{"as_of":"2026-08-07T22:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ca4253b8c9d8261e34ea205e931705fdcbfa5d0584f3c578833c614941cd5af0","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:41:10.219766Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.13276/citation-record","integrity":"/paper/2506.13276/integrity","json":"/paper/2506.13276/citation-record.json","paper":"/paper/2506.13276"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:13.815451Z","title":"A comprehensive study on text-attributed graphs: Benchmarking and rethinking,","venue":null,"work_id":"55483d8c-b66b-4e8e-8566-90819100602c","year":2023},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:07.998075Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:42adfd1a4b8298328595d2bcfa6c76afe2a1e81eab4419092bb1c6e543e01a64","observation_id":"0e20e4f5-da4a-4990-8fb2-de0a1cf1666c","resolution":{"observed_at":"2026-08-07T00:41:13.873823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:13.706164Z","title":"Adversarial attack on graph structured data,","venue":null,"work_id":"d00ba187-86f3-460d-bfe6-76dddf1b07ed","year":2018},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:08.074203Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:0f83ca1b72d3b4853ddf22fa6c34443c2a9047abc498424856ff0270a9f01f96","observation_id":"7a05a54a-819c-4d0a-8106-85a63605ad20","resolution":{"observed_at":"2026-08-07T00:41:13.749821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:13.553154Z","title":"Adversarial attacks on neural networks for graph data,","venue":null,"work_id":"f35c26eb-2037-4b04-b92b-129ee2006b8f","year":2019},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:08.167067Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:1440ef2d0d391031eacba28c5a3f49b84c52668dfe8f7da057affb327c06e476","observation_id":"d57fc83d-06a2-4188-8a8e-12ed298c08b0","resolution":{"observed_at":"2026-08-07T00:41:13.632308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.05271","last_updated":"2018-12-13T05:32:43Z","snapshot_observed_at":"2026-07-06T07:20:54.523864Z","submitted_at":"2018-12-13T05:32:43Z","title":"TextBugger: Generating Adversarial Text Against Real-world Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.05271","snapshot_observed_at":"2026-08-07T00:41:08.262653Z","title":"Textbugger: Generating adversarial text against real-world applications,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:08.262653Z"},"links":{"cited_paper":"/paper/1812.05271","citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:007269838ab873a27559f94c25b06d3fa7c63b75be885045d565026780fc503a","observation_id":"5645341a-76a6-4dc1-88f8-9f9dc3c1d4b1","resolution":{"observed_at":"2026-08-07T00:41:08.262653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:13.393419Z","title":"Petgen: Personalized text generation attack on deep sequence embedding-based classifica- tion models,","venue":null,"work_id":"8b16df9f-7a04-4fe3-8813-9e6f26c2c7d3","year":2021},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:08.360966Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:ff01ca04c11d775282696052250bfb5f35ed9887683ea8a22d55ff2c17fdaf3d","observation_id":"8bf501f2-0f0b-4484-af94-9014393f58e4","resolution":{"observed_at":"2026-08-07T00:41:13.478290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:13.240732Z","title":"Fasttextdodger: Decision-based adversarial attack against black-box nlp models with extremely high efficiency,","venue":null,"work_id":"503863cd-c2b6-4ea8-875d-e2ac4ce37416","year":2024},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:08.442213Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:9e3427e8777acdf09d594718ff91c3836eb593dc7a274247b7d936275b625315","observation_id":"f49748d3-8ca7-4e63-b430-cd8d9d2a44fc","resolution":{"observed_at":"2026-08-07T00:41:13.298773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:13.109979Z","title":"Adversarial attack and defense on graph data: A survey,","venue":null,"work_id":"deea251a-01ac-4c83-9979-fe4de0959ab7","year":2022},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:08.550741Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:a39f5e894568d6904ac0a126a29c6e48bf221caf1d06729c22dfeffbbdc1d1a2","observation_id":"5c41b451-5b3f-4b42-a7cf-6e2a6df4a9ba","resolution":{"observed_at":"2026-08-07T00:41:13.168352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:12.914831Z","title":"Adversarial attacks on node embeddings via graph poisoning,","venue":null,"work_id":"e90dcca1-a907-4d18-8d19-2b0034b77126","year":2019},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:08.663004Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:418ec888e69272813468ee88aba6182be0b6dc17f86c47beaff73cbf1c9c2d73","observation_id":"211f4f8c-b2a6-47f0-8d8f-77b87ea77643","resolution":{"observed_at":"2026-08-07T00:41:12.972380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:12.682963Z","title":"Let graph be the go board: Gradient-free node injection