{"as_of":"2026-08-11T08:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1f78aa41a8b3eac1647366929ead581bdcfc00a13ecba4aad3de07f1b4c5ba90","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T12:07:46.188133Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2607.19674/citation-record","integrity":"/paper/2607.19674/integrity","json":"/paper/2607.19674/citation-record.json","paper":"/paper/2607.19674"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:07:42.282019Z","title":"Dynamic multi-interest graph neural network for session-based recommendation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:42.282019Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:655bd91c6e47e4bb89807d58f8ca8bb2020e927e91e05b859bc5b03e0bbbaa87","observation_id":"584d4c04-5761-4676-9a56-201c843ba053","resolution":{"observed_at":"2026-08-01T12:07:42.282019Z","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":"2026-08-01T12:07:42.342933Z","title":"Dual graph neural networks for dynamic users’ behavior prediction on social networking services.IEEE Transactions on Computational Social Systems, 11(5):7020–7031, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:42.342933Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:6b48710d53ed3854c0d53314387f85dc4dfd3889d4bd5c61fd2b778cf2af40dc","observation_id":"eddc17c7-514d-4ea6-9c3f-04757b7f6301","resolution":{"observed_at":"2026-08-01T12:07:42.342933Z","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":"2026-08-01T12:07:42.466490Z","title":"Refine then classify: Robust graph neural networks with reliable neighborhood contrastive refinement","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:42.466490Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:7d77824a8bc101b31d14bd79272aba7e36269466ac39b73d7223dc47bf30a0a3","observation_id":"f1863bcc-ccf6-4e93-8271-f7b5b6b3ed49","resolution":{"observed_at":"2026-08-01T12:07:42.466490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.10351","last_updated":"2023-06-17T13:51:33Z","snapshot_observed_at":"2026-07-06T15:43:50.669695Z","submitted_at":"2023-06-17T13:51:33Z","title":"Bkd-FedGNN: A Benchmark for Classification Backdoor Attacks on Federated Graph Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.10351","snapshot_observed_at":"2026-08-01T12:07:42.586839Z","title":"Bkd-fedgnn: A benchmark for classification backdoor attacks on federated graph neural network.arXiv preprint arXiv:2306.10351, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:42.586839Z"},"links":{"cited_paper":"/paper/2306.10351","citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:09368c94b770db7e01b97f870383ec8bcf244d7b4d0f1c27bc06e31e9ca0dc8a","observation_id":"b59ed9ab-6551-43cb-98d9-7f4be1dfb7ed","resolution":{"observed_at":"2026-08-01T12:07:42.586839Z","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":"2026-08-01T12:07:42.712213Z","title":"More is better (mostly): On the backdoor attacks in federated graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:42.712213Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:9d54f4531a4a31dfdcd124e4dc9095ff6714975687c5d1bdd7e967dbc820eb9e","observation_id":"15ca1e49-336b-4509-b223-51c46c69f25c","resolution":{"observed_at":"2026-08-01T12:07:42.712213Z","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":"2026-08-01T12:07:42.831765Z","title":"Backdoor attacks to graph neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:42.831765Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:e43355d564025a08814a42b1824a570380067f6ceab92d2d2d238054d3b84bc0","observation_id":"1bc146c2-2aed-4817-83b9-b36879ef84fe","resolution":{"observed_at":"2026-08-01T12:07:42.831765Z","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":"2026-08-01T12:07:42.956816Z","title":"Unnoticeable backdoor attacks on graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:42.956816Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:480dcd76791b2d1d1e9a55355cdf63e40c5fb672429f12afb596dc11458a7792","observation_id":"9a628f9f-8f7c-47a2-9851-d2c4c749b931","resolution":{"observed_at":"2026-08-01T12:07:42.956816Z","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":"2026-08-01T12:07:43.076149Z","title":"Rethinking graph backdoor attacks: A distribution- preserving perspective","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:43.076149Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:db245bc40dcdd9d3d908f15d198832ea634aa88c493d6b6516cffd58810ad277","observation_id":"9e60607b-5559-4052-a150-5d51f8635625","resolution":{"observed_at":"2026-08-01T12:07:43.076149Z","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":"2026-08-01T12:07:43.201107Z","title":"Flmaacbd: Defending against backdoors in federated learning via model anomalous activation behavior detection.Knowledge-Based Systems, 289:111511, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:43.201107Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:d99c581523f7cd37f0fbb697bd39488b64635c23df0855d4529fd9e6a31ed7dd","observation_id":"a58788f3-d848-4162-a490-246385d5d999","resolution":{"observed_at":"2026-08-01T12:07:43.201107Z","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":"2026-08-01T12:07:43.326220Z","title":"Pham, Khoa