{"as_of":"2026-08-17T07:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b32f18e9a7e4d4539e47216c6b3d750e01424667b05c3fe3ca29283973a31e17","coverage":[{"denominator":92,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":92,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:00:58.216322Z","state":"measured"},{"denominator":92,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":92,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2506.14098/citation-record","integrity":"/paper/2506.14098/integrity","json":"/paper/2506.14098/citation-record.json","paper":"/paper/2506.14098"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1806.01261","last_updated":"2018-10-17T17:51:36Z","snapshot_observed_at":"2026-08-17T06:40:59.890283Z","submitted_at":"2018-06-04T17:58:18Z","title":"Relational inductive biases, deep learning, and graph networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.01261","snapshot_observed_at":"2026-08-15T20:00:57.510135Z","title":"Battaglia, Jessica B","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.510135Z"},"links":{"cited_paper":"/paper/1806.01261","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:bf13756f7834df0d888ea4278669e5f0550ca590904d6e8f8a021792f9559b1a","observation_id":"f63084db-3121-4e75-ad1a-2b7705a2b86a","resolution":{"observed_at":"2026-08-15T20:00:57.510135Z","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":"2026-08-15T20:00:57.520958Z","title":"Foundations of data science","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.520958Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:d2c464c9d04826650722fc25a50d53eb08b5437fa69365449abd82f4b6dcbe0c","observation_id":"ea9c76c8-979c-4e84-9b54-559330f32359","resolution":{"observed_at":"2026-08-15T20:00:57.520958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07258","last_updated":"2022-07-12T23:45:14Z","snapshot_observed_at":"2026-08-02T09:20:40.804790Z","submitted_at":"2021-08-16T17:50:08Z","title":"On the Opportunities and Risks of Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07258","snapshot_observed_at":"2026-08-15T20:00:57.533820Z","title":"On the opportunities and risks of foundation models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.533820Z"},"links":{"cited_paper":"/paper/2108.07258","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:ec6b8e731ee7d81e6976c8b1e31fe324256059930fd41040140c77d9651bd084","observation_id":"6e851380-d256-4816-bf2d-4f92c0c222b0","resolution":{"observed_at":"2026-08-15T20:00:57.533820Z","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":"2026-08-15T20:00:57.548056Z","title":"Translating embeddings for modeling multi-relational data","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.548056Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:9c215f45bab0f9d6c5cf1634e8d55022fae53d9de1417c4274d6dab299dddb9d","observation_id":"7eb2f467-7bd7-4949-b3ca-26a6c9d820f1","resolution":{"observed_at":"2026-08-15T20:00:57.548056Z","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":"2026-08-15T20:00:57.552839Z","title":"Shortest-path kernels on graphs","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.552839Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:43dfa79e278a049ac80fc970aade602ce6004a33938956d0e5a6ca78b35db668","observation_id":"840714c3-25b1-428d-b068-2fa4dc7c50b3","resolution":{"observed_at":"2026-08-15T20:00:57.552839Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05845","last_updated":"2023-10-09T16:42:00Z","snapshot_observed_at":"2026-08-16T14:53:45.330716Z","submitted_at":"2023-10-09T16:42:00Z","title":"GraphLLM: Boosting Graph Reasoning Ability of Large Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05845","snapshot_observed_at":"2026-08-15T20:00:57.557472Z","title":"Graphllm: Boosting graph reasoning ability of large language model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.557472Z"},"links":{"cited_paper":"/paper/2310.05845","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:ac6e8560f3e82b52478c3c3c9869b70be6614df759045670e98e9c1a42624171","observation_id":"e1d4878b-8207-4a1c-a913-31efe03bdb20","resolution":{"observed_at":"2026-08-15T20:00:57.557472Z","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":"2026-08-15T20:00:57.562908Z","title":"Structure-aware transformer for graph representation learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.562908Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:cacf39c3d0c3314739f54e65fdb5cdc91f29adab339c767cec40d73d2d1e99c7","observation_id":"50c46094-e77c-4a98-8aec-29833f4740e1","resolution":{"observed_at":"2026-08-15T20:00:57.562908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.03386","last_updated":"2024-10-07T14:01:11Z","snapshot_observed_at":"2026-08-16T13:45:50.178603Z","submitted_at":"2024-06-05T15:36:57Z","title":"Learning Long Range Dependencies on Graphs via Random Walks","version":2},"cited_work":{"arxiv_id":"2406.03386","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.03386","snapshot_observed_at":"2026-08-15T20:00:58.551081Z","title":"Learning Long Range Dependencies on Graphs via Random Walks","venue":"cs.LG","work_id":"d34039c1-f7d5-4ea1-8cd7-c091066ada70","year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.567138Z"},"links":{"cited_paper":"/paper/2406.03386","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:5e9196e78d88bf1a5644dfc80e9136a825a9af3d1baa3452e79df3fd4b0de74d","observation_id":"8315e1b2-abd4-4b7d-b5fe-6a0ebfcd9025","resolution":{"observed_at":"2026-08-15T20:00:58.556717Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:00:57.573450Z","title":"FastGCN: Fast learning with graph convolutional networks via importance sampling","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.573450Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:1475450ff34accafbb9348448205d4864656f34b070e476c488d92208f805f21","observation_id":"5d7ecffd-e5d9-4a7a-8109-78b4657d59a8","resolution":{"observed_at":"2026-08-15T20:00:57.573450Z","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":"2026-08-15T20:00:57.577703Z","title":"NAGphormer: A tokenized graph transformer for node classification in large