{"as_of":"2026-08-24T01:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b7c1bc14f6d376d118dbcbc5611aab3b1a235bf005bb39c7d4b4fe17fc8e235a","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:16:10.112592Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T18:16:53.701080Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-12T05:26:23.605615Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.22252","snapshot_observed_at":"2026-08-05T18:16:53.701080Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15015","last_updated":"2025-08-20T19:15:53Z","snapshot_observed_at":"2026-08-20T17:16:13.633665Z","submitted_at":"2025-08-20T19:15:53Z","title":"Fragment-Wise Interpretability in Graph Neural Networks via Molecule Decomposition and Contribution Analysis","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-05T18:16:53.701080Z"},"links":{"cited_paper":"/paper/2505.22252","citing_paper":"/paper/2508.15015"},"observation_digest":"sha256:ea7fc5d44522a795a993292ef48987842c6d042f7e2ef873dbae398e8626c414","observation_id":"5552bf49-d28f-4d7c-9d67-e3fff47cecb8","resolution":{"observed_at":"2026-08-05T18:16:53.701080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"cited_work":{"arxiv_id":"2505.22252","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.22252","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2505.22252 , year=","venue":null,"work_id":"654e7877-6cd5-495f-b115-e3988e589290","year":null},"citing_paper":{"arxiv_id":"2605.10230","last_updated":"2026-05-11T09:06:42Z","snapshot_observed_at":"2026-08-15T19:28:41.332367Z","submitted_at":"2026-05-11T09:06:42Z","title":"FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-05-12T05:25:48.965001Z"},"links":{"cited_paper":"/paper/2505.22252","citing_paper":"/paper/2605.10230"},"observation_digest":"sha256:1166d4d99457a29d6da37cc30ef9b4a00bee7586303b48302b25cbac36d9f0e6","observation_id":"5dad0f9a-b241-42c7-8858-01f7a37b7bb8","resolution":{"observed_at":"2026-05-12T05:26:23.608604Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.22252","snapshot_observed_at":"2026-07-11T16:37:28.727065Z","title":"B-xaic dataset: Benchmarking explainable ai for graph neural networks using chemical data.arXiv preprint arXiv:2505.22252, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04600","last_updated":"2026-07-06T02:03:39Z","snapshot_observed_at":"2026-08-13T05:13:50.149781Z","submitted_at":"2026-07-06T02:03:39Z","title":"Measuring What Matters: A Unified Evaluation Framework for GNN Explainability","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-11T16:37:28.727065Z"},"links":{"cited_paper":"/paper/2505.22252","citing_paper":"/paper/2607.04600"},"observation_digest":"sha256:705cf6b9ff0b4877db478b44428ccc4e404f39b47b45e5ceaf8e356e7c4b86f0","observation_id":"2d1cb0d3-b77a-4a32-8d19-ee042c2580a7","resolution":{"observed_at":"2026-07-11T16:37:28.727065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.22252/citation-record","integrity":"/paper/2505.22252/integrity","json":"/paper/2505.22252/citation-record.json","paper":"/paper/2505.22252"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:20.138739Z","title":"Towards a unified framework for fair and stable graph representation learning","venue":null,"work_id":"cfc002f3-9f1c-4d7a-8931-b56c04c41eb5","year":2021},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:04.386105Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:11595c065e485b10c9df480460172d354b2dea557dcc6ff0276443e5975be580","observation_id":"7c0fca69-feba-4dd5-9680-8dd64834cd12","resolution":{"observed_at":"2026-08-07T13:16:20.211068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:19.986732Z","title":"Evaluating explainability for graph neural networks.Scientific Data, 10(144), 2023","venue":null,"work_id":"09a8cfd6-eeb4-412a-93d1-5f3909de1ad0","year":2023},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:04.502685Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:edc315894bdd6f149a2431155c26f2c2814a36339a620bbc0aeab796fb5ad5f2","observation_id":"d301e0da-0439-4169-a1c4-72abf055bda7","resolution":{"observed_at":"2026-08-07T13:16:20.060107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:19.795538Z","title":"Graphframex: Towards systematic evaluation of