{"as_of":"2026-08-09T11:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b00850425be7818e712f214c0014ffeec39879acafcbf1322b306781ba46ba09","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":12,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:14:38.389741Z","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":"2026-07-03T08:17:46.013955Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-08-07T11:14:38.389741Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03087","last_updated":"2026-06-02T15:24:26Z","snapshot_observed_at":"2026-08-09T10:31:16.361484Z","submitted_at":"2025-06-03T17:11:05Z","title":"Do Explanations Increase the Risk of Decision Logic Leakage? Explanation-Guided Stealing of Graph Models","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:14:38.389741Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2506.03087"},"observation_digest":"sha256:499070da1cd1c142dc7e197114b2fe92eb23722d9d16b7545ba468352536032b","observation_id":"5daa2697-85bf-4ddb-8660-c16a798e59e0","resolution":{"observed_at":"2026-08-07T11:14:38.389741Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-08-06T21:22:24.790695Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.00440","last_updated":"2025-07-01T05:46:29Z","snapshot_observed_at":"2026-08-06T21:12:41.053038Z","submitted_at":"2025-07-01T05:46:29Z","title":"A Recipe for Causal Graph Regression: Confounding Effects Revisited","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-06T21:22:24.790695Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2507.00440"},"observation_digest":"sha256:469040914ee446adfc48d1892ca3840aef96b3cd34bf41e6ec37de48b43792e3","observation_id":"1081973c-ca81-41f6-afcc-50400aecb9d0","resolution":{"observed_at":"2026-08-06T21:22:24.790695Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-08-03T18:48:42.060780Z","title":"Discovering Invariant Rationales for Graph Neural Networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.03578","last_updated":"2026-06-27T13:11:16Z","snapshot_observed_at":"2026-08-08T13:03:11.879586Z","submitted_at":"2025-12-03T09:01:41Z","title":"When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T18:48:42.060780Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2512.03578"},"observation_digest":"sha256:1b53cbe1426ffc5bb45afe8fae44d84bc90000aa87dc1d30f30cd735825f509d","observation_id":"f6955993-81bc-42ba-a01e-4e291f6c9498","resolution":{"observed_at":"2026-08-03T18:48:42.060780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2201.12872","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-07-03T08:17:46.013955Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":"224904f2-e0e8-4c30-b710-f2efd033d19f","year":2022},"citing_paper":{"arxiv_id":"2604.03154","last_updated":"2026-04-03T16:23:59Z","snapshot_observed_at":"2026-08-02T16:57:40.164429Z","submitted_at":"2026-04-03T16:23:59Z","title":"DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-13T19:34:21.724329Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2604.03154"},"observation_digest":"sha256:cfb75864591acbaf360d3c9cafb3031368cf7a01ef1c43af776385edb947da64","observation_id":"37019dfb-75cc-4d6d-b843-91dba13e9283","resolution":{"observed_at":"2026-05-13T19:38:10.584767Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2201.12872","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-07-03T08:17:46.013955Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":"224904f2-e0e8-4c30-b710-f2efd033d19f","year":2022},"citing_paper":{"arxiv_id":"2604.08404","last_updated":"2026-04-20T18:01:41Z","snapshot_observed_at":"2026-07-06T22:57:31.046146Z","submitted_at":"2026-04-09T16:02:07Z","title":"Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T17:00:51.046061Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2604.08404"},"observation_digest":"sha256:cb9c15075d2bdd439be8aac4c9280fe17caa79b7d30b637de37136ed3d60ebbd","observation_id":"59a1eeb8-4a45-44bb-a005-8a28023d393f","resolution":{"observed_at":"2026-05-11T07:41:01.643746Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2201.12872","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-07-03T08:17:46.013955Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":"224904f2-e0e8-4c30-b710-f2efd033d19f","year":2022},"citing_paper":{"arxiv_id":"2604.26301","last_updated":"2026-04-29T05:04:53Z","snapshot_observed_at":"2026-07-06T23:11:57.238808Z","submitted_at":"2026-04-29T05:04:53Z","title":"Cheeger--Hodge Contrastive Learning for Structurally Robust Graph Representation Learning","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-05-07T13:38:30.600152Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2604.26301"},"observation_digest":"sha256:b3534d8f06e44685acfbd99fdf8270dc12f0d7117b3f8d103a8cff262658f8ce","observation_id":"43792937-2f70-42b6-9b33-47e15e392a01","resolution":{"observed_at":"2026-05-12T08:51:24.688717Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2201.12872","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-07-03T08:17:46.013955Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":"224904f2-e0e8-4c30-b710-f2efd033d19f","year":2022},"citing_paper":{"arxiv_id":"2605.19778","last_updated":"2026-05-27T07:50:54Z","snapshot_observed_at":"2026-08-01T00:55:27.707527Z","submitted_at":"2026-05-19T12:44:58Z","title":"B-cos