graphs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.577703Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:c9fbf78c82e06decfe11cb44a3e24f4112dae894599608abb8bf8baf45a97635","observation_id":"047e923d-bfec-44a1-97b5-700043c9f309","resolution":{"observed_at":"2026-08-15T20:00:57.577703Z","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":"2026-08-15T20:00:57.582987Z","title":"Simple and deep graph convolutional networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.582987Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:07a1d6d909df2ff148a8f70cd2a5a3b124bf7a4669973152b9ddca13aa30a293","observation_id":"d660237d-9a7b-42de-a0f5-32d4952026a7","resolution":{"observed_at":"2026-08-15T20:00:57.582987Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08170","last_updated":"2024-04-11T05:01:12Z","snapshot_observed_at":"2026-08-16T14:19:08.144752Z","submitted_at":"2024-02-13T02:03:26Z","title":"LLaGA: Large Language and Graph Assistant","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.08170","snapshot_observed_at":"2026-08-15T20:00:57.587855Z","title":"Llaga: Large language and graph assistant","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.587855Z"},"links":{"cited_paper":"/paper/2402.08170","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:24ad4dd898c329a6219c06e8ac16909a4fc3eadac65d54fb4062102578317506","observation_id":"d6777166-fe29-442b-8b42-c8c5f0471c16","resolution":{"observed_at":"2026-08-15T20:00:57.587855Z","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":"2026-08-15T20:00:57.592872Z","title":"Exploring the potential of large language models (LLMs) in learning on graph","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.592872Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:49012418a0fb2d91aa217c3c3e1151e5c529bcd0133caf4cd64260267db4a504","observation_id":"09f1cd3a-e343-4cda-801d-e6330333f1e2","resolution":{"observed_at":"2026-08-15T20:00:57.592872Z","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":"2026-08-15T20:00:57.598814Z","title":"Node feature extraction by self-supervised multi-scale neighborhood prediction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.598814Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:5123f2c9ed067271cd6a215585e8a9b793d2d111470de9a89f2c806b5d771faf","observation_id":"ca912c27-6ad2-4852-848d-0b80d1905660","resolution":{"observed_at":"2026-08-15T20:00:57.598814Z","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":"2026-08-15T20:00:57.624324Z","title":"Rethinking attention with performers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.624324Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:0a7c9daa8deb3ed0195819095abd685921c67f1ef9cf821a6e4417f09f1c5ffa","observation_id":"8644ef16-d90a-4020-87fb-6f3fa6ffb087","resolution":{"observed_at":"2026-08-15T20:00:57.624324Z","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":"2026-08-15T20:00:57.650203Z","title":"Convolutional 2d knowledge graph embeddings","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.650203Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:ac77eb1ef5f7ed3c2a03b3fce04eaf1a31cb38dc6004c27a974bbcde424ba05e","observation_id":"302a8e37-c5d2-419f-87e0-6e2f9b05a76e","resolution":{"observed_at":"2026-08-15T20:00:57.650203Z","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":"2026-08-15T20:00:57.674420Z","title":"A generalization of transformer networks to graphs","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.674420Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:2ab7965490d6bf59eea313833bd8725b115a05827091829702bc48ea15faee83","observation_id":"66043159-cbeb-4fb5-8218-716eda9b3b5b","resolution":{"observed_at":"2026-08-15T20:00:57.674420Z","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":"2026-08-15T20:00:59.410926Z","title":"Long range graph benchmark","venue":null,"work_id":"3eacf50c-ea6d-4d12-b552-1c2807bfe9eb","year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.698079Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:8913a484549f48f604d334544e8df7592d9d5e33be0926136966b7858b8d74b5","observation_id":"b5fd6e73-cafb-48f5-abef-2ed5e5f9479c","resolution":{"observed_at":"2026-08-15T20:00:59.415699Z","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":"2026-08-15T20:00:59.394945Z","title":"Talk like a graph: Encoding graphs for large language models","venue":null,"work_id":"3bb20f09-9b8b-40c8-b567-e642f5c85827","year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.716856Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:19fc11c2f084db612ef01ffeaa6fcdbb796413870cd2a7d27f1226283bfa4543","observation_id":"33c7f844-ba04-490a-bf21-11d44b46e91f","resolution":{"observed_at":"2026-08-15T20:00:59.400053Z","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":"2310.04562","last_updated":"2024-04-09T19:48:22Z","snapshot_observed_at":"2026-08-16T14:54:21.682492Z","submitted_at":"2023-10-06T20:00:07Z","title":"Towards Foundation Models for Knowledge Graph Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04562","snapshot_observed_at":"2026-08-15T20:00:57.753022Z","title":"Towards foundation models for knowledge graph reasoning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.753022Z"},"links":{"cited_paper":"/paper/2310.04562","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:6cff932d8f8842db0c8b01f31fcbc15fb22f34cd2775221fe210f2302d1448fc","observation_id":"4aa8fa5e-9b22-411d-ac54-0ca20b94da30","resolution":{"observed_at":"2026-08-15T20:00:57.753022Z","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":"2026-08-15T20:00:57.793647Z","title":"Predict then propagate: Graph neural networks meet personalized pagerank","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.793647Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:cdf8f3680067e287a7826728d4caf73ba6b04a5936bd659fb1f7e76b106a5e21","observation_id":"27fa8522-4a55-4b53-9c03-d3fe20e82ecf","resolution":{"observed_at":"2026-08-15T20:00:57.793647Z","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":"2026-08-15T20:00:57.799048Z","title":"Chembl: a large-scale bioactivity database for drug discovery","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.799048Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:8fbb783f109ca689e32a73db4e29c146495fa01629736d8e4239fe52c7415454","observation_id":"3b27d68b-90ef-4b5f-9d11-ba3d322c84c5","resolution":{"observed_at":"2026-08-15T20:00:57.799048Z","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":"2026-08-15T20:00:57.804241Z","title":"Citeseer: