{"as_of":"2026-08-15T06:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0ff77fd02068c87546d6e069af1a74a7865b0046e416a48a5aed906fd2bd1a49","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T05:24:03.972289Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T11:32:26.736665Z","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":"2026-05-19T13:12:18.291600Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00521","snapshot_observed_at":"2026-08-09T11:32:26.736665Z","title":"A self-explainable heterogeneous gnn for relational deep learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.02719","last_updated":"2025-06-25T09:52:40Z","snapshot_observed_at":"2026-08-15T00:01:57.413528Z","submitted_at":"2025-02-04T21:08:23Z","title":"Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-09T11:32:26.736665Z"},"links":{"cited_paper":"/paper/2412.00521","citing_paper":"/paper/2502.02719"},"observation_digest":"sha256:e8849fe459facc1d814f24b9a55c5317389b5f34f8d898888e41784765dcba99","observation_id":"6f46bc88-8c32-4eda-ac08-d2c5a2642f48","resolution":{"observed_at":"2026-08-09T11:32:26.736665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"cited_work":{"arxiv_id":"2412.00521","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.00521","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A self-explainable heterogeneous gnn for relational deep learning","venue":null,"work_id":"d632bc50-7cc5-4356-829a-a2467fe03de6","year":2024},"citing_paper":{"arxiv_id":"2505.23875","last_updated":"2025-05-29T12:59:36Z","snapshot_observed_at":"2026-08-11T02:23:58.701113Z","submitted_at":"2025-05-29T12:59:36Z","title":"A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-05-19T13:10:12.353451Z"},"links":{"cited_paper":"/paper/2412.00521","citing_paper":"/paper/2505.23875"},"observation_digest":"sha256:0ffccb186a0d8bd7b17de7974d6cfbb34f8fcee69348cd64dff4ba5674b62ce8","observation_id":"d7666ef6-441e-4a4f-86ce-e131f4eeabbd","resolution":{"observed_at":"2026-05-19T13:12:18.294071Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.00521/citation-record","integrity":"/paper/2412.00521/integrity","json":"/paper/2412.00521/citation-record.json","paper":"/paper/2412.00521"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:24:05.426600Z","title":"Evaluating explainability for graph neural networks","venue":null,"work_id":"dfcfd98c-8753-4e2f-97fb-803fa87aa2c7","year":2023},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.661212Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:9be01391abc943d2320b436b21ee69c0c3da1042893fcf8369fc85f6d4f027a9","observation_id":"4a23a098-8e97-4496-aa8b-515955a3bd33","resolution":{"observed_at":"2026-08-12T05:24:05.434623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:05.404677Z","title":"Graphframex: Towards systematic evaluation of explainability methods for graph neural networks","venue":null,"work_id":"ecfc5b63-85bb-47e1-b2c4-6ea1a410526f","year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.668945Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:183b9207e75d86172b9c6eae0240799d564531e6e9347013b699d48d61b287ce","observation_id":"63eae07d-e846-4a88-adcb-55554ab94270","resolution":{"observed_at":"2026-08-12T05:24:05.411798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:05.379381Z","title":"GI nx-eval: Towards in-distribution evaluation of graph neural network explanations","venue":null,"work_id":"ebcc97d5-e4be-418c-9f38-e8cb38264536","year":2023},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.675477Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:ad6db639b8211f978770ce0a1644ca6e5c0ec2f30d1a86766ca4c07ad82623a1","observation_id":"8460b0c8-c989-4a92-ba16-3e99ce7e64d4","resolution":{"observed_at":"2026-08-12T05:24:05.387708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:03.682858Z","title":"Global explainability of gnns via logic combination of learned concepts","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.682858Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:916fa5e43f835f00dfa69bbe18122fed814fca2669347a2a43be8b31d9c762e4","observation_id":"f7f5e97f-e752-41eb-886e-3d0766391699","resolution":{"observed_at":"2026-08-12T05:24:03.682858Z","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":"2026-08-12T05:24:05.338950Z","title":"Reconsidering faithfulness in regular, self-explainable and domain invariant GNN