{"as_of":"2026-08-10T11:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:547f89c92ea860e19b87d2223bbefac89c3357061fe019948362b07813a6b4f2","coverage":[{"denominator":116,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T23:39:46.455658Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2508.05070/citation-record","integrity":"/paper/2508.05070/integrity","json":"/paper/2508.05070/citation-record.json","paper":"/paper/2508.05070"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T23:39:45.986771Z","title":"Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:45.986771Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:0a16a7f8158447e77057f17f8909b35e8db15e84d48e852fb9441903fdbde3c9","observation_id":"653a8993-fa70-4e25-bfc8-9be6ff794df0","resolution":{"observed_at":"2026-08-05T23:39:45.986771Z","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":"2026-08-05T23:39:45.991924Z","title":"On the bottleneck of graph neural networks and its practical implications","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:45.991924Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:15a265a25c95540bf3a2d60d14ae636e1fa7ba3070032f2a5332ce4d838425f6","observation_id":"837b765f-d242-4875-9aea-ccab4874a444","resolution":{"observed_at":"2026-08-05T23:39:45.991924Z","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":"2026-08-05T23:39:45.996846Z","title":"On vanishing gradients, over- smoothing, and over-squashing in gnns: Bridging recurrent and graph learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:45.996846Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:81933fbe26d0063240b50bef3cd3017fd3188f9094066681943456e84ed942fa","observation_id":"104fdfea-8529-4838-95ec-2b2d581e4376","resolution":{"observed_at":"2026-08-05T23:39:45.996846Z","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":"2026-08-05T23:39:46.001755Z","title":"Accurate prediction of protein structures and interactions using a three-track neural network","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.001755Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:c7abb57fa05feded126dc37988cf180cf38d3effa6099fbd1b90a71fa9affeba","observation_id":"63222f8e-98d0-4cb8-83a5-10d6078ed39c","resolution":{"observed_at":"2026-08-05T23:39:46.001755Z","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":"2026-08-05T23:39:46.006502Z","title":"Directional graph networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.006502Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:1a033d2f7cff68d941d0c6f82f21f4aa5fd5a373f4d86795609042ea78379239","observation_id":"f0575e5a-102f-4c2e-ad79-1e5e1741e572","resolution":{"observed_at":"2026-08-05T23:39:46.006502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08678","last_updated":"2024-02-19T18:53:13Z","snapshot_observed_at":"2026-08-06T16:35:04.650921Z","submitted_at":"2024-02-13T18:58:17Z","title":"Graph Mamba: Towards Learning on Graphs with State Space Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.08678","snapshot_observed_at":"2026-08-05T23:39:46.010872Z","title":"Graph Mamba: Towards Learning on Graphs with State Space Models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.010872Z"},"links":{"cited_paper":"/paper/2402.08678","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:05287bdf45a9d255a104cece0bf1556e443f0873f070f485cd2f2fe60fbbaff8","observation_id":"b1160578-65bc-4b7b-8698-15c37612d9ba","resolution":{"observed_at":"2026-08-05T23:39:46.010872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.11588","last_updated":"2022-11-11T10:50:38Z","snapshot_observed_at":"2026-08-09T17:48:48.692812Z","submitted_at":"2022-09-23T13:41:54Z","title":"Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Network","version":2},"cited_work":{"arxiv_id":"2209.11588","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.11588","snapshot_observed_at":"2026-08-05T23:39:47.802955Z","title":"Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Network","venue":"cs.LG","work_id":"e9df21dd-8cbb-4ac4-b621-d484eb81ea9e","year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.015488Z"},"links":{"cited_paper":"/paper/2209.11588","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:61cdb6228e047c63af7007384475679835199db962bf93ebe8ca4513334ba183","observation_id":"b5adc7cb-3442-41f2-9097-6ad7ffd3dac1","resolution":{"observed_at":"2026-08-05T23:39:47.806746Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:46.019209Z","title":"Understanding oversquashing in gnns through the lens of effective resistance","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.019209Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:dc97d1bd9946cf95d649b6be257bd44b5adc3de7a1a0b49a5dad4a3f0f047c94","observation_id":"534d332e-23a3-40eb-9b8a-507fbefa889a","resolution":{"observed_at":"2026-08-05T23:39:46.019209Z","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":"2026-08-05T23:39:46.023001Z","title":"Beyond low-frequency information in graph convolutional networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.023001Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:387f91607d2acb5bcab7db0e5609784b80c79310983c84fbd388b18bb81294ac","observation_id":"362e2c61-1e56-412f-9f7a-2199c2b63824","resolution":{"observed_at":"2026-08-05T23:39:46.023001Z","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":"2026-08-05T23:39:46.027025Z","title":"Convex optimization","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.027025Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:0fe06531af231b595a151c56fba7f7c341872b9a91e1203cd057d0833f3313b5","observation_id":"b2cc40eb-23df-40da-b8f8-d40fdd311881","resolution":{"observed_at":"2026-08-05T23:39:46.027025Z","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":"2026-08-05T23:39:46.030726Z","title":"Worrall, and Max Welling","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.030726Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:24d39e1f85302b23358ca55c14547ddf2498530ce749fc20a630aaef2f833313","observation_id":"b700b004-f0b7-46b0-ab99-ee594bda14fd","resolution":{"observed_at":"2026-08-05T23:39:46.030726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.07553","last_updated":"2018-04-24T08:19:32Z","snapshot_observed_at":"2026-08-09T01:06:08.452911Z","submitted_at":"2017-11-20T21:28:40Z","title":"Residual Gated Graph ConvNets","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.07553","snapshot_observed_at":"2026-08-05T23:39:46.034720Z","title":"Residual Gated Graph