An automatic citation indexing system","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.804241Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:cfe25ec00c76bc214616f425bc003272f2fcbebcafe766855a5a2f439c6031e3","observation_id":"10d39324-7f59-41f2-b155-5d4370f5257d","resolution":{"observed_at":"2026-08-15T20:00:57.804241Z","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":"2026-08-15T20:00:57.808843Z","title":"Schoenholz, Patrick F","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.808843Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:a6572ddb7cc10d4c6893ac865ed3ae450ebff1f843d3916fd8fdddb0874cfadc","observation_id":"ae521761-b334-460d-bdd5-83a5f8901fce","resolution":{"observed_at":"2026-08-15T20:00:57.808843Z","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":"2026-08-15T20:00:57.813565Z","title":"node2vec: Scalable feature learning for networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.813565Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:81a64250fe7b0d0b4761e0be782b20eb7b43ac37080f7d60e2cfbb9d77e5cd25","observation_id":"f9e7ff23-a64f-4683-89e4-8575ec3b2241","resolution":{"observed_at":"2026-08-15T20:00:57.813565Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15066","last_updated":"2023-07-11T15:08:00Z","snapshot_observed_at":"2026-08-16T15:30:11.640476Z","submitted_at":"2023-05-24T11:53:19Z","title":"GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15066","snapshot_observed_at":"2026-08-15T20:00:57.817903Z","title":"GPT4Graph: Can large language models understand graph structured data ? an empirical evaluation and benchmarking","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.817903Z"},"links":{"cited_paper":"/paper/2305.15066","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:e5d5797f9374e14707985d2ac7519c19370b8dd613f8bb9fae96e3d5eb298f76","observation_id":"0eaf1dc2-4b73-4b6f-9ea6-50ebb03c9aef","resolution":{"observed_at":"2026-08-15T20:00:57.817903Z","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":"2026-08-15T20:00:59.329098Z","title":"Gutmann and Aapo Hyvärinen","venue":null,"work_id":"a09e1daf-cfd3-42ca-a6f0-40ebc3dee520","year":2012},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.823227Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:11cf2f3e87c992aead85072ebca9f9db10aef939c205d1fd3ba24f0fabe19184","observation_id":"d00ccdbf-2c98-425c-9e6e-a4b2274bc0e1","resolution":{"observed_at":"2026-08-15T20:00:59.334076Z","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":"2026-08-15T20:00:59.313529Z","title":"Hamilton, Rex Ying, and Jure Leskovec","venue":null,"work_id":"96feed95-d45d-4f71-82db-bf248129a0d6","year":2017},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.827833Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:0fd6ec31edacf50cfc7355a1289e534152475a5f9260b1703bfde13190ad56e7","observation_id":"d9b144b5-1f1a-480e-b4da-0eb2e03f45cd","resolution":{"observed_at":"2026-08-15T20:00:59.318335Z","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":"2305.19523","last_updated":"2024-03-07T02:45:36Z","snapshot_observed_at":"2026-08-16T15:28:05.962866Z","submitted_at":"2023-05-31T03:18:03Z","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19523","snapshot_observed_at":"2026-08-15T20:00:57.837836Z","title":"Harnessing explanations: Llm-to-lm interpreter for enhanced text-attributed graph representation learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.837836Z"},"links":{"cited_paper":"/paper/2305.19523","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:a0524cd9b3fb1820dc14f76a1e6b501620b1db57322010797de93eb84ec399cf","observation_id":"a10b644a-f88c-40c3-9174-5aa238ef3b5b","resolution":{"observed_at":"2026-08-15T20:00:57.837836Z","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":"2026-08-15T20:00:59.298359Z","title":"Unigraph: Learning a cross-domain graph foundation model from natural language","venue":null,"work_id":"7fe9b64c-5c89-49f7-a3e0-81ae3d203786","year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.842207Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:be158587c5334cafaddf8a09d1ec8d3e3fa84186620f477dc04c8c200b6fff69","observation_id":"102d0fe2-495a-4b40-8911-b7289ca29958","resolution":{"observed_at":"2026-08-15T20:00:59.303271Z","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":"2026-08-15T20:00:57.846710Z","title":"Learning deep representations by mutual information estimation and maximization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.846710Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:3be9e949e56cc24c8b8f76bcb670fdab42bcd9d828584d878d5c60397e26623a","observation_id":"2b7d0e8c-e30f-4332-896a-1a5169c67205","resolution":{"observed_at":"2026-08-15T20:00:57.846710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.15556","last_updated":"2022-03-29T13:38:03Z","snapshot_observed_at":"2026-08-09T19:52:33.533277Z","submitted_at":"2022-03-29T13:38:03Z","title":"Training Compute-Optimal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.15556","snapshot_observed_at":"2026-08-15T20:00:57.850385Z","title":"Rae, Oriol Vinyals, and Laurent Sifre","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.850385Z"},"links":{"cited_paper":"/paper/2203.15556","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:5af9855c1540821416509c8c7a243673aa63647aba745809ee994ff1b0504c1d","observation_id":"5cc1b95d-52b9-421c-9d65-49ac24cfbf2a","resolution":{"observed_at":"2026-08-15T20:00:57.850385Z","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":"2026-08-15T20:00:59.273174Z","title":"GraphMAE: Self-supervised masked graph autoencoders","venue":null,"work_id":"057e3c19-95a6-469f-926f-6efd4ceec9ce","year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.854897Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:f1b0b48f0aaae58faff49931ff28427e2d6374e1ba1745d2c3ded7068b7d0f85","observation_id":"b18b623f-91bf-48ce-963d-57b6b0f5b467","resolution":{"observed_at":"2026-08-15T20:00:59.277906Z","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":"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":"2026-08-15T20:00:57.858995Z","title":"Open graph benchmark: Datasets for machine learning on