s","venue":null,"work_id":"8c02db1c-da07-435e-aaca-0c87aa485d08","year":2025},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.688926Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:3ed4ce033d54283b6dde10583267e883f95ec9e80a4771e586ffbd8ebfca6e24","observation_id":"06205351-6936-494c-8db4-49067fae42fd","resolution":{"observed_at":"2026-08-12T05:24:05.348430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:03.695367Z","title":"Interaction networks for learning about objects, relations and physics","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.695367Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:7996b1d56666c9b16f9849547d84a27d1eab69c45d750ecf48f73fe4b730712d","observation_id":"37f856d7-e13d-4d95-a7e4-75725ed9f108","resolution":{"observed_at":"2026-08-12T05:24:03.695367Z","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":"2026-08-12T05:24:05.299737Z","title":"Simple decision forests for multi-relational classification","venue":null,"work_id":"bf2ca95c-285f-472e-912d-de1952e46fea","year":2013},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.702467Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:fa40bded0c4d68544ff997cd118870b35d6e4d4820edb7c38abc35ffb2e1c3c5","observation_id":"cbcb4112-4c2e-4a65-94d7-194fa7085ccb","resolution":{"observed_at":"2026-08-12T05:24:05.307324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:03.709698Z","title":"Megnn: Meta-path extracted graph neural network for heterogeneous graph representation learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.709698Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:3fa2e62dd8917a8ced5b6e17ef1c07dd8a0aa843101b009805e3dcd83518d061","observation_id":"6cfd30be-454f-4253-b23b-82c555f924d3","resolution":{"observed_at":"2026-08-12T05:24:03.709698Z","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":"2026-08-12T05:24:05.273089Z","title":"D4explainer: In-distribution explanations of graph neural network via discrete denoising diffusion","venue":null,"work_id":"26ac0bf7-4299-4eb2-88c4-4ef5e34e0176","year":2024},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.716437Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:8baf3277f0467ee132a245438371aff4ed46ea502100ad4714752081e8017f94","observation_id":"5bb37944-898c-4c85-9a5d-b819be2b8446","resolution":{"observed_at":"2026-08-12T05:24:05.284161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.15096","last_updated":"2023-08-29T08:04:45Z","snapshot_observed_at":"2026-08-13T10:25:12.195948Z","submitted_at":"2023-08-29T08:04:45Z","title":"How Faithful are Self-Explainable GNNs?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.15096","snapshot_observed_at":"2026-08-12T05:24:03.723200Z","title":"How faithful are self-explainable gnns? arXiv preprint arXiv:2308.15096, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.723200Z"},"links":{"cited_paper":"/paper/2308.15096","citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:7533d3d8dd08c697a70d03a621b90cbcb711494379e9383ba32999dabfc10c8a","observation_id":"39e04d27-9dc6-4771-9818-ed3971e0895d","resolution":{"observed_at":"2026-08-12T05:24:03.723200Z","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":"2026-08-12T05:24:05.243277Z","title":"A density-based algorithm for discovering clusters in large spatial databases with noise","venue":null,"work_id":"10321af5-815f-462a-b302-d8816bdd8c2e","year":1996},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.729072Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:a4a7a572c27356df71847f294121867f383e2831bb907aa04eeb514cc6d31942","observation_id":"b1c1dd75-7d39-40fe-9fd0-71680e4f0048","resolution":{"observed_at":"2026-08-12T05:24:05.250667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:05.217356Z","title":"Meta-path learning for multi-relational graph neural networks","venue":null,"work_id":"ac72c06e-92d5-4032-b624-9c0ab95cf2e3","year":2024},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.734612Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:90637e816e423462d3928f44501ed27e8064b99a141d64ba10114b163a2a1f45","observation_id":"d7eb4194-94a0-49d1-9d5a-c7b60fab3059","resolution":{"observed_at":"2026-08-12T05:24:05.225326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.04615","last_updated":"2023-12-07T18:51:41Z","snapshot_observed_at":"2026-08-13T05:07:43.941227Z","submitted_at":"2023-12-07T18:51:41Z","title":"Relational Deep Learning: Graph Representation Learning on Relational Databases","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.04615","snapshot_observed_at":"2026-08-12T05:24:03.741546Z","title":"Relational