ConvNets","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.034720Z"},"links":{"cited_paper":"/paper/1711.07553","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:9dc49319792af65520ad2ad1a42d9e53caee41115f64d04a1de67bab8d84ee4c","observation_id":"f4b577b2-6d0d-474e-a981-f5a929137ae8","resolution":{"observed_at":"2026-08-05T23:39:46.034720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.13478","last_updated":"2021-05-02T16:16:03Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-04-27T21:09:51Z","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.13478","snapshot_observed_at":"2026-08-05T23:39:46.038724Z","title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.038724Z"},"links":{"cited_paper":"/paper/2104.13478","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:8584009c5df5096caabb0f1ee59b74bbd331c2559dd1c827acdeab58d1bd3dfb","observation_id":"f7135985-177d-454f-9997-0c3399b2824d","resolution":{"observed_at":"2026-08-05T23:39:46.038724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.13318","last_updated":"2020-06-23T20:36:56Z","snapshot_observed_at":"2026-07-06T09:32:05.177891Z","submitted_at":"2020-06-23T20:36:56Z","title":"A Note on Over-Smoothing for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.13318","snapshot_observed_at":"2026-08-05T23:39:46.043567Z","title":"A note on over-smoothing for graph neural networks.arXiv preprint arXiv:2006.13318, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.043567Z"},"links":{"cited_paper":"/paper/2006.13318","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:c5c3a13a499dfff79ebdcd2c08a14103896ee6858af72112e095910081f3e114","observation_id":"40db5b14-6da4-4aee-b708-3ace3a9ae556","resolution":{"observed_at":"2026-08-05T23:39:46.043567Z","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":"2026-08-05T23:39:46.048954Z","title":"Beltrami flow and neural diffusion on graphs","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.048954Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:3f0e678c0d18878c7a21e4f679ec6903e5bfcbaf0d6a3213d3db8cb3c0728b5f","observation_id":"328a9964-a9aa-4d59-b09f-3a6b1bbc4618","resolution":{"observed_at":"2026-08-05T23:39:46.048954Z","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":"2026-08-05T23:39:46.052784Z","title":"GRAND: Graph neural diffusion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.052784Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:a6034acc6dd08c83fa481ec57782b833e08cd9b92e32832dea62b30528c19c05","observation_id":"d75ab464-06fb-428e-b54d-36e315e8a25d","resolution":{"observed_at":"2026-08-05T23:39:46.052784Z","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":"2026-08-05T23:39:46.058242Z","title":"Simple and Deep Graph Convolutional Networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.058242Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:20347f9e9b5e1c8a9ec4891976aa1af527ae42daedbc9d5a9f7b7ecfde174d3a","observation_id":"03d01af8-95fd-409f-aaad-ceab762d9edb","resolution":{"observed_at":"2026-08-05T23:39:46.058242Z","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":"2026-08-05T23:39:46.061548Z","title":"Neural ordinary differential equations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.061548Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:c96cd5bdb52a6439de8b0c2ff339bf087d5aca6958d5d947957defd5a5cedfcf","observation_id":"b0871e48-9b67-45c1-9a24-0894d6ce7716","resolution":{"observed_at":"2026-08-05T23:39:46.061548Z","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":"2026-08-05T23:39:46.064750Z","title":"Adaptive universal generalized pagerank graph neural network","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.064750Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:cabb8b59a351e6c1fbcdfa97943e5c571fb2f35929ecaa58e94a064ce56a7362","observation_id":"c5ff78c6-2c03-4376-9f16-3e7e48d20f19","resolution":{"observed_at":"2026-08-05T23:39:46.064750Z","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":"2026-08-05T23:39:46.072289Z","title":"Gread: Graph neural reaction-diffusion networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.072289Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:3e8ab409e5ecb8757ecbd53ec282da96873cad5abead701f5790ff1014d87eb2","observation_id":"ae09191b-60b2-406a-82d3-db71e7e5503a","resolution":{"observed_at":"2026-08-05T23:39:46.072289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.14743","last_updated":"2020-09-30T15:29:05Z","snapshot_observed_at":"2026-07-06T10:00:12.181391Z","submitted_at":"2020-09-30T15:29:05Z","title":"Multi-channel Deep 3D Face Recognition","version":1},"cited_work":{"arxiv_id":"2009.14743","doi":null,"metadata_source":"pith","pith_arxiv_id":"2009.14743","snapshot_observed_at":"2026-08-05T23:39:47.636828Z","title":"Multi-channel Deep 3D Face Recognition","venue":"cs.CV","work_id":"aadf83e0-7640-4353-935f-d07b2262dd72","year":2020},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.077368Z"},"links":{"cited_paper":"/paper/2009.14743","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:f744dda6c1f4755a0028a2e448ab4f79bef6938dbf43589324a02ddb959b6b11","observation_id":"42b2b07b-d113-47a3-852c-0043d8d4c5cd","resolution":{"observed_at":"2026-08-05T23:39:47.712915Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:46.081493Z","title":"From block-toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.081493Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:9cbbdddf09332af0323c6e53b6f3ea4e121e77fa6f95fae8b96e9e0b878cae21","observation_id":"70e3b6d1-4f0b-4274-acd2-96a7fa371a80","resolution":{"observed_at":"2026-08-05T23:39:46.081493Z","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":"2026-08-05T23:39:46.087242Z","title":"Principal Neighbourhood Aggregation for Graph Nets","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.087242Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:f6361a4439ea8b47f065de00383c1469bf85b3162097624cb072b96435a12d9c","observation_id":"ffd18064-af35-4d6f-97e1-8f660b94ff37","resolution":{"observed_at":"2026-08-05T23:39:46.087242Z","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":"2026-08-05T23:39:46.091401Z","title":"On over-squashing in message passing neural networks: the impact of width, depth, and topology","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.091401Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:fe52ab76ff1939b93ef17bed2feeb7731074abf53ecda3d7efeef0f494d3bd67","observation_id":"e194f986-6e06-46ef-942f-fb943abd2654","resolution":{"observed_at":"2026-08-05T23:39:46.091401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10991","last_updated":"2023-09-06T06:58:11Z","snapshot_observed_at":"2026-08-10T06:11:19.584898Z","submitted_at":"2022-06-22T11:45:36Z","title":"Understanding