{"as_of":"2026-08-17T08:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c3a9354fc47359b5a150789b69d5f9d458ae5bb4f9b339ff53338bbf7eb9a40d","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:08:13.418953Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T07:07:04.336590Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.19031","snapshot_observed_at":"2026-08-03T07:07:04.336590Z","title":"InInternational conference on machine learning, 13052–13065","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.21309","last_updated":"2026-05-27T11:13:16Z","snapshot_observed_at":"2026-08-03T07:06:48.201629Z","submitted_at":"2026-01-29T06:13:35Z","title":"Transferable Graph Condensation from the Causal Perspective","version":4},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-03T07:07:04.336590Z"},"links":{"cited_paper":"/paper/2507.19031","citing_paper":"/paper/2601.21309"},"observation_digest":"sha256:bb0c4e212155b8987863347fb6f7bd354e2af2928e4920cba018ee65fc8bb9a6","observation_id":"65b6f5bf-ad98-493b-92c1-328b31ecf3b5","resolution":{"observed_at":"2026-08-03T07:07:04.336590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2507.19031/citation-record","integrity":"/paper/2507.19031/integrity","json":"/paper/2507.19031/citation-record.json","paper":"/paper/2507.19031"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-17T04:59:42.373592Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-15T18:08:13.191697Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.191697Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:1c3aacb32a30bfeb1f7bc2d7c4200e218bd8f542e530383748e5e25254cfe79a","observation_id":"17a9b145-052d-4a5c-a847-a41a93c2ee51","resolution":{"observed_at":"2026-08-15T18:08:13.191697Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-08-13T22:35:40.714745Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-15T18:08:13.197449Z","title":"Graph attention networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.197449Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:b32d48d2bf01ee8d84bb08c3c5d55ca23d1ccf351416d51a15d763db10d21cb2","observation_id":"b2af614c-5837-4763-960c-79bbfb1c7529","resolution":{"observed_at":"2026-08-15T18:08:13.197449Z","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":"2026-08-15T18:08:13.202684Z","title":"Inductive representation learning on large graphs,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.202684Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:1ca8d7a73c786039f3e40fc2ab37c8981f05ee16da45a0ba7ac9310f63791f1b","observation_id":"fa0cf006-2a10-43cb-87ae-965bb6308bc6","resolution":{"observed_at":"2026-08-15T18:08:13.202684Z","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":"2026-08-15T18:08:13.207171Z","title":"Simplifying graph convolutional networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.207171Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:b895fbab4232469a1d6338dde61501a39216dcfedf9d687ad6218eabb29ae6fc","observation_id":"d53d308e-2a1a-42f8-a2a1-138c1f164729","resolution":{"observed_at":"2026-08-15T18:08:13.207171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00826","last_updated":"2019-02-22T19:15:54Z","snapshot_observed_at":"2026-08-13T05:06:48.606308Z","submitted_at":"2018-10-01T17:11:31Z","title":"How Powerful are Graph Neural Networks?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.00826","snapshot_observed_at":"2026-08-15T18:08:13.212273Z","title":"How powerful are graph neural networks?","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.212273Z"},"links":{"cited_paper":"/paper/1810.00826","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:a773922c0537b0d961767ba79c96b15974678a7b6c913cd23ec7604895f7b8ec","observation_id":"7c45bdfd-22db-4c12-ba1e-05023f05ec75","resolution":{"observed_at":"2026-08-15T18:08:13.212273Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.05997","last_updated":"2022-04-05T11:39:26Z","snapshot_observed_at":"2026-08-16T22:36:46.056142Z","submitted_at":"2018-10-14T08:36:54Z","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.05997","snapshot_observed_at":"2026-08-15T18:08:13.216711Z","title":"Predict then propagate: Graph neural networks meet personalized