D","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:43.326220Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:576f14947fcf30ef3e744aae0ab1d3898767cd62ceaeef28cca7994005d8ae74","observation_id":"4e778912-27a6-4f3c-9696-7c79d4df3764","resolution":{"observed_at":"2026-08-01T12:07:43.326220Z","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":"2026-08-01T12:07:43.415265Z","title":"Neurotoxin: Durable backdoors in federated learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:43.415265Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:df1ac1b113d40f53c880e50270bd6ff30c44b61f6a1567ef23dbe75fc4e9db05","observation_id":"34bfd749-3e54-45a5-86f3-1a0ad014a8a9","resolution":{"observed_at":"2026-08-01T12:07:43.415265Z","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":"2026-08-01T12:07:43.535716Z","title":"A simple and yet fairly effective defense for graph neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:43.535716Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:4956c24460f679253e4cbcfdfb88f8070372e559256d130557ba1853bfc19557","observation_id":"2ecc43ca-eece-4610-b436-e851bca045bb","resolution":{"observed_at":"2026-08-01T12:07:43.535716Z","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":"2026-08-01T12:07:43.651098Z","title":"Robustness inspired graph backdoor defense","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:43.651098Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:cb54c7dc5bc517d2defb19ad9072b7e76cf2f25d8504c4dd5746e39d01fe9578","observation_id":"efaba89e-9bbb-49f3-b1e9-d127d9b2e019","resolution":{"observed_at":"2026-08-01T12:07:43.651098Z","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":"2026-08-01T12:07:43.745942Z","title":"Beyond redundancy: Information-aware unsupervised multiplex graph structure learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:43.745942Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:74f78d0fad7d6082298f39fbdc44fcaaa4779c5dc394207d3bbe6d11bce8ca43","observation_id":"7d761871-e9ef-4ee6-af42-4c823dc9e5c3","resolution":{"observed_at":"2026-08-01T12:07:43.745942Z","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":"2026-08-01T12:07:43.846023Z","title":"Defending against backdoors in federated learning with robust learning rate","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:43.846023Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:f281b6a5e5ef370ec2437321ee10e1050d6596972d3cda036cc6728dee40578e","observation_id":"87e59339-7e92-466e-99c8-b8be3dda45e0","resolution":{"observed_at":"2026-08-01T12:07:43.846023Z","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":"2026-08-01T12:07:43.971620Z","title":"Energy-based back- door defense against federated graph learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:43.971620Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:aadee6ae08d69c0d6a5b4e8ed82b0b6a1498d146caf1ff962371b6847d5a186a","observation_id":"c82e5a6e-4cab-4587-8b88-d1769bafe4de","resolution":{"observed_at":"2026-08-01T12:07:43.971620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19455","last_updated":"2025-03-25T08:43:08Z","snapshot_observed_at":"2026-08-07T16:39:01.679812Z","submitted_at":"2025-03-25T08:43:08Z","title":"Data-centric Federated Graph Learning with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19455","snapshot_observed_at":"2026-08-01T12:07:44.065447Z","title":"Data-centric federated graph learning with large language models.arXiv preprint arXiv:2503.19455, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:44.065447Z"},"links":{"cited_paper":"/paper/2503.19455","citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:9b529e7d8dca64f40472ebddbdd21a043a26c7cabe43d9e917e69e4462d3d699","observation_id":"d5345c98-6734-49f4-b29f-2f79fbdbaa1a","resolution":{"observed_at":"2026-08-01T12:07:44.065447Z","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":"2026-08-01T12:07:44.163282Z","title":"Llm-guided dynamic-umap for personalized federated graph learning.arXiv preprint arXiv:2511.09438, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:44.163282Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:d0e4b780a20187dd7e3700c424c2bcf885ea765967390e85ef5ec1396b8fa90e","observation_id":"bcfbf107-ad45-4130-acb4-236a9776a2e5","resolution":{"observed_at":"2026-08-01T12:07:44.163282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13283","last_updated":"2024-02-11T11:38:38Z","snapshot_observed_at":"2026-08-09T14:54:38.526340Z","submitted_at":"2023-10-20T05:24:28Z","title":"pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.13283","snapshot_observed_at":"2026-08-01T12:07:44.278166Z","title":"pfedlora: Model-heterogeneous personalized federated learning with lora tuning.arXiv preprint