explainability methods for graph neural networks, 2022","venue":null,"work_id":"7aae60c7-6ca3-485d-bd9d-1e4b1eb6be1b","year":2022},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:04.596180Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:cc8c768968ef539fa47abd14ab8d6e47f2fa9a6869614777a67f7fe80c8b99f3","observation_id":"eb825d5c-ddbe-4fb7-b72b-4d77e8c35772","resolution":{"observed_at":"2026-08-07T13:16:19.877230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:19.586370Z","title":"Global explainability of gnns via logic combination of learned concepts","venue":null,"work_id":"083a1f17-4d23-458a-b1b3-f291c315c94b","year":2023},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:04.681907Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:c1ec92bdea6cdaac6275bc309d22b3bd66498d96e294df9055fc3ebe03737513","observation_id":"9eba9748-ef9f-44c7-93e0-115cda667e22","resolution":{"observed_at":"2026-08-07T13:16:19.682513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:19.382962Z","title":null,"venue":null,"work_id":"d6c74198-110c-45cf-9c56-64bdbdc61221","year":2010},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:04.761022Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:ece5968e379e4cacf74898428a41d0387ef6f124e8d2115817d0705d020dab96","observation_id":"fef99660-a879-488c-a6e4-5fae7968a2f7","resolution":{"observed_at":"2026-08-07T13:16:19.449285Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:19.153437Z","title":"Robust counterfactual explanations on graph neural networks","venue":null,"work_id":"7645adb8-a929-494c-8565-0b64f6ec08ba","year":2021},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:04.859015Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:bb032195504622f45184f9795daed7c53e84598d70b5fb5a4fd65e4bb0d339b8","observation_id":"aa7c130d-1e5d-4a41-be3b-768a23215942","resolution":{"observed_at":"2026-08-07T13:16:19.279504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:18.970511Z","title":"Borgwardt, Cheng Soon Ong, Stefan Schönauer, S","venue":null,"work_id":"e83183d2-56a6-4aaa-8255-6534884059df","year":2005},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:04.928712Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:585c8ec2fb9d1dcaefdd5e76c87657a63d6c96adcae1956ae342924deec01d68","observation_id":"46f1312a-1d14-4a79-a71e-e69a6f077675","resolution":{"observed_at":"2026-08-07T13:16:19.059347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:18.797091Z","title":"Grease: Generate factual and counterfactual explanations for gnn-based recommendations, 2022","venue":null,"work_id":"5207fc8f-6d96-46ef-80b1-e2ec80692568","year":2022},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.011768Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:eabe83fb12b1f96d096e88b3c7ea526e6b6c2102b7104cd63947756493326c02","observation_id":"44e3b3ce-3628-4ad5-b208-5da3b205174e","resolution":{"observed_at":"2026-08-07T13:16:18.877504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:18.528430Z","title":"Bronstein, Emanuele Rodolà, Luca Rossi, and Andrea Torsello","venue":null,"work_id":"7fd9349b-68d3-4450-b427-13d7f81f9ce4","year":2025},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.080853Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:efe721f27ed0109ca5af84bfef467cf6a4569600f5931d387ab97f0f811fb27f","observation_id":"7f124b9a-6a28-4b5a-bd6b-823224463ec1","resolution":{"observed_at":"2026-08-07T13:16:18.638967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:18.291951Z","title":"Towards self-explainable graph neural network, 2021","venue":null,"work_id":"17c0d15a-1598-41ed-bf92-7f2ffd96e42a","year":2021},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.158119Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:a00af5d2fb23c0a2bc5abbdf1659837e5d5a3120eb7ab744650e107c759ae317","observation_id":"b507842b-8742-4007-893f-6cba5447f9b3","resolution":{"observed_at":"2026-08-07T13:16:18.409174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:18.052821Z","title":"Lopez de Compadre, Gargi Debnath, Alan