pagerank,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.216711Z"},"links":{"cited_paper":"/paper/1810.05997","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:52a83d8d3ad39a30ee2a68246c83af4605956f400b634bfcaabc840da5a60dc4","observation_id":"275f46bf-ba0b-45b2-8769-ca553a9b5ef4","resolution":{"observed_at":"2026-08-15T18:08:13.216711Z","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":"2026-08-15T18:08:14.195776Z","title":"Skipnode: On alleviating performance degradation for deep graph convolutional networks,","venue":null,"work_id":"10d0cf83-ca15-4b64-a90e-c1ed470327e4","year":2024},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.226691Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:e24e2b60f5e38afe171be54d4b2636523b0f9082ee17eb0353cf0f887ce1b3df","observation_id":"8b9f3b6a-005c-4d02-84b6-7a3fdc041e53","resolution":{"observed_at":"2026-08-15T18:08:14.200934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:14.176476Z","title":"Graph-less neural networks: Teaching old mlps new tricks via distillation,","venue":null,"work_id":"0a95f63c-969b-400d-82f6-007da8975cc5","year":2021},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.230507Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:62a1c38fb1651b5e44001f8407e2c47281cf993e23ab9221f0a22f3d035d61b3","observation_id":"202c7e70-303a-4120-b1cd-a59122da45ad","resolution":{"observed_at":"2026-08-15T18:08:14.181717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:14.156198Z","title":"Learning mlps on graphs: A unified view of effectiveness, robustness, and efficiency,","venue":null,"work_id":"9f6cba72-e184-44fe-9286-aff9c3f85e78","year":2022},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.234369Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:48e616356622cae86cfc2aa28fe8c4f44268d2aad82a5b15eec5a35db610b7c3","observation_id":"32e368dd-6971-41ee-9752-075a0631f02b","resolution":{"observed_at":"2026-08-15T18:08:14.161742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.05628","last_updated":"2023-06-09T02:23:37Z","snapshot_observed_at":"2026-08-16T15:25:17.985798Z","submitted_at":"2023-06-09T02:23:37Z","title":"Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs","version":1},"cited_work":{"arxiv_id":"2306.05628","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.05628","snapshot_observed_at":"2026-08-15T18:08:13.739178Z","title":"Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs","venue":"cs.LG","work_id":"7935e008-3649-4254-9cc0-3bbe2f153d40","year":2023},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.238244Z"},"links":{"cited_paper":"/paper/2306.05628","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:89a577a822f6d7b1c504d4185a067d6cda615bd0bc323b91730f6657143163af","observation_id":"c7a9ecc5-4513-4c8e-9957-5f0ff5db118b","resolution":{"observed_at":"2026-08-15T18:08:13.743544Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10758","last_updated":"2023-06-04T14:48:07Z","snapshot_observed_at":"2026-08-16T15:32:06.489625Z","submitted_at":"2023-05-18T06:57:06Z","title":"Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework","version":2},"cited_work":{"arxiv_id":"2305.10758","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.10758","snapshot_observed_at":"2026-08-15T18:08:13.719925Z","title":"Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework","venue":"cs.LG","work_id":"2f2ffff2-98f4-48e1-94fb-13e3b97a9f41","year":2023},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.243284Z"},"links":{"cited_paper":"/paper/2305.10758","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:95914c3c77da3d918f6c8e9609f4e9694d38e6460ed6bbf809355162f62f65fa","observation_id":"48fc9060-1fa2-47aa-b3e0-f736365da8ae","resolution":{"observed_at":"2026-08-15T18:08:13.725201Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:14.138084Z","title":"Adagmlp: Adaboosting gnn-to- mlp knowledge distillation,","venue":null,"work_id":"68b5aa09-e07a-442c-86ec-4c40c4309b31","year":2024},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.247648Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:8664284d72d9129cfd326091f6a97c234e8997b9eae03a3348c2eef94c21481d","observation_id":"daeeb282-11e7-4871-8818-8790c40d7f4c","resolution":{"observed_at":"2026-08-15T18:08:14.146502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.251432Z","title":"An