{"as_of":"2026-08-20T13:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ee93dd687013a8d88c6465e8ff4f18485215f5be7b631f6904044529e16aba14","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T19:01:37.435879Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2412.07243/citation-record","integrity":"/paper/2412.07243/integrity","json":"/paper/2412.07243/citation-record.json","paper":"/paper/2412.07243"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:01:52.904822Z","title":"Entrywise eigenvector analysis of random matrices with low expected rank","venue":null,"work_id":"0c12de30-0355-412d-bd9b-f28d206767bc","year":2020},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.280102Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:cbec7e01ef88dbe66890ad248e6209775abb709c72e28dd29f536ceb85fa3b2f","observation_id":"157c2542-e0fe-4d4c-889e-f1350d99f959","resolution":{"observed_at":"2026-08-11T19:01:52.907860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.896282Z","title":"Convergence rates of neural networks for supervised learning on manifolds","venue":null,"work_id":"566de03b-d5fd-4c9e-b77a-4bdc737c9330","year":2019},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.284391Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:b388adce1c3ffdf9c81bf313c75e69197d0ac73a64ee18797042148e20d5b928","observation_id":"ff5f83b1-bb15-4be8-819e-e3f1c51efbc3","resolution":{"observed_at":"2026-08-11T19:01:52.899394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-08-15T04:53:45.483331Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-11T19:01:37.288424Z","title":"Layer normalization","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.288424Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:c4c709afef543734a939536f282c72bbb7cbf5b0b9e6e0b34dc6d20716c2ae91","observation_id":"a7d2126b-96f0-45d4-a1c8-8f5aa78309c0","resolution":{"observed_at":"2026-08-11T19:01:37.288424Z","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":"2026-08-11T19:01:52.887472Z","title":"A note on over-smoothing for graph neural networks","venue":null,"work_id":"59355064-d22a-4c87-b37c-0b70bc324418","year":2020},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.292093Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:52579acdf40765c3893c14a3257b5e694da5ec8c3348b064b53c3bf2b26d524e","observation_id":"22730b5c-7509-403a-9376-c7528e68378c","resolution":{"observed_at":"2026-08-11T19:01:52.890787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.878411Z","title":"Characterization of generalizability of spike timing dependent plasticity trained spiking neural networks","venue":null,"work_id":"4854a9d0-cb50-4cd5-89f3-1341a40d3556","year":2021},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.295503Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:c20eb9b8afc5ac209e4d21298fa0ad6beb826937fda37a681b27ad8f1c727316","observation_id":"ebe9ec3a-caf3-4571-ab8b-dab9b69040b2","resolution":{"observed_at":"2026-08-11T19:01:52.881742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:37.298836Z","title":"Heterogeneous recurrent spiking neural network for spatio-temporal classification","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.298836Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:965e925dc34a62568cf140eb5a1d0c97eeecb54afe796462bb4929da32517b5c","observation_id":"3c288f2f-f135-40fd-b0c4-722d24471632","resolution":{"observed_at":"2026-08-11T19:01:37.298836Z","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":"2026-08-11T19:01:52.869190Z","title":"darts: Model uncertainty-aware differentiable architecture search","venue":null,"work_id":"3c4e1444-6e52-4d0c-b3a1-9f0bfaba8947","year":2022},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.302948Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:41d831d0d20901aadd838b35a02f4c548fe1aa797847114466b52b816334e030","observation_id":"e3e02db9-71e3-4cbe-96c7-b21f46c40229","resolution":{"observed_at":"2026-08-11T19:01:52.872527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.859685Z","title":"Brain-inspired spiking neural network for online unsupervised time series prediction","venue":null,"work_id":"44bb0ae6-1ae4-4fea-9ce1-613ae8335eb6","year":2023},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.305990Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:15ad176e3dacd8b6a7052d14c077f73e3eac747a9c740acbe103fdd9a0340d2e","observation_id":"7c1d6f0f-47a3-4337-81d7-dbd21eb0bbc4","resolution":{"observed_at":"2026-08-11T19:01:52.862884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.850762Z","title":"Heterogeneous