{"as_of":"2026-08-08T10:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cdea481e6fd7c075c92596bf235191126f2b2e84c272fa4519dc1c6a83d3d2ff","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:26:20.955313Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2506.14114/citation-record","integrity":"/paper/2506.14114/integrity","json":"/paper/2506.14114/citation-record.json","paper":"/paper/2506.14114"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2025.13463","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:26:22.006741Z","title":null,"venue":null,"work_id":"1a779845-8334-4f66-bd79-c55427d6a6e4","year":2025},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.735350Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:cb875a9faac520a3f98de6055aa1b59261eb8de2cd8d8694fa760e5d06fb8095","observation_id":"2222e974-e0f4-4fcd-ac3f-35c16103f3f8","resolution":{"observed_at":"2026-08-07T00:26:22.136849Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:20.740205Z","title":null,"venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.740205Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:fb78b171b6d069dea2d1ef267a051266da310557bc782b42969f3acc3b88345e","observation_id":"f23e3c2d-51fa-4e87-975c-1eb54829f8e6","resolution":{"observed_at":"2026-08-07T00:26:20.740205Z","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":"2026-08-07T00:26:25.973153Z","title":null,"venue":null,"work_id":"aa546422-d15a-4f95-8b41-e4f7c85ae869","year":2016},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.744809Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:d0b12ccaa018b7aa9aef64b6885f2c5bc47d42a3df13df9709f645348efae016","observation_id":"ca531a2d-a682-4dad-98aa-6b120e676536","resolution":{"observed_at":"2026-08-07T00:26:26.055837Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1613/jair.1.14768","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:26:21.178870Z","title":null,"venue":null,"work_id":"1e3952c4-91d2-45b2-a349-90b2dd15e42d","year":2023},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.749194Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:364ba42ee3fa389879018a6d5be98c988d3d9448ebebad870f9d50577e7d93be","observation_id":"0afb691a-02f5-4a07-b9e9-9f6abb778a4f","resolution":{"observed_at":"2026-08-07T00:26:21.183221Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.3390/e22020197","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:26:21.164952Z","title":null,"venue":null,"work_id":"3a0e1cab-3d29-4fa0-90bd-d82dd38be591","year":2020},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.753951Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:877e319a0989b4e8e82e9cfe87a03edf1f42713ac7d9b55ba6435690da9daf8d","observation_id":"6ec6a529-7dc7-43a7-a4c6-f675c5bdf5b4","resolution":{"observed_at":"2026-08-07T00:26:21.169027Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/comnet/cnac030","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:26:21.150622Z","title":null,"venue":null,"work_id":"2b9242d8-a90b-4230-a08a-451035c024f0","year":2022},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.758506Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:261cd1f9b5fa13239743de1e439d03f86cb1f0b4728235852eb727ab415192f2","observation_id":"4c202e30-1b06-4dca-aa72-e53922314dcd","resolution":{"observed_at":"2026-08-07T00:26:21.155020Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01535","last_updated":"2024-09-18T14:20:32Z","snapshot_observed_at":"2026-07-06T17:38:51.653737Z","submitted_at":"2024-03-03T15:28:47Z","title":"Neural Graph Generator: Feature-Conditioned Graph Generation using Latent Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.01535","snapshot_observed_at":"2026-08-07T00:26:20.763495Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.763495Z"},"links":{"cited_paper":"/paper/2403.01535","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:a6349a37c08fc1ae6c356db209fce7117d39f644250d3bd038d7b2bda6d9e5b8","observation_id":"5ce0b845-c42c-4ad7-b3ee-2e24bccd5c0e","resolution":{"observed_at":"2026-08-07T00:26:20.763495Z","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":"2026-08-07T00:26:25.788698Z","title":null,"venue":null,"work_id":"0ada63b8-abe8-4464-90a8-3e043269c72a","year":2023},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.768086Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:eaeca7f6e4068f7a0243376dcfb03119aa750eec66990d346dda6c2464cbc7e1","observation_id":"9cedf8d6-50aa-4590-a062-c43337136433","resolution":{"observed_at":"2026-08-07T00:26:25.844779Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:25.580258Z","title":null,"venue":null,"work_id":"6839c0ce-9d3a-4386-b2fe-3dcf59ddda52","year":2017},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.772347Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:43ba3895bf5ca5ee831d938f355ab506f68894bae1b6e33f53d25f7d57332e49","observation_id":"26989d75-6e41-4b2c-89e8-9627e88210dc","resolution":{"observed_at":"2026-08-07T00:26:25.657515Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09131","last_updated":"2024-08-26T13:48:32Z","snapshot_observed_at":"2026-07-06T18:30:19.486766Z","submitted_at":"2024-06-13T14:02:18Z","title":"OLGA: One-cLass Graph Autoencoder","version":2},"cited_work":{"arxiv_id":"2406.09131","doi":"10.48550/arxiv.2406.09131","metadata_source":"pith","pith_arxiv_id":"2406.09131","snapshot_observed_at":"2026-08-07T06:16:28.064256Z","title":"OLGA: One-cLass Graph Autoencoder","venue":"cs.LG","work_id":"8e22e7e2-4487-468c-9f25-b54c7d8229fa","year":2024},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.776602Z"},"links":{"cited_paper":"/paper/2406.09131","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:0b7b740f050215d782b718d1f3f1e08834321f2739df44d2700a8cbf43b06cd9","observation_id":"d606a3d0-4d5b-4cd1-bc3a-b79561659d0b","resolution":{"observed_at":"2026-08-07T00:26:21.123683Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:25.393351Z","title":null,"venue":null,"work_id":"60bd775c-acd0-4065-b29d-f7d6849693d0","year":2020},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.781644Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:b7fb10877f6faa84a7365a9c28abe45360a7570eeeac4746470496244a119568","observation_id":"0b2c7440-f4c8-4c05-adf9-3d73290abb44","resolution":{"observed_at":"2026-08-07T00:26:25.478275Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:25.218561Z","title":null,"venue":null,"work_id":"5ee3e181-0bf6-4be5-b2ec-f81f8da1d6e9","year":2016},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.785723Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:765d1830c23eba732b77f6b970104ce78c76f47405e11d59c22427cd1dd8e97f","observation_id":"7c649219-af2e-42d0-9f55-a4d567634bd0","resolution":{"observed_at":"2026-08-07T00:26:25.296124Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:20.789626Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.789626Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:79db307716ebbab97a279e46775f5db2f55fc7b38b7b7f9d86545bb172cd6298","observation_id":"784f717c-cd25-4fd9-a98a-2bd19e180872","resolution":{"observed_at":"2026-08-07T00:26:20.789626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.01122","last_updated":"2025-04-01T18:47:16Z","snapshot_observed_at":"2026-08-08T07:11:47.792627Z","submitted_at":"2025-04-01T18:47:16Z","title":"ffstruc2vec: Flat, Flexible and Scalable Learning of Node Representations from Structural Identities","version":1},"cited_work":{"arxiv_id":"2504.01122","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.01122","snapshot_observed_at":"2026-08-07T00:26:21.773826Z","title":"ffstruc2vec: Flat, Flexible and Scalable Learning of Node Representations from Structural Identities","venue":"cs.LG","work_id":"71bf1182-cd37-439a-9ef9-428c06515284","year":2025},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.793707Z"},"links":{"cited_paper":"/paper/2504.01122","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:3db14264eac942be20dbb272589b2d9fe078e6454fd61c3cc74d20edd657572e","observation_id":"f1245e13-d003-4d26-be46-17351b2e15cc","resolution":{"observed_at":"2026-08-07T00:26:21.845485Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1609/aaai.v34i04.5843","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:26:21.099766Z","title":null,"venue":null,"work_id":"a4f5ddb7-b125-4543-8e8b-95c812fafa0e","year":2020},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.797985Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:46e2ec2b527999c16b743b00148a77564b3942356f35f9aad5bb8ceedb1d7211","observation_id":"d3eeafee-0d45-423e-b079-1aeae2c517d7","resolution":{"observed_at":"2026-08-07T00:26:21.103928Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17345","last_updated":"2024-02-27T09:23:54Z","snapshot_observed_at":"2026-07-06T17:36:05.934286Z","submitted_at":"2024-02-27T09:23:54Z","title":"LocalGCL: Local-aware Contrastive Learning for Graphs","version":1},"cited_work":{"arxiv_id":"2402.17345","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.17345","snapshot_observed_at":"2026-08-07T00:26:21.593504Z","title":"LocalGCL: Local-aware Contrastive Learning for Graphs","venue":"cs.LG","work_id":"53530884-b2c9-4275-b059-9a70f3cefe27","year":2024},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.802321Z"},"links":{"cited_paper":"/paper/2402.17345","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:be293450e5f5ad6e8dc5d180959130c92a04860aa9af9155988adf6cd1f51ba7","observation_id":"65b3e173-f41d-44f6-b005-44bea9f13e8d","resolution":{"observed_at":"2026-08-07T00:26:21.682924Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:20.806594Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.806594Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:4b1975d18817282f69a7fbdc1e38565b748a4d68ab3d075d0b5ec9a0f8c74f3b","observation_id":"6c63a4e0-8076-471d-8544-dd59f26ada1c","resolution":{"observed_at":"2026-08-07T00:26:20.806594Z","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":"2026-08-07T00:26:25.069774Z","title":null,"venue":null,"work_id":"69682354-4421-484b-a806-81e5f37a5f0a","year":2022},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.810580Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:224d6db34ec2c682e6474a23e6be81dc85cbbbb98b4c64f0d6c1955754d04ba9","observation_id":"4403c57e-eefe-45cc-b5a0-3f8485ce2e85","resolution":{"observed_at":"2026-08-07T00:26:25.133708Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01214","last_updated":"2025-03-05T07:02:28Z","snapshot_observed_at":"2026-07-06T18:39:29.270369Z","submitted_at":"2024-07-01T11:59:59Z","title":"Revisiting Random Walks for Learning on Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01214","snapshot_observed_at":"2026-08-07T00:26:20.814785Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.814785Z"},"links":{"cited_paper":"/paper/2407.01214","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:07ac994f5ec8358e1c85abf1dd3d25eb628f2cb35c6b25d707397552ae09bec3","observation_id":"c44ce8d4-aa4e-4ee4-ae2a-a8b7bc04b415","resolution":{"observed_at":"2026-08-07T00:26:20.814785Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-07-06T05:10:16.862707Z","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":"2026-08-07T00:26:20.819501Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.819501Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:9f4b3d28aaff88c35d7a8dbd9a7a80b10030b595fe2cf170a9bb9f3fb4947f7c","observation_id":"250d4786-9b7b-43c9-a0e2-4f8dd42e8ac4","resolution":{"observed_at":"2026-08-07T00:26:20.819501Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07308","last_updated":"2016-11-21T11:37:17Z","snapshot_observed_at":"2026-08-06T06:17:37.090691Z","submitted_at":"2016-11-21T11:37:17Z","title":"Variational Graph Auto-Encoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.07308","snapshot_observed_at":"2026-08-07T00:26:20.823749Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.823749Z"},"links":{"cited_paper":"/paper/1611.07308","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:db6c2ea27b650894751c44aa7765220475249278c7da235b89ae131bc7952850","observation_id":"2f4dba24-d8fa-4ece-996f-afe3f33751c7","resolution":{"observed_at":"2026-08-07T00:26:20.823749Z","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":"2026-08-07T00:26:24.876342Z","title":null,"venue":null,"work_id":"4671b071-b6e2-42a4-bc0e-615f0bd6213b","year":2023},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.827995Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:b8ff33b2aa08ce5932946aee92a3d40566d44329fa4d6b0fa3a970ec3509f4b0","observation_id":"d2338d14-3f18-4468-a9c8-fef3b20f91a3","resolution":{"observed_at":"2026-08-07T00:26:24.960943Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2022.31462","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:26:21.504652Z","title":null,"venue":null,"work_id":"8b53260d-8291-4dd8-b09c-7c67fe86c748","year":2023},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.831802Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:800961f5b2c613e09dea26edc078fec516b3e3761c31e15843879bbf137dcab2","observation_id":"4989b30c-6c9a-4bf9-a43b-4c2a55471fda","resolution":{"observed_at":"2026-08-07T00:26:21.519052Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:24.624235Z","title":"Gribova, Vladimir Fedorovich Filaretov, and De-Shuang