graphs","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.858995Z"},"links":{"cited_paper":"/paper/2005.00687","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:7b4dfaf97757e9fb7005ee59620cd128c18c29be27f38d24172c8492e60dd400","observation_id":"3a1510c9-837c-4907-b226-b696858b67aa","resolution":{"observed_at":"2026-08-15T20:00:57.858995Z","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":"2026-08-15T20:00:59.257223Z","title":"Strategies for pre-training graph neural networks","venue":null,"work_id":"71383c91-1a9a-4b4a-b2bd-f587ab145dad","year":2020},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.863828Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:d1122ef651ba68f2d5e8407fe6ab611f754e5d7f13871154bbf770f9ff18d850","observation_id":"59dc465a-6b33-4646-869d-86912350d200","resolution":{"observed_at":"2026-08-15T20:00:59.262484Z","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":"2026-08-15T20:00:59.243815Z","title":"PRODIGY: Enabling in-context learning over graphs","venue":null,"work_id":"016f98bb-3371-40d0-8fd2-7778d01d3861","year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.868184Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:ac52c029ab8d997c8282091446d3e4b2980a8caa9e195edd30ffe798e8dfcf04","observation_id":"135a469f-cf5a-4ddd-b827-d2dbc141142f","resolution":{"observed_at":"2026-08-15T20:00:59.248095Z","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":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-08-13T17:41:53.092611Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-15T20:00:57.872620Z","title":"Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.872620Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:89d090046bbfe83d9ed952a9852fe194fa0e3dce81a687a1333b4279c8fb0b78","observation_id":"236bc5e2-7faa-4b6e-8031-c86fe8cdc0e9","resolution":{"observed_at":"2026-08-15T20:00:57.872620Z","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":"2026-08-15T20:00:57.877288Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.877288Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:8535711adcff215e942214e99d4da35b5e2f5bc95666b5abc253997559f87764","observation_id":"587eca61-4285-42e8-9250-d6b59b24d520","resolution":{"observed_at":"2026-08-15T20:00:57.877288Z","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":"2026-08-15T20:00:57.881518Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.881518Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:82a1ce421b8599089568b670f9f1a6d2aa579bcafae60330d32c0866c548a71e","observation_id":"315de6de-9d6a-449c-9392-43daaa617c8b","resolution":{"observed_at":"2026-08-15T20:00:57.881518Z","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":"2026-08-15T20:00:59.209767Z","title":"Hamilton, Vincent Létourneau, and Prudencio Tossou","venue":null,"work_id":"1853707f-75ad-49e5-8ae2-56c1cb263f40","year":2021},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.886150Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:0c58a02e77cf43636ca4ef12bae26327f2e553e59c1dd773038d99684ef543d3","observation_id":"394f387b-74a8-4e6c-8da9-33e3c24ccca4","resolution":{"observed_at":"2026-08-15T20:00:59.214216Z","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":"2026-08-15T20:00:59.194041Z","title":"What’s behind the mask: Understanding masked graph modeling for graph autoencoders","venue":null,"work_id":"d964a605-cc04-4563-9712-7c224087630f","year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.890819Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:fa3e310622a1fa2f0f6623ea9732a105af524dbb30f58f1e6008bd3623d8fb59","observation_id":"4a34d486-d7f3-4893-a1be-b092770b221c","resolution":{"observed_at":"2026-08-15T20:00:59.199349Z","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":"2026-08-15T20:00:59.178370Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":"ef258f9d-d7f9-4378-bd67-6fb91ad88f57","year":2018},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.895335Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:41abcc72cfd249e9d561fbaeb1fc80f0c82722798def28907716dab4fb8f360b","observation_id":"e34640b2-9bc3-44ab-84d0-b6145d88d00d","resolution":{"observed_at":"2026-08-15T20:00:59.182958Z","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":"2026-08-15T20:00:59.163689Z","title":"Gated graph sequence neural networks","venue":null,"work_id":"56dd16cf-d807-4eac-b4dc-7f2528c9da9a","year":2016},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.900745Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:297c0691fcea948ca518e4a170da711c1687eccef20e14d2f5891bba542ed947","observation_id":"9c621bd0-cb66-450e-9cfd-c2846aab5797","resolution":{"observed_at":"2026-08-15T20:00:59.168308Z","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":"2026-08-15T20:00:57.905365Z","title":"One for all: Towards training one graph model for all classification tasks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.905365Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:fe456ede1469711b408c3070ae5b5fd20810b081547370206673aac3b7ffcb1e","observation_id":"8a99c4e4-0d9a-4015-b0ae-fd785c29097c","resolution":{"observed_at":"2026-08-15T20:00:57.905365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11829","last_updated":"2025-03-10T16:14:30Z","snapshot_observed_at":"2026-08-16T14:51:07.649322Z","submitted_at":"2023-10-18T09:31:21Z","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11829","snapshot_observed_at":"2026-08-15T20:00:57.909843Z","title":"Towards graph foundation models: A survey and beyond","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.909843Z"},"links":{"cited_paper":"/paper/2310.11829","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:f1a6865aee18c67e4334f647804e6bfb31a44405d3dd67d7cf55fbf7bc873a6d","observation_id":"b9511f35-de2a-429d-bddb-07412a00f19d","resolution":{"observed_at":"2026-08-15T20:00:57.909843Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.10198","last_updated":"2018-01-30T20:07:01Z","snapshot_observed_at":"2026-08-14T19:50:32.053437Z","submitted_at":"2018-01-30T20:07:01Z","title":"Generating Wikipedia by Summarizing Long Sequences","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.10198","snapshot_observed_at":"2026-08-15T20:00:57.932699Z","title":"Generating Wikipedia by summarizing long