recurrent spiking neural network for spatio-temporal classification","venue":null,"work_id":"b38784ad-4165-487d-9047-11266668ac20","year":2023},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.309283Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:38d9b4573b09c838f3cf08becb581fbfcf503a67329ab8c6b4abbcbab5b773b8","observation_id":"6f56bc5c-011f-4f64-b605-70d003f7d531","resolution":{"observed_at":"2026-08-11T19:01:52.853998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11618","last_updated":"2023-08-05T15:22:00Z","snapshot_observed_at":"2026-08-18T10:28:54.337742Z","submitted_at":"2023-02-22T19:48:02Z","title":"Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles","version":2},"cited_work":{"arxiv_id":"2302.11618","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.11618","snapshot_observed_at":"2026-08-11T19:01:37.544361Z","title":"Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles","venue":"cs.AI","work_id":"8a140622-6f27-4d0e-876c-e7036cc1b280","year":2023},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.312677Z"},"links":{"cited_paper":"/paper/2302.11618","citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:b5c7c1e4f05f179d7a2e25e005363fb40af47c7486d15fce7c7db0972958ab21","observation_id":"ce88e80f-b1fc-4daa-abee-152d23025e39","resolution":{"observed_at":"2026-08-11T19:01:37.547952Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06452","last_updated":"2024-07-08T23:33:12Z","snapshot_observed_at":"2026-08-17T02:41:51.604100Z","submitted_at":"2024-07-08T23:33:12Z","title":"Exploiting Heterogeneity in Timescales for Sparse Recurrent Spiking Neural Networks for Energy-Efficient Edge Computing","version":1},"cited_work":{"arxiv_id":"2407.06452","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.06452","snapshot_observed_at":"2026-08-11T19:01:37.531111Z","title":"Exploiting Heterogeneity in Timescales for Sparse Recurrent Spiking Neural Networks for Energy-Efficient Edge Computing","venue":"cs.NE","work_id":"b2cae212-6550-4cb9-8a25-d7d8da273f3c","year":2024},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.316262Z"},"links":{"cited_paper":"/paper/2407.06452","citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:2e2d3a53669d47fc600a58802de741adcb7fd2b7ec086f171ba8c730f50a3050","observation_id":"10adf7d7-0ca7-43d0-88a5-6874e4c32481","resolution":{"observed_at":"2026-08-11T19:01:37.534816Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12462","last_updated":"2024-03-19T05:37:26Z","snapshot_observed_at":"2026-08-18T15:06:53.669378Z","submitted_at":"2024-03-19T05:37:26Z","title":"Topological Representations of Heterogeneous Learning Dynamics of Recurrent Spiking Neural Networks","version":1},"cited_work":{"arxiv_id":"2403.12462","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.12462","snapshot_observed_at":"2026-08-11T19:01:37.518885Z","title":"Topological Representations of Heterogeneous Learning Dynamics of Recurrent Spiking Neural Networks","venue":"cs.NE","work_id":"1c58059b-ab71-4862-bdc2-030e2062da6c","year":2024},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.319911Z"},"links":{"cited_paper":"/paper/2403.12462","citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:da9c2c6bc6df77641f24138538809a96b0ec170b223a828c02ba380cfd5148ab","observation_id":"3debb4d5-c295-4604-9d0c-7e88e026bdbb","resolution":{"observed_at":"2026-08-11T19:01:37.522378Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.841824Z","title":"A fully spiking hybrid neural network for energy-efficient object detection","venue":null,"work_id":"33319acf-5b26-4dbf-b2f7-a049e6aaf2b3","year":2021},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.323324Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:f1eedaaf4c4ef362dd690f3d60de430276c882f3dddd9fecfa20410f6f1a8a01","observation_id":"87163576-ac58-4a61-931c-a626296cbaaf","resolution":{"observed_at":"2026-08-11T19:01:52.844987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.832114Z","title":"Brain-inspired spatiotemporal processing algorithms for efficient event-based