{"as_of":"2026-08-13T17:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:538e11ed9ad7a661600c8cc06f6c5e7364be79a6e911808f19318b1786f5d0f7","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T08:34:21.585593Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.21094/citation-record","integrity":"/paper/2607.21094/integrity","json":"/paper/2607.21094/citation-record.json","paper":"/paper/2607.21094"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T08:34:19.031438Z","title":"Graph neural networks in recommender systems: a survey.ACM Computing Surveys, 55(5):1–37, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.031438Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:d65276ecea82ea19f60ddfba112eb138f407bf3a732581a12c901b56c721d0ad","observation_id":"4f73eca9-a405-47c2-b180-215068bee891","resolution":{"observed_at":"2026-08-01T08:34:19.031438Z","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":"2026-08-01T08:34:19.159336Z","title":"Graph neural networks for social recommendation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.159336Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:dc7943df47a052102cad1cb8fe01f2e7bd52ab2d603e2628919a3c944899260f","observation_id":"86b28588-e88c-4d34-a4dc-cf6fa59c57a5","resolution":{"observed_at":"2026-08-01T08:34:19.159336Z","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":"2026-08-01T08:34:19.223364Z","title":"Graph convolutional networks for text classification","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.223364Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:3051ad8acc0ac6edfec13a6151fa66aa8fd2bc95168079a48fb735989a0e39d4","observation_id":"c97ca59d-9490-4562-9aee-2e68d18ae30b","resolution":{"observed_at":"2026-08-01T08:34:19.223364Z","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":"2026-08-01T08:34:19.296849Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.296849Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:f1ee6448dc75734e9eb80bd9a6ef850982fe31640f09c2db9ade517052e9b506","observation_id":"88433f79-1927-45f2-a08b-638432cdde92","resolution":{"observed_at":"2026-08-01T08:34:19.296849Z","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":"2026-08-01T08:34:19.380916Z","title":"Neural message passing for quantum chemistry","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.380916Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:9a35bb85726bb7f3f966600eb8c787b37d23f8ae85c20b83dbbf8b3b793f6b10","observation_id":"88a373c5-4d0a-4e93-8518-9108f7a35ce8","resolution":{"observed_at":"2026-08-01T08:34:19.380916Z","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":"2026-08-01T08:34:19.462167Z","title":"Axiomatic attribution for deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.462167Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:40bd89c1729532ceb739e3f908725bd80a7844c2ffda742b984da10d337dc1e4","observation_id":"addf6c10-f26a-4581-a1d7-5c5f16903964","resolution":{"observed_at":"2026-08-01T08:34:19.462167Z","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":"2026-08-01T08:34:19.543952Z","title":"Princeton University Press, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.543952Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:5bbddd47d82deee1c120bf8558426ee857c2b34020f5a7be5ba0c32ce64b5c39","observation_id":"8df0fed7-fed5-4c0e-b45c-2fb736b4f32d","resolution":{"observed_at":"2026-08-01T08:34:19.543952Z","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":"2026-08-01T08:34:19.624222Z","title":"The many shapley values for model explanation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.624222Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:697ad9367f4bc26b0bbd50a8afb0d7f3256527a4b09a7bcacc07597974a0ba23","observation_id":"f9e27a86-8510-4eeb-a8e4-20baf6231793","resolution":{"observed_at":"2026-08-01T08:34:19.624222Z","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":"2026-08-01T08:34:19.707951Z","title":"Explainability in graph neural networks: A taxonomic survey.IEEE transactions on pattern analysis and machine intelligence, 45(5):5782–5799, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.707951Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:4a5af203f54492cda9b23561e27e64198ab4497563520dcd729f83c90bab04bb","observation_id":"1490e240-9834-460e-a285-99b23dbf7254","resolution":{"observed_at":"2026-08-01T08:34:19.707951Z","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":"2026-08-01T08:34:19.768846Z","title":"Gnnexplainer: Generating explanations for graph neural networks.