sequences","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.932699Z"},"links":{"cited_paper":"/paper/1801.10198","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:cd8d8b50d3e8a70836b1102b3ca9fd8e7cf86a0de29b9b5c4ef903017d97207c","observation_id":"403e2f1e-1667-4ad3-bea6-ea710ad0c86b","resolution":{"observed_at":"2026-08-15T20:00:57.932699Z","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":"2026-08-15T20:00:59.138970Z","title":"Graphprompt: Unifying pre-training and downstream tasks for graph neural networks","venue":null,"work_id":"f07323e5-a862-4224-97cb-1c5c890af794","year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.955313Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:38a5ddea092d5372df29f147af04ee20f2049b8a524d70cdffd0798c71b614d2","observation_id":"333bf381-a1e6-4cba-ac07-31fa2a6a8a37","resolution":{"observed_at":"2026-08-15T20:00:59.144148Z","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":"2026-08-15T20:00:59.124326Z","title":null,"venue":null,"work_id":"ca499c3b-736d-49f0-863b-3200fb019496","year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.978995Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:f9713ba4999f808ea61a22c40d3fd7105dde0b5709a4a7e7683fe08aadb4fe3c","observation_id":"2bcf8b1e-2227-42c1-a051-22d8899ef061","resolution":{"observed_at":"2026-08-15T20:00:59.128831Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-15T20:00:57.991159Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:57.991159Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:ee70be2c8c698ce85f77d2a47e821ef2863b36b9ae2e79a8a24e9820c413a600","observation_id":"0bc38845-9076-46d3-a829-a21d18937583","resolution":{"observed_at":"2026-08-15T20:00:57.991159Z","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":"2026-08-15T20:00:59.108701Z","title":"Dokania, Mark Coates, Philip Torr, and Ser-Nam Lim","venue":null,"work_id":"a5c66106-4f2d-4b0a-bb05-3215e0b4bbf4","year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.002236Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:de1bb850497d22c97f1c9f9b1548ba60b06dd43dc2eecede85c00da6c047ab58","observation_id":"beb65345-c400-43b8-99f2-1298b1a1efb5","resolution":{"observed_at":"2026-08-15T20:00:59.113820Z","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":"2026-08-15T20:00:58.015093Z","title":"Position: Graph foundation models are already here","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.015093Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:707e929413b2110694b7bb81129bd91c22d81423c45bebdbcbb3e593a23aa80a","observation_id":"6f887a48-e65f-4e9f-a7f3-61ce7e2fe7ce","resolution":{"observed_at":"2026-08-15T20:00:58.015093Z","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":"2026-08-15T20:00:59.084873Z","title":"Graph reconstruction via distance oracles","venue":null,"work_id":"5f8ffc1f-b9c2-46a0-8ceb-670abe8055bf","year":2013},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.026495Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:78f8d0244c2c2ce857b2493ef840339807b69d0e04c726b7900c8e17f904cc6f","observation_id":"27afb228-8ae6-496a-a3e3-3fb553cc8888","resolution":{"observed_at":"2026-08-15T20:00:59.089373Z","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":"2026-08-15T20:00:58.031067Z","title":"Automating the construction of internet portals with machine learning","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.031067Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:97fed9523f24915ef851a0570390f83f3cd98f189eb762b09dec9eab35f307c9","observation_id":"d764f73b-0938-454c-8ae1-6cc609329c89","resolution":{"observed_at":"2026-08-15T20:00:58.031067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.02901","last_updated":"2022-01-09T23:19:38Z","snapshot_observed_at":"2026-08-09T07:12:13.529182Z","submitted_at":"2020-07-06T17:25:47Z","title":"Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.02901","snapshot_observed_at":"2026-08-15T20:00:58.036347Z","title":"Wiki-cs: A wikipedia-based benchmark for graph neural networks","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.036347Z"},"links":{"cited_paper":"/paper/2007.02901","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:38087725fb24ae4e0f33cfa90bbf13796407f79f82b6ca3e88e7de875ea9e087","observation_id":"95cfccfa-eab1-4d2b-95da-3e87bf720cb9","resolution":{"observed_at":"2026-08-15T20:00:58.036347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.03561","last_updated":"2020-10-30T09:37:18Z","snapshot_observed_at":"2026-08-17T01:26:56.755090Z","submitted_at":"2019-11-08T22:14:35Z","title":"Graph-to-Graph Transformer for Transition-based Dependency Parsing","version":4},"cited_work":{"arxiv_id":"1911.03561","doi":null,"metadata_source":"pith","pith_arxiv_id":"1911.03561","snapshot_observed_at":"2026-08-15T20:00:58.343391Z","title":"Graph-to-Graph Transformer for Transition-based Dependency Parsing","venue":"cs.CL","work_id":"b0b562c3-3ac6-498e-9f6f-fa354e2f50d2","year":2019},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.041818Z"},"links":{"cited_paper":"/paper/1911.03561","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:65b57822527957801005acbaa4030dcd2c76975f5f977bd9928c2b0e583e6491","observation_id":"25b0a3b8-cf83-4fd8-8f3a-8bb8502dddf1","resolution":{"observed_at":"2026-08-15T20:00:58.350389Z","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":"2026-08-15T20:00:59.060230Z","title":"Recursive non-autoregressive graph-to-graph transformer for dependency parsing with iterative refinement","venue":null,"work_id":"be030d92-9443-4e28-a6e9-e63f6f9cabb3","year":2021},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.047145Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:9c70d5e73ff32532f8002bedfe5a69c63eb73f27dd07058d50f53293207bd650","observation_id":"bf3ec320-bfb7-4b94-a31a-22b6643228e4","resolution":{"observed_at":"2026-08-15T20:00:59.064983Z","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":"2026-08-15T20:00:59.043354Z","title":"DeepWalk: Online learning of social representations","venue":null,"work_id":"4b9dbcff-715f-4319-943d-dc74bc26f58f","year":2014},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.051372Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:6d8ba0e70825c32978dde87bcd8de19922488d3bd02b341ea2fcb6e1e5255192","observation_id":"2d98fe2b-ec4d-4d12-8516-256c06810251","resolution":{"observed_at":"2026-08-15T20:00:59.049942Z","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":"2026-08-15T20:00:59.023906Z","title":"Gcc: Graph contrastive coding for graph neural network pre-training","venue":null,"work_id":"85f72d4f-8e5b-4f3b-a850-296125c0dd2d","year":2020},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.056017Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:820ec25a336deb778192b0e934a43d60e7f9b6bc7ec6719c1112a44d82690bf5","observation_id":"748d13cf-d118-4a3a-b64e-c3b4b865861c","resolution":{"observed_at":"2026-08-15T20:00:59.030587Z","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":"2026-08-15T20:00:59.008462Z","title":"Improving language understanding by generative pre-training","venue":null,"work_id":"634a80e8-5b5f-44b8-adb0-b95ee8906167","year":2018},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.060519Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:4191c309fd4bd175c0384bebe3642a056cb1f3a4a892b3d9ee50cf52e4703d71","observation_id":"0ef6ca97-a42e-442e-b8f4-77b900112675","resolution":{"observed_at":"2026-08-15T20:00:59.012834Z","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":"2026-08-15T20:00:58.993076Z","title":"Recipe for a general, powerful, scalable graph transformer","venue":null,"work_id":"1699b1c1-2ffa-44ee-8daa-88160e16c323","year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.065327Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:2564384348a997a1c6dddf81695c154c147887916b02df696e5e126e19265ff7","observation_id":"bc3bb65c-3a01-42a2-a3af-d105a822e557","resolution":{"observed_at":"2026-08-15T20:00:58.998767Z","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":"2026-08-15T20:00:58.979052Z","title":"Learning and verifying graphs using queries with a focus on edge counting","venue":null,"work_id":"e01e199d-4daa-481f-879a-3dfd32c8406b","year":2007},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.069768Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:6be4fb3a22ea856e41a49607c9abf96210418dbdcc417f29babe93de5be125d9","observation_id":"89270f6d-c9eb-48f7-9157-e3914af4e005","resolution":{"observed_at":"2026-08-15T20:00:58.983638Z","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":"2026-08-15T20:00:58.964250Z","title":"DropEdge: Towards deep graph convolutional networks on node classification","venue":null,"work_id":"64b91b88-097e-49b4-a79b-eee611cf5adb","year":2020},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.074880Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:1f3d8ab993a2f7e4bd54041128402de231b31511036dcd68d3763c9c3ce114d7","observation_id":"d68b6481-8dac-406e-a851-512f7f0ca65d","resolution":{"observed_at":"2026-08-15T20:00:58.969028Z","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":"2026-08-15T20:00:58.948457Z","title":"GPPT: Graph pre-training and prompt tuning to generalize graph neural networks","venue":null,"work_id":"f4b6104c-23be-476a-b4fa-8ad6b51dd032","year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.079416Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:9a7362aba6b4d209fdb4dfc723beda324f837ec7a0c904d4bd7e70fc83750923","observation_id":"5c55d825-0e28-46f7-b6c7-8c517aeaefb5","resolution":{"observed_at":"2026-08-15T20:00:58.953868Z","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":"2026-08-15T20:00:58.084045Z","title":"All in one: Multi-task prompting for graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.084045Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:ba47994c0869b22b0a3fa7200d7e794a01bda6b3a680a2056d6411dcadcff48f","observation_id":"036d28a0-4c79-4d04-a766-fa8be04159e4","resolution":{"observed_at":"2026-08-15T20:00:58.084045Z","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":"2026-08-15T20:00:58.923500Z","title":"Walklm: A uniform language model fine-tuning framework for attributed graph embedding","venue":null,"work_id":"c75b086d-1ba3-4c2f-82c1-7debf86af74d","year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.088246Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:690dced9350f41bc44bba87d67fb6c71d77d7df35c38b9bf34ec79dcb75eaaa0","observation_id":"a74bb996-f7ee-4023-b532-d8bb032b23dd","resolution":{"observed_at":"2026-08-15T20:00:58.928516Z","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":"2026-08-15T20:00:58.907362Z","title":"Graphgpt: Graph instruction tuning for large language models","venue":null,"work_id":"13a08660-9648-4324-be63-7dbcfbb74693","year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.093270Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:f59e92596b94211fc0de023397bc1a998a4c442cc5ebb4aaf6ddbd982423766e","observation_id":"344e9a19-ba0a-4e29-999f-6110a9851e7c","resolution":{"observed_at":"2026-08-15T20:00:58.912144Z","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":"2026-08-15T20:00:58.892169Z","title":"Dyer, Rémi Munos, Petar Veliˇckovi´c, and Michal Valko","venue":null,"work_id":"d775069e-ccf0-433f-aa00-82ce2b59e81b","year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.098348Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:ddde33677b10efd7560338bee5eacea24d851efad16aee76e042d11bd33cbd7d","observation_id":"d1d3a92e-52c6-4f41-a376-e8c976e0df70","resolution":{"observed_at":"2026-08-15T20:00:58.897008Z","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":"2026-08-15T20:00:58.876694Z","title":"Chawla, and Panpan Xu","venue":null,"work_id":"b5d6908f-2f1c-4d82-9998-67fab8f2ffe6","year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.102774Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:302c6dd63fb67a3076256d0ff0bd60373b82ec534c6a214cfac6ef8a7754749c","observation_id":"0a2766d4-14d1-4c50-a496-b6f6bf0c00e2","resolution":{"observed_at":"2026-08-15T20:00:58.881895Z","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":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-15T20:00:58.107638Z","title":"Llama 2: Open foundation and fine-tuned chat