perception","venue":null,"work_id":"1fb2d1db-37f0-4ef2-bf07-1d830df3f9d8","year":2023},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.326353Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:37042cf44221f937f62447f2409ba1c9ed167f959724e70dd6c000bc03783451","observation_id":"51efc1ae-1641-4521-a162-787febd4c36e","resolution":{"observed_at":"2026-08-11T19:01:52.835360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03409","last_updated":"2024-03-06T02:36:15Z","snapshot_observed_at":"2026-08-16T14:12:27.323223Z","submitted_at":"2024-03-06T02:36:15Z","title":"Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN","version":1},"cited_work":{"arxiv_id":"2403.03409","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.03409","snapshot_observed_at":"2026-08-11T19:01:37.506246Z","title":"Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN","venue":"cs.NE","work_id":"ed13fa00-6b55-41bd-843b-51af62e91dd5","year":2024},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.329340Z"},"links":{"cited_paper":"/paper/2403.03409","citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:6647a759b7e73cf1de243b0e16153bcee5b98d177877f98d80c04e7009325002","observation_id":"3073045d-87e6-4f48-a5b5-9d792a189c86","resolution":{"observed_at":"2026-08-11T19:01:37.509847Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.822925Z","title":"Measuring and relieving the over-smoothing problem for graph neural networks from the topological view","venue":null,"work_id":"b621a0b9-8b9d-4808-9046-9a61af42300d","year":2020},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.333365Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:15e618f1ef67b321327f718b0d0b3a0d595c3fd59f8001371d9894b0cbcbc623","observation_id":"fa2ee311-bd1a-4b46-995c-3b0fd8bb202f","resolution":{"observed_at":"2026-08-11T19:01:52.826307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03589","last_updated":"2024-02-12T19:24:06Z","snapshot_observed_at":"2026-08-16T15:26:13.157252Z","submitted_at":"2023-06-06T11:15:53Z","title":"How does over-squashing affect the power of GNNs?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.03589","snapshot_observed_at":"2026-08-11T19:01:37.336447Z","title":"How does over-squashing affect the power of gnns? arXiv preprint arXiv:2306.03589, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.336447Z"},"links":{"cited_paper":"/paper/2306.03589","citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:0f8192c9b728b51ddd1d41bc41f708616030a76a05a79a66f610e7156ff87a94","observation_id":"ba78d5d7-1b57-465a-9355-212e2c769c35","resolution":{"observed_at":"2026-08-11T19:01:37.336447Z","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":"2026-08-11T19:01:37.339787Z","title":"Graph neural networks for social recommendation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.339787Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:962a2953d05f88a875a81a04e006cd6d9504a71d48f60d5cebe719a214586f04","observation_id":"87c86152-e861-4d21-8e34-62abdb357bf6","resolution":{"observed_at":"2026-08-11T19:01:37.339787Z","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":"2026-08-11T19:01:52.808666Z","title":"Gemnet: Universal directional graph neural networks for molecules","venue":null,"work_id":"575dc74d-491c-4950-ac91-86b6749ff55e","year":2021},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.342784Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:b1f735c8bade364b88941183711f7e1691362266e683f533b3af2b25b2314956","observation_id":"68c41ea3-3762-40ac-aa7f-f85d0144c89e","resolution":{"observed_at":"2026-08-11T19:01:52.811896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.799704Z","title":"Neural message passing for quantum chemistry","venue":null,"work_id":"dc3f1432-9366-47eb-896f-251cc589e666","year":2017},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.345827Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:d09842acc47a3d42e1b5eda9877e383c172dd7787fe6da7f7670ca3dcf2d4dde","observation_id":"b4ed58ab-2344-45f5-9735-17eb80a84c93","resolution":{"observed_at":"2026-08-11T19:01:52.802946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:37.349468Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.349468Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:5eba9c60828cd8e78fc97ca92672980339dc3acd909afb64f614fbec81e3b7b3","observation_id":"0e10a8d9-0334-4bca-aa8a-43430a668e29","resolution":{"observed_at":"2026-08-11T19:01:37.349468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11622","last_updated":"2023-02-22T19:57:12Z","snapshot_observed_at":"2026-08-16T15:53:26.566786Z","submitted_at":"2023-02-22T19:57:12Z","title":"Unsupervised 3D Object Learning through Neuron Activity aware Plasticity","version":1},"cited_work":{"arxiv_id":"2302.11622","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.11622","snapshot_observed_at":"2026-08-11T19:01:37.486307Z","title":"Unsupervised 3D Object Learning through Neuron Activity aware