deep learning: Graph representation learning on relational databases, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.741546Z"},"links":{"cited_paper":"/paper/2312.04615","citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:72e6db5af69ee31b2438de4b5f741938fa153d3dac3e6179b8a11cbfd5f317d9","observation_id":"f16d605f-c888-44bb-a347-444e41037faa","resolution":{"observed_at":"2026-08-12T05:24:03.741546Z","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":"2026-08-12T05:24:05.034263Z","title":"A review of multi-instance learning assumptions","venue":null,"work_id":"f60fddc4-9103-4b24-8ccf-e0ddbe3e2fc5","year":2010},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.747385Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:3ec11cca580e9f5f83515b9829548e9367fbbd832bda9498adda0658f60be279","observation_id":"a9b5d29a-66c5-42e7-8192-9a609d4a4e11","resolution":{"observed_at":"2026-08-12T05:24:05.196873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:03.753712Z","title":"Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.753712Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:6f4fa66bf87e572f69a2227d8e99f17f643adbde56df50a3b5169814e78ed957","observation_id":"882af10f-f8a7-4d25-88ae-5bbd32f33023","resolution":{"observed_at":"2026-08-12T05:24:03.753712Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.05674","last_updated":"2017-06-20T01:33:33Z","snapshot_observed_at":"2026-08-14T20:53:20.910341Z","submitted_at":"2017-06-18T15:53:59Z","title":"Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.05674","snapshot_observed_at":"2026-08-12T05:24:03.759138Z","title":"Knowledge transfer for out-of-knowledge-base entities: A graph neural network approach","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.759138Z"},"links":{"cited_paper":"/paper/1706.05674","citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:60f1c81515a4e6159e46dbdd5e969b2578de9e97990a092cab9f8b1f79c9a845","observation_id":"2ba0a616-0857-4d39-b4cd-5ed0763f71a4","resolution":{"observed_at":"2026-08-12T05:24:03.759138Z","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":"2026-08-12T05:24:04.996807Z","title":"Heterogeneous graph transformer","venue":null,"work_id":"0f782414-3b7d-45ab-8ffc-8c8524e98571","year":2020},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.765301Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:97eb71d82d1abfd1a521adfeba3114f3ae9ec8b9b7089ada5e6e9c960acc0f77","observation_id":"3fa97318-8bef-4000-8edd-aab4367f12ee","resolution":{"observed_at":"2026-08-12T05:24:05.002293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:03.770480Z","title":"Johnson, T","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.770480Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:f2a46807b6500505732666525d3b428217a81a65a8ca05fcc8b9875fbb54df8b","observation_id":"86ebdee5-d730-4614-9cbf-459d0b964227","resolution":{"observed_at":"2026-08-12T05:24:03.770480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.01958","last_updated":"2023-06-02T23:36:49Z","snapshot_observed_at":"2026-08-13T11:25:20.838325Z","submitted_at":"2023-06-02T23:36:49Z","title":"A Survey on Explainability of Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.01958","snapshot_observed_at":"2026-08-12T05:24:03.775714Z","title":"A survey on explainability of graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.775714Z"},"links":{"cited_paper":"/paper/2306.01958","citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:3c49613fa3c7046b6984ec3341ab3b98c8eded33b0a29051894bd1511e69ab1a","observation_id":"966e4de8-b92d-494e-9286-c7a546b4cbd7","resolution":{"observed_at":"2026-08-12T05:24:03.775714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-13T11:38:10.906031Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-12T05:24:03.781556Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.781556Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:b898a5244e01af6f0db8f8011bad24c329565f096e8fbc09fe5a3233303d43f5","observation_id":"a0258509-4302-4366-92c1-92968c150fd1","resolution":{"observed_at":"2026-08-12T05:24:03.781556Z","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":"2026-08-12T05:24:04.968813Z","title":"Graphmse: Efficient meta-path selection in semantically aligned feature space for graph neural