{"as_of":"2026-08-12T23:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dfbdf307f16bc5adeba323868a3cdecdaf2fbe44d718918f4a3021e870f7b470","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:42:49.781355Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2505.14005/citation-record","integrity":"/paper/2505.14005/integrity","json":"/paper/2505.14005/citation-record.json","paper":"/paper/2505.14005"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:46.346447Z","title":"Evaluating explainability for graph neural networks.Scientific Data, 10(1):144,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:46.346447Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:1b451523176428b326e9eb4f6217aeb15fa630bea2ef7271597d663f879e0f96","observation_id":"ff9e9a91-0b93-4b3f-9a2f-95aff87cb610","resolution":{"observed_at":"2026-08-07T15:42:46.346447Z","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":"2026-08-07T15:42:50.218928Z","title":"the model to preserve more crucial structures within the explanation subgraphs, thereby boosting positive fidelity","venue":null,"work_id":"a028868a-1c77-458e-8251-ce695734159c","year":2000},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:49.781355Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:7d30e19a7f07773ef019a7f80bb3ee93cc303e5fb1325b1a415287dd631c4b4a","observation_id":"d5adc241-91e5-41f3-9866-8436216d5bc4","resolution":{"observed_at":"2026-08-07T15:42:50.265955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:50.416627Z","title":null,"venue":null,"work_id":"9fb3ab41-f82d-47bb-9c66-abcbef7e307e","year":2000},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:49.718519Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:c6b63715299f359ccb44671bc0330cfe64975108a4af6e9d7337f1d61ba3a2b2","observation_id":"c7cb232c-9edf-4275-b83a-7f4c5caa1955","resolution":{"observed_at":"2026-08-07T15:42:50.459853Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:56.689625Z","title":"D4explainer: in-distribution gnn explana- tions via discrete denoising diffusion","venue":null,"work_id":"cb6a3278-ee4c-4bd0-8600-68ab8acf326b","year":2023},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:46.661002Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:9d84caeedc125c46198b30f2bf54a47262178840223fb2595666c6d8ff259401","observation_id":"ba78e0b7-e2db-4b66-950e-7cb313fe61ef","resolution":{"observed_at":"2026-08-07T15:42:56.733925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:56.409489Z","title":null,"venue":null,"work_id":"3cf8b3bf-c984-42f7-af4b-283d9d5101f2","year":2019},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:46.826426Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:6d7726330c6663d177318d8ab02f0e40dcc516c0fd7d918cea511dd8b8af32b1","observation_id":"e5b7a549-b9b6-4fe9-9cd9-dd5d5e057733","resolution":{"observed_at":"2026-08-07T15:42:56.468467Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:56.124647Z","title":"Good: A graph out-of-distribution benchmark","venue":null,"work_id":"ee62c8c1-3a55-4dc9-905d-e03a06b08702","year":2022},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.015349Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:d2b7c4fc32d3633c7408aff12bc86ea7730f1f62ce50ca55711770d85262548b","observation_id":"1411bf58-cb18-499c-afad-5799b3d74b97","resolution":{"observed_at":"2026-08-07T15:42:56.173594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:55.987643Z","title":"Mean-field theory of graph neural networks in graph partitioning","venue":null,"work_id":"801a8b6c-00f9-4f36-8e09-f0c534658adc","year":2018},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.093794Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:473f140f2bcee8431a370fa88dfb2facc455241463736fe2091e8411b703eae5","observation_id":"86118534-cd9f-48b8-9224-f3e9a53ec3c0","resolution":{"observed_at":"2026-08-07T15:42:56.041190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:55.555750Z","title":"Distribution shift detection for the postmarket surveillance of medical ai algorithms: a retro- spective simulation study.NPJ Digital Medicine, 