Plasticity","venue":"cs.AI","work_id":"f8262b5e-6e60-461a-a3a0-1e0da5c42561","year":2023},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.352583Z"},"links":{"cited_paper":"/paper/2302.11622","citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:62ee5494c1d7fb7f35e5176c876b4552099260ea324be6944331198e1ed34ae3","observation_id":"505e3364-4671-4afc-a22b-2d5e7431c8a5","resolution":{"observed_at":"2026-08-11T19:01:37.489685Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.785422Z","title":"Not too little, not too much: a theoretical analysis of graph (over)smoothing","venue":null,"work_id":"1e59614b-99f5-407e-934b-b9ea9a9977ee","year":2022},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.355750Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:d6061fe6a2ce7389bff5aebd9b7cdf2a1d68e1abf85f5e59465693094e757ce5","observation_id":"2231b11b-f8d5-475e-8fae-c7b1cb535b98","resolution":{"observed_at":"2026-08-11T19:01:52.788731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.776953Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":"6a2be711-a8e7-415a-b513-9cece95dc840","year":2017},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.358684Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:4dd5d1b260af8192f1c3b94ab584b89db17ff9d254bba277313839ab63b7b042","observation_id":"2abc0833-eaf8-4445-982c-570c6dbdf538","resolution":{"observed_at":"2026-08-11T19:01:52.780071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.768225Z","title":"Deepgcns: Can gcns go as deep as cnns? Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9267--9276, 2019","venue":null,"work_id":"a0e925c4-1a78-4657-8bf8-8186644b285f","year":2019},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.362080Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:6bafbaf722f0067bb6a5fb43af12b199da45ab57cc6e31946bb04a738fdfd7c6","observation_id":"6ac06020-423a-49b6-bf4b-970d806287b8","resolution":{"observed_at":"2026-08-11T19:01:52.771365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.759944Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":"2b557387-283c-4748-9bc6-0ce278ebbbfe","year":2018},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.365362Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:37d3b96c53eb16d57b1b109c610b21d90a5252b0ab0986e52f43f3cacdf72e66","observation_id":"902d8314-e701-4193-adb7-59a181299525","resolution":{"observed_at":"2026-08-11T19:01:52.762943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.751722Z","title":"Automating the construction of internet portals with machine learning","venue":null,"work_id":"0e3d3191-6130-4e76-ba0f-64da2b1cf834","year":2000},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.368568Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:2373024a14c6a61613520e2b5be5f4fdbe6575224e61c9b62edf12866ad77944","observation_id":"65fdc68a-aa00-40d3-a44e-8a307dde0c7c","resolution":{"observed_at":"2026-08-11T19:01:52.754762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.743184Z","title":"Using noise to probe recurrent neural network structure and prune synapses","venue":null,"work_id":"01fb7f5a-4e0a-4679-a769-25382a148675","year":2020},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.372239Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:9a16d562fd2ba2788450fd65c2a3c7e96db9d80528b415e48b4b526c0f04cdff","observation_id":"d96583f3-1c11-4cfa-af57-6d61edf26b5a","resolution":{"observed_at":"2026-08-11T19:01:52.746301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.734791Z","title":"Graph neural networks exponentially lose expressive power for node classification","venue":null,"work_id":"3c52fc00-cefc-4b51-881b-3b9f81de5460","year":2020},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.375867Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:e2affd3d3913e4d28faa759da6a1811d6fad2b8d730a153ce7ff46f9c8998ef8","observation_id":"b148ef62-ae9c-4fea-85f9-44978ed0c9c4","resolution":{"observed_at":"2026-08-11T19:01:52.737909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.726298Z","title":"Graph neural networks for materials science and chemistry","venue":null,"work_id":"7c2a5fda-b95c-4ccd-bbf9-57252124d230","year":2022},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.379704Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:ed1e92c7bac7ba1a89df21ac185ca8c6068b4f6d38e6a21ad05e541a778eb78d","observation_id":"facef2f1-0961-46f2-a244-2ea608993d8a","resolution":{"observed_at":"2026-08-11T19:01:52.729590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.11876","last_updated":"2024-09-02T09:49:49Z","snapshot_observed_at":"2026-08-16T13:33:41.976314Z","submitted_at":"2024-07-16T16:00:42Z","title":"Simplifying