digest":"sha256:76582663e791e547fe0fad9287404af96d3e070481fa0c2bd3129aab2b8ab0c1","observation_id":"39d658cb-3b59-4a50-8354-cb3d0ed4b899","resolution":{"observed_at":"2026-08-12T04:46:25.660211Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.01072","last_updated":"2024-12-02T03:18:47Z","latest_version":1,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-12T22:40:51.812136Z","submitted_at":"2024-12-02T03:18:47Z","title":"When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":97,"verified_exact":1,"verified_fuzzy":1},"total_outbound_references":119},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 100 of 119 outbound references and 1 inbound Pith citation observation for arXiv:2412.01072."}