convolution on graphs via energies","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.10991","snapshot_observed_at":"2026-08-05T23:39:46.095588Z","title":"Chamberlain, Thomas Markovich, and Michael M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.095588Z"},"links":{"cited_paper":"/paper/2206.10991","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:540403b5bdb16374dfc6e4ada9ce2ca4f744c815fb4ffd7a4a41eaf0a5decfe9","observation_id":"30ef06ba-f79f-4ca9-9d40-6a58fd146348","resolution":{"observed_at":"2026-08-05T23:39:46.095588Z","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":"2026-08-05T23:39:46.100864Z","title":"Gbk-gnn: Gated bi-kernel graph neural networks for modeling both homophily and heterophily","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.100864Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:fa92b9b9c379f3bacdb93049d5ddecdcb4a6997286b0d6ac460f7daf4a9f31ec","observation_id":"86c0422c-8e43-4944-951a-9cfba1904ada","resolution":{"observed_at":"2026-08-05T23:39:46.100864Z","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":"2026-08-05T23:39:46.105016Z","title":"Implicit generation and modeling with energy based models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.105016Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:435bba7b3d7226f349ae88cc87d73a1abc7c10a5119ba62a561173ded079778f","observation_id":"7e9261f7-74b2-4d7c-8d83-6ecf2c732a51","resolution":{"observed_at":"2026-08-05T23:39:46.105016Z","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":"2026-08-05T23:39:46.109709Z","title":"A Generalization of Transformer Networks to Graphs","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.109709Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:e3684d1eb389f344a3a823498c5a7aa74d2916461959e4635bf8d1bc3e675f9e","observation_id":"11b809dd-7253-462b-9e7a-5ae6df93c750","resolution":{"observed_at":"2026-08-05T23:39:46.109709Z","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":"2026-08-05T23:39:46.114082Z","title":"Graph neural networks with learnable structural and positional representations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.114082Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:4a2ad6afe720aaded404f0a3f12a1957b108edb4cf7d791e6e81a53e038072c6","observation_id":"fcc79015-0ba2-40c0-b9d4-56d67195ba50","resolution":{"observed_at":"2026-08-05T23:39:46.114082Z","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":"2026-08-05T23:39:46.117624Z","title":"Long Range Graph Benchmark","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.117624Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:9c2e1da0c435ff7542714d628ec4763832f09495877dc5132ee4e2e8d07a55e8","observation_id":"fb3184a9-3c5a-4cb5-965c-bedecd32be9e","resolution":{"observed_at":"2026-08-05T23:39:46.117624Z","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":"2026-08-05T23:39:46.121387Z","title":"Benchmarking graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.121387Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:754486419ce1afd08e8b16c431a3efce3fd8ad43b2c4a027a88ba306bb023307","observation_id":"52e6e211-df45-47b7-bf4c-0512b92fa622","resolution":{"observed_at":"2026-08-05T23:39:46.121387Z","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":"2026-08-05T23:39:46.125891Z","title":"PDE-GCN: Novel architectures for graph neural networks motivated by partial differential equations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.125891Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:5a3a0d71565fd7cdc72c01fb55e0062c9a1aab4a5d0a6fb39c15fde8b3b1259d","observation_id":"2857972b-d576-4a1f-999a-1670a6562732","resolution":{"observed_at":"2026-08-05T23:39:46.125891Z","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":"2026-08-05T23:39:46.130413Z","title":"Feature transportation improves graph neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.130413Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:de0abc0f4f0af04b1c71ea285d07d8354a8f115a76dcee0557328e826c7f03c6","observation_id":"cbbd1159-8c07-48c6-b303-bd5dd055ae8f","resolution":{"observed_at":"2026-08-05T23:39:46.130413Z","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":"2026-08-05T23:39:46.134314Z","title":"On the temporal domain of differential equation inspired graph neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.134314Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:d5f701f0233f15dbb60254e3e4ab0c74aa5c346dd6994d805015f8997479eb08","observation_id":"8520524c-246c-42ad-9fcb-76eab1aec656","resolution":{"observed_at":"2026-08-05T23:39:46.134314Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.15360","last_updated":"2025-03-19T16:00:53Z","snapshot_observed_at":"2026-08-07T23:31:01.692494Z","submitted_at":"2025-03-19T16:00:53Z","title":"Lyapunov-Based Graph Neural Networks for Adaptive Control of Multi-Agent Systems","version":1},"cited_work":{"arxiv_id":"2503.15360","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.15360","snapshot_observed_at":"2026-08-05T23:39:47.385164Z","title":"Lyapunov-Based Graph Neural Networks for Adaptive Control of Multi-Agent Systems","venue":"eess.SY","work_id":"e0fe5a85-53fe-46c5-989f-f67f2e53700d","year":2025},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.138089Z"},"links":{"cited_paper":"/paper/2503.15360","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:134040dd2a34c79124fadfef6b3b01e5ae90d31a26a027b6d5bd05e9ad0e0e07","observation_id":"2544fc9a-3f71-4482-a6af-0d3d3264e0b0","resolution":{"observed_at":"2026-08-05T23:39:47.471750Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:46.142410Z","title":"Bronstein, and Ismail Ilkan Ceylan","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.142410Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:3bef9c946acc648a4856ac8fcb4e30d985c63cf9be78a10a0e95ad9c436e2855","observation_id":"2a3193eb-1b87-4408-9165-631dd82a01e0","resolution":{"observed_at":"2026-08-05T23:39:46.142410Z","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":"2026-08-05T23:39:46.146214Z","title":"A large-scale database for graph representation learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.146214Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:9af524b4dfa1efaea902d1b988cbad7f22c64866226f420e41f5da4ad3678a51","observation_id":"e6d5e96e-afa9-4b36-a5a5-0b6b00193123","resolution":{"observed_at":"2026-08-05T23:39:46.146214Z","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":"2026-08-05T23:39:46.151591Z","title":"Physics-informed graph neural galerkin networks: A unified framework for solving pde-governed forward and inverse