J","venue":null,"work_id":"f2cd1523-9430-43aa-a266-39a82519a705","year":1991},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.239102Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:4686ac3445765f6c425537ac65264a5f7587d4d27d38aa2f4f1c692140d5956c","observation_id":"b73aa34f-cc1d-4de4-a799-f49d6b2f83bb","resolution":{"observed_at":"2026-08-07T13:16:18.143313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2502.09340","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:10.394644Z","title":"This looks like what? challenges and future research directions for part-prototype models.ArXiv preprint, abs/2502.09340, 2025","venue":null,"work_id":"ad8de05b-3b2e-413c-8b1f-05b48a297ec9","year":2025},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.330207Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:761dfeac156d0603250239cf41447001bc81e590cbf0ebb745cdedc8ad0a6e2f","observation_id":"b909cb39-4d9a-466a-871f-8f4a2e0fc8ce","resolution":{"observed_at":"2026-08-07T13:16:10.495766Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:17.868556Z","title":"Moghaddam, and Roger Wattenhofer","venue":null,"work_id":"5f07c17b-c257-4bda-879b-e0efd151c092","year":2021},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.418228Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:6dd2acb1a94c5b34e37a60c5b42ec3f1ea4921293180acff11c4868b044e3dfc","observation_id":"f8caaf4f-e3e7-4de2-9e61-6051459ccb83","resolution":{"observed_at":"2026-08-07T13:16:17.957164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:17.665530Z","title":"Kergnns: Interpretable graph neural networks with graph kernels","venue":null,"work_id":"86aaff16-8656-4390-b5f7-c3e018fa02d1","year":2022},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.496092Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:62f4e352668439d031647c22ad4dd44cd2a4273a86f8ad617aacdc2443eb01e2","observation_id":"9870d258-f7d7-4e43-8f89-b0e9f194640e","resolution":{"observed_at":"2026-08-07T13:16:17.737714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:05.572477Z","title":"Chembl: a large-scale bioactivity database for drug discovery.Nucleic acids research, 40(D1):D1100–D1107, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.572477Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:204dcad5ba23eb2a22f4664198c3f0cc9bef0ba46177565fe826c391779ffe46","observation_id":"937a4ce5-2a44-4a85-900f-644026406b5e","resolution":{"observed_at":"2026-08-07T13:16:05.572477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:05.664197Z","title":"Drug discovery with explainable artificial intelligence.Nature Machine Intelligence, 2(10):573–584, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.664197Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:2012db94fd9dcb4b0eca6c396458afc454345f011167abe1fa9c2c6fa29bcd23","observation_id":"25aba738-9ccd-4f6f-98e7-21897d20eab2","resolution":{"observed_at":"2026-08-07T13:16:05.664197Z","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":"2026-08-07T13:16:17.471306Z","title":"A survey on explainability of graph neural networks, 2023","venue":null,"work_id":"1acfb450-da95-4183-a7e5-03bda52f7026","year":2023},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.756027Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:fcb9d5bfbafd18267662b036289e102fb81770fc74c62b3708da2e4f9329ed65","observation_id":"7dc29b15-2507-4cc2-a6b6-3e066fad2ab8","resolution":{"observed_at":"2026-08-07T13:16:17.555316Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:05.849965Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.849965Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:139ef9df2f9f49ced6ed266ba25f0bbb1be344a8590aacb8865b2d81a62dfe7e","observation_id":"bc20b512-8255-4de7-a2f3-c02c24bd8d4b","resolution":{"observed_at":"2026-08-07T13:16:05.849965Z","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":"2026-08-07T13:16:17.309248Z","title":"Taylor, and Mohamed R","venue":null,"work_id":"4411b2d0-4ad9-4d1c-8485-b46d2d40a6e5","year":2019},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:05.929014Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:a48cb59cccc2dc7bd9f8006bb5057996350a407517cf5ff7405c2df5bbc58463","observation_id":"0f8ae1d5-af75-4f90-840d-f1dc6a72ba92","resolution":{"observed_at":"2026-08-07T13:16:17.387170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:17.136713Z","title":"Explaining the explainers in graph neural networks: a comparative