7(1):120,","venue":null,"work_id":"d82da163-5ea4-4fad-ba91-b41caae05cd4","year":2024},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.274223Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:0b748d8f79477df2580022ac52f2fed484848c8130a9b4abc8fe0c265038033e","observation_id":"6d68baf3-a044-42d5-b904-3824d74f3f42","resolution":{"observed_at":"2026-08-07T15:42:55.643179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:55.276937Z","title":"Xgexplainer: Robust evaluation-based explanation for graph neural networks","venue":null,"work_id":"2b38b768-6ff3-4c34-adf7-61ec9041eb5e","year":2024},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.363134Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:0a7ac6131186d0c336e9d9e054549118ea886cb8276c4380bb9da45aa1ad6b4b","observation_id":"3e269927-18a2-4e89-9363-d2621eafd72f","resolution":{"observed_at":"2026-08-07T15:42:55.426920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:55.060629Z","title":"Graph representation learning in biomedicine and healthcare.Nature Biomedical Engineering, 6(12):1353– 1369,","venue":null,"work_id":"0ff0c327-c5de-4ea3-b75d-4c60e79e8f45","year":2022},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.486088Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:0db8d96b7b8d4737c30d971f87fd533f490abaa9c89ceed1a4fdeaec900b1342","observation_id":"dc24fc07-4a55-4534-9798-91e8dd39a15d","resolution":{"observed_at":"2026-08-07T15:42:55.121921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:54.846841Z","title":"DIG: A turnkey library for diving into graph deep learning research","venue":null,"work_id":"f06fc473-684c-4549-ac9a-22658488e868","year":2021},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.673889Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:0a62fbf8b53b56d7df700d0e3aa1759f6d25643768d2daabcf1f994a13490aa0","observation_id":"a8bed3aa-d058-4064-8424-7b74de91a7f8","resolution":{"observed_at":"2026-08-07T15:42:54.939042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:54.678376Z","title":"Cf-gnnexplainer: Counterfactual explanations for graph neural networks","venue":null,"work_id":"8c5994d1-4fac-4879-81eb-17bc98340788","year":2022},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.797297Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:b329894ff1b9513533b727a9973475dc101a9b6f06d5e54ce96d333c2d19e224","observation_id":"856cef43-5f6e-4e8f-8d61-2ce3ad9b04e7","resolution":{"observed_at":"2026-08-07T15:42:54.741762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:54.418509Z","title":"Parameterized explainer for graph neural network","venue":null,"work_id":"29ec67b9-b8ab-473d-97d4-a16d2f6a1ae4","year":2020},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.908499Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:63faa25900de2e5b0c980d9ba2a95daf7562b8161c31098516b866caaa05226e","observation_id":"e6ee0b65-6067-411d-a830-7c083de9670a","resolution":{"observed_at":"2026-08-07T15:42:54.530780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:54.043460Z","title":"Graph neural collaborative filtering with medical content-aware pre-training for treatment pattern recommendation.Pattern Recognition Letters, 185:210– 217,","venue":null,"work_id":"5322517a-8bfe-4fe8-8ebd-a0f9b9c7993a","year":2024},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:48.098212Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:19744bc41d28cdf011eca074a18288daa03a4ff74422ce9eb10aca91baf2f601","observation_id":"f7165ccb-5a5d-4e25-8a4a-857e7ac36e8d","resolution":{"observed_at":"2026-08-07T15:42:54.101661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:53.761049Z","title":"Pope, Soheil Kolouri, Moham- mad Rostami, Charles E","venue":null,"work_id":"68ff0ec1-1298-4754-9144-edca35962c38","year":2019},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:48.219194Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:3673f58b9a65ed4eff9604f59b441f8cbac89c58f3562d9419bc892803748063","observation_id":"7476c316-8f34-4c06-ac8f-0cd19acd35d3","resolution":{"observed_at":"2026-08-07T15:42:53.906720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.19519","last_updated":"2024-04-30T12:49:54Z","snapshot_observed_at":"2026-07-06T18:07:38.875884Z","submitted_at":"2024-04-30T12:49:54Z","title":"Generating Robust Counterfactual