problems","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.151591Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:99ef58f7cb77e6d3a57b8d467d18a8b8e4ea4edcdbf3c843d699504f7cc23cac","observation_id":"9aa0ff67-6ec5-4ff1-a13f-1cb999e37ac8","resolution":{"observed_at":"2026-08-05T23:39:46.151591Z","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":"2026-08-05T23:39:46.156294Z","title":"Diffusion Improves Graph Learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.156294Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:94cd9de24d636d5dae23ae20de2d5e66e0242d03304400ca7d5b63e29f0eb8c2","observation_id":"c9074d12-57c9-41bb-85c9-84b8e1f62fd2","resolution":{"observed_at":"2026-08-05T23:39:46.156294Z","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":"2026-08-05T23:39:46.160647Z","title":"On the trade-off between over-smoothing and over-squashing in deep graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.160647Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:25c677f5b3b07ff4b97ea7b9d6dfd953cfe0a2f928a5b329d39c276eb8388143","observation_id":"9bc43ef5-214c-414c-8323-e9af054ff359","resolution":{"observed_at":"2026-08-05T23:39:46.160647Z","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":"2026-08-05T23:39:46.164867Z","title":"Anti-Symmetric DGN: a stable architecture for Deep Graph Networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.164867Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:1f89b2f152b4fffb95f045fac7b373dcc9e19f9a8eb90835efa262e86c4dece1","observation_id":"fce9e59f-03ed-4c98-a345-622ba51b7fda","resolution":{"observed_at":"2026-08-05T23:39:46.164867Z","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":"2026-08-05T23:39:46.168950Z","title":"On oversquashing in graph neural networks through the lens of dynamical systems","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.168950Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:440d201abf8168207d81bb5a247e7696114b262c836763b52362fe8014bf426c","observation_id":"d67ed53f-a586-4978-a8d4-59996ad39a3e","resolution":{"observed_at":"2026-08-05T23:39:46.168950Z","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":"2026-08-05T23:39:46.172621Z","title":"Efficiently modeling long sequences with structured state spaces","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.172621Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:6e606425e1e90a258b0bee6102c04625606f244b52ecc093151748b0ff6132e0","observation_id":"5de35a24-85ca-4e79-9c62-7a66f6aeb1c2","resolution":{"observed_at":"2026-08-05T23:39:46.172621Z","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":"2026-08-05T23:39:46.177935Z","title":"Egc: Image generation and classification via a diffusion energy-based model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.177935Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:f4d4ed9942d7a7fd933063f14e1ebf9224107204cec9886923da0a61047a20aa","observation_id":"ea980318-18a0-48ea-afcb-bbb41597db4b","resolution":{"observed_at":"2026-08-05T23:39:46.177935Z","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":"2026-08-05T23:39:46.181405Z","title":"Drew: Dynamically rewired message passing with delay","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.181405Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:9b12afd2cbab253f711d713d89a4f66a43623c0091a9cfa730257a52aa33db14","observation_id":"5ef1aeaf-fb01-4178-82db-196f582deddc","resolution":{"observed_at":"2026-08-05T23:39:46.181405Z","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":"2026-08-05T23:39:46.185097Z","title":"Hamilton, Rex Ying, and Jure Leskovec","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.185097Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:103e648b7a83dd3de3ab2e2d479c0ea81fbd5f0ff7b9cde0030bb4a74180b988","observation_id":"fa5eb6e6-0c40-497a-8411-b6437ab30964","resolution":{"observed_at":"2026-08-05T23:39:46.185097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10121","last_updated":"2023-10-29T21:31:53Z","snapshot_observed_at":"2026-08-05T17:32:49.898075Z","submitted_at":"2023-10-16T06:57:24Z","title":"From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyond","version":2},"cited_work":{"arxiv_id":"2310.10121","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.10121","snapshot_observed_at":"2026-08-05T23:39:47.183817Z","title":"From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyond","venue":"cs.LG","work_id":"c4c00451-6556-4ab2-a5b9-c481374c25dc","year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.189334Z"},"links":{"cited_paper":"/paper/2310.10121","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:02728e4318cd8ccfd648f517f8168fbd9918509eda9399286819574e188f048d","observation_id":"9dfdd0f0-8b49-4cec-8388-19c77a11e714","resolution":{"observed_at":"2026-08-05T23:39:47.262395Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.489356Z","title":"Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks","venue":null,"work_id":"63752149-ecf5-4622-98fe-a9aad2df4f07","year":2025},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.194135Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:d336a874fe3c39d89f6748de778cef25b8f7cadb298d1699ff341b5daafad97b","observation_id":"3741fd4c-eb0d-4463-9782-420f8564919b","resolution":{"observed_at":"2026-08-05T23:39:48.493141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:46.197573Z","title":"Long short-term memory","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.197573Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:d3a241efe6c1a06bae766c6fa725b49873acd0e49cfa9ecbf5bf4f10fc023f5b","observation_id":"6bd25e75-b0b4-4ff9-b844-12b8fefdb313","resolution":{"observed_at":"2026-08-05T23:39:46.197573Z","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":"2026-08-05T23:39:48.477777Z","title":"Strategies for Pre-training Graph Neural Networks","venue":null,"work_id":"579eab16-fffb-4a54-8da2-a481e70842b2","year":2020},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.201380Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:17b9f3db71764d16ea868c56e64851a09d93b06b0e1eaca66069b7eace52fd66","observation_id":"72d95d9d-3cf5-4126-94a2-a4a411b51dd3","resolution":{"observed_at":"2026-08-05T23:39:48.481893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.465605Z","title":"Global self- attention as a replacement for graph convolution","venue":null,"work_id":"4f448987-8f06-4885-b88c-ee4f8451f72c","year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.205291Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:2bff15671bdd12550a50fc74e736618e2f6a5928cb1aedf45d4ba2a9015ca140","observation_id":"e7311c36-c4c9-4607-9efb-ce20fe970d3f","resolution":{"observed_at":"2026-08-05T23:39:48.469268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.454104Z","title":"Spectral