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.768846Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:6cad82bdbb23d8cf61bfa6426cdee7089507889574497aae0b584594f755a7f2","observation_id":"0fa378f9-4b66-4c43-9e2f-c9dacce406c1","resolution":{"observed_at":"2026-08-01T08:34:19.768846Z","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":"2026-08-01T08:34:19.873452Z","title":"Parameter- ized explainer for graph neural network.Advances in neural information processing systems, 33:19620–19631, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.873452Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:ab6967a9a8420dff095f7344ccdf0ffa26985031556874a062a49bf34ccefbee","observation_id":"22a2f2d6-4776-4f0c-a06e-1dd80e222b99","resolution":{"observed_at":"2026-08-01T08:34:19.873452Z","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":"2026-08-01T08:34:19.964461Z","title":"On explainability of graph neural networks via subgraph explorations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:19.964461Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:600e404898f8451a90b8142b3d678bced06b207a165168f65ef7d57ae5890719","observation_id":"99033ea0-853e-4160-868f-b97e9ef2b981","resolution":{"observed_at":"2026-08-01T08:34:19.964461Z","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":"2026-08-01T08:34:20.076053Z","title":"Flowx: Towards explainable graph neural networks via message flows.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(7):4567–4578, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:20.076053Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:f5455e40aaf9f8193faffcbb3d2793827b3f26b24f1dd030f4bef4d1ac15cced","observation_id":"be485fbe-b208-4457-9266-1e0f0ff1480d","resolution":{"observed_at":"2026-08-01T08:34:20.076053Z","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":"2026-08-01T08:34:20.219165Z","title":"Explainability methods for graph convolutional neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:20.219165Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:f814c381e7dbb1c6a4303b8c2f5eb97622e50502051f1d05c095a5b8b2039d89","observation_id":"9c89c020-1b70-42e5-a7dd-6f1fd6ce98eb","resolution":{"observed_at":"2026-08-01T08:34:20.219165Z","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":"2026-08-01T08:34:20.339595Z","title":"A value for n-person games","venue":null,"work_id":null,"year":1953},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:20.339595Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:b8e9b2ceb61137426d2b108157adc7b93076aadf02cdd088b075730b3bec55ad","observation_id":"23334b34-c1d1-4cfe-a5e3-54796f334f41","resolution":{"observed_at":"2026-08-01T08:34:20.339595Z","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":"2026-08-01T08:34:20.484906Z","title":"Fast axiomatic attribution for neural networks.Advances in Neural Information Processing Systems, 34:19513–19524, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:20.484906Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:291ef697816e93d4a8f2aaf29330abf882bb429ae5af5f3671942e8bd6d01304","observation_id":"83a0224c-0110-4441-9901-3986eef54c19","resolution":{"observed_at":"2026-08-01T08:34:20.484906Z","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":"2026-08-01T08:34:20.693083Z","title":"On the expressive power of deep polynomial neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:20.693083Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:934da6914e30759e24a3a0e36e96ded8105c614502c607d0bf0525170e64926b","observation_id":"0b7e3823-857e-405c-9abd-28bac231c4cb","resolution":{"observed_at":"2026-08-01T08:34:20.693083Z","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":"2026-08-01T08:34:20.795715Z","title":"P-nets: Deep polynomial neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:20.795715Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:3f5126d8c8c85583201f9ff496b55e864873b6c6583e0e078acaa1cfa770f65b","observation_id":"6a0e0de9-1a8f-47a1-ab8f-2abf3ab9c068","resolution":{"observed_at":"2026-08-01T08:34:20.795715Z","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":"2026-08-01T08:34:20.943656Z","title":"Convolutional neural networks on graphs with fast localized spectral filtering.Advances in neural information processing systems, 29, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:20.943656Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:630e2679817448a1d2ef1391ebc36d56389c8709943265a70216c948ec5c7fef","observation_id":"5ede044b-ffc6-419a-b2fa-563f23ce712c","resolution":{"observed_at":"2026-08-01T08:34:20.943656Z","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":"2026-08-01T08:34:21.061798Z","title":"How powerful are graph neural networks? In International Conference on Learning