arXiv:2310.13283, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:44.278166Z"},"links":{"cited_paper":"/paper/2310.13283","citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:489e29cf8dc475d4e459e5b1672abe345fc07199403f4f9fcb6bfb3171e0b6d0","observation_id":"af1b5c7c-4115-45bc-9ebe-5bf1174286da","resolution":{"observed_at":"2026-08-01T12:07:44.278166Z","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":"2026-08-01T12:07:44.392586Z","title":"Personalized federated fine-tuning for llms via data-driven heterogeneous model architectures","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:44.392586Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:8c3a7ca9c97fd07f4132453bf185a16e89866bebb1487a796aa2a7f125e28eb5","observation_id":"72cd2957-dfc3-4a2d-86a8-5c0b78e4eeb2","resolution":{"observed_at":"2026-08-01T12:07:44.392586Z","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":"2026-08-01T12:07:44.500492Z","title":"Fedex-lora: Exact aggregation for federated and efficient fine-tuning of large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:44.500492Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:2799397e98892f006d1dc595d676be075d96ec0518c9ac312bda8ccef9412c81","observation_id":"27085ec8-e83c-4cde-b78d-53fdade213cc","resolution":{"observed_at":"2026-08-01T12:07:44.500492Z","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":"2026-08-01T12:07:44.600972Z","title":"Fedalt: Federated fine-tuning through adaptive local training with rest-of-world lora","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:44.600972Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:945f7b61d3eb1a3a15dcb2f607214101b6f173040002449a7114cfcb68ad770d","observation_id":"2ea82013-208c-43e9-9fd4-63594a56a1c7","resolution":{"observed_at":"2026-08-01T12:07:44.600972Z","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":"2026-08-01T12:07:44.695405Z","title":"Federatedscope- gnn: Towards a unified, comprehensive and efficient package for federated graph learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:44.695405Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:bb0c56ba227aafcfc5797eb1f8a49d907b520f0789131ea5b66e120b41f8c2ed","observation_id":"be0043f7-bc6f-492e-ae8c-3fd28c729e16","resolution":{"observed_at":"2026-08-01T12:07:44.695405Z","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":"2026-08-01T12:07:44.805446Z","title":"E-sage: Explainability- based defense against backdoor attacks on graph neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:44.805446Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:23c37365fdc8e2b56df9cf2e3a407e6e4d13df40d64378a2ab2ae33215572cf2","observation_id":"644a5805-0261-43e1-9d18-790ff0d8edbc","resolution":{"observed_at":"2026-08-01T12:07:44.805446Z","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":"2026-08-01T12:07:44.913516Z","title":"Dshield: Defending against backdoor attacks on graph neural networks via discrepancy learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:44.913516Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:8e3fbd17b16e0f5b1d784796fc39f3e6c19ab96c7f77d352173a4165b93bab9c","observation_id":"e84b4d3a-7ac7-4b8c-8050-46413e374e67","resolution":{"observed_at":"2026-08-01T12:07:44.913516Z","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":"2026-08-01T12:07:44.997050Z","title":"Gnnguard: Defending graph neural networks against adversarial attacks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:44.997050Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:27a419b437298eb1f1e4717f33d99283b6c63329388587ff2a1c5df7474db519","observation_id":"f1133080-d14a-4eb4-8d19-05ae698189cc","resolution":{"observed_at":"2026-08-01T12:07:44.997050Z","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":"2026-08-01T12:07:45.106584Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.106584Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:ab2e4b8dcbc99f1c4623fbffc57d71ccb5ca07fcaf632a3a9bd5efad8318a93c","observation_id":"4fad02d0-0ee5-45bc-bfaf-9f9f67070a1d","resolution":{"observed_at":"2026-08-01T12:07:45.106584Z","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":"2026-08-01T12:07:45.216116Z","title":"Comprehensive risk assessment method of power grid based on grey relational weight game theory.IOP Conference Series: Earth and Environmental Science, 453(1):12068, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.216116Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:9dd217d03cfd507dcf548dd2a548b038f649fdecc4e97153d30e93e66cc293a9","observation_id":"c9b5b2f2-da73-4fe7-9a6b-3220412c5937","resolution":{"observed_at":"2026-08-01T12:07:45.216116Z","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":"2026-08-01T12:07:45.265666Z","title":"Evidential supplier selection based on DEMATEL and game theory","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.265666Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:206484a5bad5ebd2c67308157eb9bbd0f2437d32a19bf32f114edf6f9c669ae3","observation_id":"ef32ad0c-921b-47db-abcb-2ef1a0d7e6e1","resolution":{"observed_at":"2026-08-01T12:07:45.265666Z","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":"2026-08-01T12:07:45.308561Z","title":"Collective