graph pruning against over-squashing and over-smoothing","venue":null,"work_id":"62fd987c-0660-485d-bda2-96f60321961e","year":2024},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.209363Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:a123cbaba9e5017ae70b9406308d0113ba018b1fbccaaa21c4220629d5886ae9","observation_id":"83e00248-561f-44e2-9821-d299a269e93e","resolution":{"observed_at":"2026-08-05T23:39:48.458296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.441407Z","title":"Nonlinear systems, volume 3","venue":null,"work_id":"4aa8cfce-5d42-4db7-8564-470478717d06","year":2002},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.212745Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:e09b8a18a68d884c63c68dca88b830168a19d38d1ed91902d94c9d786f0b8f87","observation_id":"08a9c6d6-7f44-46eb-a456-4e80128e36d6","resolution":{"observed_at":"2026-08-05T23:39:48.445282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.429873Z","title":"Kipf and M","venue":null,"work_id":"564d9f1a-d587-47c1-a5de-32fcfc072e19","year":2016},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.216642Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:6543bff5e1ffdff7a924e601b925b6f1271ad4e54ff2bd0f48c45b3be47465d2","observation_id":"42178800-f0ef-46ad-a882-d8ed25c522a8","resolution":{"observed_at":"2026-08-05T23:39:48.433600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.415703Z","title":"Bayan Bruss, and Tom Goldstein","venue":null,"work_id":"907453cb-25a2-4f2a-ba43-38d7cbd5369b","year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.220139Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:7db20ea6b710d130bc3c3f5520a1962c141ae324107af738d565176919d42758","observation_id":"dc63a956-fb37-4070-be0f-8f9169e23c3e","resolution":{"observed_at":"2026-08-05T23:39:48.420274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.405335Z","title":"Rethinking graph transformers with spectral attention","venue":null,"work_id":"e824ce5f-62f6-4e58-aec9-89cf6fe10fee","year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.228474Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:07d55dafae1b304d44a249cc2bd513ab8b9c5cd4abd7b344744376f1acc090f1","observation_id":"f64220b8-2d25-4c84-a8d9-199472f0b91f","resolution":{"observed_at":"2026-08-05T23:39:48.408555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.392724Z","title":null,"venue":null,"work_id":"5c75a387-bce7-4d5c-90f7-a0cc933f471b","year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.231766Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:b89c0a791ee660fae8a91992eeef94c46cf644ef0413d0e6415c4830bc0d6160","observation_id":"e8be2647-8e48-468c-ae53-1a79d7024453","resolution":{"observed_at":"2026-08-05T23:39:48.397019Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.381482Z","title":"A tutorial on energy-based learning","venue":null,"work_id":"0b56052c-b8f3-4e85-b9c7-6354255d8230","year":2006},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.235885Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:a06b50cf5cffd3e442ac29bad16865ca56045d83d79ed9de736ed8a8d1e9f8b1","observation_id":"47ac86af-c2fa-4193-bb05-4acc71985145","resolution":{"observed_at":"2026-08-05T23:39:48.384921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.369456Z","title":"Finding global homophily in graph neural networks when meeting heterophily","venue":null,"work_id":"490ffb3c-4219-43fd-b272-e8f3868d6c78","year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.240358Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:db08acdf145a37c7bfb167d98a7b2718575ac9ea29d1fcf9c811f66e10dd5f71","observation_id":"fae87206-8625-4bfe-825e-286cc2eee42a","resolution":{"observed_at":"2026-08-05T23:39:48.373536Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.5281/zenodo.7620796","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"Toloker Graph: Interaction of Crowd Annotators, February 2023","venue":"Zenodo (CERN European Organization for Nuclear Research)","work_id":"899986c3-eef4-48b2-a6d0-087673cd0b9a","year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.244252Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:560260342dc51f2b607e4ab76a1c9018a4e9eae9e2c32ce68dd8f0abcb410b85","observation_id":"3c49000c-535b-4e65-920d-55adb381a198","resolution":{"observed_at":"2026-08-05T23:39:46.798712Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.356718Z","title":"GraphEBM: Molecular graph generation with energy-based models","venue":null,"work_id":"0cb1d349-e1b5-4b6e-a193-41548070bf38","year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.248573Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:42861b3951e9d5fe8fb41c15c90e1e92f35e4e61a9a860496e549c9e54f9423f","observation_id":"8cfa8343-5d56-48b3-8322-f502ce62e81b","resolution":{"observed_at":"2026-08-05T23:39:48.360299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.09618","last_updated":"2024-07-12T18:04:32Z","snapshot_observed_at":"2026-08-06T01:25:59.316954Z","submitted_at":"2024-07-12T18:04:32Z","title":"The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.09618","snapshot_observed_at":"2026-08-05T23:39:46.252436Z","title":"Li, Jian Tang, Guy Wolf, and Stefanie Jegelka","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.252436Z"},"links":{"cited_paper":"/paper/2407.09618","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:829ded9d11675dfc353f1fe996f72779d417a6b2a6fbb27bf5d9bc1033c4036c","observation_id":"4e104999-b88c-4a3e-8255-51f4b46f9bce","resolution":{"observed_at":"2026-08-05T23:39:46.252436Z","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":"2026-08-05T23:39:48.345300Z","title":"Graph inductive biases in transformers without message passing","venue":null,"work_id":"85eaccf3-d9ea-436c-a00d-afd4537c65a4","year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.256072Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:eeebb64a28b76f9d61f78d582fc7a67a3f68e34c52dee8b8ba0536da12a16542","observation_id":"778cc62b-9381-44e8-9cc4-d2581060aeef","resolution":{"observed_at":"2026-08-05T23:39:48.349248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.333781Z","title":"Qdc: Quantum diffusion convolution kernels on graphs, 2023","venue":null,"work_id":"a2a196e4-50b3-4881-aec1-045eeb0d493d","year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.259723Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:10f7ae5580e33009edabe06dd6f72c8b16266b7a36344d30d0d7eadcdec67a79","observation_id":"0566e39f-c3f2-4c0e-8e50-9bc44a6091ee","resolution":{"observed_at":"2026-08-05T23:39:48.337436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.321054Z","title":"A