networks","venue":null,"work_id":"abefea1d-dd40-44d5-80ea-549141e2afd8","year":2021},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.787092Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:2e4db853660e7eb47cd409558e9ed90907e6d9522a000363dafb6b9177f67ee7","observation_id":"c2769593-3998-4aa2-9ddf-49c9aab80eca","resolution":{"observed_at":"2026-08-12T05:24:04.975276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:03.792489Z","title":"Explaining the explainers in graph neural networks: a comparative study","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.792489Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:832aa019df3eea3d26ccd6bbf683155cbec72ee32a614beff81cc224f90deb10","observation_id":"5834aabe-48bc-4409-96bd-ce6b123d9b27","resolution":{"observed_at":"2026-08-12T05:24:03.792489Z","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":"2026-08-12T05:24:03.797976Z","title":"Are we really making much progress? revisiting, benchmarking and refining heterogeneous graph neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.797976Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:c8c844a5baf3e500e3f000c4c840389408274560c0ad12e8698b0b69343454ed","observation_id":"7a285cde-defd-4a25-99bd-b2f611a5bf0a","resolution":{"observed_at":"2026-08-12T05:24:03.797976Z","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":"2026-08-12T05:24:04.948170Z","title":"Are we really making much progress? revisiting, benchmarking and refining heterogeneous graph neural networks","venue":null,"work_id":"2700cbd3-0527-4fdd-9001-209dbe62bae2","year":2021},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.803308Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:fe0b93a4a905b11fdde06e1f4d69848fdda7c1be8a0ee8d236ed787f0eb337bd","observation_id":"0f94cb0d-ffc5-406e-80e6-fd407c8e8188","resolution":{"observed_at":"2026-08-12T05:24:04.955175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.926257Z","title":"at Freiburg, Institut f\\","venue":null,"work_id":"d207cc6a-42f8-4dee-b261-390af2ee9a4b","year":1999},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.809065Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:7dbf9a2b31b350cbb7245b9eec873c4e947b62d7e187bc4d97ca02581fbc9ef9","observation_id":"f969f6b7-51cc-47a6-9d02-74f9db02009f","resolution":{"observed_at":"2026-08-12T05:24:04.933320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.907179Z","title":"Interpretable and generalizable graph learning via stochastic attention mechanism","venue":null,"work_id":"3d2317fc-952c-468e-acf9-422e3208ba62","year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.814197Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:23f96c3066e8facfeee092c90e50a382c2a33de26641d05e888cb708f50c6668","observation_id":"e862d06e-27c8-4b06-87be-30d64e08e6a2","resolution":{"observed_at":"2026-08-12T05:24:04.912891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.885428Z","title":"Revisiting link prediction on heterogeneous graphs with a multi-view perspective","venue":null,"work_id":"462bec94-bc26-40e2-9fa0-bb671536c4fd","year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.820526Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:b29ca535d0b5337f5a6422173f04245cb5c8db7b69e331f38b0f1a78486edf97","observation_id":"59341883-02a4-4ee9-bf87-c2466eac3327","resolution":{"observed_at":"2026-08-12T05:24:04.892622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.857601Z","title":"Prototype-based interpretable graph neural networks","venue":null,"work_id":"67a667a9-28a8-4752-8310-700a1b4f99e2","year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.828226Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:6371f9c7eea1839c512e453b407d1813a528ea0e71fb3d5affa17ad37222cc19","observation_id":"c99ca787-db6f-4d06-8d82-ef4c348644c6","resolution":{"observed_at":"2026-08-12T05:24:04.866509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.20060","last_updated":"2024-07-29T14:46:13Z","snapshot_observed_at":"2026-08-13T14:24:05.277329Z","submitted_at":"2024-07-29T14:46:13Z","title":"RelBench: A Benchmark for Deep Learning on Relational Databases","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.20060","snapshot_observed_at":"2026-08-12T05:24:03.834429Z","title":"Lenssen, Yiwen Yuan, Zecheng Zhang, Xinwei He, and Jure Leskovec","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.834429Z"},"links":{"cited_paper":"/paper/2407.20060","citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:a63bbecd7e8e518617bb5a90fa481e5355073eaec871d6b6e36521d0c3e91cd4","observation_id":"8ef77644-72be-468e-beaa-970b2475fbc4","resolution":{"observed_at":"2026-08-12T05:24:03.834429Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.01242","last_updated":"2018-06-04T17:29:40Z","snapshot_observed_at":"2026-08-14T19:07:43.218984Z","submitted_at":"2018-06-04T17:29:40Z","title":"Graph