attack for graph neural networks via reinforcement learning,","venue":null,"work_id":"d3652c6c-b9b3-4773-b312-b2169b30389a","year":2023},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:08.739708Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:fe0f47c3ad4abb54e16aa9d16fbcdc941de8acb041ec4f92138651d8d3125ed3","observation_id":"2dd6f12e-2a29-45bc-8e80-263f3cd304a0","resolution":{"observed_at":"2026-08-07T00:41:12.818920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:12.484278Z","title":"Tdgia: Effective injection attacks on graph neural networks,","venue":null,"work_id":"0454064a-6793-4cac-9f60-3d94bdf9b083","year":2021},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:08.826974Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:0e0bf4ac73ea03f804c4f13126b153a9c828b4ccd0646bf939a94cda6c6dfd64","observation_id":"91013029-705f-407d-8259-716187b624c6","resolution":{"observed_at":"2026-08-07T00:41:12.588013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:12.310900Z","title":"Understanding and improving graph injection attack by promoting unnoticeability,","venue":null,"work_id":"2d8456ac-da99-4b4f-b667-cd79afd74b4f","year":2022},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:08.918075Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:118886f52ced79eaf9e013f21aa6eab344397dc23d4391a073343252c01e7b42","observation_id":"96dd2625-6f31-41d2-b9c1-89d737d244b5","resolution":{"observed_at":"2026-08-07T00:41:12.392414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:12.139954Z","title":"Adversarial camouflage for node injection attack on graphs,","venue":null,"work_id":"67852c54-0e05-4e14-b517-abb77bb5f4b8","year":2023},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:09.008727Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:1f40165b194492c8a5e6f73980393620e858b645d0bd6e33f57587cf0d93f95d","observation_id":"afb2fc7a-6c3b-4681-8a46-9cddabbbce47","resolution":{"observed_at":"2026-08-07T00:41:12.221144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:11.949978Z","title":"Single node injection attack against graph neural networks,","venue":null,"work_id":"d3c749a0-03f8-47c3-929f-d2e26daca837","year":2021},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:09.122712Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:124154c38b2024573527c7c05691f6e9783b3999f3cdbd1444475a49150b1259","observation_id":"bdf03449-b775-468e-97d2-b0652990b4a0","resolution":{"observed_at":"2026-08-07T00:41:12.045116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:11.804050Z","title":"Scalable attack on graph data by injecting vicious nodes,","venue":null,"work_id":"37ab86b5-f899-45e2-947d-bc1b83265865","year":2020},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:09.238239Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:a8b6b0aae511266437f30bf306f57a328a79ce7b44140c70e79a53694ada4cbf","observation_id":"c19b4c95-3e89-402f-a5f0-7344944bd862","resolution":{"observed_at":"2026-08-07T00:41:11.870614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16405","last_updated":"2024-11-01T12:15:36Z","snapshot_observed_at":"2026-08-06T14:08:30.364746Z","submitted_at":"2024-05-26T02:12:02Z","title":"Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level","version":2},"cited_work":{"arxiv_id":"2405.16405","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.16405","snapshot_observed_at":"2026-08-07T00:41:10.594435Z","title":"Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level","venue":"cs.LG","work_id":"eeee2e7b-9966-4a73-b7dc-447412ed0f15","year":2024},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:09.352617Z"},"links":{"cited_paper":"/paper/2405.16405","citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:008e1da9dab4738a9e51e7ca079f903b666d1d7c7fa3eb572a528112e676cdc3","observation_id":"9e579968-86a6-4863-b6fe-8e5ecd24bb93","resolution":{"observed_at":"2026-08-07T00:41:10.663043Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:11.621766Z","title":"How does heterophily impact the robustness of graph neural networks?: Theoretical connections and practical implications,","venue":null,"work_id":"2ae9a19f-967e-40be-95d3-01390b5b58af","year":2022},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:09.464520Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:6e212ee282d88701179b8afe1fccc9e309b4d10a1dcb05e30fa1d13668e76266","observation_id":"95fbeb95-006a-47a3-8a07-a098649d2693","resolution":{"observed_at":"2026-08-07T00:41:11.701591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:11.403587Z","title":"Gn- nexplainer: Generating explanations for graph neural