{"as_of":"2026-08-05T06:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:04d951c8e0c553636299605571534ea15c134b187faecb3db34fdff17c3099db","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T17:18:42.590627Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2605.07961/citation-record","integrity":"/paper/2605.07961/integrity","json":"/paper/2605.07961/citation-record.json","paper":"/paper/2605.07961"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T17:18:42.590627Z","title":"Parameter-efficient fine-tuning of large-scale pre-trained language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:18346eabe0e96745f6606d26f2c8b414d0ff087fb4d330bfee8360f245b95c2a","observation_id":"53e2a203-4604-488f-b892-70c11e95afe4","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"A survey on federated fine-tuning of large language models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:ee4ea26d20b033c252a91900915b15248823d71059044c1b2c8ab31eb57cbf62","observation_id":"3db0d8a5-41d4-465d-9c4f-8e94a71af3e5","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.01240","last_updated":"2025-04-01T23:06:45Z","snapshot_observed_at":"2026-07-06T21:02:42.779646Z","submitted_at":"2025-04-01T23:06:45Z","title":"Towards Resilient Federated Learning in CyberEdge Networks: Recent Advances and Future Trends","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.01240","snapshot_observed_at":"2026-07-12T17:18:42.590627Z","title":"Towards resilient federated learning in cyberedge networks: Recent advances and future trends,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"cited_paper":"/paper/2504.01240","citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:06e28738cf55df408968f523e914ef95dd3645f7a684ef9e9881405d2190bf2b","observation_id":"ee7ac98e-9be2-40d6-b91a-dcd596d9bbbf","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Lbkd: Rethinking federated backdoors for low-altitude economy via llms and bidirectional knowledge distillation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:5132e8dcf6f9899edce1729ca7c19a780fa3a79bc8f82267ba8661529fa021a1","observation_id":"64d0fd33-2b52-4b75-9dfd-9ba42a37db61","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Edge-based communication optimization for distributed federated learning,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:6fa5ba4cfdf481d4b299e11fb030c3134802cc13591b438480ddae0cd23284b2","observation_id":"c23331b9-9b7b-4456-86b6-dadf84fcbc41","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Saferag: Secure cloud-based retrieval-augmented generation for llm-empowered voice assistants,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:af73576a7b9e727169bf54fcc2a0db1b69e3e40966333ca24905dab7f01ac686","observation_id":"69676c46-b12f-4056-86e4-9a80f2a9a33e","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Llm-based edge intelligence: A comprehensive survey on architectures, applications, security and trustworthiness,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:3b1d20f57faead7bf6d16a221feb928d051f7e4473fa2ce4c18e7a07e2203d1a","observation_id":"0898cbfe-785f-48d4-9a41-2efb69314cf6","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Federated fine-tuning for pre-trained foundation models over wireless networks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:43f1ded803df140209e6009a4c3563077ac04da67d8fc9ce3262cc582aa74572","observation_id":"8b755329-61b9-4187-9634-e0d016c94f5b","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Flora: Federated fine-tuning large language models with heterogeneous low- rank adaptations,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:484c41489bda4dfeb10bf08e64c7b96c191ffac04d7e089b45b0a7ad97817958","observation_id":"f5832b4b-7106-4b29-a968-b926104803b6","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Fedacl: A collaborative federated fine-tuning framework for large language models with awlora and contrastive learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:285e11cf7ae3beba4199d8f226a0682c16cb5d69dbed861f0d2155bc9495b659","observation_id":"e348254f-fa3b-4bed-abee-de2fa0ddc031","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Towards federated large language models: Motivations, methods, and future directions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:0dfc9f7555bc36c20a325b32ed1d373f18f9097332cf249c22530d4278344b03","observation_id":"506bd503-c4b1-440c-8024-90d544bbfa52","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Federated large language model: Solutions, challenges and future