{"as_of":"2026-08-13T06:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a0480ccbe0847a182ea6271b7eb54a7b9b1a2d30c9744e2b8a1b540bded34a5f","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T23:15:52.376752Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T02:33:34.084111Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.04224","last_updated":"2025-02-06T17:07:52Z","snapshot_observed_at":"2026-08-08T23:03:36.272014Z","submitted_at":"2025-02-06T17:07:52Z","title":"Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04224","snapshot_observed_at":"2026-07-14T02:33:34.084111Z","title":"Provably robust explainable graph neural networks against graph perturbation attacks, 2025 c","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.11871","last_updated":"2026-07-13T17:55:19Z","snapshot_observed_at":"2026-08-05T16:49:44.432361Z","submitted_at":"2026-07-13T17:55:19Z","title":"Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias","version":1},"reference_index":157,"source":"arxiv_source","source_observed_at":"2026-07-14T02:33:34.084111Z"},"links":{"cited_paper":"/paper/2502.04224","citing_paper":"/paper/2607.11871"},"observation_digest":"sha256:8eb87da29f10781cb103e306e6095d41b3b876f5bae517104bd7d14a3d8a3460","observation_id":"4d01c195-8e28-4213-ba51-307097b3a7cb","resolution":{"observed_at":"2026-07-14T02:33:34.084111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.04224/citation-record","integrity":"/paper/2502.04224/integrity","json":"/paper/2502.04224/citation-record.json","paper":"/paper/2502.04224"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T23:15:52.505480Z","title":null,"venue":null,"work_id":"a5c405d9-ecc6-43d4-b72a-6d2d73bb1a4b","year":2025},"citing_paper":{"arxiv_id":"2502.04224","last_updated":"2025-02-06T17:07:52Z","snapshot_observed_at":"2026-08-08T23:03:36.272014Z","submitted_at":"2025-02-06T17:07:52Z","title":"Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T23:15:52.359246Z"},"links":{"citing_paper":"/paper/2502.04224"},"observation_digest":"sha256:54b2d90a02a54f1ca81e7569dd6f73715c57f4d2cc139e525faeeea2bd85bf0a","observation_id":"4c3a5604-c95d-407f-a492-0937c93a67bc","resolution":{"observed_at":"2026-08-08T23:15:52.510125Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-08T23:15:52.475672Z","title":"For Refine, we set its gamma parameter as 1, beta parameter as 1 and tau parameter as 0.1","venue":null,"work_id":"32c18b34-f3d7-489a-b550-77438951ae0e","year":2025},"citing_paper":{"arxiv_id":"2502.04224","last_updated":"2025-02-06T17:07:52Z","snapshot_observed_at":"2026-08-08T23:03:36.272014Z","submitted_at":"2025-02-06T17:07:52Z","title":"Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T23:15:52.367807Z"},"links":{"citing_paper":"/paper/2502.04224"},"observation_digest":"sha256:0c24a8a937beb68e2e529cc258f00591573d66878eb247f20cf3a31fe3d3011a","observation_id":"6701316f-bb96-4b54-b91e-bae826f57952","resolution":{"observed_at":"2026-08-08T23:15:52.480428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-08T23:15:52.594669Z","title":"Certified robustness of graph convolution networks for graph classification under topological attacks","venue":null,"work_id":"752aaa2a-34bf-4aa1-8854-321af0c1dac0","year":2025},"citing_paper":{"arxiv_id":"2502.04224","last_updated":"2025-02-06T17:07:52Z","snapshot_observed_at":"2026-08-08T23:03:36.272014Z","submitted_at":"2025-02-06T17:07:52Z","title":"Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T23:15:52.323786Z"},"links":{"citing_paper":"/paper/2502.04224"},"observation_digest":"sha256:4681438cbdad49c6e12ca02b32b2c362a2c40a930bc8508baa99442cc1a2793f","observation_id":"3c24abdb-34db-44cb-8d61-e18b084babf1","resolution":{"observed_at":"2026-08-08T23:15:52.599519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.12105","last_updated":"2019-10-17T23:09:36Z","snapshot_observed_at":"2026-08-13T05:53:47.281170Z","submitted_at":"2019-05-28T21:49:40Z","title":"Certifiably