networks,","venue":null,"work_id":"c09a02f3-73cf-4f73-93b5-789d9ae3d206","year":2019},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:09.541347Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:1f602a385b1e7f01cb7c6a46b95765bb3bbebb3d5700dafae01b5b9834084348","observation_id":"9a55e287-8128-42b1-a8b5-16fe17f0140a","resolution":{"observed_at":"2026-08-07T00:41:11.472373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:11.273420Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":"5de64d1f-4151-4cfb-a8bb-6d93dcbb767e","year":2017},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:09.673372Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:b9951162f5fc17e6d2bd22a5d23e8443eac90212d98afe97f57e50fb0737d79a","observation_id":"ef3cfb4b-e134-48a8-8abe-0d91dd3e4fab","resolution":{"observed_at":"2026-08-07T00:41:11.335873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06543","last_updated":"2019-09-14T06:35:22Z","snapshot_observed_at":"2026-07-06T08:21:44.176052Z","submitted_at":"2019-09-14T06:35:22Z","title":"Node Injection Attacks on Graphs via Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"1909.06543","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.06543","snapshot_observed_at":"2026-08-07T00:41:10.372256Z","title":"Node Injection Attacks on Graphs via Reinforcement Learning","venue":"cs.LG","work_id":"2838660b-f482-4f38-b591-f40bf067ae57","year":2019},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:09.771898Z"},"links":{"cited_paper":"/paper/1909.06543","citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:83abc1d9bd1200e89b0333809945f156b20eb133a9ac0204d415fa60f7a01296","observation_id":"18b510a5-2247-4ec4-a322-f979b5df13a0","resolution":{"observed_at":"2026-08-07T00:41:10.478071Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:11.098092Z","title":"Message injection attack on rumor detection under the black-box evasion setting using large language model,","venue":null,"work_id":"a1ded2f8-3487-45a5-9bfb-5703aa108b7c","year":2024},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:09.852081Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:c2a29177b5c7093fe68ef68e1511ca367260af92d06907c1c8bdc8c758af70de","observation_id":"ce261ddb-435b-4ee3-8d19-4ddf348cc9f2","resolution":{"observed_at":"2026-08-07T00:41:11.157470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:10.929635Z","title":"A survey of graph meets large language model: Progress and future directions,","venue":null,"work_id":"aa4f3c03-f843-48d7-a516-1836ba706d6e","year":2024},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:09.933260Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:dba380176598f6c08f3f772766b490bde1d3bdd3ba3ab1868490b8fc5ce7bc85","observation_id":"a71eed4c-ce8f-4942-8a7f-0a6182c527aa","resolution":{"observed_at":"2026-08-07T00:41:10.979981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.12068","last_updated":"2024-07-28T16:44:21Z","snapshot_observed_at":"2026-07-06T18:47:25.751118Z","submitted_at":"2024-07-16T09:05:31Z","title":"Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.12068","snapshot_observed_at":"2026-08-07T00:41:10.041480Z","title":"Learning on graphs with large language models(llms): A deep dive into model robustness,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:10.041480Z"},"links":{"cited_paper":"/paper/2407.12068","citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:0e2bdad2fbde8e88f8bb49260c8b720ffff443ffc0fc1d68b44f26a254820afe","observation_id":"77dd4d27-3b43-4a21-9113-62438765568b","resolution":{"observed_at":"2026-08-07T00:41:10.041480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15183","last_updated":"2025-03-10T14:04:39Z","snapshot_observed_at":"2026-08-05T11:53:56.367640Z","submitted_at":"2024-02-23T08:29:42Z","title":"GraphEdit: Large Language Models for Graph Structure Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15183","snapshot_observed_at":"2026-08-07T00:41:10.129273Z","title":"Graphedit: Large language models for graph structure learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:10.129273Z"},"links":{"cited_paper":"/paper/2402.15183","citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:a52ac15dd43139e80e4366d4e7b36fc8d4c4e2d52620155aa11090171a5a7d47","observation_id":"73933d08-d1c9-4659-8663-5ac2aa331a18","resolution":{"observed_at":"2026-08-07T00:41:10.129273Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:41:10.771854Z","title":"Can large language models improve the adversarial ro- bustness of graph neural networks?","venue":null,"work_id":"21d2b067-916d-43da-9b43-b87b0b1d20db","year":2025},"citing_paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T00:41:10.219766Z"},"links":{"citing_paper":"/paper/2506.13276"},"observation_digest":"sha256:995d3c5ca629d8ad3e0a64e67d7a1cabe23c45805343e7d90792c374223e5cc5","observation_id":"b4e31686-bd66-4d4e-b815-e4313d59518a","resolution":{"observed_at":"2026-08-07T00:41:10.836355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.13276","last_updated":"2025-06-16T09:16:21Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T00:34:32.754747Z","submitted_at":"2025-06-16T09:16:21Z","title":"Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":2,"verified_fuzzy":19},"total_outbound_references":24},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2506.13276."}