Huang","venue":null,"work_id":"bb0ef1ed-7e2d-4f92-9b19-a005cf1f9652","year":2024},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.835562Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:9a93c1ffea3db66ef84fdfe79dc1fc9fcdd475bc8232fd92e4db6441e76e9d3b","observation_id":"76b5e3c6-12e8-4acf-8d8d-f847c1c10870","resolution":{"observed_at":"2026-08-07T00:26:24.780954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.23345","last_updated":"2025-06-15T04:04:46Z","snapshot_observed_at":"2026-08-07T12:45:32.756495Z","submitted_at":"2025-05-29T11:10:11Z","title":"Graph Positional Autoencoders as Self-supervised Learners","version":2},"cited_work":{"arxiv_id":"2505.23345","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.23345","snapshot_observed_at":"2026-08-07T00:26:21.378079Z","title":"Graph Positional Autoencoders as Self-supervised Learners","venue":"cs.LG","work_id":"0e7631dc-6fd8-4437-b6c6-0315eb0b64ca","year":2025},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.839602Z"},"links":{"cited_paper":"/paper/2505.23345","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:c8bc690054ade58f230d0695dd2d73997c5afdf69afd8411a988d6d9613f0beb","observation_id":"9c5925f6-b3b2-4b66-8ed0-47c328f56f2d","resolution":{"observed_at":"2026-08-07T00:26:21.382624Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:24.308880Z","title":null,"venue":null,"work_id":"ddb031a5-375b-4c67-990e-09fb906116b6","year":2023},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.843616Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:96bcc4f552cb7be3c5e7bd60e77c08499ab8fa0cb2af24361340689bef6a80f6","observation_id":"11e62d70-42d3-4b6a-9611-a8f6616f87cd","resolution":{"observed_at":"2026-08-07T00:26:24.496949Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.03845","last_updated":"2025-08-28T09:08:33Z","snapshot_observed_at":"2026-07-06T19:46:06.343310Z","submitted_at":"2024-11-06T11:29:47Z","title":"Reconsidering the Performance of GAE in Link Prediction","version":4},"cited_work":{"arxiv_id":"2411.03845","doi":"10.48550/arxiv.2411.03845","metadata_source":"pith","pith_arxiv_id":"2411.03845","snapshot_observed_at":"2026-08-07T06:16:28.064256Z","title":"Reconsidering the Performance of GAE in Link Prediction","venue":"cs.LG","work_id":"1832680c-937a-4758-988f-4080f6798288","year":2024},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.848098Z"},"links":{"cited_paper":"/paper/2411.03845","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:734536a2768ee1406f07b086b7eb9f7e08fb6e1d01ce95c3dddda543f54fc59d","observation_id":"b3f0c9e8-2a92-4f94-a82a-efa54fbf5a7f","resolution":{"observed_at":"2026-08-07T00:26:21.078828Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:24.081973Z","title":null,"venue":null,"work_id":"15fb2910-c1dd-4755-827a-0a6859b03cbc","year":2022},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.852292Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:120d1ee60e5ed7b847ebbc746e2f4508493752fe02520b976534bdf8df1d7ea7","observation_id":"55377e2a-384d-46af-bba5-aa2a6214768c","resolution":{"observed_at":"2026-08-07T00:26:24.194372Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.01427","last_updated":"2020-03-16T21:42:17Z","snapshot_observed_at":"2026-08-08T06:13:08.056055Z","submitted_at":"2019-01-05T15:07:35Z","title":"Poincar\\'e Wasserstein Autoencoder","version":2},"cited_work":{"arxiv_id":"1901.01427","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.01427","snapshot_observed_at":"2026-08-07T00:26:21.357719Z","title":"Poincar\\'e Wasserstein Autoencoder","venue":"cs.LG","work_id":"4e860a61-5e89-4933-9397-f85b27bd90c4","year":2019},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.856270Z"},"links":{"cited_paper":"/paper/1901.01427","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:2dce916de2e4adf339ff3f77009dcb412e2d5cb7abe0487c4250219b1f77e0f7","observation_id":"36a1d0e2-ca1e-4626-bee0-2701b5139304","resolution":{"observed_at":"2026-08-07T00:26:21.361998Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:23.762121Z","title":null,"venue":null,"work_id":"4b0b48f1-a59e-4c60-8fe6-472302ff3dc7","year":2014},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.860494Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:d57fc4129e56b132e3fa2db20f7327b78cb1f4b2b8ba24fc2fc8101a940b4ade","observation_id":"5e147859-b4c8-44eb-9e4d-9286152ac6b1","resolution":{"observed_at":"2026-08-07T00:26:23.927496Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:23.508117Z","title":null,"venue":null,"work_id":"c5d8c911-f2f6-4b71-9592-20b4fa52223f","year":2017},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.864380Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:83a8d00d30061aeb2dc6b221a132ea1c6a2759c3f50918d46c1e454f59506