fractional graph laplacian approach to oversmoothing","venue":null,"work_id":"7d126e87-bbda-4c3d-b592-55c53aff275f","year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.263248Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:f347dd6e2c97d28789d24a5a38a461b375f36036d6cb3edcea283be95ffc0d8d","observation_id":"6c01912c-f197-44f1-b5d8-730fce036ba1","resolution":{"observed_at":"2026-08-05T23:39:48.324510Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.309182Z","title":"Simplifying approach to node classification in graph neural networks","venue":null,"work_id":"8ecb55f9-d794-4559-a582-73c2eacb0a4d","year":null},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.266908Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:c96bd24b1b164cffb8a970024cb7965f3400181199399e4c01e3875c9222402e","observation_id":"e463088a-393e-46a0-9986-ecf672726132","resolution":{"observed_at":"2026-08-05T23:39:48.312414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.298695Z","title":"Attending to graph transformers","venue":null,"work_id":"5e63a95d-1ff8-4f14-a666-6a5f04161834","year":2024},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.274293Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:7d6ffd50f4de45cd8913a020f34d90bbdf29b410a7aae0e9eae18362e58e46cc","observation_id":"941d10e1-b759-409a-8beb-bf20eff4e2eb","resolution":{"observed_at":"2026-08-05T23:39:48.301760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.287002Z","title":"Nocedal and S","venue":null,"work_id":"2a34253e-e8b4-4ed7-b3f5-44d463b98b9a","year":1999},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.277620Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:eab17773502d41ddb94746bb59493dceb1b636b378451e5231630d0506bb9e0b","observation_id":"225d4764-eee2-4a8b-bdcb-3b4b414dfba9","resolution":{"observed_at":"2026-08-05T23:39:48.290318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.09550","last_updated":"2019-05-26T05:21:04Z","snapshot_observed_at":"2026-07-06T07:54:54.802338Z","submitted_at":"2019-05-23T09:27:21Z","title":"Revisiting Graph Neural Networks: All We Have is Low-Pass Filters","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.09550","snapshot_observed_at":"2026-08-05T23:39:46.281000Z","title":"Revisiting graph neural networks: All we have is low-pass filters","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.281000Z"},"links":{"cited_paper":"/paper/1905.09550","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:6a040ecb9f5525ba9deb2f63dbc0085c01a32e33e12ae5b8396f707edf8fd7b8","observation_id":"52a5a9e2-118f-44b8-8733-5070cf613a43","resolution":{"observed_at":"2026-08-05T23:39:46.281000Z","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":"2026-08-05T23:39:48.276659Z","title":"Graph neural networks exponentially lose expressive power for node classification","venue":null,"work_id":"39f767d1-e7ca-4311-af3b-ef4acd6ae5c2","year":2020},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.286511Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:df6dd5b3ecb770047b6a5a07237a89352e93610025e501849e7475e25762ab31","observation_id":"d9ffe4b8-94fe-4d55-b936-1b01ae85df22","resolution":{"observed_at":"2026-08-05T23:39:48.279860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:46.290834Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.290834Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:42c0dd51a4c521dee4a7632c6e6e18db294b92d343435783e46d1e2621c60fe6","observation_id":"99583dd7-8813-4b56-96a4-caeb11bd3d92","resolution":{"observed_at":"2026-08-05T23:39:46.290834Z","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":"2026-08-05T23:39:48.253892Z","title":"Beyond over-smoothing: Uncovering the trainability challenges in deep graph neural networks","venue":null,"work_id":"af097e2b-4626-4b76-9a84-e43a468f409f","year":2024},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.294567Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:031801a836faa85e1618c81b5bd5a301176e982ddb2725ed5fa465bbea0cccc0","observation_id":"14a3c9f6-8efb-4788-9dbc-e78fddf11176","resolution":{"observed_at":"2026-08-05T23:39:48.258355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.241303Z","title":"A critical look at the evaluation of GNNs under heterophily: Are we re- ally making progress? In The Eleventh International Conference on Learning Representations,","venue":null,"work_id":"65784ac3-e781-45de-b69e-d7c08ab4e508","year":null},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.298604Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:b212a1cfeccf18e5df9da2de2f70ebb7f7429244eac5c3678bc55d2363c93173","observation_id":"267f0df6-7af7-44c3-a8f4-efd87dd1c2b3","resolution":{"observed_at":"2026-08-05T23:39:48.245457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12454","last_updated":"2023-01-15T13:04:02Z","snapshot_observed_at":"2026-08-09T11:05:42.828157Z","submitted_at":"2022-05-25T02:56:24Z","title":"Recipe for a General, Powerful, Scalable Graph Transformer","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.12454","snapshot_observed_at":"2026-08-05T23:39:46.317375Z","title":"Recipe for a general, powerful, scalable graph transformer (graphgps)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.317375Z"},"links":{"cited_paper":"/paper/2205.12454","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:2f1550774a4d01e8872b0fb499a9af6fb4b1953979722ea626ed34fdd1b470e9","observation_id":"e7967d9c-7540-4455-b4eb-0372a664a8f7","resolution":{"observed_at":"2026-08-05T23:39:46.317375Z","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":"2026-08-05T23:39:46.322170Z","title":"Recipe for a General, Powerful, Scalable Graph Transformer","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.322170Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:9712733065ca5c38b7e097a1d05041fd82aaa531964cc9092bec5522e56cf0eb","observation_id":"9204b7c0-5ff8-4518-be99-b5fc9e4ba8ae","resolution":{"observed_at":"2026-08-05T23:39:46.322170Z","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":"2026-08-05T23:39:46.325492Z","title":"Graph neural networks for materials science and chemistry","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.325492Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:5f062ef1da8394e02eeefefbf0b8b8472f39aac0f51a7bd1e730a4ab83a2a488","observation_id":"0330d85b-9fd7-4fb3-92ce-ef631f0c84ea","resolution":{"observed_at":"2026-08-05T23:39:46.325492Z","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":"2026-08-05T23:39:48.206202Z","title":"Lyanet: A lyapunov framework for training neural odes","venue":null,"work_id":"204cf1ee-dcbb-4cc9-b422-f28463c6ad5d","year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.328823Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:3a92402911acac839bcefbaa70cde5a41aaf0be0bfcab196cee67544a26fa948","observation_id":"515afaf9-856c-4ea6-bc71-4671393a502c","resolution":{"observed_at":"2026-08-05T23:39:48.209987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.195618Z","title":"Graph-coupled oscillator networks","venue":null,"work_id":"35e2c222-711a-430c-9c79-4c98432af97a","year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.331894Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:cdf9ae2b1821c350085c420d3b62f238952be8fc3f15b7844dcb1e2a847a5985","observation_id":"1a7d6221-e243-4925-a9bf-ebbf0600f4c1","resolution":{"observed_at":"2026-08-05T23:39:48.198763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10993","last_updated":"2023-03-20T10:21:29Z","snapshot_observed_at":"2026-08-10T02:14:11.377359Z","submitted_at":"2023-03-20T10:21:29Z","title":"A Survey on Oversmoothing in Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.10993","snapshot_observed_at":"2026-08-05T23:39:46.336055Z","title":"Konstantin Rusch, Michael M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.336055Z"},"links":{"cited_paper":"/paper/2303.10993","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:1aa4c45a8640c5eb96401ae1fb9a7c5a6ff87557f9a761ff37611452a8d917c9","observation_id":"f658564b-6ec8-45fd-b573-8d10aa6d4e4e","resolution":{"observed_at":"2026-08-05T23:39:46.336055Z","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":"2026-08-05T23:39:48.183281Z","title":"Deep neural networks motivated by partial differential equations","venue":null,"work_id":"78e89363-d5fc-43cb-9456-f89cfe3eda33","year":2020},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.339505Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:37f78cb02e7b495613229eecaef763d9ff6de1675476b60ad33085d7a2d325f5","observation_id":"5bfdc4af-9e80-4750-83ac-87df6bb46aac","resolution":{"observed_at":"2026-08-05T23:39:48.187629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.172948Z","title":"Qm/mm methods for biomolecular systems","venue":null,"work_id":"67987060-cc82-487e-915d-770aa0c55ba3","year":2009},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.343064Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:6f08add65992de5af3cbf7aa245d7815cae4788cc4228f301f784029b61abacc","observation_id":"806d9dce-ed76-4a22-a66b-a80213e2140f","resolution":{"observed_at":"2026-08-05T23:39:48.175859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07073","last_updated":"2023-11-17T22:51:23Z","snapshot_observed_at":"2026-07-06T16:46:26.447076Z","submitted_at":"2023-11-13T04:40:13Z","title":"Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challenges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07073","snapshot_observed_at":"2026-08-05T23:39:46.347371Z","title":"Exposition on over-squashing prob- lem on gnns: Current methods, benchmarks and challenges","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.347371Z"},"links":{"cited_paper":"/paper/2311.07073","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:65d49e231f0e8eab3f79b321bd9388d6a0f76a25d2786b3dcc2f8dfa993d436f","observation_id":"a20d2ff8-c089-4101-a640-98cd97761036","resolution":{"observed_at":"2026-08-05T23:39:46.347371Z","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":"2026-08-05T23:39:46.351018Z","title":"Masked label prediction: Unified message passing model for semi-supervised classifica- tion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.351018Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:2c5e406e5c6627d951def03bc23e681a95170e7ab00505f50da0ea6aa9efd5b3","observation_id":"55f3551a-7ba6-4232-b657-4fab5783a4ff","resolution":{"observed_at":"2026-08-05T23:39:46.351018Z","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":"2026-08-05T23:39:48.163101Z","title":"Rahmani, and Marzieh Aghaei","venue":null,"work_id":"0894ff0a-7c6b-48e8-9b2d-2694d1db25d9","year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.355821Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:da19587cc9c4633c96533520a5f88f2e95f203caa9fb5f0e49841fbdfe43e560","observation_id":"9ea2dfb0-0b63-4b96-95b2-f9a3b3de19e8","resolution":{"observed_at":"2026-08-05T23:39:48.166492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.151857Z","title":"Where did the gap go? reassessing the long-range graph benchmark","venue":null,"work_id":"6f16001f-94bd-455f-8fec-6a0c8db83bfa","year":null},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.359038Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:2e5a558b7e6f1f88060faaa125e4b7462a5179548f668084b558c65f463d2f9b","observation_id":"d5ec6284-acdd-489a-9c6e-4e78eb03cdba","resolution":{"observed_at":"2026-08-05T23:39:48.155899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.130687Z","title":"Walking out of the weis- feiler leman hierarchy: Graph learning beyond message passing","venue":null,"work_id":"8140db6f-5136-4329-9fb3-a81673f095e7","year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.367538Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:78704db4e8c15ec0b82bc24739b927ce37174f5eebfdbe455b5561de97129ab4","observation_id":"adef06a8-4848-497c-8532-a8e0acbca58e","resolution":{"observed_at":"2026-08-05T23:39:48.134332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:46.372579Z","title":"Bronstein","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.372579Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:c6397cdef72a3b97b06a8041547ebdc977f417cefc769fdf99590f4af7ebe600","observation_id":"10f10dd2-6684-46b6-857e-fbd8628dcd9a","resolution":{"observed_at":"2026-08-05T23:39:46.372579Z","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":"2026-08-05T23:39:48.111452Z","title":"Capturing graphs with hypo-elliptic diffusions","venue":null,"work_id":"3887be40-b5d7-452d-a0d3-1989a4edbf1b","year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.377886Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:10ac8ccebaae08e7f156318eb2d04f91216ae2416ecf9cc86e2b99ab9765624e","observation_id":"844f643b-af78-4e86-81da-723900977566","resolution":{"observed_at":"2026-08-05T23:39:48.115138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.098912Z","title":"Vaswani et