models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.107638Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:35b9ce1570f804cd73b73f20106fd9918fb5e70575843d67244680739e37ceed","observation_id":"c7cc2f2b-68f8-41eb-a328-8ac7a9e7237a","resolution":{"observed_at":"2026-08-15T20:00:58.107638Z","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":"2026-08-15T20:00:58.113101Z","title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.113101Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:135020ec5d8aa9bedc192a53750dcbb6da4f9658e66092b38df6df2e428473b0","observation_id":"bf21e75e-4f2c-42bd-a422-b2f5f6886c46","resolution":{"observed_at":"2026-08-15T20:00:58.113101Z","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":"2026-08-15T20:00:58.118216Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.118216Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:ad394ed27f9113618ab2c1c5253f0cad24dabdfc9e3694f827cabb29376eec06","observation_id":"5bed2888-2965-41ec-896b-ad086008e923","resolution":{"observed_at":"2026-08-15T20:00:58.118216Z","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":"2026-08-15T20:00:58.122529Z","title":"Hamilton, Pietro Liò, Yoshua Bengio, and R Devon Hjelm","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.122529Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:786be651105712446734a5da0e22bc964c932e8009309f2f2dfca2fd665658b2","observation_id":"477462b9-e2e2-49c1-9021-70733fdc90be","resolution":{"observed_at":"2026-08-15T20:00:58.122529Z","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":"2026-08-15T20:00:58.835218Z","title":"Can language models solve graph problems in natural language? In NeurIPS, 2023","venue":null,"work_id":"a132336f-cc17-4ddf-96a6-6335a829d4aa","year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.127013Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:4a9a9643490a800ad7d1318911f7c21d5c5c15b19a9531116bfe28949d1a9d83","observation_id":"bb6d147f-e387-4584-a6f1-899646083e40","resolution":{"observed_at":"2026-08-15T20:00:58.839728Z","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":"2026-08-15T20:00:58.820890Z","title":"GFT: Graph foundation model with transferable tree vocabulary","venue":null,"work_id":"fd51c5fe-a8d8-48b8-94be-95b9d7e55c83","year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.131839Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:ad62e17f1a0dbd1b97fa9539ede981cd2467972fbc85cc53c88f401e796921cc","observation_id":"c73ee7ec-a2e7-4026-876d-b778174d1c6d","resolution":{"observed_at":"2026-08-15T20:00:58.825403Z","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":"2026-08-15T20:00:58.805843Z","title":"Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus","venue":null,"work_id":"a184e1fe-c36a-43b3-b2a3-9cf6bfe19e7c","year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.136334Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:1d718b05fc1786157917bd95ddd01a20e1ba15e5f62e1bb64d47db55a5d4ba8d","observation_id":"68498aee-a252-4241-82d0-a01aec4dc61a","resolution":{"observed_at":"2026-08-15T20:00:58.810271Z","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":"2026-08-15T20:00:58.791462Z","title":"NodeFormer: A scalable graph structure learning transformer for node classification","venue":null,"work_id":"c4c8f8fe-fbf3-4870-85d2-281bb6090d92","year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.140754Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:e74e818ba5393105fdd7fa154a76aa273bb5edd150d0131b7d80614e330495b7","observation_id":"c8a97882-ef1c-44cb-ab3b-0bd5d6d85beb","resolution":{"observed_at":"2026-08-15T20:00:58.796178Z","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":"2026-08-15T20:00:58.145379Z","title":"Wright, Azalia Mirhoseini, Joseph E","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.145379Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:1a734ee648be9b4d73e55b2b05099e59c55b71afc124b3a8a9316dcc03cf5d7a","observation_id":"ef65b827-8a32-42f5-8b6a-ef56df412d20","resolution":{"observed_at":"2026-08-15T20:00:58.145379Z","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":"2026-08-15T20:00:58.149981Z","title":"Moleculenet: a benchmark for molecular machine learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.149981Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:b7fb85a257bd169abf56b7f78d9ec7a1b99e301d60436a3a422852ebb16c2f5c","observation_id":"e47797ad-0716-4b43-b770-b617dae8af88","resolution":{"observed_at":"2026-08-15T20:00:58.149981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01121","last_updated":"2024-10-09T12:10:38Z","snapshot_observed_at":"2026-08-16T14:13:32.272142Z","submitted_at":"2024-03-02T08:05:03Z","title":"OpenGraph: Towards Open Graph Foundation Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.01121","snapshot_observed_at":"2026-08-15T20:00:58.154365Z","title":"Opengraph: Towards open graph foundation models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.154365Z"},"links":{"cited_paper":"/paper/2403.01121","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:61b3ca071d4f290994f871c1a433aae6b76202b940608b18acd8455f850fbc06","observation_id":"8ff08a91-34cc-40ff-bc7a-0d37030770df","resolution":{"observed_at":"2026-08-15T20:00:58.154365Z","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":"2026-08-15T20:00:58.158525Z","title":"How powerful are graph neural networks? In ICLR, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.158525Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:0fd83d1381f59a0c38ad0b8c46746ecd0a327460d1bca62f7ecc7b2121e48214","observation_id":"0871e673-56a3-4d37-b39e-3e970463aa67","resolution":{"observed_at":"2026-08-15T20:00:58.158525Z","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":"2026-08-15T20:00:58.162781Z","title":"Revisiting semi-supervised learning with graph embeddings","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.162781Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:34add88d5beeae1cf92a56f3be8cee0ccbc5824722a303da8d8b6f4264f76958","observation_id":"724b74f8-c2a5-40d8-a41e-a009340706e1","resolution":{"observed_at":"2026-08-15T20:00:58.162781Z","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":"2026-08-15T20:00:58.727403Z","title":"Do transformers really perform bad for graph representation? In NeurIPS, 2021","venue":null,"work_id":"6ddc1026-e3d5-4d18-a3f8-07b97bf8558d","year":2021},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.166937Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:275e98ef58cb9508656aa96c1f4461591d8355f11abb86c75bad586120c9f87d","observation_id":"727dfc3b-93ca-4f31-861d-7b93cf6580b6","resolution":{"observed_at":"2026-08-15T20:00:58.733019Z","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":"2026-08-15T20:00:58.710220Z","title":"Graph contrastive learning with