ee5","observation_id":"d36d9f4b-ab83-4331-a0eb-d46feb727d09","resolution":{"observed_at":"2026-08-07T00:26:23.599402Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:23.250791Z","title":null,"venue":null,"work_id":"80916dd7-2e76-4570-9647-43872f099525","year":2025},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.868180Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:9ccc20c631dab92913ae65b7ef08786f5b9ef0b7b6c98ead3dff34e608f554f9","observation_id":"b7235532-46fe-4e5a-8184-9c1b280ef1f1","resolution":{"observed_at":"2026-08-07T00:26:23.358315Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.02534","last_updated":"2022-01-07T16:48:07Z","snapshot_observed_at":"2026-07-06T12:25:30.741916Z","submitted_at":"2022-01-07T16:48:07Z","title":"MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.02534","snapshot_observed_at":"2026-08-07T00:26:20.872142Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.872142Z"},"links":{"cited_paper":"/paper/2201.02534","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:41e148c13840970964404090a0b6f071cbbaa9a929873b00d3241144ca35d3a9","observation_id":"2b5e540e-2a45-4904-af7e-c9a8725782ca","resolution":{"observed_at":"2026-08-07T00:26:20.872142Z","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":"2026-08-07T00:26:23.097725Z","title":null,"venue":null,"work_id":"7be0b615-10bd-4624-b283-c6a148a8f1c6","year":2015},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.876174Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:2d0d72e52f24b8387e1ed818a6f7e91dc6e76ed641722e6d00465dd88569e878","observation_id":"a709e2d5-6be4-4684-b5b3-48509b4941ab","resolution":{"observed_at":"2026-08-07T00:26:23.156653Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16562","last_updated":"2023-07-17T22:41:18Z","snapshot_observed_at":"2026-07-06T15:33:42.279377Z","submitted_at":"2023-05-26T01:06:44Z","title":"Unsupervised Embedding Quality Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.16562","snapshot_observed_at":"2026-08-07T00:26:20.880180Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.880180Z"},"links":{"cited_paper":"/paper/2305.16562","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:c9981f5fb94603a140a506c0e56b71746a5dcd46e4abf20553d19c88ef94b472","observation_id":"1b308946-ef0a-4850-b8ba-4d527267eea2","resolution":{"observed_at":"2026-08-07T00:26:20.880180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.16904","last_updated":"2023-06-01T01:24:33Z","snapshot_observed_at":"2026-08-04T11:34:44.915779Z","submitted_at":"2020-06-30T15:30:49Z","title":"Graph Clustering with Graph Neural Networks","version":3},"cited_work":{"arxiv_id":"2006.16904","doi":null,"metadata_source":"pith","pith_arxiv_id":"2006.16904","snapshot_observed_at":"2026-08-07T00:26:21.307800Z","title":"Graph Clustering with Graph Neural Networks","venue":"cs.LG","work_id":"5517c426-9ef5-4dbe-b273-87affa9256a5","year":2020},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.884100Z"},"links":{"cited_paper":"/paper/2006.16904","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:4cf3e780fd9682411a8a18540981b4f6afdf3d4d03d23eb6cd3653c305e5eb13","observation_id":"4369152c-3b86-44d0-94ea-cbb58c62876a","resolution":{"observed_at":"2026-08-07T00:26:21.312030Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:20.888204Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.888204Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:c7ce359e4b82f63ad6ef73bee6ee50ff834650b6f6075dab65ed9482d04dfc55","observation_id":"e2c73f23-9407-4ac6-a635-5b55d8eb8a16","resolution":{"observed_at":"2026-08-07T00:26:20.888204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.10341","last_updated":"2018-12-21T15:44:59Z","snapshot_observed_at":"2026-07-06T07:04:37.077852Z","submitted_at":"2018-09-27T04:53:24Z","title":"Deep Graph Infomax","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.10341","snapshot_observed_at":"2026-08-07T00:26:20.892005Z","title":"Hamilton, Pietro Liò, Yoshua Bengio, and R","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.892005Z"},"links":{"cited_paper":"/paper/1809.10341","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:4d1aaf07ecc7865cb799f6c2be1147053c8631b86cfebb12fda7c6850062691e","observation_id":"4de7bb14-4c34-49ac-81dc-469e00441499","resolution":{"observed_at":"2026-08-07T00:26:20.892005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14830","last_updated":"2024-03-21T20:43:44Z","snapshot_observed_at":"2026-07-06T17:48:45.803098Z","submitted_at":"2024-03-21T20:43:44Z","title":"Deep