overview on edge computing research,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.251432Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:96043021662894a46f630fe67f82c5f938941b5289e00689254553dd233fcc2a","observation_id":"21d3ae14-8795-44d8-8819-c7c0b3abe6b2","resolution":{"observed_at":"2026-08-15T18:08:13.251432Z","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":"2026-08-15T18:08:13.255409Z","title":"A survey on mobile edge computing: The communication perspective,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.255409Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:32fb9dabedfb48605569cb608a8855d59de805c46d0b11f68821d513b691302c","observation_id":"2afc2b28-a1c8-4747-bbbc-415fa97bf4f7","resolution":{"observed_at":"2026-08-15T18:08:13.255409Z","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":"2026-08-15T18:08:13.259137Z","title":"Deep learning with edge computing: A review,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.259137Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:c8e5742d928d129912f007fdf15bd57a18b5dcdee9926c726e8675b3fcefd641","observation_id":"037b095c-cdd5-4482-9a24-c5af72ee4b2c","resolution":{"observed_at":"2026-08-15T18:08:13.259137Z","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":"2026-08-15T18:08:13.264019Z","title":"Edge computing: Vision and challenges,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.264019Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:251fca9fb3bc8f5ee98568f50487007e98015a0a90958ef2d7db6224a1ff32c7","observation_id":"fa5c87bc-7593-4df0-862e-1ca8a7f97329","resolution":{"observed_at":"2026-08-15T18:08:13.264019Z","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":"2026-08-15T18:08:14.083271Z","title":"Mobile application usability,","venue":null,"work_id":"785f7b15-8803-49de-8ea4-c44babc8b058","year":2015},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.268878Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:33f3096531568b0acf45dc44083c384f4cbe3474fb340bf2c3cdbf863b22c66d","observation_id":"53bd5bcb-7d31-401f-b6e9-7d8cec0fb3a3","resolution":{"observed_at":"2026-08-15T18:08:14.088407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:14.067883Z","title":"Mobile application and its global impact,","venue":null,"work_id":"18246d92-4c20-4a05-b737-2d7ce9649e54","year":2010},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.274510Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:19bf37216d0925cb92311c01dae84bb297e3d09aba1e0e5fb770cb93e89744ca","observation_id":"122a437a-904c-4385-b2ee-0ad75a577c8b","resolution":{"observed_at":"2026-08-15T18:08:14.074019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:14.054043Z","title":"Adaptive neural networks for efficient inference,","venue":null,"work_id":"1a1a712b-0583-4559-8105-088cf27fd119","year":2017},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.279252Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:a9cd43f3b88c98d120c20d9ca10456c68580d82e0602c91e751de9061ff7f388","observation_id":"deec65b5-478d-4a30-9c67-259881e3b88d","resolution":{"observed_at":"2026-08-15T18:08:14.059624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:14.039565Z","title":"Multiple instance learning for efficient sequential data classification on resource-constrained devices,","venue":null,"work_id":"070659eb-ebb5-4ca3-ab90-9bac33957a79","year":2018},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.283662Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:fc08b105ffb468584687209ad94d823872cce4dcdf0992bc9388b943d4877a9c","observation_id":"03f4b645-dfa7-4064-bcbb-4b31305d2e5d","resolution":{"observed_at":"2026-08-15T18:08:14.045041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:14.022210Z","title":"Anytime inference with distilled hierarchical neural ensembles,","venue":null,"work_id":"f6d3dab9-e221-4839-9417-615b724b0b04","year":2021},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.288022Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:6d45ecc3e666a1978ce0cbb4f7af94c199ae8c251cd25bb77c986a4eb58eea80","observation_id":"51bf87b0-7234-4bc1-a973-46b5ceaf1ab2","resolution":{"observed_at":"2026-08-15T18:08:14.029724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.09844","last_updated":"2018-06-07T14:39:29Z","snapshot_observed_at":"2026-08-14T21:09:29.929249Z","submitted_at":"2017-03-29T00:19:20Z","title":"Multi-Scale