classification in network data.AI Magazine, 29(3):93–106, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.308561Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:6769db11068f080c7098b04ff8b7bad8edaead49e94e3fad094afa39a7caeef9","observation_id":"07ac184d-9d32-41eb-ad1f-f12a56f5e918","resolution":{"observed_at":"2026-08-01T12:07:45.308561Z","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":"2026-08-01T12:07:45.342805Z","title":"Graphsaint: Graph sampling based inductive learning method","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.342805Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:74d0f8c5521a70c940ff68e2d467964d0c9a2b7324d103adbc972651899c550e","observation_id":"9840e1a9-d196-4b64-a3c9-d4053f86e93a","resolution":{"observed_at":"2026-08-01T12:07:45.342805Z","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":"2026-08-01T12:07:45.360473Z","title":"Open graph benchmark: Datasets for machine learning on graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.360473Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:6f10bcd5eb3f9af206d1fbf33dd300b67064b785b36567c0f309fe82c0a7e807","observation_id":"583b767c-b883-4915-8060-74908f096407","resolution":{"observed_at":"2026-08-01T12:07:45.360473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-10T16:40:37.411115Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-01T12:07:45.399688Z","title":"The llama 3 herd of models.arXiv preprint arXiv:2407.21783, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.399688Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:502752cd1bbd2bcb4b838635268eb46f3feaf23653a8efe8a1054cc789309f47","observation_id":"d5e25a68-30de-4d68-8918-1f75b303d21e","resolution":{"observed_at":"2026-08-01T12:07:45.399688Z","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":"2026-08-01T12:07:45.440900Z","title":"Garnet: Reduced-rank topology learning for robust and scalable graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.440900Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:cd53ecf9984c261d5a57e05b199f014f2be976b4630847116a6f9bd9ba55aa3d","observation_id":"c0a17961-cb38-4c54-8da7-01b502dfa174","resolution":{"observed_at":"2026-08-01T12:07:45.440900Z","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":"2026-08-01T12:07:45.487462Z","title":"Adversarial attacks on graph neural networks via meta learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.487462Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:d3e1041cf2517e08dd6dada79f5af88dca603934644c7b03d107c29365d21063","observation_id":"9ee40238-d5ce-4e72-8127-3d9fa13b0152","resolution":{"observed_at":"2026-08-01T12:07:45.487462Z","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":"2026-08-01T12:07:45.537060Z","title":"Relative to the base GAT, the additional structural operation is the similarity-aware edge scoring in Eq","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.537060Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:08981b04661c71658b15a774b81731e71f1c139e5ba4b5323f1d1ecd863d2dbb","observation_id":"e123c90e-8c17-4905-bddf-1b07c575b077","resolution":{"observed_at":"2026-08-01T12:07:45.537060Z","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":"2026-08-01T12:07:45.582184Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.582184Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:1ba379545743aac12a8001c236a0efb971072b30728f07dbbaa05f2f3c85ea90","observation_id":"f6e78adb-7c05-4985-a7b5-22d588dab5e6","resolution":{"observed_at":"2026-08-01T12:07:45.582184Z","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":"2026-08-01T12:07:45.630508Z","title":"From Eqs","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.630508Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:dcfe492b3604832d61f81e1e80f096b9df44c3a111f7fb592e8f8e23bee059c2","observation_id":"429ec312-29fd-47ec-b2c5-9ce03560ab7f","resolution":{"observed_at":"2026-08-01T12:07:45.630508Z","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":"2026-08-01T12:07:45.669033Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.669033Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:832bf7bacf8aacbdee69459f5fe949d6a1f24259f50ecf58c5dfe5eab1d89321","observation_id":"ca32bfde-3fcf-4ac8-9713-0c1f429409b8","resolution":{"observed_at":"2026-08-01T12:07:45.669033Z","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":"2026-08-01T12:07:45.709719Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.709719Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:7ee753a66865e034565cb0e05ea03b847e708316177130dd9555fae381735b5e","observation_id":"de64710a-fc23-4563-ae31-28668cc8b504","resolution":{"observed_at":"2026-08-01T12:07:45.709719Z","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":"2026-08-01T12:07:45.753894Z","title":"Instead, the server keeps the remaining L−k semantic blocks and provides detached teacher targets for