networks as learnable physics engines for inference and control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.01242","snapshot_observed_at":"2026-08-12T05:24:03.840580Z","title":"Graph networks as learnable physics engines for inference and control, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.840580Z"},"links":{"cited_paper":"/paper/1806.01242","citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:fd8b952cc293f8b8fd193fc268844bf34f39ec6edde8fa882c276862c65d3d91","observation_id":"2c3daa57-b50b-4418-96ed-d0faeb2be6f7","resolution":{"observed_at":"2026-08-12T05:24:03.840580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.06103","last_updated":"2017-10-26T19:53:49Z","snapshot_observed_at":"2026-08-14T21:11:18.226937Z","submitted_at":"2017-03-17T17:09:14Z","title":"Modeling Relational Data with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.06103","snapshot_observed_at":"2026-08-12T05:24:03.846195Z","title":"Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.846195Z"},"links":{"cited_paper":"/paper/1703.06103","citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:f2912989ccb83b43ac1982090ba92a0abfb1b6c3b28a6b587bed62be4eef0dd9","observation_id":"f5af7938-02c0-480d-8b4c-f13f8ecca0eb","resolution":{"observed_at":"2026-08-12T05:24:03.846195Z","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":"2026-08-12T05:24:04.833229Z","title":"Modeling relational data with graph convolutional networks","venue":null,"work_id":"b8e88b35-27be-418e-906a-aa0b15ce1a23","year":2018},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.851760Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:34710501f172570fcfdfab1c6681064ec11f5ecf3eef9eb449ad3579d3f854a5","observation_id":"3205c5e0-a140-4dda-b18d-6e83a44bee58","resolution":{"observed_at":"2026-08-12T05:24:04.839240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.810666Z","title":"A hierarchy of independence assumptions for multi-relational bayes net classifiers","venue":null,"work_id":"b9606122-56b2-44c8-a48c-f652ef861fd5","year":2013},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.856751Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:53c0ec47138ddda880ab337a82aa325289c9d6555b55771090bc7dd45febde5e","observation_id":"0f5cd35d-816c-48a8-8602-7bd861c3518f","resolution":{"observed_at":"2026-08-12T05:24:04.817902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.787770Z","title":"Interpretable prototype-based graph information bottleneck","venue":null,"work_id":"87b628b9-9792-4a4c-a3cb-135964dd1185","year":2023},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.863089Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:08de87e939c517e91b724e923c250d9acfcb7a4d6399e776cd99fc0da72f6dae","observation_id":"b9fc3b61-dbf3-4049-bba5-9415a38703c4","resolution":{"observed_at":"2026-08-12T05:24:04.794878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.754661Z","title":"Pgm-explainer: Probabilistic graphical model explanations for graph neural networks","venue":null,"work_id":"f11adc9c-b752-40c0-9087-390264028a40","year":2020},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.868627Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:e112d7e6075351915a13ce5fbe78f140a8d7e6fe44b5a4ad91ef8650b65b27f5","observation_id":"9be86eb1-c2f7-4734-9495-047e4e58a488","resolution":{"observed_at":"2026-08-12T05:24:04.762422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.730790Z","title":"Heterogeneous graph attention network","venue":null,"work_id":"a3cfee14-bcb2-4df9-b68d-17456ed5786e","year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.874152Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:7e7c94bf8a2688967d2a00a18d4ad894a468e388c23521128c09c4eda4e503b1","observation_id":"c0c25cfd-4861-4511-b7ff-ed91f0922ed4","resolution":{"observed_at":"2026-08-12T05:24:04.738776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:03.879630Z","title":"Gnninterpreter: A probabilistic generative model-level explanation for graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.879630Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:3e8ad6c995f96c2eb96c849f92dd869f1669140e21d4be888a05a6e933185c62","observation_id":"2a5f358d-cac8-4fda-ab63-32018f7c5d9a","resolution":{"observed_at":"2026-08-12T05:24:03.879630Z","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":"2026-08-12T05:24:03.885456Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.885456Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:5c0b87e3e6ad2acbff02fb11b237259578d226683f42fbdc540c8655a36e63cd","observation_id":"1db882bd-c828-440e-8ff7-5c24c857b3e3","resolution":{"observed_at":"2026-08-12T05:24:03.885456Z","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":"2026-08-12T05:24:04.684507Z","title":"Graph convolutional networks with markov random field reasoning for social spammer detection","venue":null,"work_id":"b1ba2ba9-9d17-4789-b55c-ee5ae183b5ca","year":2020},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.891333Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:8f7de98561d4364c43497d8504324d403e9333c8bd64f603a7c83bbde3354d9f","observation_id":"a8278fb2-fcc3-4a45-baf4-6906485ff172","resolution":{"observed_at":"2026-08-12T05:24:04.691809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:03.896495Z","title":"Gnnexplainer: Generating explanations for graph neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.896495Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:1fc5f698ac02300523e63b872f204c43bead9f2637fe75ca7f5fc2182e435ea6","observation_id":"6d2bd249-6e83-4573-a6c4-db5d877216a7","resolution":{"observed_at":"2026-08-12T05:24:03.896495Z","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":"2026-08-12T05:24:04.648059Z","title":"Graph information bottleneck for subgraph recognition","venue":null,"work_id":"0ff8ace1-3c8f-4a20-a29b-a5ab803218df","year":2020},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.901493Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:b7b36cdbc0b14bc3a79996eefc2a8fb03ad720b9e681a630f5e23f267966f8ef","observation_id":"d7b76479-62dc-4a09-a2db-d68e3dde94f5","resolution":{"observed_at":"2026-08-12T05:24:04.654555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.11122","last_updated":"2022-04-17T02:26:49Z","snapshot_observed_at":"2026-08-13T19:17:54.029322Z","submitted_at":"2021-05-24T07:01:41Z","title":"Heterogeneous Graph Representation Learning with Relation Awareness","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.11122","snapshot_observed_at":"2026-08-12T05:24:03.906681Z","title":"Heterogeneous graph representation learning with relation awareness","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.906681Z"},"links":{"cited_paper":"/paper/2105.11122","citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:fa6182c27515ab95a75dfcf4d0afd0211b1203752887a0a9e6dff2d1827dc2b1","observation_id":"7bda0f90-7212-4aa7-90f3-4f87044723fa","resolution":{"observed_at":"2026-08-12T05:24:03.906681Z","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":"2026-08-12T05:24:04.624372Z","title":"Heterogeneous graph representation learning with relation awareness","venue":null,"work_id":"823896e5-858a-44c5-8f42-48a926baeaea","year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.911989Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:3024e474696b707ed37161e0d5625d21748b1aeedfc9b7304d37b84fd077a12e","observation_id":"4b57656d-7000-405a-98a6-cde13ad14c2e","resolution":{"observed_at":"2026-08-12T05:24:04.630545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.604602Z","title":"Xgnn: Towards model-level explanations of graph neural networks","venue":null,"work_id":"13a3ede3-9438-49ab-b607-9ee3984c1413","year":2020},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.917270Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:8ea41ce1e8be1cddd370ade2513473574366e2e132e444025d9e4ee539005be1","observation_id":"4c4d8cb0-11ff-4e51-9302-7a22926321cd","resolution":{"observed_at":"2026-08-12T05:24:04.610265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.584686Z","title":"On explainability of graph neural networks via subgraph explorations","venue":null,"work_id":"be714fd9-9063-4d44-9a91-f2724535eb1c","year":2021},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.923707Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:d5e91d81c8d87cb6e48f2e7dfcb15cfa619ca09cbb1918c118afc85dd2dedee9","observation_id":"d32d09c0-b9a0-49a9-9997-216e92e7c080","resolution":{"observed_at":"2026-08-12T05:24:04.591570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.562186Z","title":"Explainability in graph neural networks: A taxonomic