Dense Networks for Resource Efficient Image Classification","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.09844","snapshot_observed_at":"2026-08-15T18:08:13.292835Z","title":"Multi-scale dense networks for resource efficient image classification,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.292835Z"},"links":{"cited_paper":"/paper/1703.09844","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:4c8ce46f243c0a9056c6996fb873e42bf9e05e3a487d99832bb17ad414b53987","observation_id":"0d5265c7-eb9a-4c3e-8b41-4ac62db61dc3","resolution":{"observed_at":"2026-08-15T18:08:13.292835Z","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":"2026-08-15T18:08:14.009343Z","title":"Progressive ensemble distillation: building ensembles for efficient inference,","venue":null,"work_id":"1357f0b4-b12f-4e59-b469-4af1af3e7c8d","year":2023},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.297809Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:9aaaef2aad4a89ba04fae64fd0cbc5f10f1fffde6cb4c81b5c7a6bfc408673f0","observation_id":"ac63f075-5852-49e6-8760-bc34258d0384","resolution":{"observed_at":"2026-08-15T18:08:14.013509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.302452Z","title":"Simple and deep graph convolutional networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.302452Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:70bfd40166e932187513c67c3556930dfea50d0f49ff4374fdb70242345fb08f","observation_id":"c6b6bec9-1d02-43e4-beb9-d407bb4f7eb5","resolution":{"observed_at":"2026-08-15T18:08:13.302452Z","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":"2026-08-15T18:08:13.306759Z","title":"Representation learning on graphs with jumping knowledge networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.306759Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:e5f1f0b069bbacca2da413800c7bc3fa03c06fd0dc4a664d149bd26bbaf25537","observation_id":"85e5a609-a31b-4523-a876-477d121ca74c","resolution":{"observed_at":"2026-08-15T18:08:13.306759Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.09532","last_updated":"2023-12-19T03:35:13Z","snapshot_observed_at":"2026-08-16T15:54:20.365268Z","submitted_at":"2023-02-19T10:34:08Z","title":"Pseudo Contrastive Learning for Graph-based Semi-supervised Learning","version":3},"cited_work":{"arxiv_id":"2302.09532","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.09532","snapshot_observed_at":"2026-08-15T18:08:13.692167Z","title":"Pseudo Contrastive Learning for Graph-based Semi-supervised Learning","venue":"cs.LG","work_id":"a7d413a2-05d9-443e-98f5-663e3e23638c","year":2023},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.311269Z"},"links":{"cited_paper":"/paper/2302.09532","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:da68dd06a8f81d09afd25966de12967bf077583ecd8b5f5d8232dab5b4823e48","observation_id":"9120659f-20e3-4242-98f9-449cfbb2d761","resolution":{"observed_at":"2026-08-15T18:08:13.696639Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.976571Z","title":"Nodemixup: Tackling under-reaching for graph neural networks,","venue":null,"work_id":"d5cc9517-d110-43af-b590-4569764d1c9c","year":2024},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.316479Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:a28fca0afaac039209624d61acf405a34c099f5b98de4babb89a9228a1431f27","observation_id":"6ec46e8e-9ea4-490f-b46a-945b804b6bf0","resolution":{"observed_at":"2026-08-15T18:08:13.981498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.964000Z","title":"Lpformer: An adaptive graph transformer for link prediction,","venue":null,"work_id":"3af966f7-c0d6-4c8d-9981-0573ea4055a4","year":2024},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.320791Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:5a18c69c463b60084995c97c41c3a0b987fe974f079cb5e9c2a8f7ca86e42ae7","observation_id":"2d85fd2d-fd79-4880-915d-19e018ee955c","resolution":{"observed_at":"2026-08-15T18:08:13.968224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:14.211027Z","title":"Graph substructure assembling