Representations, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:21.061798Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:f4423f778af65c0c4c18210ff59312e4d2118f61b458fc16cf3637a03667c202","observation_id":"3438040c-332e-4dcc-b5fb-5b9db473c69e","resolution":{"observed_at":"2026-08-01T08:34:21.061798Z","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":"2026-08-01T08:34:21.195204Z","title":"Calculation of gauss quadrature rules.Mathematics of computation, 23(106):221–230, 1969","venue":null,"work_id":null,"year":1969},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:21.195204Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:2ee4e493b1bc68bd05b480f0b6eddb17677b8319dd4f18ae1852e1351cb0e547","observation_id":"60496242-487b-4344-9dd3-45bb894972c7","resolution":{"observed_at":"2026-08-01T08:34:21.195204Z","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":"2026-08-01T08:34:21.317735Z","title":"Robust design with arbitrary distributions using gauss-type quadrature formula.Structural and Multidisciplinary Optimization, 39(3):227–243, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:21.317735Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:06a0b004d2c4903143898c7e06d2f051c09440b9961b1f1a68d8011360296193","observation_id":"9b8bdd9e-6055-4918-8278-4da184a92151","resolution":{"observed_at":"2026-08-01T08:34:21.317735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.09677","last_updated":"2024-05-22T12:11:48Z","snapshot_observed_at":"2026-08-13T15:20:23.656947Z","submitted_at":"2022-06-20T09:33:12Z","title":"GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.09677","snapshot_observed_at":"2026-08-01T08:34:21.444225Z","title":"Graphframex: Towards systematic evaluation of explainability methods for graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:21.444225Z"},"links":{"cited_paper":"/paper/2206.09677","citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:3b669217b2226399a097479f7bdbf9db2dabd5d0e16f9f4c3dd960916b64c47e","observation_id":"e3fb7017-0189-4916-a90b-c21bf908fd5a","resolution":{"observed_at":"2026-08-01T08:34:21.444225Z","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":"2026-08-01T08:34:21.499199Z","title":"Towards robust fidelity for evaluating explainability of graph neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:21.499199Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:1840e88585ea213b0379f49f0d403695daad66cbf870e079ec6be88d432952f6","observation_id":"5d3ed831-259c-4a97-9e94-30a92fd62148","resolution":{"observed_at":"2026-08-01T08:34:21.499199Z","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":"2026-08-01T08:34:21.541705Z","title":"Cambridge university press, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:21.541705Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:8bce98ba07e33223cadd2edc9aba400b38e14e95e037cf8aca4941172fa43d69","observation_id":"76bfe305-5f4e-4803-8d5b-6faf60309c9c","resolution":{"observed_at":"2026-08-01T08:34:21.541705Z","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":"2026-08-01T08:34:21.578056Z","title":"Moleculenet: a benchmark for molecular machine learning.Chemical science, 9(2):513–530, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:21.578056Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:1bac4888881a16c148eecf7cea36c7298f88d4bf6cc4f09c0c111bd955c2dbe0","observation_id":"ab29ca4e-4e92-436a-8d08-a1b98407228e","resolution":{"observed_at":"2026-08-01T08:34:21.578056Z","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":"2026-08-01T08:34:21.582199Z","title":"Derivation and validation of toxicophores for mutagenicity prediction.Journal of medicinal chemistry, 48(1):312–320, 2005","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:21.582199Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:411abe1ce1631a773253aec62371d86fd60072890ca9b04de11273b28b44b27c","observation_id":"2314ed1c-b8cb-4c8b-8670-094a10f72639","resolution":{"observed_at":"2026-08-01T08:34:21.582199Z","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":"2026-08-01T08:34:21.585593Z","title":"can”, “moving","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T08:34:21.585593Z"},"links":{"citing_paper":"/paper/2607.21094"},"observation_digest":"sha256:3eee92f9693c19ed5220d81815678322f837301afccbbd4d37af85d1e641aec4","observation_id":"51cdd3b0-bd13-49ce-b2eb-f309dc15ca98","resolution":{"observed_at":"2026-08-01T08:34:21.585593Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.21094","last_updated":"2026-07-23T09:26:15Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T08:54:16.999692Z","submitted_at":"2026-07-23T09:26:15Z","title":"A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":27,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":28},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2607.21094."}