directions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:52feb0e2a4aa7f31c991fb4279bd192bceb5471c3f97c9ce04f155f25695136a","observation_id":"f4fa1f9e-fee0-488b-af4e-024c93d47bed","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:6d3c778add5b50a194b64c3e3ba6b7dc87668b1443384918831adaf57af6161c","observation_id":"1efa5842-55a1-4dcb-a1fe-7e0186c2b87b","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Federated fine-tuning of llms: Framework comparison and research directions,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:77f4d28c586ae723bee98bebfd30706d9186bace641e7d5c70732f1355df8f65","observation_id":"312a5e90-1b1e-47d0-87da-fa25a440ea95","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Flocoff: Data heterogeneity resilient federated learning with communication-efficient edge offloading,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:deec06b0240f7114ba62e9bb88293a814b7c59e917e032c9e683665ddcbd506f","observation_id":"a1c9817a-87c9-4c47-aa6f-cc728a2b384f","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Fedlodrop: Federated lora with dropout for generalized llm fine-tuning,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:2370c5f783084d11dd7d87ff664f76fed2516e53c5f35d475354134026437c50","observation_id":"22736a0f-8562-46a7-92a4-ceaafb8a5fa2","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Federated adaptive fine-tuning of large language models with heterogeneous quantization and lora,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:12f2d951db66f292f170da2e1b3d947986c92626c6044b322ae14d190ce2adf8","observation_id":"3175161b-27b9-4680-a50a-527e57516ec6","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Efficient parallel split learning over resource-constrained wireless edge networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:043429470013dfe0646a513b9fa4336ee9bfac6a58529a1e745136cc4e7c8f00","observation_id":"16f3e63a-70ae-4737-87fa-97a0d86f0384","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Adaptive model slimming for communication and computation efficient federated edge learning under non-iid data distribution,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:54499249a83608ae69bf1d372e2327cc3ace912cf0abad23f139f71536d4992e","observation_id":"03776bb4-3957-4eb2-af32-f5e2555ff813","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Dataset distillation-based hybrid federated learning on non-iid data,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:9f6bfd6107d5b64d800ec11d4ce2a42ce6a58d25bf422e540f381df30c3a1e2c","observation_id":"dc0bb80f-e21f-4788-a951-ea30b9c43366","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Fedsv: Byzantine-robust federated learning via shapley value,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:295729bdf484b7e962482c6e6bcdeaa6b8385a35c099330c7e993853ecc2db7b","observation_id":"d5e35eb8-1480-4b8f-b7e1-b23999b5d849","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Federated learning meets multi-objective optimization,","venue":null,"work_id":null,"year":2039},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:1e0ecc8f80310216654e2f538dc8085ed0b29df7068c828abb1252d500ad49c2","observation_id":"9dabcda4-72f2-4913-8fc0-00de56f2f8bd","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Filling the missing: Exploring generative ai for enhanced federated learning over heterogeneous mobile edge devices,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:6f536e3b1e6af5e458e1ba695766697d703cb692e44ae9a1ef93daff6d3555a6","observation_id":"b162a4c5-b38a-4ae0-addd-81c57f751a50","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Fedsecurity: A benchmark for attacks and defenses in federated learning and federated llms,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:038217d7abd69dcbdf108c23bedfef17d527cb1cf2afea9f0219f2e6dcc7db7d","observation_id":"fb159d44-6acf-46ff-a6a8-dbae97a05898","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Straggler-resilient federated learning: Tackling computation heterogeneity with layer-wise partial model training in mobile edge network,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:b67f5ce5b140fc7fe699e5d6ff73e1fb7fe97ca25e6f65f98f8377735c4451d5","observation_id":"66f33329-9d18-448e-a83d-07bcfae48533","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Large model based agents: State-of-the-art, cooperation paradigms, security and privacy, and future trends,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:e5bac5e23620130418d1d05950832bd49d31d9f6ec33f5c2fedbbedf3ec41181","observation_id":"e4e3fdaa-8520-406f-865b-cec61c9cd8ee","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Dm-fedmf: A recommendation model of federated matrix factorization with detection