Witnesses for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2404.19519","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.19519","snapshot_observed_at":"2026-08-07T15:42:49.948585Z","title":"Generating Robust Counterfactual Witnesses for Graph Neural Networks","venue":"cs.LG","work_id":"fc4a2134-c36a-45ea-aeda-1128dc757788","year":2024},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:48.326548Z"},"links":{"cited_paper":"/paper/2404.19519","citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:44617d2162739006cbe6f7df9d2b2010452bbcd01e62a3d89e59bfd1e04df538","observation_id":"5e6d22ea-d2f6-4b77-b123-1c578c41ee8a","resolution":{"observed_at":"2026-08-07T15:42:50.116039Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:53.558050Z","title":"Graphvae: Towards generation of small graphs using variational autoencoders","venue":null,"work_id":"77453c71-afe7-4e7a-8309-5a0984b6c8db","year":2018},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:48.424115Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:5e6f79a00b44345eee53a292b2cedd4590a83930d12d7c1fbb9f0475bf3af91b","observation_id":"9b85fe0f-ad01-4ae2-81c4-7026c31b136b","resolution":{"observed_at":"2026-08-07T15:42:53.643001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:53.345605Z","title":"Wasserstein weisfeiler-lehman graph kernels","venue":null,"work_id":"0a74a1fb-f0d3-4d9f-a257-068ab66d8407","year":2019},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:48.595020Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:be3be1e81c6c1828e9daea5bbee89ac468afa6c542ca2b2dbeefecb889f3863d","observation_id":"fea3a0d6-7f6f-4fc3-8078-557d5babee44","resolution":{"observed_at":"2026-08-07T15:42:53.465267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:53.153702Z","title":"Graph attention networks.stat, 1050(20):10–48550,","venue":null,"work_id":"7622c9cf-7395-4152-ad34-08cab8d5158d","year":2018},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:48.667874Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:f5d89e6214b4081544e9467fa95ec8a5aad210f4b657bbb7be376862143a7423","observation_id":"39758b3c-3328-4c6e-b928-68f59b60d365","resolution":{"observed_at":"2026-08-07T15:42:53.247095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:52.906813Z","title":"Pgm-explainer: Probabilistic graphical model explanations for graph neural networks","venue":null,"work_id":"66193169-8d70-423c-b08b-d4efb9efb872","year":2020},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:48.747157Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:222b8b65147b27db390ef2f1465d9899f41ad7267ea16d786d7e43ad9623f9f2","observation_id":"22073dff-5102-497c-a33f-ccdc91fe5226","resolution":{"observed_at":"2026-08-07T15:42:53.033635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:52.594289Z","title":"Gn- ninterpreter: A probabilistic generative model-level expla- nation for graph neural networks","venue":null,"work_id":"c559ecda-fbb1-4b7a-aee0-3554b7c79a2f","year":2023},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:48.820827Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:63d7a116ed6e5853e02a18e77630bf5fa5d018c6ecef0d1a0182aeb98bdcfbef","observation_id":"52985295-7b0e-4848-950a-4f5e753ce453","resolution":{"observed_at":"2026-08-07T15:42:52.691136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:52.364742Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":"ff8a25cd-bfdb-4f2e-9317-aa8bfd01da3c","year":2021},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:48.957766Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:badb33279c2ea39a08c14dcc7c0931c057f3f02089d751e86d99247492bfe8a1","observation_id":"d9caacbc-6174-4732-b01e-0cba06a5c7cc","resolution":{"observed_at":"2026-08-07T15:42:52.463816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:52.089849Z","title":"Heterogeneous graph knowledge enhanced stock market prediction.AI Open, 2:168–174,","venue":null,"work_id":"928c513c-4f63-4c42-928f-61c013a06db9","year":2021},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:49.057084Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:3c88439e141fb76d463a024fb6d2a940476541c4c9d9a7e45b20562b404e5dbd","observation_id":"cf03edfb-1ce2-4b7a-9909-83d07149266d","resolution":{"observed_at":"2026-08-07T15:42:52.218890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:51.814340Z","title":"Adaptive