GNNs: Faithful Explanations through Dynamic Linearity","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-20T07:36:37.630198Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2605.19778"},"observation_digest":"sha256:6bb408563f097d7b0e9066bf9d67433154fa0176e7f8fce37416f04c5abd87a0","observation_id":"7e54b03d-1ca6-4311-bb48-a5625eca1e8e","resolution":{"observed_at":"2026-05-20T07:38:09.274616Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2201.12872","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-07-03T08:17:46.013955Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":"224904f2-e0e8-4c30-b710-f2efd033d19f","year":2022},"citing_paper":{"arxiv_id":"2605.19778","last_updated":"2026-05-27T07:50:54Z","snapshot_observed_at":"2026-08-01T00:55:27.707527Z","submitted_at":"2026-05-19T12:44:58Z","title":"B-cos GNNs: Faithful Explanations through Dynamic Linearity","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-30T18:36:38.696506Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2605.19778"},"observation_digest":"sha256:9ddfbaca2c27711f16971423d1d9b8c0adbbd7b8c94e98a925b3cbc3836c4fd9","observation_id":"c0e740a2-cf10-47ac-b068-c3e9ece418b4","resolution":{"observed_at":"2026-07-01T14:55:48.372959Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2201.12872","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-07-03T08:17:46.013955Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":"224904f2-e0e8-4c30-b710-f2efd033d19f","year":2022},"citing_paper":{"arxiv_id":"2606.05756","last_updated":"2026-06-04T06:32:02Z","snapshot_observed_at":"2026-08-09T06:41:55.442578Z","submitted_at":"2026-06-04T06:32:02Z","title":"Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-28T03:10:42.043883Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2606.05756"},"observation_digest":"sha256:0722451627222401095302a1d396e2951a05631073012ebdb9b7e41bd4213ea8","observation_id":"517b908d-0263-4dbc-80fd-fe2e09bd80b5","resolution":{"observed_at":"2026-07-02T11:36:55.590895Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2201.12872","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-07-03T08:17:46.013955Z","title":"Discovering invariant rationales for graph neural networks","venue":null,"work_id":"224904f2-e0e8-4c30-b710-f2efd033d19f","year":2022},"citing_paper":{"arxiv_id":"2606.18287","last_updated":"2026-06-10T05:10:36Z","snapshot_observed_at":"2026-07-06T23:53:45.117607Z","submitted_at":"2026-06-10T05:10:36Z","title":"Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-06-27T10:46:17.503537Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2606.18287"},"observation_digest":"sha256:4c56db35a2c8615bffe08078022ea08bad5de9073459a8e0308a9834302fc16e","observation_id":"6c58d23f-8f5e-4249-9a71-d4de40001849","resolution":{"observed_at":"2026-07-03T08:17:46.015683Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-07-12T04:11:50.269344Z","title":"arXiv preprint arXiv:2201.12872 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03200","last_updated":"2026-07-03T11:13:59Z","snapshot_observed_at":"2026-08-06T05:08:28.708203Z","submitted_at":"2026-07-03T11:13:59Z","title":"OpFlow: Learning Opportunity-Conditioned Choice Potentials for Robust OD Flow Prediction","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-07-12T04:11:50.269344Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2607.03200"},"observation_digest":"sha256:9973350a23defa98c0842f49da457aef21d4ac12de9717bc50e7e18955f36df6","observation_id":"eb56d278-59e4-4bac-bf20-41dbe9cc4c82","resolution":{"observed_at":"2026-07-12T04:11:50.269344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12872","snapshot_observed_at":"2026-08-03T08:31:24.145916Z","title":"arXiv preprint arXiv:2201.12872 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.29365","last_updated":"2026-07-31T12:52:10Z","snapshot_observed_at":"2026-08-07T19:39:07.552840Z","submitted_at":"2026-07-31T12:52:10Z","title":"Cross-Resolution Semantic Learning for Graph Domain Adaptation","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-03T08:31:24.145916Z"},"links":{"cited_paper":"/paper/2201.12872","citing_paper":"/paper/2607.29365"},"observation_digest":"sha256:14b090caed3cbaca198eb4588f2d8342a79f23c6ad8df26017e7e21a66106aee","observation_id":"9f9c5ecd-e644-47f1-a665-4d966f0637a7","resolution":{"observed_at":"2026-08-03T08:31:24.145916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2201.12872/citation-record","integrity":"/paper/2201.12872/integrity","json":"/paper/2201.12872/citation-record.json","paper":"/paper/2201.12872"},"outbound":[],"paper":{"arxiv_id":"2201.12872","last_updated":"2022-01-30T16:43:40Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T12:32:40.356858Z","submitted_at":"2022-01-30T16:43:40Z","title":"Discovering Invariant Rationales for Graph Neural Networks"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 12 inbound Pith citation observations for arXiv:2201.12872."}