mechanism,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:ad5039a285976af367c10c9ef35e37ea58d127db00fa60887bfc89a5ce98596c","observation_id":"6bec13d1-1576-48c4-9634-dc0b7cabcde0","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Federated learning while pro- viding model as a service: Joint training and inference optimization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:340a1618e99bcfef1a05ddcd369a46692795295cf0b20dac2ec0cedf2f7d5a6a","observation_id":"668a3273-0388-4f8e-8f46-fb3bea6dbc35","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Securing billion bluetooth devices leveraging learning-based techniques,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:de8901e28b030f62974adc64ae746c1d4ed98d59ffe3f7144c00a322bf08e4d7","observation_id":"ac75f670-2765-4572-bafa-f47373f3f0ab","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Rofed- llm: robust federated learning for large language models in adversarial wireless environments,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:37747340cfa31c1f6ddc63cd494c142f250104f5e22f9ba966cd4ae042ea2e26","observation_id":"2deb4a26-6564-4262-a42e-294136209252","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.07176","last_updated":"2026-04-08T13:31:48Z","snapshot_observed_at":"2026-07-06T22:35:22.282985Z","submitted_at":"2025-11-10T15:06:26Z","title":"Graph Representation-based Model Poisoning on the Heterogeneous Internet of Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.07176","snapshot_observed_at":"2026-07-12T17:18:42.590627Z","title":"Graph representation-based model poisoning on the heterogeneous internet of agents,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"cited_paper":"/paper/2511.07176","citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:038f623613a0bd6520d6943f3f398e681aa206e96bbaf62ab751a733f146c293","observation_id":"d83aa1a3-7903-4a98-8659-8b459b4beec5","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Prism: Privacy-aware routing for adaptive cloud–edge llm inference via semantic sketch collaboration,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:b3b70f7cf1a76b4b76b35e095d87c9432cbc10ba40c59d052f22cb068a9bb84a","observation_id":"a08730e5-67c4-473d-b94c-dd59e806739e","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Falcon: Federated active learning-based concept drift adapta- tion for malware detection,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:4e76c7fae824ae4e6ddf571d2861800f38b54556db777c333f3db99ded3832f2","observation_id":"a9b13f91-86fb-4347-932d-b2ca7033b841","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Local model poisoning attacks to{Byzantine-Robust}federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:b19b58c15adb83e4d9b38fa57a2df28640a09b67a5aa1f637e2838cfae9b5dda","observation_id":"a985e802-8619-4e10-9641-ed0d9deb64a5","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"A little is enough: Circumvent- ing defenses for distributed learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:1095ca6bf67349b8a1978858710132d54e8f921ee4c2bda7fdd70d07ac7d47c3","observation_id":"044aea3b-11ca-4602-8dfa-a7c00ee67605","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Mpaf: Model poisoning attacks to federated learning based on fake clients,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:85896d04f7442f2dd83ff9bffcb2df76f81d0ce035a9e17106b8de495224156a","observation_id":"35023f81-7dfd-4074-a8cb-ce422c6b1a47","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Data-agnostic model poisoning against federated learning: A graph autoencoder approach,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:45d6345f089283f582b0fac864fe5554bf95abcf579c1ced70dbf1abd4d98570","observation_id":"75957fd6-b451-42cd-90c4-455bf9991fd2","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Lever- age variational graph representation for model poisoning on federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:d79efe5f5d2cf2f6c82a7fb90a93c4f881d6df049e20a428abdd00717a5aff75","observation_id":"fa14d0e7-297a-4f2b-af3b-2c9786b65db8","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"User isolation poisoning on decentralized federated learning: An adversarial message-passing graph neural network approach,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:44e8f7ffe31e0bd25365f95f0a3d83ea1e85faea0099855238f83d7b6811a6fd","observation_id":"247745e2-8a60-42fc-a2c8-4c16ebbd753c","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.19335","last_updated":"2024-12-19T14:30:23Z","snapshot_observed_at":"2026-08-05T04:56:01.301898Z","submitted_at":"2024-11-28T19:05:01Z","title":"PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.19335","snapshot_observed_at":"2026-07-12T17:18:42.590627Z","title":"Peft-as-an-attack! jailbreaking