Clustering Evaluation: How to Validate Internal Clustering Validation Measures","version":1},"cited_work":{"arxiv_id":"2403.14830","doi":"10.48550/arxiv.2403.14830","metadata_source":"pith","pith_arxiv_id":"2403.14830","snapshot_observed_at":"2026-08-07T06:16:28.064256Z","title":"Deep Clustering Evaluation: How to Validate Internal Clustering Validation Measures","venue":"stat.ML","work_id":"35a858e1-238a-47ce-b14c-2b100d37c534","year":2024},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.896418Z"},"links":{"cited_paper":"/paper/2403.14830","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:b66fa4da300df868607e0968b10b52bf3c39e6a388d7092471aae93397f67583","observation_id":"275d3c80-0fba-4df2-8e9d-d3d3c202f7a4","resolution":{"observed_at":"2026-08-07T00:26:21.058462Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.02591","last_updated":"2019-07-31T22:10:01Z","snapshot_observed_at":"2026-08-07T09:37:01.633122Z","submitted_at":"2019-07-31T22:10:01Z","title":"Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.02591","snapshot_observed_at":"2026-08-07T00:26:20.900505Z","title":"Weidele, Claudio Bellei, Tom Robinson, and Charles E","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.900505Z"},"links":{"cited_paper":"/paper/1908.02591","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:92575ac039652fcfcf76ab2a9cbcaa39df7ad7a154253b8ec5025c13d8e78eac","observation_id":"9b55efd2-d488-4b01-a827-903d329b53b0","resolution":{"observed_at":"2026-08-07T00:26:20.900505Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.07150","last_updated":"2024-11-11T17:23:07Z","snapshot_observed_at":"2026-07-06T19:48:36.508447Z","submitted_at":"2024-11-11T17:23:07Z","title":"Variational Graph Contrastive Learning","version":1},"cited_work":{"arxiv_id":"2411.07150","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.07150","snapshot_observed_at":"2026-08-07T00:26:21.255680Z","title":"Variational Graph Contrastive Learning","venue":"cs.LG","work_id":"70ed452d-86cd-4911-867c-cfecf5168271","year":2024},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.904692Z"},"links":{"cited_paper":"/paper/2411.07150","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:1470da2433a40836eceffaa87af14ebea89f983c96335e5835af9765b7e89764","observation_id":"fe0431f0-16ef-4803-b822-a552ab957bc3","resolution":{"observed_at":"2026-08-07T00:26:21.260536Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00826","last_updated":"2019-02-22T19:15:54Z","snapshot_observed_at":"2026-07-06T07:05:24.565760Z","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":"2026-08-07T00:26:20.908870Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.908870Z"},"links":{"cited_paper":"/paper/1810.00826","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:586125cc352aa972a9b4d5798b12ecb5d452d0ff9bae8d1e507a98882d6be6c7","observation_id":"1b829f11-f78a-4c3a-ae5b-ddd18c0038b8","resolution":{"observed_at":"2026-08-07T00:26:20.908870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.05519","last_updated":"2023-12-09T10:16:53Z","snapshot_observed_at":"2026-07-06T16:59:11.649584Z","submitted_at":"2023-12-09T10:16:53Z","title":"Isomorphic-Consistent Variational Graph Auto-Encoders for Multi-Level Graph Representation Learning","version":1},"cited_work":{"arxiv_id":"2312.05519","doi":"10.48550/arxiv.2312.05519","metadata_source":"pith","pith_arxiv_id":"2312.05519","snapshot_observed_at":"2026-08-07T06:16:28.064256Z","title":"Isomorphic-Consistent Variational Graph Auto-Encoders for Multi-Level Graph Representation Learning","venue":"cs.LG","work_id":"db77c4ce-fba7-47a3-8103-c102a6a4f47c","year":2023},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.913198Z"},"links":{"cited_paper":"/paper/2312.05519","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:75f3e4b44dc813f416958cad40b02bbd11b27f63af05a5204609575bb37e54ff","observation_id":"c3217083-80c9-4185-a11f-3f1e28025571","resolution":{"observed_at":"2026-08-07T00:26:21.038222Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:22.923523Z","title":null,"venue":null,"work_id":"71887c6a-279e-4170-9b35-2e13d72edd2f","year":2020},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.917413Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:b9c3f3b71c7d2eaea90390303e1a31f2d0f1738eb6de7fe85276133b8b023bdb","observation_id":"be668fc1-0b51-445a-940f-88ede3dbe713","resolution":{"observed_at":"2026-08-07T00:26:23.001678Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:22.819097