network with soft sequence and context attention,","venue":null,"work_id":"dacdf666-4ba9-4ae4-92a7-6b1d5d6fb53e","year":2022},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.325593Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:e5bff7be2c191175fba74697c34019589ef74623e6a98087dba992ab17315e1b","observation_id":"821f1be2-3e95-4bf3-9503-51b7e5ef0832","resolution":{"observed_at":"2026-08-15T18:08:14.215915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.951384Z","title":"Deep geometric knowledge distillation with graphs,","venue":null,"work_id":"4f43c281-43ba-4db5-a818-61bd956b7b22","year":2020},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.330921Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:7a22bd39b076b168e949c75db84aa2288e27415216e81c50979551ca771782b5","observation_id":"9dbda959-3247-4c0d-a579-f65fd7c4f0b4","resolution":{"observed_at":"2026-08-15T18:08:13.956123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.938448Z","title":"Iterative graph self-distillation,","venue":null,"work_id":"c2f83c00-18dc-4314-b871-979406b12d29","year":2023},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.335577Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:c5ffefec9a2c567970c2099781fab5552dd111a6cb9eda0a055aed0735c0a109","observation_id":"11ccb554-a930-4d14-acef-e850b38045c6","resolution":{"observed_at":"2026-08-15T18:08:13.943008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.01174","last_updated":"2022-06-10T01:06:11Z","snapshot_observed_at":"2026-08-16T17:37:33.924007Z","submitted_at":"2021-12-02T12:43:41Z","title":"Multi-task Self-distillation for Graph-based Semi-Supervised Learning","version":3},"cited_work":{"arxiv_id":"2112.01174","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.01174","snapshot_observed_at":"2026-08-15T18:08:13.671629Z","title":"Multi-task Self-distillation for Graph-based Semi-Supervised Learning","venue":"cs.LG","work_id":"4570b0e5-ba2d-47a2-b30c-efa18ef79561","year":2021},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.339404Z"},"links":{"cited_paper":"/paper/2112.01174","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:d8043e4067d4998edb47e72168be2bf42393725bf41ba93dfe60bb48a7df7965","observation_id":"38c3ab19-ec55-4760-906d-80655052f430","resolution":{"observed_at":"2026-08-15T18:08:13.677248Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.926316Z","title":"On representation knowledge distillation for graph neural networks,","venue":null,"work_id":"85019d89-2b34-4a96-bc98-dc0279bf833a","year":2022},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.343530Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:328db55ebb51b4a6c9dd99e6156d70898bd5998d569b8a43ce35c5976bc776fd","observation_id":"62c91225-bcaf-4717-9369-fb6577209cd7","resolution":{"observed_at":"2026-08-15T18:08:13.930420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.911412Z","title":"Knowledge distillation improves graph structure augmentation for graph neural networks,","venue":null,"work_id":"99cffd19-f253-4aec-93b8-80d4e4d44b89","year":2022},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.347547Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:956735d64f8d09b2aa59ee14c5cdc1b104453757c4442b35b7d653c0dadeafb5","observation_id":"ccb31859-babc-45df-afc5-30d78b3c9782","resolution":{"observed_at":"2026-08-15T18:08:13.916548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.896765Z","title":"Be your own teacher: Improve the performance of convolutional neural networks via self distillation,","venue":null,"work_id":"a1d9ffca-9da4-4ec0-9f99-a5e5198e931d","year":2019},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.352162Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:682f9530b5d26c044b53c15e978039cb5dcfcbc29bde3aea116b86efc52589b7","observation_id":"a6980110-8505-4070-b715-210197572faa","resolution":{"observed_at":"2026-08-15T18:08:13.902176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.02255","last_updated":"2021-04-30T04:31:53Z","snapshot_observed_at":"2026-08-16T19:08:10.897830Z","submitted_at":"2020-11-04T12:29:33Z","title":"On Self-Distilling Graph Neural Network","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.02255","snapshot_observed_at":"2026-08-15T18:08:13.358498Z","title":"On