augmentations","venue":null,"work_id":"4ae84e31-9ea9-40bf-83c1-c1fdf3847250","year":2020},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.171668Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:9783177840bbd698cfd1531561f2427f0316a46a5529cd5845d8bc14c7fba3f1","observation_id":"285f48b0-a982-42cf-922e-ec6ad94f410b","resolution":{"observed_at":"2026-08-15T20:00:58.715099Z","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":"2026-08-15T20:00:58.694755Z","title":"Hierarchical graph transformer with adaptive node sampling","venue":null,"work_id":"17dc7c02-8bde-4bbf-8bbe-0d6b9bdfd409","year":2022},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.175644Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:7388c4660228d373c4a2ceec204cf603bc3b1c6f8f2b5c815c431677c45bf7f6","observation_id":"217659f6-d6c1-4f11-ad5c-456bdccac9bc","resolution":{"observed_at":"2026-08-15T20:00:58.699509Z","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":"2026-08-15T20:00:58.679447Z","title":"All in one and one for all: A simple yet effective method towards cross-domain graph pretraining","venue":null,"work_id":"7981a897-1e31-4799-93ab-4366dc9fab5d","year":2024},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.180069Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:1d2cd4c6169d163a3ac6e9dabfdfbd08db190121409baf1ae2a18181e22d3de2","observation_id":"78a06ecd-2b87-41e7-b761-b19f071953ed","resolution":{"observed_at":"2026-08-15T20:00:58.683932Z","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":"2110.13094","last_updated":"2021-10-25T16:43:32Z","snapshot_observed_at":"2026-08-16T17:46:43.987857Z","submitted_at":"2021-10-25T16:43:32Z","title":"Gophormer: Ego-Graph Transformer for Node Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.13094","snapshot_observed_at":"2026-08-15T20:00:58.184992Z","title":"Gophormer: Ego-graph transformer for node classification","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.184992Z"},"links":{"cited_paper":"/paper/2110.13094","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:972bb207973031816dd1a5cd16b32cfef66d4ec133f6af37651694baebfe0c10","observation_id":"1534a4e0-4ba4-4c8d-8a42-e89c0b749123","resolution":{"observed_at":"2026-08-15T20:00:58.184992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01089","last_updated":"2023-10-02T11:03:57Z","snapshot_observed_at":"2026-08-16T14:55:55.136483Z","submitted_at":"2023-10-02T11:03:57Z","title":"GraphText: Graph Reasoning in Text Space","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01089","snapshot_observed_at":"2026-08-15T20:00:58.189903Z","title":"Graphtext: Graph reasoning in text space","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.189903Z"},"links":{"cited_paper":"/paper/2310.01089","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:5a990e79d51a75e410a72becf5db8cb0e236cfec624f111933fa4f6fd3dc85b7","observation_id":"57f276dd-a0e5-4e54-b9d8-35f8369ce1b1","resolution":{"observed_at":"2026-08-15T20:00:58.189903Z","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":"2026-08-15T20:00:58.664836Z","title":"Hierarchical transformer for scalable graph learning","venue":null,"work_id":"ae1deec5-3383-4f69-8496-5d4f57c1d727","year":2023},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.195504Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:fee92f23a254f23aae9298f6bc5a229d163dbbd7fde41d8ebe6cd4d4bcb205f1","observation_id":"035ff7af-7698-4a92-8d3a-ea15f743c065","resolution":{"observed_at":"2026-08-15T20:00:58.669859Z","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":"2006.04131","last_updated":"2020-07-13T16:32:20Z","snapshot_observed_at":"2026-08-09T07:13:23.894027Z","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":"2026-08-15T20:00:58.200249Z","title":"Deep graph contrastive representation learning","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.200249Z"},"links":{"cited_paper":"/paper/2006.04131","citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:642fe40744e2994108b56bc04c09b02e1d3afce4dee64ca8836a852a121ed69b","observation_id":"6261c744-681a-4094-be99-7f6c5be34dc3","resolution":{"observed_at":"2026-08-15T20:00:58.200249Z","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":"2026-08-15T20:00:58.650677Z","title":"Graph contrastive learning with adaptive augmentation","venue":null,"work_id":"39f849a2-94ac-4f68-af00-b6211ee05a5c","year":2021},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.206236Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:1bbcda4d06c450c64893fc7b3f3ff255dbd2719971f119d72346b433b614d4d2","observation_id":"0c9098cd-d042-4f6c-9ce6-8491343164e7","resolution":{"observed_at":"2026-08-15T20:00:58.655229Z","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":"2026-08-15T20:00:58.635204Z","title":null,"venue":null,"work_id":"12fa33cb-0fb5-4d62-a9fc-ecce00c39680","year":null},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.210900Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:5e253a5e48e15c0622debc5499b3a3c907047f18eb1634392bfc42157e933c9b","observation_id":"9c244d28-eaab-4e94-88cb-22de1d1bdda9","resolution":{"observed_at":"2026-08-15T20:00:58.640587Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-15T20:00:58.619809Z","title":"PAPER TITLE AND ABSTRACT:","venue":null,"work_id":"d686f1d1-04f5-48b4-a2bb-931141329bd0","year":null},"citing_paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-15T20:00:58.216322Z"},"links":{"citing_paper":"/paper/2506.14098"},"observation_digest":"sha256:8525fc457b49a609e138f0969cac8105f729e777101c932d3fdb56b7648ee96b","observation_id":"2bd8fe55-a546-4c23-87ba-440410cc786a","resolution":{"observed_at":"2026-08-15T20:00:58.624903Z","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"}}],"paper":{"arxiv_id":"2506.14098","last_updated":"2025-06-17T01:28:34Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T06:56:57.933457Z","submitted_at":"2025-06-17T01:28:34Z","title":"Toward a Graph Foundation Model: Pre-Training Transformers With Random Walks"},"reference_resolution":{"displayed":92,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":52,"verified_exact":2,"verified_fuzzy":38},"total_outbound_references":92},"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 92 of 92 outbound references and 0 inbound Pith citation observations for arXiv:2506.14098."}