hypergraph network for trust prediction","venue":null,"work_id":"f77f8b9f-45d9-467f-8b7f-0ba919907a7d","year":2024},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:49.142339Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:566e5d3a1cccca66b5cbc6bc2c4269547a4bde98f1c34fa0b2f2a4f8fb6a711a","observation_id":"4af47348-af29-42df-81fb-149bfd3b6fd4","resolution":{"observed_at":"2026-08-07T15:42:51.921546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:51.542250Z","title":"Gnnexplainer: Generating explanations for graph neural networks","venue":null,"work_id":"671e6b04-7747-444f-b760-6fd991f274dd","year":2019},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:49.235917Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:ada207c7e0a02d1ab94a6fad1ee5b3a314591a1f2a8894aac87a1c2d6eb8c5f6","observation_id":"d72b8c86-3d02-4d56-b5d6-5c0ede7f87c2","resolution":{"observed_at":"2026-08-07T15:42:51.699210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:51.319845Z","title":"Xgnn: Towards model-level explanations of graph neural networks","venue":null,"work_id":"2c63dee7-5190-47dc-8d2b-774769adc86a","year":2020},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:49.307980Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:9d7ca6e3d577b78b6ee0c2a5817ff36792a354f7bdd9af6d22d6ccc070ab4541","observation_id":"5614de41-d6ee-45e8-8be4-7bd31d70fa3a","resolution":{"observed_at":"2026-08-07T15:42:51.427196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:51.146112Z","title":"Research on graph neural network in stock market.Procedia Computer Science, 214:786–792,","venue":null,"work_id":"5994f487-ef30-4ed8-8649-49ed62b2d730","year":2022},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:49.393002Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:3f6ec30d971c707e5d96f3f1fda73886c397885a6becbbd76c28f809dc860d66","observation_id":"03fde2a3-f3c2-4c39-a8cc-10930b46cbc0","resolution":{"observed_at":"2026-08-07T15:42:51.222058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:50.960810Z","title":"Mixupexplainer: Generalizing explanations for graph neural networks with data augmentation","venue":null,"work_id":"8e65d202-19e1-45e0-af02-9ee5d89d2f4f","year":2023},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:49.475016Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:cd9490b24ac28c99208f095913c86dafa22ff6478fdd402af38978b019b70393","observation_id":"935bc60f-3ae7-4c00-8ce1-929d1ebecb11","resolution":{"observed_at":"2026-08-07T15:42:51.052441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:50.715098Z","title":"Domain disentanglement with interpolative data aug- mentation for dual-target cross-domain recommendation","venue":null,"work_id":"96a45a4d-5e7e-43a6-a42b-d0dfacca5776","year":2023},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:49.561696Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:00e3d8d4d369c9f196c6765b2e74b2b6e5f8e27f9edf76a7b7a262062dd60edc","observation_id":"bb3c4bc3-1910-4bf6-9715-5f43a814cd8c","resolution":{"observed_at":"2026-08-07T15:42:50.798423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:50.576826Z","title":null,"venue":null,"work_id":"c4c40ed3-f4e3-471f-9de7-49a93cdb531a","year":2000},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:49.666886Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:cf84b63f9c7402a70993984f95d43ccaff03d7aca3f0ac91479d47338248c65d","observation_id":"46fbd5b2-1224-47db-b31b-38d0ec707285","resolution":{"observed_at":"2026-08-07T15:42:50.650114Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:55.706237Z","title":"Hidden in plain sight: Subgroup shifts escape ood detection","venue":null,"work_id":"7d539ffb-1b0c-450e-b8cb-6f71bc07bfec","year":2022},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.196138Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:75ad1ff6368d1f13762625973a2978440ec136dc91a730159de7e1b7f9ff8c06","observation_id":"2663186a-1e4a-4bb5-ad95-b2766998a5eb","resolution":{"observed_at":"2026-08-07T15:42:55.773599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:55.853631Z","title":"Auto-encoding