{"as_of":"2026-08-15T07:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7be79238ddccf68d5925dd72bf02f0a73b56a2ed13a97c6d81b69bbfe953180d","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:42:26.752908Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-14T20:22:43.876230Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-14T20:22:54.429975Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"cited_work":{"arxiv_id":"2506.22510","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.22510","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards text-free graph foundation models: Rethinking multi-domain graph contrastive learning","venue":null,"work_id":"fcd1f0bd-fb92-4967-9c05-7a1644d566f6","year":2025},"citing_paper":{"arxiv_id":"2605.13540","last_updated":"2026-05-13T13:50:03Z","snapshot_observed_at":"2026-08-11T14:07:09.034244Z","submitted_at":"2026-05-13T13:50:03Z","title":"Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-05-14T20:22:43.876230Z"},"links":{"cited_paper":"/paper/2506.22510","citing_paper":"/paper/2605.13540"},"observation_digest":"sha256:a288639ca2774dfec95d5a5a65c5b89fb5db0535aa9f39a6a51cf0b08d35e961","observation_id":"73280774-c3da-4893-b98c-e83b90f7650b","resolution":{"observed_at":"2026-05-14T20:22:54.434176Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.22510/citation-record","integrity":"/paper/2506.22510/integrity","json":"/paper/2506.22510/citation-record.json","paper":"/paper/2506.22510"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-06T22:42:23.683905Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:23.683905Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:362a0f7483cbb8d3cc6df614123acd3fb995aee7ea1a98868d4eaf25fec40b12","observation_id":"24fcf2a0-a44a-493a-9a55-78a64e0e8458","resolution":{"observed_at":"2026-08-06T22:42:23.683905Z","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":"2026-08-06T22:42:30.546406Z","title":"All nlp tasks are generation tasks: A general pretraining framework","venue":null,"work_id":"16186791-81f1-49d2-99e4-f1b5a300014e","year":2021},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:23.719095Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:8c9e584fdd97d9b076599fde225ee83cba4417862322e6c3758a7c47e2344cee","observation_id":"0f398f0e-ee43-41e0-a859-85ee611fc300","resolution":{"observed_at":"2026-08-06T22:42:30.586925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-06T22:42:23.774235Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:23.774235Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:bcd272b3965cab112ee1be1d7db19a81f3bf7bc8cbc5262700f28674404da7fa","observation_id":"91e02ca8-3dd9-4f20-9e54-0cf4bcf8fdf6","resolution":{"observed_at":"2026-08-06T22:42:23.774235Z","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":"2026-08-06T22:42:30.379136Z","title":"Understanding and improving visual prompting: A label-mapping perspective","venue":null,"work_id":"2e42729f-a4a6-4f1b-8335-046663ea53d5","year":2022},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:23.816235Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:5ff421569fdbbe4b0f737666d7dd2d503a7d398895908a41ea95c9821576b9f7","observation_id":"e57bef61-566e-4640-98ee-10a189f79cad","resolution":{"observed_at":"2026-08-06T22:42:30.443741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:30.227486Z","title":null,"venue":null,"work_id":"76a24d77-49e1-495b-93f5-b797dcacb86e","year":2020},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:23.923452Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:2b2475032af6d006ee22d0abd04b889ed806c3c4826fc465152bc7e609c27a2f","observation_id":"c3d06c70-f310-426b-8e1c-a50aec924053","resolution":{"observed_at":"2026-08-06T22:42:30.288890Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:30.070076Z","title":"Imagenet-21k pretraining for the masses","venue":null,"work_id":"13901f8f-f690-429f-96b8-e7ce991c8843","year":2021},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:23.984246Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:b6e230b695b781602cfe8dfe9d938fd3b8f1cf3118f15ef6970f103aaa5be5f6","observation_id":"45f96d63-90c9-4e9d-81f6-4f2c7f0e2353","resolution":{"observed_at":"2026-08-06T22:42:30.145931Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:29.917200Z","title":"Selectivity drives productivity: Efficient dataset pruning for enhanced transfer learning","venue":null,"work_id":"89fce73f-b694-43a6-86b6-8b48ce9dcc01","year":2023},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.053783Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:4e747fde1c93ce1bdcc6ea2951d20fea0f30c13e53f32220c8a9afd456c118d4","observation_id":"711f207b-6474-4412-b3e1-af66ed22ef5b","resolution":{"observed_at":"2026-08-06T22:42:29.995307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:29.747191Z","title":"Hhan: Comprehensive infectious disease source tracing via heterogeneous hypergraph neural