the Theory on Over-Smoothing","version":2},"cited_work":{"arxiv_id":"2407.11876","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.11876","snapshot_observed_at":"2026-08-11T19:01:37.470992Z","title":"Simplifying the Theory on Over-Smoothing","venue":"cs.LG","work_id":"65dc079c-ebcd-4a34-82bf-0f22412f9110","year":2024},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.383417Z"},"links":{"cited_paper":"/paper/2407.11876","citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:e8f23c0c6d7a92633c8e868d7ffd6f82c1f75940afd6e84e7cf6638b98e31842","observation_id":"a555038d-254e-44b2-93d7-fb9eb7f90eee","resolution":{"observed_at":"2026-08-11T19:01:37.476002Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.717555Z","title":"Graph-coupled oscillator networks","venue":null,"work_id":"0ece06ee-3fb2-4e7b-886a-345cf04158d0","year":2022},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.386843Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:c97efc14257fe0e0bfb7b72ec76bf0822a7209c0456d1f6f3c4b37c999540857","observation_id":"d003268f-0824-40d7-89fd-997e5b2f591f","resolution":{"observed_at":"2026-08-11T19:01:52.720746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.708866Z","title":"Rusch, M.M","venue":null,"work_id":"018a2695-4fbf-4b63-b7e9-19095ac7e8f1","year":2023},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.390438Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:e7a7c5ad00b662a2b5a1bb5cfc431a80e75c38696bbfbec9a1450b3b8ce88be5","observation_id":"43bc2ec7-0d2f-4a3b-a310-45ab716bd224","resolution":{"observed_at":"2026-08-11T19:01:52.711881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10993","last_updated":"2023-03-20T10:21:29Z","snapshot_observed_at":"2026-08-18T15:05:00.145825Z","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":"2026-08-11T19:01:37.393667Z","title":"Bronstein, and Siddhartha Mishra","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.393667Z"},"links":{"cited_paper":"/paper/2303.10993","citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:b0dfb64c65111130ee88158942a14a75a7aca0b20855d92500260b8e0700c33b","observation_id":"b989d4c5-1acd-4157-aa8a-4cff56989cea","resolution":{"observed_at":"2026-08-11T19:01:37.393667Z","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":"2026-08-11T19:01:52.699995Z","title":"Collective classification in network data","venue":null,"work_id":"c8095199-4a41-4754-97f8-32559bc238d2","year":2008},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.397059Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:776f744cbd453c8ba45d7f4c749e76c8950ed77e22aa605c3322b16fdcf7f2d6","observation_id":"007bb2aa-e705-451d-8322-365868608ef5","resolution":{"observed_at":"2026-08-11T19:01:52.703053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.691660Z","title":"Webkb dataset","venue":null,"work_id":"35545a68-e9e5-4202-95c5-dbd46678362f","year":2024},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.400344Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:80241d3e0998d81accbf9348b950363ca77e20f024383ccd0c5b574686867842","observation_id":"0247d4f7-1f6e-45f2-a1bc-6c0b35609ef0","resolution":{"observed_at":"2026-08-11T19:01:52.694564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.682882Z","title":"Graph attention networks","venue":null,"work_id":"ed68f6cc-5ef4-40fc-bb0d-b8e3affa7af2","year":2018},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.404033Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:37df8af05473e32744d3115481c7ddfd4b03eb956dd6d19c8686df2a812d39c0","observation_id":"ed28ab15-8294-406e-ae6d-718c9d467d9a","resolution":{"observed_at":"2026-08-11T19:01:52.686126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.673647Z","title":"Graph attention networks","venue":null,"work_id":"4e1e097d-eb49-4230-a59b-48faebeeec0a","year":2018},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.406943Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:87aa6ffd1dee5bd95c7b81026d17ab320091813eedbb139fa7da7e9a9c0932c9","observation_id":"acca94a3-4d1e-4c82-9585-8e88ef631b10","resolution":{"observed_at":"2026-08-11T19:01:52.676780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.664948Z","title":"Demystifying the weak performance of graph attention networks","venue":null,"work_id":"ecb8dd5d-b709-4ad4-985a-a576aa1e09e8","year":2023},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.410048Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:9ffbb111d0128f48a53d24bf0158508808e0912f0c7f52f2f5d386ef82fd5840","observation_id":"15a230e5-dad1-4acc-a4c4-59c5998c7551","resolution":{"observed_at":"2026-08-11T19:01:52.668162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.656020Z","title":"Demystifying