variational bayes.stat, 1050:1,","venue":null,"work_id":"3313813c-aed8-4568-8b8c-415e3ae8f54d","year":2014},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.147850Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:c3b2d53625a035ff857ae0f6960de430166f186ead8077324a0672b5ca7f3ed3","observation_id":"4a1cd1da-5755-4c6c-9762-50b1bf030489","resolution":{"observed_at":"2026-08-07T15:42:55.910272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:56.276809Z","title":"Deepnote-gnn: predicting hospital readmission using clin- ical notes and patient network","venue":null,"work_id":"1d45f35a-9537-4d8d-867f-3ed417b6ffed","year":2021},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:46.924745Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:c5cc4b7a7a1010439479f9fe3e1ad8f495f992ff0f21dce8a88ed84adf1fb023","observation_id":"baf62fbc-f8e9-4efd-bec5-51daf9701a68","resolution":{"observed_at":"2026-08-07T15:42:56.336286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:54.227936Z","title":"Adversarial learning targeting deep neural network classification: A comprehensive review of defenses against attacks","venue":null,"work_id":"5052ce87-f8ee-4e39-8ac1-435d4f8afa9a","year":2020},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:47.978089Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:2279f97a8d74406a2c9ee56c40523f074ecdc37815967417f102f162152e208b","observation_id":"042c0891-74ca-4955-bb16-3cd37a0ecf27","resolution":{"observed_at":"2026-08-07T15:42:54.329601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:56.989532Z","title":"Graphframex: Towards systematic evaluation of explainability methods for graph neural networks","venue":null,"work_id":"cb733c63-26f4-4706-a79d-20d65bf37b2f","year":2022},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:46.501326Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:2aebbf33dc1fda348a361e4a5ab0353e5242d2723b598332628e8de6d3bb3683","observation_id":"8bd7df21-6bfd-4341-b9d3-00bc59cfac9c","resolution":{"observed_at":"2026-08-07T15:42:57.132460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:56.814830Z","title":"Learning causally invariant representations for out-of-distribution generalization on graphs","venue":null,"work_id":"0d30e3b5-e71e-4929-8f6b-e5790db20c35","year":2022},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:46.550795Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:601bb0be7d50d6350b91b5da9b02b774eb6e804fa9b4d418177055fafa3c4ff4","observation_id":"dac57acf-e0a5-4310-8f8e-98d8d476f8d5","resolution":{"observed_at":"2026-08-07T15:42:56.902848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:57.310460Z","title":"Invariance principle meets information bottleneck for out-of-distribution gener- alization","venue":null,"work_id":"d242df7e-ac95-4b8c-88cc-77816819cdb2","year":2021},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:46.414375Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:f233dedda467ecc22ae26e970e64a96ebd40db13955a5a3f8d6a57f14ea7759f","observation_id":"2e0be9fc-0b50-4f34-bd9c-01cf0ac57f58","resolution":{"observed_at":"2026-08-07T15:42:57.401613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:56.548341Z","title":"Few-shot causal repre- sentation learning for out-of-distribution generalization on heterogeneous graphs.TKDE, 37(4):1804–1818,","venue":null,"work_id":"3db1e42b-201f-451b-bd1f-ec05da9acf25","year":2025},"citing_paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:46.730379Z"},"links":{"citing_paper":"/paper/2505.14005"},"observation_digest":"sha256:135ed273ad405a055862782beceeea1842cb65ac8baa8952da4484d2858cd6a2","observation_id":"373072b4-85f0-47da-8adc-0f3ffc710b31","resolution":{"observed_at":"2026-08-07T15:42:56.613506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.14005","last_updated":"2025-05-23T07:00:19Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T15:40:26.234370Z","submitted_at":"2025-05-20T07:01:47Z","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":1,"verified_fuzzy":33},"total_outbound_references":38},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2505.14005."}