network","venue":null,"work_id":"2460226b-dc6e-4d22-96bd-fa4b338e8464","year":2025},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.102135Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:98ba0243f7297a4b177746a2297163ce2e8143b7056c482514c1d558db81bc9b","observation_id":"72a2fb21-a6fc-4daa-a9ca-19ee88cf2aad","resolution":{"observed_at":"2026-08-06T22:42:29.852398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:29.596336Z","title":"Social recommendation via graph-level counterfactual augmentation","venue":null,"work_id":"85121018-5089-401a-9f51-14f46e791040","year":2025},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.181708Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:e5dd137dc1232fff61f85168f6b58f516d4e42eca2fd540adb11768774a32018","observation_id":"ef84e7b2-d076-4a7f-b8d8-a874420e1b9d","resolution":{"observed_at":"2026-08-06T22:42:29.678726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:29.431915Z","title":"Hypergraph convolutional network for user-oriented fairness in recommender systems","venue":null,"work_id":"f5023768-6d95-4940-aae5-efd5b29f3bff","year":2024},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.275630Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:016ec11d1f82388ab51fc45fbfc0d0f5cb90711f9be89cda7666ae7de6e6fde3","observation_id":"cfd59b90-18b3-4fdd-a80d-67a159afde9d","resolution":{"observed_at":"2026-08-06T22:42:29.509265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:24.331754Z","title":"Graph contrastive learning with augmentations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.331754Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:df398a60c417f63713a2f0127c87750ba2843b7765e5bace175c00813a54b837","observation_id":"2ab6519f-feb5-45e2-9c51-b1b8c9e91e64","resolution":{"observed_at":"2026-08-06T22:42:24.331754Z","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":"2026-08-06T22:42:29.295014Z","title":"Graphprompt: Unifying pre-training and downstream tasks for graph neural networks","venue":null,"work_id":"ffd5203a-0828-4e28-9b89-2ce04efecf29","year":2023},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.420538Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:df50cee356893b7eee869d2a26aed816bdf6d5e066c6507f9c7665b587579ccc","observation_id":"378a2772-2449-4509-af03-ea80a841365e","resolution":{"observed_at":"2026-08-06T22:42:29.371868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:29.156999Z","title":"All in one: Multi-task prompt- ing for graph neural networks","venue":null,"work_id":"2a1a4b18-91c7-4057-b72f-241a8771d722","year":2023},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.464104Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:b00db5fadd851265714b0a115bd7e19ba3b1503c729c86a44f5af8ad76d87ebb","observation_id":"cc1a8c3e-8728-4866-9598-4b1e305f2687","resolution":{"observed_at":"2026-08-06T22:42:29.228969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:28.958704Z","title":"Universal prompt tun- ing for graph neural networks","venue":null,"work_id":"e2575a0a-e575-48f3-a107-ff96e1ab245d","year":2023},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.561847Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:dd8c515eef9b443e4eae98c554857530dcf103cf0c4376798b64cc648e8f0f6c","observation_id":"a3e7b678-324e-41e9-b613-c10230de34e7","resolution":{"observed_at":"2026-08-06T22:42:29.022757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:28.812375Z","title":"Gppt: Graph pre-training and prompt tuning to generalize graph neural networks","venue":null,"work_id":"3a413574-00c1-4091-a480-2c834ebacd74","year":2022},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.640659Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:30230f11590e9fe1f1d4263891e9739668f708c55709e7493691a4016d331ab5","observation_id":"3e12ee7b-8ede-4049-81cf-b9ecddbcfb04","resolution":{"observed_at":"2026-08-06T22:42:28.878315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:28.638469Z","title":"Simgrace: A simple framework for graph contrastive learning without data augmentation","venue":null,"work_id":"110519bc-7c7d-4c7c-b542-c374b0c3d4fd","year":2022},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.696973Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:63dc2027fe3871c6ea00b4e6e736af07b901bfb3f5ba00ca1438d7a13376351c","observation_id":"f10369c1-5e6f-448f-95f5-92067c1edd83","resolution":{"observed_at":"2026-08-06T22:42:28.714237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:28.479280Z","title":"Higpt: Heterogeneous graph language model","venue":null,"work_id":"4f178d75-a068-4448-920f-a3e96f8734dd","year":2024},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.807310Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:c9217a17b4f4f17d6b484b4bad6719f2b88d7816463349d80936bd8029064259","observation_id":"80fef6a3-4d15-402c-bd20-3215af5c2a03","resolution":{"observed_at":"2026-08-06T22:42:28.531074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00149","last_updated":"2024-07-12T23:01:32Z","snapshot_observed_at":"2026-08-14T03:13:16.635373Z","submitted_at":"2023-09-29T21:15:26Z","title":"One