study.ACM Computing Surveys, 57(5):1–37, January 2025","venue":null,"work_id":"49044348-8d63-4ce2-9ff3-ba8f545a118f","year":2025},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.008053Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:459e370f73a376a33efea58927e4140c80b2a2d41e6f9f0ca543e332b3fffa1f","observation_id":"41adfcff-af5c-4d62-9722-0185b3cec1db","resolution":{"observed_at":"2026-08-07T13:16:17.221465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:16.977263Z","title":"ter Hoeve, Gabriele Tolomei, Maarten de Rijke, and Fabrizio Silvestri","venue":null,"work_id":"a0910627-f280-40f2-bbd2-11a0bf37dc66","year":2022},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.133204Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:1881c1eb0f3e8411840d920a8aedf68cf7346ea989147f06827f08efb7d7b227","observation_id":"adb1030c-abee-4156-9a8d-22703f003f44","resolution":{"observed_at":"2026-08-07T13:16:17.062309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:16.787251Z","title":"Parameterized explainer for graph neural network","venue":null,"work_id":"b7801b97-975e-4958-8150-4d5bcd34c8c4","year":2020},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.233732Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:4595774dd7100af69db61f62b3d5a9fc4f8b7c90e30a5e779083e83da3a6d584","observation_id":"80766479-11b4-4cc2-bf4e-2b5051553916","resolution":{"observed_at":"2026-08-07T13:16:16.889213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:16.592231Z","title":"Salient deconvolutional networks","venue":null,"work_id":"259f343e-77ef-4448-b912-1f1e60b5834e","year":2016},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.339089Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:3261f850aba41a3985123d3163cefc107fa720f8e78ec62ba8e1c33fae8d6648","observation_id":"20c851e1-df65-4053-a2b8-78b264eec199","resolution":{"observed_at":"2026-08-07T13:16:16.685420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:16.428493Z","title":"Teixeira, Luis Pinheiro, and Andre O","venue":null,"work_id":"f22c356c-5825-495e-960b-13ed8861d6b7","year":2012},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.421064Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:7cde29d857ec7fce94d590b8e6cbbd84b253efd8365d2ebb3568a5a63d0f50f5","observation_id":"6ce81439-ecb5-473b-9691-1b99f9c5652f","resolution":{"observed_at":"2026-08-07T13:16:16.499273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:16.214506Z","title":"Deeptox: Toxicity prediction using deep learning.Frontiers in Environmental Science, V olume 3 - 2015, 2016","venue":null,"work_id":"0bbaf87f-3b22-4312-97f2-d5f2e2660653","year":2015},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.518156Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:4717a7dae503e2f013e2eb1e4e6dba73966ba58b2777f318cd9fccd342727628","observation_id":"65854b85-065b-47d4-8f52-4d101deed0e7","resolution":{"observed_at":"2026-08-07T13:16:16.302829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:16.033133Z","title":"Brenner, and Lucy J","venue":null,"work_id":"eb4a97f1-6441-4776-8db9-ba5af588224a","year":2019},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.595006Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:8531fcd6cf7abba89ee4a1a4c902e08668191596553b7e96449621ec430145c2","observation_id":"33c228f7-1e1b-447b-87f0-bfa5cd47917f","resolution":{"observed_at":"2026-08-07T13:16:16.117420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:15.878844Z","title":"Interpretable and generalizable graph learning via stochastic attention mechanism","venue":null,"work_id":"89942593-ca98-49b3-8db6-6998e064a5c1","year":2022},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.675092Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:c3e58250beab43b23286f1e504b27bcf69afff7b4ebef5760218db8b5d382bc0","observation_id":"9092d9cb-0aca-4cf1-9992-206f19586e48","resolution":{"observed_at":"2026-08-07T13:16:15.951041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:15.776856Z","title":"From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable ai.ACM Computing Surveys, 55(13s):1–42, July 