Robust Interpretation in Deep Learning","version":3},"cited_work":{"arxiv_id":"1905.12105","doi":null,"metadata_source":"pith","pith_arxiv_id":"1905.12105","snapshot_observed_at":"2026-08-08T23:15:52.411636Z","title":"Certifiably Robust Interpretation in Deep Learning","venue":"cs.LG","work_id":"dd4a2ae1-ebcc-4769-b0a6-79e6926a15c6","year":2019},"citing_paper":{"arxiv_id":"2502.04224","last_updated":"2025-02-06T17:07:52Z","snapshot_observed_at":"2026-08-08T23:03:36.272014Z","submitted_at":"2025-02-06T17:07:52Z","title":"Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T23:15:52.333498Z"},"links":{"cited_paper":"/paper/1905.12105","citing_paper":"/paper/2502.04224"},"observation_digest":"sha256:c1407b4d8da6220c63fbcf18fb3b5161be1c3bf376fceb7e0e697c492ad0ec13","observation_id":"3bf99a70-8722-4885-8e7e-cacb32c42430","resolution":{"observed_at":"2026-08-08T23:15:52.418544Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-08T23:15:52.565535Z","title":"Explainability methods for graph convolutional neural networks","venue":null,"work_id":"61adef26-eaf9-41c7-950a-c283f90ea563","year":2025},"citing_paper":{"arxiv_id":"2502.04224","last_updated":"2025-02-06T17:07:52Z","snapshot_observed_at":"2026-08-08T23:03:36.272014Z","submitted_at":"2025-02-06T17:07:52Z","title":"Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T23:15:52.338923Z"},"links":{"citing_paper":"/paper/2502.04224"},"observation_digest":"sha256:72210e2c7a240379f9be5ebf5ec6039352db69ee45bf45cc6fead0a501033378","observation_id":"e7f18ee9-eeb2-4dd1-9f1f-7b5c3ad5b39f","resolution":{"observed_at":"2026-08-08T23:15:52.570021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-08T23:15:52.551242Z","title":"Reinforcement learning enhanced explainer for graph neural networks","venue":null,"work_id":"7bec7727-8989-4b0f-a020-18c5552debd0","year":2021},"citing_paper":{"arxiv_id":"2502.04224","last_updated":"2025-02-06T17:07:52Z","snapshot_observed_at":"2026-08-08T23:03:36.272014Z","submitted_at":"2025-02-06T17:07:52Z","title":"Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T23:15:52.344182Z"},"links":{"citing_paper":"/paper/2502.04224"},"observation_digest":"sha256:51a1e0d8685a33481a2a79d32c6c09edcf6dc34b12829d3dd111e866463c7b10","observation_id":"13ff4dd8-b4b1-457e-86f9-d4ec112c8062","resolution":{"observed_at":"2026-08-08T23:15:52.556034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-08T23:15:52.536944Z","title":"Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking","venue":null,"work_id":"4992c194-a9e4-4e75-b9ac-bb1e24a03093","year":2025},"citing_paper":{"arxiv_id":"2502.04224","last_updated":"2025-02-06T17:07:52Z","snapshot_observed_at":"2026-08-08T23:03:36.272014Z","submitted_at":"2025-02-06T17:07:52Z","title":"Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T23:15:52.348648Z"},"links":{"citing_paper":"/paper/2502.04224"},"observation_digest":"sha256:3adda8a3a62539e2eaf5009b92b0f89130fc63f9be1ee78b315ef8eebffc63aa","observation_id":"8a88358f-e1b0-466a-935b-4827a33fe9d0","resolution":{"observed_at":"2026-08-08T23:15:52.541736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-08T23:15:52.490557Z","title":"the classifier: Mf = ⌊ ny −nb+I(y