Z","title":null,"venue":null,"work_id":"d4317901-e8f2-4235-b965-a2acd8d6a948","year":2019},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.921581Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:3035644904887bbf8733c1b0654ea450e634ddddb60d0f64e75d49f91c4af1f9","observation_id":"a8c6e812-0b05-453b-b470-1fc4f410aeaa","resolution":{"observed_at":"2026-08-07T00:26:22.882261Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:22.661711Z","title":null,"venue":null,"work_id":"9714d898-36bc-44b7-8c92-77cb7f88079b","year":2024},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.925795Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:749333ae31124aef50b6a38934333e9a28a7d8f059981c8173c47fe6c44e82e6","observation_id":"2ec976ae-70de-4d17-9f53-8c9c9764e812","resolution":{"observed_at":"2026-08-07T00:26:22.732250Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:22.520402Z","title":null,"venue":null,"work_id":"97f3f3f4-b273-45db-887c-ece5ff5a3e10","year":2022},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.929799Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:0c2e5f6926457fcaf818075bc65ef53176a436208df408fbd00b4c276528e8df","observation_id":"cbbbf687-53f6-44a7-9073-b68cc438e139","resolution":{"observed_at":"2026-08-07T00:26:22.564058Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-07-06T20:17:24.683086Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.03451","snapshot_observed_at":"2026-08-07T00:26:20.933649Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.933649Z"},"links":{"cited_paper":"/paper/2501.03451","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:0669f0f5f024e24098e7397b661297ed20a86e168167eefc25d9ce3d2095a7c8","observation_id":"40f61ae3-65f6-45d4-a6e6-825b589bfe89","resolution":{"observed_at":"2026-08-07T00:26:20.933649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-07-06T20:17:24.683086Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"cited_work":{"arxiv_id":"2501.03451","doi":"10.48550/arxiv.2501.03451","metadata_source":"pith","pith_arxiv_id":"2501.03451","snapshot_observed_at":"2026-08-07T06:16:28.064256Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","venue":"stat.ML","work_id":"cf6f97e8-f95c-421b-bd2e-d0c823effdb7","year":2025},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.938452Z"},"links":{"cited_paper":"/paper/2501.03451","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:20cabd13afea14fe092c2910e41522c083b76a86b26f6b88c857ec6af02af529","observation_id":"b34df0ed-f01a-4782-92ef-8c3c108d98fe","resolution":{"observed_at":"2026-08-07T00:26:21.016694Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:22.372342Z","title":null,"venue":null,"work_id":"6456e6c1-be7e-4efe-9926-1595c6ee40b5","year":2023},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.943069Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:2743d305b9fa53e37fccaec966b2b80b586603bc592159219652ec92013bfbfa","observation_id":"8b4a1627-8144-4afc-af40-d018eee42989","resolution":{"observed_at":"2026-08-07T00:26:22.441334Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T00:26:22.214597Z","title":null,"venue":null,"work_id":"84a87573-2de2-439a-a1aa-590c1f89d152","year":2022},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.951392Z"},"links":{"citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:cab4efb68d9feb035f0b20eddad07dce139fbab90544b5d4f4424626c41e712a","observation_id":"37945952-c5c2-42f9-9d2a-0aeb117b390c","resolution":{"observed_at":"2026-08-07T00:26:22.294741Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.04131","last_updated":"2020-07-13T16:32:20Z","snapshot_observed_at":"2026-08-05T13:22:44.473317Z","submitted_at":"2020-06-07T11:50:45Z","title":"Deep Graph Contrastive Representation Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.04131","snapshot_observed_at":"2026-08-07T00:26:20.955313Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.955313Z"},"links":{"cited_paper":"/paper/2006.04131","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:04d036f89f908ba38b567697409eccbebea653c87194765bf8f9b54164324ad0","observation_id":"6f52ff62-3ec2-4bc0-b756-5d5466b33e04","resolution":{"observed_at":"2026-08-07T00:26:20.955313Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T00:16:03.088051Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":1,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":33,"verified_exact":15,"verified_fuzzy":1},"total_outbound_references":52},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2506.14114."}