2023","venue":null,"work_id":"171564f9-2cc1-4f99-9176-44ae7cde131a","year":2023},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.772591Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:32e23862c88f8bae119a83c4ccc0a78fe69e68814e735317d807dcab75dad8a0","observation_id":"a1cf07bf-1b46-4bfe-a1a2-0573f12fabe1","resolution":{"observed_at":"2026-08-07T13:16:15.828329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:15.606869Z","title":"Progrest: Prototypical graph regression soft trees for molecular property prediction","venue":null,"work_id":"0b6c81dc-ee0b-4be6-9eb5-59ccc3b8a41b","year":2023},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.840524Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:cee487ee1cf81e1eb0923569f67381cdb9de657be2ad6fbd86e90734eebd6304","observation_id":"564f3d29-a868-40e4-99af-256100ebc176","resolution":{"observed_at":"2026-08-07T13:16:15.724269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:15.344296Z","title":"Wei, Brian K","venue":null,"work_id":"54c90256-5c49-4b32-a30e-f2e6c689a292","year":2020},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.864870Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:3768d0c0073c574f200d7241a58d3e5e6bf5f21c76f5097090db2dd95f8d8584","observation_id":"846c3061-e08d-4421-a584-e418bdb4a806","resolution":{"observed_at":"2026-08-07T13:16:15.502760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:15.078472Z","title":"Interpreting graph neural networks for NLP with differentiable edge masking","venue":null,"work_id":"50162e2e-878c-4f67-b1ec-fded4ee70ae1","year":2021},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:06.972419Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:3f7b0dad5a372168e911519255c46cf6fdd177fee07179a60a64e737e0d6e2b0","observation_id":"31fb0198-b5d1-4674-a6f8-d866ce9b98a8","resolution":{"observed_at":"2026-08-07T13:16:15.186589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:14.840664Z","title":"Not just a black box: Learning important features through propagating activation differences, 2016","venue":null,"work_id":"eb90b438-6a8b-4160-afdf-42529bcdc42d","year":2016},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:07.083432Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:a5660cf38b0dd8877514fb80093539aa96ca11bb8b3fe7b504b724dd770801ec","observation_id":"4077a532-1114-4dff-9544-570b5c43b933","resolution":{"observed_at":"2026-08-07T13:16:14.976099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:07.259470Z","title":"Deep inside convolutional networks: Visualising image classification models and saliency maps, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:07.259470Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:8fb697259b7d3bd350b83b74d6299270b1b0c8e269f20227e449ea1cd595f0ee","observation_id":"54872920-84c0-4fce-9872-7f96aab5afe1","resolution":{"observed_at":"2026-08-07T13:16:07.259470Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:07.371311Z","title":"Striving for simplicity: The all convolutional net, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:07.371311Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:1d913bd8329c7192c8468c5b5cd333f9a9b4c5e6918bc0f95155a97f5f3424da","observation_id":"c83d4aa9-e7f1-4fa7-beca-28bd6923be4a","resolution":{"observed_at":"2026-08-07T13:16:07.371311Z","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":"2026-08-07T13:16:14.556398Z","title":"An efficient explanation of individual classifications using game theory.J","venue":null,"work_id":"96aca1af-3fe9-4c19-b0db-756b84da42f3","year":2010},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:07.538978Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:17ea7865fbb43ce7340ad475e8b65520d9cf1b87062620a8e91fc4c3e9cde05c","observation_id":"275519e0-f619-476e-b6b4-ab61cdaa7d60","resolution":{"observed_at":"2026-08-07T13:16:14.630520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:14.296565Z","title":"Axiomatic attribution for deep networks","venue":null,"work_id":"0736a5c9-b2f7-4f0d-99c1-db0d87503756","year":2017},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:07.719704Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:19a5787a5d9b4533112ecb58f46800c7dc54c55802bb5b3e0bb2dc24cb8e127a","observation_id":"457739a4-e7e5-4a76-a10d-a210650e585c","resolution":{"observed_at":"2026-08-07T13:16:14.435971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:14.058272Z","title":"Learning