for All: Towards Training One Graph Model for All Classification Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00149","snapshot_observed_at":"2026-08-06T22:42:24.882715Z","title":"One for all: Towards training one graph model for all classification tasks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.882715Z"},"links":{"cited_paper":"/paper/2310.00149","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:05935a74a72c129e0089d9943936a263f6c66d6b246d5ad133f7381e5508a929","observation_id":"c6dbf751-68f6-4729-a142-ba296dee624d","resolution":{"observed_at":"2026-08-06T22:42:24.882715Z","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":"2026-08-13T04:05:05.150667Z","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":"2026-08-06T22:42:24.954045Z","title":"Opengraph: Towards open graph foundation models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:24.954045Z"},"links":{"cited_paper":"/paper/2403.01121","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:3bded8c6f74fe4a5f62611a67f88b8a00ff13101ea6f15b8828b1a25b5372d1b","observation_id":"9bf7dbc1-8404-4194-8a5f-59bd50571c65","resolution":{"observed_at":"2026-08-06T22:42:24.954045Z","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":"2026-08-06T22:42:28.262658Z","title":"Augmenting low-resource text classification with graph-grounded pre-training and prompting","venue":null,"work_id":"64c25d1f-061c-408c-8a75-144f47040226","year":2023},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.071382Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:14b5fb1ebc71164b47e93c240047019a27a33438d3e4610196e033bae7d7e07e","observation_id":"c2a7208c-2874-4cda-8d54-39cb0ed26680","resolution":{"observed_at":"2026-08-06T22:42:28.369407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.14709","last_updated":"2023-03-01T14:09:04Z","snapshot_observed_at":"2026-08-14T19:55:52.899070Z","submitted_at":"2022-10-26T13:40:57Z","title":"Learning on Large-scale Text-attributed Graphs via Variational Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.14709","snapshot_observed_at":"2026-08-06T22:42:25.137386Z","title":"Learning on large-scale text-attributed graphs via variational inference","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.137386Z"},"links":{"cited_paper":"/paper/2210.14709","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:b2749c4ba7d5867875b3873fff30595dcd0da6ea6ffd4350e7d66cc4595aae33","observation_id":"e63ce4b7-51a1-4071-97d4-23a88aeba899","resolution":{"observed_at":"2026-08-06T22:42:25.137386Z","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":"2026-08-06T22:42:28.139890Z","title":"All in one and one for all: A simple yet effective method towards cross-domain graph pretraining","venue":null,"work_id":"e8fd5ce0-97ac-4779-a800-26f944d61d18","year":2024},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.175948Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:ba8735e7a3657429883e4396481ae83bc8624b0d55cd89d5d770e572dd53da05","observation_id":"f06af779-3ee3-4450-8625-18439df8f00a","resolution":{"observed_at":"2026-08-06T22:42:28.207306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.05424","last_updated":"2025-04-12T06:20:31Z","snapshot_observed_at":"2026-08-15T05:13:46.026693Z","submitted_at":"2025-02-08T03:24:25Z","title":"SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation","version":2},"cited_work":{"arxiv_id":"2502.05424","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.05424","snapshot_observed_at":"2026-08-06T22:42:26.891222Z","title":"SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation","venue":"cs.CL","work_id":"40fe64be-524b-4211-8170-4e7ace25c73d","year":2025},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.235651Z"},"links":{"cited_paper":"/paper/2502.05424","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:07c4369f5b48bc30f590816800abe37601dcfddf1081a51ef5b44221744bcdc9","observation_id":"b4241a0e-b127-4294-a90e-d443b5a16639","resolution":{"observed_at":"2026-08-06T22:42:26.923842Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:27.998393Z","title":"Collective classification in network data","venue":null,"work_id":"3305ca65-80bd-472b-abb5-388444fed63c","year":2017},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.303076Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:198980c5a9a1a80ea13f96aa78c2e306ccb1c1c6bf539cba6887029c448e115d","observation_id":"26f5b4ff-b15b-467b-80fa-dba8ecde62c9","resolution":{"observed_at":"2026-08-06T22:42:28.052694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:25.397224Z","title":"Multi-scale attributed node