distillation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.753894Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:82e0650b506b052e2872780b45c50dfce3af53dca62822941a52bca3d0ba0922","observation_id":"8f1367bb-bb26-44e8-8fc0-a5e820093b57","resolution":{"observed_at":"2026-08-01T12:07:45.753894Z","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":"2026-08-01T12:07:45.792173Z","title":"FedLoRA+GAT + one server-side LLM teacher,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.792173Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:2744a5e5469a51a6ef4910124fd7c31b2e18b6ad216522ed0cb1dc81839d79cd","observation_id":"c1797519-0ce5-4de2-bf0e-e3ba147e8de2","resolution":{"observed_at":"2026-08-01T12:07:45.792173Z","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":"2026-08-01T12:07:45.829666Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.829666Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:77ae1c7905158ead495e15d901bceb43c7d3695984ebca61be02cda691b86d4e","observation_id":"ac82ba40-2588-4583-bb68-c144e29f903a","resolution":{"observed_at":"2026-08-01T12:07:45.829666Z","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":"2026-08-01T12:07:45.867381Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.867381Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:54ac7502e550427a567e53f509289f0385ea5ef3d05e8727f8a9c166d777d2d6","observation_id":"8559a7c0-b463-425a-aa0b-69a0f1658e97","resolution":{"observed_at":"2026-08-01T12:07:45.867381Z","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":"2026-08-01T12:07:45.905764Z","title":"In FL scenarios, the attack surface becomes even broader","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.905764Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:22eece8f3884b544c22d56ebf42cc2b83ba186e56430115f0bc1d927520595ec","observation_id":"42bd970b-246c-47a0-9210-d78cef9d55ee","resolution":{"observed_at":"2026-08-01T12:07:45.905764Z","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":"2026-08-01T12:07:45.942968Z","title":"They establish a comprehensive benchmark that systematically evaluates backdoor attacks in federated graph learning, facilitating more standardized comparisons across methods","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:45.942968Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:1f15fa04677c1b0883ec957ef1d2d2647e133f5efcf3c713f495575415395ad3","observation_id":"91e236ad-3e8e-4122-ac03-d0fb4d013727","resolution":{"observed_at":"2026-08-01T12:07:45.942968Z","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":"2026-08-01T12:07:46.024626Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:46.024626Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:eb07d00790cb22f63c1a6e059804158934689c839ae79256c0afb2c334cb8b9f","observation_id":"344c1429-a65c-462b-9278-33ead7592c23","resolution":{"observed_at":"2026-08-01T12:07:46.024626Z","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":"2026-08-01T12:07:46.062167Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:46.062167Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:31c4b52b1704110403c25c16f9cddecf156e0e4e4d8d0a420ea77d7ac7725232","observation_id":"40b293d0-27dc-4813-9051-e51621057ec0","resolution":{"observed_at":"2026-08-01T12:07:46.062167Z","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":"2026-08-01T12:07:46.106885Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:46.106885Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:001f8ce5cfe19f5b181858ff4306582ab7db66efc5367b8c309fea28c3d7c45a","observation_id":"33ecacde-e7f0-4c12-8374-962b23742aac","resolution":{"observed_at":"2026-08-01T12:07:46.106885Z","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":"2026-08-01T12:07:46.144798Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:46.144798Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:86ac53c0eb09e220f66be803e35d8fdc69c9e79c70b9788e10d216e0b5857934","observation_id":"4bbc1017-f586-4c77-8aed-34e39ec47932","resolution":{"observed_at":"2026-08-01T12:07:46.144798Z","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":"2026-08-01T12:07:46.188133Z","title":"19 Running Title for Header A.6 Parameter Settings We summarize the parameter settings used for Citeseer, Pubmed, Flickr, and Ogb-arxiv according to the released implementation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T12:07:46.188133Z"},"links":{"citing_paper":"/paper/2607.19674"},"observation_digest":"sha256:5bcaaa908b7b044a418612a76477dae6108fe9e82197ba3b4c8b17a99c351e70","observation_id":"deb97e10-5921-494e-9846-064b0454c825","resolution":{"observed_at":"2026-08-01T12:07:46.188133Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.19674","last_updated":"2026-07-22T02:23:14Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-10T17:08:53.158103Z","submitted_at":"2026-07-22T02:23:14Z","title":"FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":50,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":51},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2607.19674."}