language models during federated parameter-efficient fine-tuning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"cited_paper":"/paper/2411.19335","citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:e1afe2676d378303db3a523286a06831548767f66f70a072455bc1aa9eb679c4","observation_id":"769b2381-0a49-4c1a-a2e5-4cf20c741cbb","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10630","last_updated":"2024-06-15T13:24:22Z","snapshot_observed_at":"2026-08-04T15:55:04.436415Z","submitted_at":"2024-06-15T13:24:22Z","title":"Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10630","snapshot_observed_at":"2026-07-12T17:18:42.590627Z","title":"Emerging safety attack and defense in federated instruction tuning of large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"cited_paper":"/paper/2406.10630","citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:33f1e441741829347cb7579557a5a698a4f3ec001c2aad4deb61a4be67dbe32e","observation_id":"f92bb088-bae5-4314-8b0f-0eb913073a3d","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Silent penetrator: Breaching cross-domain federated fine-tuning via feature shift-induced backdoor,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:6a2549dbdac3ae7b655d52ad2c63ea10c7c42cdad19d029a928e052c9a5f3aac","observation_id":"89a6523f-d17b-47fa-b69a-b475c07b9a1f","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Low rank comes with low security: Gradient assembly poisoning attacks against distributed lora-based llm systems,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:e28ebeb7e4be5defea15b12488d07a000c741697d38eacbcf6f72d4461036fb5","observation_id":"f7021534-013f-4f33-96d2-5636530521ec","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"A comprehensive survey of federated open-world learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:92b8357e6a6865a399035a2684aea3d027863fb3debc371eee22ed958da0c270","observation_id":"89b760cc-a791-4246-ab04-7b6e85fcc11a","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Lora-fair: Federated lora fine- tuning with aggregation and initialization refinement,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:89f1e106e21df691c1c4c96024cfe3e65654fcc169080e6f7033e2009ab83baa","observation_id":"04ee442b-eaea-4c7b-8f16-ff7e8750737b","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Privacy and robustness in federated learning: Attacks and defenses,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:af8588beefd0df7376f8be60f974fae224ff7de2cf9bcd49d1b72c0a1c2ffbfa","observation_id":"d1939537-ed3f-40b5-9b79-0e520af20632","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Federated learning for urban sensing systems: A comprehensive survey on attacks, defences, incentive mech- anisms, and applications,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:06b7b98543a2e2f50d6139c8c16147d1e2287b7f0b5e3f72acc28080c44dddb2","observation_id":"31a4c16c-e3b0-4c60-a1a9-7c1e8741ba79","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"The impact of adversarial attacks on federated learning: A survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:a31b51ae522809c5c6c7daa934176790246e17a733609337d80c76b2397c17dd","observation_id":"55bc477d-96ba-4032-bb5f-bd7d27182593","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-07-06T20:32:00.585460Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.03801","snapshot_observed_at":"2026-07-12T17:18:42.590627Z","title":"Sok: Benchmarking poisoning attacks and defenses in federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"cited_paper":"/paper/2502.03801","citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:8219a53780fa86044d771cbccc49f9d43669ce48cff184b82467f2fc104860f2","observation_id":"88335609-46cf-4e7f-ac89-9de7938219af","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Practical framework for privacy-preserving and byzantine-robust federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:f8319966091765f8c696cf053f49d828bddc4adb8e493076d67ffbb153244e43","observation_id":"812b7d18-2709-4ac9-a9f6-c9d440bb31d2","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Overcoming noisy labels and non-iid data in edge federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:5b8dbe33d4ad10bbf1024799877552e7d748c915d45fffb5317a15cb3071ddf7","observation_id":"abc6a9c4-2729-420e-812d-95f951636b54","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Fedapm: Federated learning via admm with partial model