oversmoothing in attention-based graph neural networks","venue":null,"work_id":"1a72b396-9832-46dc-b008-2c7c08993995","year":2024},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.413025Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:4c5553511687bc88fd645e37695c94fa7889fc8197f9fd61d8000b476bdfa575","observation_id":"132953eb-f14b-4780-af35-5d5772555298","resolution":{"observed_at":"2026-08-11T19:01:52.659381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.647385Z","title":"A comprehensive survey on graph neural networks","venue":null,"work_id":"aca363f3-df13-4c14-93b8-9067a9146e05","year":2020},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.415980Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:0be52c3d5d5c5584579c0a23bd47f9699ad7e11bf4edb25cd331c29dd043f26f","observation_id":"7cc01ac3-36ff-4e01-83d0-400a3f9c96ef","resolution":{"observed_at":"2026-08-11T19:01:52.650473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.638420Z","title":"Representation learning on graphs with jumping knowledge networks","venue":null,"work_id":"3e6c357e-b9f7-4836-a82a-0fb8921af076","year":2018},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.420055Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:ff05c549855e1ef327e03edbd290d8ad044acab64751b9abac227d758430bf98","observation_id":"065b7739-9c25-4406-996d-e7a593a1768f","resolution":{"observed_at":"2026-08-11T19:01:52.641674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:37.423151Z","title":"How powerful are graph neural networks? In International Conference on Learning Representations, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.423151Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:ea1ef79eb40c671c1c0dbc1149d42730642054151f99a594b8e4478926053631","observation_id":"a23d93eb-a2f3-4d28-8f68-a4b0517ca322","resolution":{"observed_at":"2026-08-11T19:01:37.423151Z","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":"2026-08-11T19:01:52.623838Z","title":"Graph convolutional neural networks for web-scale recommender systems","venue":null,"work_id":"fd247da0-aed6-4bda-9d35-c731f4779a73","year":2018},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.427107Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:12501a2b74b38ff2cf2f431a988e6a40101565f541f173ab31e7edf688dd9d43","observation_id":"47eaea5c-da63-4ac2-9bf3-2fe9071fc379","resolution":{"observed_at":"2026-08-11T19:01:52.627098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.614861Z","title":"Sparsity preserving low-rank decomposition for compression of deep networks","venue":null,"work_id":"7a2ce5ec-4bf1-4548-9bf8-93a7f7bb7625","year":2020},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.430013Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:ac644542eadeb61e7f5f002b82a0d8619372c254e8b0c3d03fb47bf11bcd7e06","observation_id":"e20a17f9-beeb-4338-9354-73ba5fdcac74","resolution":{"observed_at":"2026-08-11T19:01:52.618058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.605820Z","title":"Towards deeper graph neural networks with differentiable group normalization","venue":null,"work_id":"44a7ba5e-00cc-4d57-abdc-2eb417c7bd84","year":2020},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.432926Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:619e9a89b6edc3dd6433b47cc041abb0b415b75b0b9cb691634ef076f211ecd5","observation_id":"0d0e8508-b28c-4537-bbae-e09aba8c1fc0","resolution":{"observed_at":"2026-08-11T19:01:52.608976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-11T19:01:52.596507Z","title":"Beyond homophily in graph neural networks: Current limitations and effective designs","venue":null,"work_id":"a0768fb0-ada7-4c61-b526-3efff38a5249","year":2020},"citing_paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-11T19:01:37.435879Z"},"links":{"citing_paper":"/paper/2412.07243"},"observation_digest":"sha256:35931939cd5b5a28615e8af05e168304b4cdcdfcb75292ca575446a2b2b533fc","observation_id":"67b56044-e3c6-4f57-a1af-194ffeab6ec0","resolution":{"observed_at":"2026-08-11T19:01:52.599959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.07243","last_updated":"2024-12-10T07:07:06Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T18:58:15.604329Z","submitted_at":"2024-12-10T07:07:06Z","title":"A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":6,"verified_fuzzy":34},"total_outbound_references":47},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2412.07243."}