self- distilling graph neural network,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.358498Z"},"links":{"cited_paper":"/paper/2011.02255","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:3191a53c77eed1f1ace0601532d3343e1381f8298fe41a491c2e895838fe128a","observation_id":"e408589e-34ad-44b8-8787-24068ec35693","resolution":{"observed_at":"2026-08-15T18:08:13.358498Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-16T18:00:58.008096Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-15T18:08:13.363280Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.363280Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:438f2425d583093242332393c558fd72646262b251ac3a1db1fcc2903d899507","observation_id":"3cded3fa-246a-484e-b430-cbe9ac5c024c","resolution":{"observed_at":"2026-08-15T18:08:13.363280Z","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":"2026-08-15T18:08:13.882828Z","title":"Do deep nets really need to be deep?","venue":null,"work_id":"118af02a-d650-46d2-b659-24ce2ffdb348","year":2014},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.368055Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:7a0dd7c9027938dcd47e3615dd50f41e729095ab95e961b85e376a2d8919ae3b","observation_id":"0042bb7c-a313-4b6a-8fd9-31aa9dd9a4cd","resolution":{"observed_at":"2026-08-15T18:08:13.887145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.870965Z","title":"Distilling knowledge from graph convolutional networks,","venue":null,"work_id":"dfc57936-9f23-4af1-97cf-01255cae8726","year":2020},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.372242Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:fdbcb09d7cd944ab98e6e4d39d8d3bf9e795d2d1cb6e4bf76c02e57c7edbcfd5","observation_id":"c7a95756-b318-404d-a65a-f5db7ad422a0","resolution":{"observed_at":"2026-08-15T18:08:13.875174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.857883Z","title":"Tinygnn: Learning efficient graph neural networks,","venue":null,"work_id":"6cf09418-0939-46d5-a4e5-3345484afc95","year":2020},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.376530Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:02bb0d0746a19b89451956444e8bf9f2beef0ee0bfdd571b27b8cad316252c40","observation_id":"a20b39e9-42e3-4c68-baa3-a7f65cb478ae","resolution":{"observed_at":"2026-08-15T18:08:13.862363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.380643Z","title":"Reliable data distillation on graph convolutional network,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.380643Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:53473a11c01375c3c882d24a57e003280fa25a2a8f1a2d478f65fc4882f64ef9","observation_id":"cc1bd8ac-c29a-47fa-8dc0-b02ca4ea0fcd","resolution":{"observed_at":"2026-08-15T18:08:13.380643Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02097","last_updated":"2023-06-04T14:49:21Z","snapshot_observed_at":"2026-08-17T07:35:36.363744Z","submitted_at":"2022-10-05T08:35:34Z","title":"Teaching Yourself: Graph Self-Distillation on Neighborhood for Node Classification","version":5},"cited_work":{"arxiv_id":"2210.02097","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.02097","snapshot_observed_at":"2026-08-15T18:08:13.564397Z","title":"Teaching Yourself: Graph Self-Distillation on Neighborhood for Node Classification","venue":"cs.LG","work_id":"355cfb82-4bed-4710-96a9-49feb4206063","year":2022},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.384807Z"},"links":{"cited_paper":"/paper/2210.02097","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:3d5198ec76d126e34a4ffc25e623de136c082eec4b7e7baf0167da939ad240ac","observation_id":"068d2010-4cbb-467b-b730-cf4a5d0e82e8","resolution":{"observed_at":"2026-08-15T18:08:13.571920Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.845615Z","title":"Vqgraph: Rethinking graph representation space for bridging gnns and mlps,","venue":null,"work_id":"1a0452fc-ec79-4242-a8e0-cd620cb97b02","year":2024},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.389869Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:c30b6f52694036b4639018e8e5acb496498cc568ca22accacdbda85a18596f44","observation_id":"4bb505b8-6ced-4962-bd5c-5ec4c1ba28a9","resolution":{"observed_at":"2026-08-15T18:08:13.850206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.831779Z","title":"Adaptive