embedding","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.397224Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:c5d02f7fe5df7d6fa980f492901f1963d88030052e450227d231fde430191dd5","observation_id":"cbdb2961-b3e9-4b55-a9fb-1a8dcab896d9","resolution":{"observed_at":"2026-08-06T22:42:25.397224Z","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":"2026-08-06T22:42:27.845752Z","title":"Revisiting semi-supervised learning with graph embeddings","venue":null,"work_id":"a236e06d-9d7d-4a64-ba6e-d61f3d594d4a","year":2016},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.481658Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:710f83afec3e9966875fa3d81759d1851ffa25ef6377e3401d35f4a9ec23b719","observation_id":"051eb3d6-1aa0-491e-8c38-a8d8ab00ef84","resolution":{"observed_at":"2026-08-06T22:42:27.899523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:27.725483Z","title":"Pitfalls of graph neural network evaluation","venue":null,"work_id":"0c237df4-4e29-4342-80f2-6c35ababd601","year":2018},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.565607Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:4e7de07a7f21ebed8222be2a563c9983dbbfc8d3d2c8c1be9d51f2df64d73d44","observation_id":"0dd01d43-888a-4103-b811-0aab5fa46c5a","resolution":{"observed_at":"2026-08-06T22:42:27.791910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:25.653958Z","title":"Image-based recommendations on styles and substitutes","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.653958Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:d09c30259fa58ddcbbec29d54c07ec7881e32a7933716778e0a63513f57f9100","observation_id":"59a8ab37-1a85-4457-bd3c-7a2ff29f6126","resolution":{"observed_at":"2026-08-06T22:42:25.653958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-13T11:38:10.906031Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-06T22:42:25.733330Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.733330Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:0c69d895cde522873a7f0cba2d1f532cb6f626e16c0eb099a44bd4c8db1397ba","observation_id":"220f9627-f3ee-471e-8b86-9d74199b9518","resolution":{"observed_at":"2026-08-06T22:42:25.733330Z","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":"2026-08-06T22:42:25.822440Z","title":"Inductive representation learning on large graphs","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.822440Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:42baae032b4a7eba710db038091fa8fe23f8d60ef11d369f193ffabfc3d883b5","observation_id":"4016d633-3ff5-43fd-8112-a64180b7e976","resolution":{"observed_at":"2026-08-06T22:42:25.822440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-08-13T22:35:40.714745Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-06T22:42:25.921959Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:25.921959Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:a65edff0e1c0a0aacc2abcec5acaad595dd82588442eeccb414703f7421a2b54","observation_id":"ad35ce9d-ebb0-4542-b058-477edf76a1fd","resolution":{"observed_at":"2026-08-06T22:42:25.921959Z","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":"2026-08-06T22:42:26.025436Z","title":"Graph transformer networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.025436Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:128141eb3fb396256dfaa0a4aed6da157513cb0a72e8b0ca588f42519509706b","observation_id":"a4bfb57e-4fe4-400f-bd76-c0e429df44d1","resolution":{"observed_at":"2026-08-06T22:42:26.025436Z","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":"2026-08-06T22:42:27.577649Z","title":null,"venue":null,"work_id":"8f9103f8-66a9-4129-9b96-d6dbd02ea263","year":1993},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.099436Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:cd5865e2b19d8f07ee64aa1812d8f536591cb5cc58055c6240d5600cde709188","observation_id":"c82e36a6-bada-4ee0-a4c0-b70eb60ca822","resolution":{"observed_at":"2026-08-06T22:42:27.630529Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:26.197057Z","title":"The pagerank citation ranking: Bringing order to the web","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.197057Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:f714785e30658a2a163fa131ba2dadd0ed2b4a0f29f345fd579a786823b8fcf9","observation_id":"c4e9e54a-5a6d-4662-b91c-6ecc4fa2689b","resolution":{"observed_at":"2026-08-06T22:42:26.197057Z","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":"2026-08-06T22:42:27.425548Z","title":"Beyond low-frequency information in graph convolutional networks","venue":null,"work_id":"94216afc-de01-473b-a57f-8cc6b7dade8f","year":2021},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.292647Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:93e3c66de67b9ff2d17baf3ccdc7434b3491132dbffc361d87b1f9eb96bf42a3","observation_id":"74ac6a00-2f85-478b-9d42-60435086a07e","resolution":{"observed_at":"2026-08-06T22:42:27.484845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:42:27.293693Z","title":"Is homophily a necessity for graph neural networks? Learning,Learning, Jun 