personalization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:dd363fc49c02fb3f38414378c978e7738c70d0c6442802c2a45f174b61171723","observation_id":"28aa7c9e-2669-4038-a349-65abf7515f01","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.05808","last_updated":"2024-11-27T19:12:50Z","snapshot_observed_at":"2026-08-03T02:43:19.055918Z","submitted_at":"2023-11-10T00:53:22Z","title":"Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.05808","snapshot_observed_at":"2026-07-12T17:18:42.590627Z","title":"Scale-mia: A scalable model inversion attack against se- cure federated learning via latent space reconstruction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"cited_paper":"/paper/2311.05808","citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:03a8756792e92bb6b2aaa868404ecd93df669a8175f269ac9b176506b3abf91b","observation_id":"e84d0c05-cc06-413e-8c88-57d04d3c60ba","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Finback: Infiltrating backdoors into gradient compressors on federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:a7ed6deb2716587d12f8d40731aa7206ee55da037ee69b649983da29c114f199","observation_id":"abbef805-a0f3-4498-b7dc-7a2b549f2775","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Efficient mobile-cloud collaborative aggregation for federated learning with la- tency resilience,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:0322143b4f853eccc65f9cdbe22f2370f1ae82682867390326c3eb9e1289f078","observation_id":"d2eedbd6-bf33-47d4-aa48-4ee584116788","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Augfl: Aug- menting federated learning with pretrained models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:e07d67fe29e2d128289a5aa21df809bf323aa6ddc3dc549bf88b43179ff283e2","observation_id":"1013c3ae-0b7d-48c2-83b1-68844da81ba1","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Snapcfl: A pre-clustering-based clustered federated learning framework for data and system heterogeneities,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:b9e6ca20f468ddfd77fd12c44af8d13f9fe0101d2f57ccb7b8226a2e8077757d","observation_id":"9ec8e31f-fbb8-4f51-839f-5e5385fe992e","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Federal graph contrastive learning with secure cross-device validation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:aabf57b95b2471aee2ed12f70c1656ddd9843ed678c3f0f0f5490be5e81ce559","observation_id":"efb86f81-4b92-49da-b86a-e6a5199cf570","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"The autoencoding variational autoencoder,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:405a8c88cf0acddbbad0f7be9bcb42d65e8e947b71e446c0e778101da1323a70","observation_id":"647d4af3-c02b-49be-8c38-952efdb2c61a","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Biasing federated learning with a new adversarial graph attention network,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:6f6c7aae45ab688c493c546aa5ba3e4aa4b700cbe7ced77eb36539fca81babc0","observation_id":"7edb6964-9e92-4c2e-a7d0-aee449feda03","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Character-level convolutional net- works for text classification,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:68059267478cc2b82ea30e9d64e47e0eb1de8d077b813ac3c68248008e80022f","observation_id":"92ab6cf2-5fdb-4677-a947-5cfb35e134d1","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-03T03:32:02.223426Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-07-12T17:18:42.590627Z","title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:adb1d33ef1b55c71ef4674b8e5d9614a570c5ab6836700d75ace065211bc5896","observation_id":"b01185d3-c119-441a-9e6c-72bacaa078b1","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-07-12T17:18:42.590627Z","title":"Pythia: A suite for analyzing large language models across training and scaling,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:d5659ca39406a0f10bc1a6e90104d8fc830c1a148355449e74d21d4d51c85e40","observation_id":"5796fafa-3fc3-4870-85b1-31446b4075a5","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12186","last_updated":"2024-11-12T13:24:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-09-18T17:57:57Z","title":"Qwen2.5-Coder Technical Report","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12186","snapshot_observed_at":"2026-07-12T17:18:42.590627Z","title":"Qwen2. 5-coder technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"cited_paper":"/paper/2409.12186","citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:f53f32cd3272d469f08a3096ae31bc572be4d0eec89320bca31a5e517c11d103","observation_id":"0eeddcb0-ab63-4174-a131-b3289c1200a4","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":64,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":64},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2605.07961."}