inference through early-exit networks: Design, challenges and directions,","venue":null,"work_id":"355038f7-fbad-4cac-b1af-82b3df7cd9cb","year":2021},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.393629Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:dc6403327df7681a953a8902f5e1bdabe87cd10df6e70824ab8d691f4b2d0b5b","observation_id":"d0f57374-7fc5-4850-a799-45d4c20b97db","resolution":{"observed_at":"2026-08-15T18:08:13.837276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T18:08:13.398532Z","title":"Branchynet: Fast inference via early exiting from deep neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.398532Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:7d8538d481c35def51a8888226fe47737d90410d645d79baf912fb3064dd93ea","observation_id":"2c148caf-bcc8-43e4-a624-9e1000c58a3b","resolution":{"observed_at":"2026-08-15T18:08:13.398532Z","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":"2026-08-15T18:08:13.403576Z","title":"Fast graph representation learning with PyTorch Geometric,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.403576Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:334793807bed14b30082db1b8e659629d262a036f7d098471198d0289abd53e0","observation_id":"6a30d18c-a163-4748-ad1e-c1f0068797ac","resolution":{"observed_at":"2026-08-15T18:08:13.403576Z","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":"2026-08-15T18:08:13.407231Z","title":"Collective classification in network data,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.407231Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:8ccb7eb6d794148e50f8b7120608f87db8139167da4dcda4dedd2fefe35ccf5e","observation_id":"f3254d1f-5c84-473b-b4fa-2b27466228b0","resolution":{"observed_at":"2026-08-15T18:08:13.407231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.05868","last_updated":"2019-06-18T13:15:39Z","snapshot_observed_at":"2026-08-14T17:59:20.424546Z","submitted_at":"2018-11-14T15:53:19Z","title":"Pitfalls of Graph Neural Network Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.05868","snapshot_observed_at":"2026-08-15T18:08:13.410860Z","title":"Pitfalls of graph neural network evaluation,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.410860Z"},"links":{"cited_paper":"/paper/1811.05868","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:776bfae41d8268908e6bcb2b239edf499a9814caab036cdbf33b7204b1e53c4a","observation_id":"e3d09e9b-b2be-4df4-8033-0d9d1e752dda","resolution":{"observed_at":"2026-08-15T18:08:13.410860Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00687","last_updated":"2021-02-25T02:06:27Z","snapshot_observed_at":"2026-08-16T13:28:09.232356Z","submitted_at":"2020-05-02T03:09:50Z","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.00687","snapshot_observed_at":"2026-08-15T18:08:13.414524Z","title":"Open graph benchmark: Datasets for machine learning on graphs,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.414524Z"},"links":{"cited_paper":"/paper/2005.00687","citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:9ae20f1b6c54357604524f0072c147395265b8bcdea1a5fa6adef4057cad9f01","observation_id":"2af4eac9-4e06-417c-a00f-588a14b09972","resolution":{"observed_at":"2026-08-15T18:08:13.414524Z","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":"2026-08-15T18:08:13.418953Z","title":"Teach harder, learn poorer: Rethinking hard sample distillation for gnn-to-mlp knowledge distillation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T18:08:13.418953Z"},"links":{"citing_paper":"/paper/2507.19031"},"observation_digest":"sha256:e181793dcb14aaf9c58fb41aba8f477427a363fdfd0cd40e43edff2097704a3d","observation_id":"69955e01-f2f0-4346-ae37-d32372e77688","resolution":{"observed_at":"2026-08-15T18:08:13.418953Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.19031","last_updated":"2025-07-25T07:35:09Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T18:00:13.385276Z","submitted_at":"2025-07-25T07:35:09Z","title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":5,"verified_fuzzy":23},"total_outbound_references":50},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 1 inbound Pith citation observation for arXiv:2507.19031."}