2021","venue":null,"work_id":"9e29b74c-623e-401c-8863-8b123a5afe9b","year":2021},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.335656Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:97ba0cff205a653b7e408a8735c2bc56bfcab8d3ca2cebb65302d79c856ef537","observation_id":"c7e6d768-8d06-44c5-90e3-c3b23dc8d237","resolution":{"observed_at":"2026-08-06T22:42:27.342855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.09618","last_updated":"2024-07-12T18:04:32Z","snapshot_observed_at":"2026-08-14T03:13:17.930494Z","submitted_at":"2024-07-12T18:04:32Z","title":"The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.09618","snapshot_observed_at":"2026-08-06T22:42:26.392950Z","title":"The heterophilic graph learning hand- book: Benchmarks, models, theoretical analysis, applications and challenges","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.392950Z"},"links":{"cited_paper":"/paper/2407.09618","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:89cbd456dc91d596b3647f1b6bb8f372e38a992030e15737cb9a1044ff0f08f8","observation_id":"5efb7658-ea89-4518-833d-7317fb9d4fe5","resolution":{"observed_at":"2026-08-06T22:42:26.392950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11640","last_updated":"2024-03-02T21:17:13Z","snapshot_observed_at":"2026-08-13T12:39:14.570583Z","submitted_at":"2023-02-22T20:32:59Z","title":"A critical look at the evaluation of GNNs under heterophily: Are we really making progress?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11640","snapshot_observed_at":"2026-08-06T22:42:26.483989Z","title":"A critical look at the evaluation of gnns under heterophily: Are we really making progress? arXiv preprint arXiv:2302.11640, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.483989Z"},"links":{"cited_paper":"/paper/2302.11640","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:fc83a9e4654887433f179dbfcdf6fbf26921aef5f4d8e4d9f3ae59cac5632f67","observation_id":"7fdea63b-89cf-46bd-8b39-37a9a1342f01","resolution":{"observed_at":"2026-08-06T22:42:26.483989Z","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":"2026-08-06T22:42:27.162525Z","title":"Harnessing language model for cross-heterogeneity graph knowledge transfer","venue":null,"work_id":"ec06d688-9316-41ee-aec1-a5035e49f887","year":2025},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.538888Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:fc49d998b4d2b4befbc7fe5c38fd0ae1ee953f2734afc5967aff058fbb5db75c","observation_id":"2bf454c1-02fc-4048-8277-00b1497b7f41","resolution":{"observed_at":"2026-08-06T22:42:27.229081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10727","last_updated":"2024-06-15T19:56:21Z","snapshot_observed_at":"2026-08-14T03:13:51.953013Z","submitted_at":"2024-06-15T19:56:21Z","title":"Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10727","snapshot_observed_at":"2026-08-06T22:42:26.613689Z","title":"Text-space graph foundation models: Comprehensive benchmarks and new insights","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.613689Z"},"links":{"cited_paper":"/paper/2406.10727","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:4b9b027b6523f7c9c6969075221b754104b7ce581c293a6bf85870d085d1e4f2","observation_id":"fdb416b1-b01c-4ab0-aaa0-f57f29b9d948","resolution":{"observed_at":"2026-08-06T22:42:26.613689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04562","last_updated":"2024-04-09T19:48:22Z","snapshot_observed_at":"2026-08-13T05:55:10.294831Z","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":"2026-08-06T22:42:26.663456Z","title":"Towards foundation models for knowledge graph reasoning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.663456Z"},"links":{"cited_paper":"/paper/2310.04562","citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:f91d2c4cb0bf2fa2b557b261f275b350105a5f146e8bbf6ef6f2d13b5d2c6751","observation_id":"38d9e24a-e173-404f-a662-ee699e847024","resolution":{"observed_at":"2026-08-06T22:42:26.663456Z","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":"2026-08-06T22:42:27.058036Z","title":"Gft: Graph foundation model with transferable tree vocabulary.Advances in Neural Information Processing Systems, 37:107403–107443, 2024","venue":null,"work_id":"e5864f52-b0f0-46fb-a29d-ec18c5934955","year":2024},"citing_paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T22:42:26.752908Z"},"links":{"citing_paper":"/paper/2506.22510"},"observation_digest":"sha256:e4f02b609a3b21099920b2dc164f5d8d643a568290bebdd97f37d6502786a8a4","observation_id":"9a2fd000-c8d1-447d-896b-68180e581621","resolution":{"observed_at":"2026-08-06T22:42:27.112524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.22510","last_updated":"2025-06-26T03:14:50Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T17:57:49.832586Z","submitted_at":"2025-06-26T03:14:50Z","title":"Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":22},"total_outbound_references":42},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2506.22510."}