and evaluating graph neural network explanations based on counterfactual and factual reasoning","venue":null,"work_id":"e43abb22-b5a9-48ad-a254-a7713ccb34d9","year":2022},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:07.854045Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:b3c9db65b2b36f366d49e370d91fdd3eaaed4ad9e40ee6e8376624e505dd00bd","observation_id":"0c5ec07e-7bf5-426e-9689-d292a2467f60","resolution":{"observed_at":"2026-08-07T13:16:14.174894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:08.009325Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:08.009325Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:60232269ce802a32beb7a14e536474efa2e3d7c34e55a75a120a8a626605c40a","observation_id":"b6ea281f-e997-43bf-ac1a-2453b82a0431","resolution":{"observed_at":"2026-08-07T13:16:08.009325Z","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":"2026-08-07T13:16:13.801972Z","title":"Comparison of descriptor spaces for chemical compound retrieval and classification","venue":null,"work_id":"bb96aad8-ada8-44f2-a9a9-c873bf28559e","year":2006},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:08.157190Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:c17a28a624a2a00bebb96abf2bd43135bd753be9751ab4e480051750372130f4","observation_id":"98dff3ce-e80e-451e-a863-7fb730620aa5","resolution":{"observed_at":"2026-08-07T13:16:13.912930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:08.284573Z","title":"A compact review of molecular property prediction with graph neural networks.Drug Discovery Today: Technologies, 37:1–12, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:08.284573Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:1e1805c8a8e085eeec59c2c98ef0c2e2727b6daa5e74efd6a93d67bcda9979f9","observation_id":"618c6ce9-4ac7-4b7f-baf3-538b2b783a24","resolution":{"observed_at":"2026-08-07T13:16:08.284573Z","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":"2026-08-07T13:16:13.547983Z","title":"Graph information bottleneck","venue":null,"work_id":"49ce521d-c1e1-488d-8c31-94bb21e17306","year":2020},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:08.487480Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:ee5957145b22482cae102245775a2234734f70f64ee276761383601be5ab649f","observation_id":"4e1db634-375d-40bf-93ca-c3a6d5abda4f","resolution":{"observed_at":"2026-08-07T13:16:13.614375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:13.278715Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":"ef5231fd-db51-4a1b-8091-ee0df0f6b144","year":2022},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:08.649140Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:9f2c7d2ee6b01f434380cdb9457fa5413716c1e1c470239db951c47baa174e0b","observation_id":"c9f12ccd-8675-432c-8d2c-cce4f56df083","resolution":{"observed_at":"2026-08-07T13:16:13.387615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:13.127552Z","title":null,"venue":null,"work_id":"f43f6292-ce5a-4f97-8c21-3e83b1cc85dd","year":2023},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:08.765210Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:3fbfdacce3fa3ec9014081faa853eb931f64738d0c32a4c7f35df6bff7da7538","observation_id":"1b723c4a-7364-4003-8a35-ba0a51a1408f","resolution":{"observed_at":"2026-08-07T13:16:13.177694Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:16:08.892093Z","title":"How powerful are graph neural networks? In7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:08.892093Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:f2c0bf40d9974977b943e03a675f610b6aa15482a0690b1c165cd8fc51b94fcf","observation_id":"1f3ac4c5-8dc8-460b-82f7-6ea12c700f5e","resolution":{"observed_at":"2026-08-07T13:16:08.892093Z","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":"2026-08-07T13:16:12.917739Z","title":"Gnnexplainer: Generating explanations for graph neural networks","venue":null,"work_id":"1fbcf956-e79c-4189-8f34-e2305c0f5362","year":2019},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:09.074817Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:c44f522bfcff227e0eb8eeaefdc5087bc91738e3923f84aa8ece793a27b0e3b8","observation_id":"687b0372-f4f4-48f8-b706-66317f0eab44","resolution":{"observed_at":"2026-08-07T13:16:13.030038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:12.713735Z","title":"Improving