survey","venue":null,"work_id":"cfec7152-40c8-40ed-b2cd-ec998b72d806","year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.929567Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:564e922488effbb5ad1e80e7c97088dbae51d1844915cdc1b320a76239d945ba","observation_id":"ff114024-4f3c-4311-b3ca-511a68f6d1fc","resolution":{"observed_at":"2026-08-12T05:24:04.567919Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.539175Z","title":"Graph transformer networks","venue":null,"work_id":"f71e866a-faaf-424a-b325-bd2718f89b59","year":2019},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.934927Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:5bd97bcb14a07ce56214dc7d265f6d291feaa5498b5e185b94acfc612a2141c7","observation_id":"1a933723-bfef-4190-ada8-0e98a515ab92","resolution":{"observed_at":"2026-08-12T05:24:04.547333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.514333Z","title":"Graph transformer networks","venue":null,"work_id":"4bdd7a68-06a1-4648-bbb5-cb044dca22d1","year":2019},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.940351Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:be6b077cbf381175bce16833cf3c4376999abd258b4cfbbbffe4ab5fb49c4f9f","observation_id":"b666cf56-c1f9-4ca6-98fe-9e1135b2744f","resolution":{"observed_at":"2026-08-12T05:24:04.520106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.493810Z","title":"Graph transformer networks: Learning meta-path graphs to improve gnns","venue":null,"work_id":"914f7085-eb5c-4836-af24-ffb70abb2b9e","year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.945582Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:fa254b799946d0dfc95b4858f50c846ed5869fcb62ab317cf2412217bd0d5846","observation_id":"d88b29cb-2db7-4394-b1f7-b0784150019f","resolution":{"observed_at":"2026-08-12T05:24:04.499588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:03.950585Z","title":"Yi, Raehyun Kim, Jaewoo Kang, and Hyunwoo J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.950585Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:9dfefb11b08d1c0656ff3383b3a83bdeb3d34092bd88724fad234fb825efd80f","observation_id":"07b08fa3-238c-4042-adda-e782a4f8511c","resolution":{"observed_at":"2026-08-12T05:24:03.950585Z","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":"2026-08-12T05:24:04.472668Z","title":"Protgnn: Towards self-explaining graph neural networks","venue":null,"work_id":"5b2a5822-9e44-43e9-971c-ae2e17405999","year":2022},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.955701Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:1dea8bfb7cb29acd710856e3b1c4b9f616128ceb14fa7c3ad6e549faf70a8af3","observation_id":"9c73f029-62d6-4816-bd12-50d5876cf086","resolution":{"observed_at":"2026-08-12T05:24:04.479592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.447173Z","title":"Towards robust fidelity for evaluating explainability of graph neural networks, 2023","venue":null,"work_id":"a44bae4c-9976-4a42-8640-889bcd2dc06b","year":2023},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.961064Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:ec709be1fa7beb3868d4bda6997dc02e1ca9d738046fb4fc2156e81b4cdf8a1f","observation_id":"77ef0601-3a51-4416-aa13-536e51a23334","resolution":{"observed_at":"2026-08-12T05:24:04.454928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:04.420064Z","title":"Relation structure-aware heterogeneous graph neural network","venue":null,"work_id":"dfa8bf28-718c-49cc-a40a-01f5c661b310","year":2019},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.966727Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:457bcea0898fc43bf52e06b7c4769d7c334af5b300688814cc7d7d657e6077d8","observation_id":"bf354dfc-8fcc-46d2-a8d6-9979698bc9f0","resolution":{"observed_at":"2026-08-12T05:24:04.428283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:24:03.972289Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-12T05:24:03.972289Z"},"links":{"citing_paper":"/paper/2412.00521"},"observation_digest":"sha256:17e06dcca2cdb87996d0337e6e05c2c5d9fa0d899ee4f70c7f520d9581f86ac6","observation_id":"23b8287e-cf64-4d8f-9843-1144856d1bc5","resolution":{"observed_at":"2026-08-12T05:24:03.972289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.00521","last_updated":"2025-02-25T12:59:12Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T07:02:20.076147Z","submitted_at":"2024-11-30T16:02:14Z","title":"A Self-Explainable Heterogeneous GNN for Relational Deep Learning"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":0,"verified_fuzzy":33},"total_outbound_references":54},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 2 inbound Pith citation observations for arXiv:2412.00521."}