al","venue":null,"work_id":"40eb2ef5-749f-4ebb-8508-ec204b8cce53","year":2017},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.383319Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:68fa5165f9d025d46172c363e468a0bb9ac26887fa13d6d95219111acdbc8382","observation_id":"e2e5f252-51b2-494a-823e-7fbea0689841","resolution":{"observed_at":"2026-08-05T23:39:48.101969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.140893Z","title":null,"venue":null,"work_id":"d674bd0e-e8d9-4511-a9bd-c2559ccea0b0","year":null},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.362823Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:bd779443b48871ac2a58040e6434bb599bb818f5b075054ebc012d1b42d43e3d","observation_id":"b3e89835-42ba-4f7c-ab00-268256b6c29f","resolution":{"observed_at":"2026-08-05T23:39:48.144423Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00789","last_updated":"2024-02-01T17:21:53Z","snapshot_observed_at":"2026-08-09T22:41:29.472963Z","submitted_at":"2024-02-01T17:21:53Z","title":"Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00789","snapshot_observed_at":"2026-08-05T23:39:46.394973Z","title":"Graph-mamba: Towards long-range graph sequence modeling with selective state spaces","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.394973Z"},"links":{"cited_paper":"/paper/2402.00789","citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:cdc7a173bf308753cc6db5c15c74990b394377273cf2448c93d216cf0ded24b1","observation_id":"23c5b6e2-2445-43a7-9fa7-f015dde1ead7","resolution":{"observed_at":"2026-08-05T23:39:46.394973Z","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":"2026-08-05T23:39:48.078146Z","title":"The heterophilic snowflake hypothesis: Training and empowering gnns for heterophilic graphs","venue":null,"work_id":"014727f6-84a7-4a14-9183-ee8738a1848d","year":null},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.401316Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:239f601d7048dff94508bf887cead9593f8959543c238add2531715d4c8e2dec","observation_id":"6a4d4f77-5809-4e86-a3e5-98488b4aede5","resolution":{"observed_at":"2026-08-05T23:39:48.081202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.067333Z","title":"How powerful are spectral graph neural networks","venue":null,"work_id":"6d575d23-6e86-497d-9be9-f6fd167fa24b","year":2022},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.413160Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:a233c97438d410082b015f78448495b18f5455063864b915daa7a74e88d6abfc","observation_id":"2c62ac03-e3fc-4d8f-963b-9578b9c9b8c4","resolution":{"observed_at":"2026-08-05T23:39:48.070486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.056109Z","title":"Dissecting the Diffusion Process in Linear Graph Convolutional Networks","venue":null,"work_id":"f110c426-6b92-4012-bae3-2298046c944e","year":2021},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.418433Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:b4a4170f21023d6cbaf0b8b795ba4886a5bd905acdf0d64e149637afa7257dc2","observation_id":"8a2a89d0-d098-45ad-9da2-cc6dfc74b832","resolution":{"observed_at":"2026-08-05T23:39:48.059979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.087532Z","title":"Graph attention networks","venue":null,"work_id":"47cba136-c14e-4989-90f6-527de4998472","year":2018},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.389803Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:dfb848e311800c0f82be77be82546ac07c847e48cc0e193e030009afdd561203","observation_id":"70f7f8df-2977-46c3-877e-7fc4f3f66257","resolution":{"observed_at":"2026-08-05T23:39:48.091485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.030480Z","title":"Recent successes of the energy landscape theory of protein folding and function","venue":null,"work_id":"6ab2d91b-0d2a-4535-8d73-fb0af966172b","year":2005},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.429433Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:8001c9faae884ca21857e82fd264c7c2f6857a5893f8c2e4736eac5772afeba9","observation_id":"90671510-482e-4ff1-9181-5ee050424836","resolution":{"observed_at":"2026-08-05T23:39:48.034701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.018011Z","title":"Continuous graph neural networks","venue":null,"work_id":"f3bbd792-f529-425d-86f0-5a967c21521d","year":null},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.435083Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:5b89d57b57f64e4af4f5623ef1ae315d976766cb44229a87e3c45b15d7e466c6","observation_id":"466b52af-1f8e-444e-9dd2-1fafff29a4fa","resolution":{"observed_at":"2026-08-05T23:39:48.022315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:47.991911Z","title":"A theory of generative convnet","venue":null,"work_id":"adf5c98a-08ce-4226-aeea-ce46e656bc49","year":2016},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.445846Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:c10f088f35f03244a3839f359b18c11d90190256dfc5872140b144e85e0ddc8d","observation_id":"4f600fce-b3ad-4cd6-9fc3-5d05c8f11724","resolution":{"observed_at":"2026-08-05T23:39:47.996803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:47.980097Z","title":"How powerful are graph neural networks? In International Conference on Learning Representations , 2019","venue":null,"work_id":"46155eda-6c0c-4427-9d39-558e36ffc30e","year":2019},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.455658Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:384beab4af6e937af4f9515851ccc04171520c51320aef88ca4092ae1c5b0eac","observation_id":"30747cab-0b31-4a43-a0b7-77c0a1672d47","resolution":{"observed_at":"2026-08-05T23:39:47.984651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T23:39:48.042513Z","title":"ACMP: Allen-cahn message passing with attractive and repulsive forces for graph neural networks","venue":null,"work_id":"74609f92-ca99-4b16-86b7-cf7e15f26f44","year":2023},"citing_paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","version":1},"reference_index":104,"source":"pdf_text","source_observed_at":"2026-08-05T23:39:46.424000Z"},"links":{"citing_paper":"/paper/2508.05070"},"observation_digest":"sha256:36ca098004ea68baa6d58efb5e766858c8bdd8f51f1d40c5c9e045d4f8cb40c0","observation_id":"046a9840-0409-4d30-84d9-6ef3dc02c999","resolution":{"observed_at":"2026-08-05T23:39:48.047134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.05070","last_updated":"2025-08-07T06:44:01Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T01:06:54.658175Z","submitted_at":"2025-08-07T06:44:01Z","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":57,"verified_exact":5,"verified_fuzzy":38},"total_outbound_references":116},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 100 of 116 outbound references and 0 inbound Pith citation observations for arXiv:2508.05070."}