subgraph recognition with variational graph information bottleneck, 2021","venue":null,"work_id":"6dfa5333-e2ee-496e-b4ea-9bdec195aa1a","year":2021},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:09.230958Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:d2444a1205fce6a0e9219a33a4948bb934eac1d1cc4476b3fda83892ba0f08cf","observation_id":"1dd2f868-1b5c-4809-92ae-087b9faae4e7","resolution":{"observed_at":"2026-08-07T13:16:12.805030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:12.488026Z","title":"Explainability in graph neural networks: A taxonomic survey, 2020","venue":null,"work_id":"6b3d0c71-d918-42e5-89c3-a94a2fcfb1f0","year":2020},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:09.416521Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:58bb3658b2d1819b395041d2ae26b03264766e01b6019950c9173b4fdc09aab9","observation_id":"b3a5bf9b-db75-4157-ada8-7e567e55b553","resolution":{"observed_at":"2026-08-07T13:16:12.623727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:12.176969Z","title":"On explainability of graph neural networks via subgraph explorations","venue":null,"work_id":"0a2a68bd-e04b-4911-897d-8cf28431f28c","year":2021},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:09.582150Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:23672d60b890ce0b8278eea1e13c5252644212d44831d38bf2d8a36a3cb4f41c","observation_id":"e0497b8c-33ec-4f5e-9ecf-a462190dedca","resolution":{"observed_at":"2026-08-07T13:16:12.332849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:11.830141Z","title":"Relex: A model-agnostic relational model explainer, 2020","venue":null,"work_id":"4b88b009-d6fb-4434-b8d5-a76d2c384160","year":2020},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:09.713224Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:173bd1c948a68e27df45fd2100d8ed443b6b4074bce656d7d506d557750f7373","observation_id":"b81336a9-bb4d-4cab-b28a-60ed48a1ffdb","resolution":{"observed_at":"2026-08-07T13:16:12.019121Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:11.460373Z","title":"Protgnn: Towards self-explaining graph neural networks","venue":null,"work_id":"f3994330-80ea-4323-bb32-233fd5676463","year":2022},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:09.845155Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:944b38c1957fab0b56624a4d3c83673ce10617379d2a250eb556e6aa34e1d91b","observation_id":"7f239a30-c7f4-4ae1-a91d-d90cd56d54e1","resolution":{"observed_at":"2026-08-07T13:16:11.607723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:10.981300Z","title":"Towards robust fidelity for evaluating explainability of graph neural networks","venue":null,"work_id":"7f1e4251-f6a6-47c2-8b6a-d20c25553709","year":2024},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:09.952316Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:1be91a4690a67a8825c6546f2d5d2fe3fbc443f6ae0283e3612ba78b50625271","observation_id":"2554e687-fccc-4d97-8664-9214b0d32308","resolution":{"observed_at":"2026-08-07T13:16:11.196514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-07T13:16:10.684377Z","title":"13 A Full Evaluation Results Here we provide the full set of results that were shown partially in the main paper","venue":null,"work_id":"4073aacf-1b73-4c1e-947a-a55b1571b2e0","year":2024},"citing_paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T13:16:10.112592Z"},"links":{"citing_paper":"/paper/2505.22252"},"observation_digest":"sha256:31052a303609606fe44035b443b2d086f5ec807432fac51d0b159507de160682","observation_id":"d3bee00d-c55d-4102-899c-7e227f6072a1","resolution":{"observed_at":"2026-08-07T13:16:10.815127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.22252","last_updated":"2025-05-28T11:40:48Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-22T16:35:53.710778Z","submitted_at":"2025-05-28T11:40:48Z","title":"B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":1,"verified_fuzzy":41},"total_outbound_references":52},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 24 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 3 inbound Pith citation observations for arXiv:2505.22252."}