{"as_of":"2026-08-13T04:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:54d19000c37b93d0fb6f165498098dbd23a86e902e574001ba1d45e4dd1132bb","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":"2026-08-12T05:35:47.457679Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:21:34.983036Z","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":"2026-05-13T04:52:17.415548Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00315","snapshot_observed_at":"2026-08-07T05:21:34.983036Z","title":"One model for one graph: A new perspective for pretraining with cross-domain graphs.arXiv preprint arXiv:2412.00315, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.08298","last_updated":"2025-06-15T02:48:38Z","snapshot_observed_at":"2026-08-10T04:47:29.938584Z","submitted_at":"2025-06-10T00:03:56Z","title":"H$^2$GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:34.983036Z"},"links":{"cited_paper":"/paper/2412.00315","citing_paper":"/paper/2506.08298"},"observation_digest":"sha256:b56180e3e83b8eec6626525c235e0eb3d158cc81444c31df76cd6bf4fff6eaaa","observation_id":"604f74e1-b47e-4f2b-abad-2adec4281498","resolution":{"observed_at":"2026-08-07T05:21:34.983036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"cited_work":{"arxiv_id":"2412.00315","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.00315","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2412.00315 , year=","venue":null,"work_id":"46953efd-92f3-4cb1-9c9c-d620b4e1694c","year":null},"citing_paper":{"arxiv_id":"2605.12061","last_updated":"2026-05-12T12:47:43Z","snapshot_observed_at":"2026-08-12T17:33:27.874797Z","submitted_at":"2026-05-12T12:47:43Z","title":"SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-05-13T04:45:34.957298Z"},"links":{"cited_paper":"/paper/2412.00315","citing_paper":"/paper/2605.12061"},"observation_digest":"sha256:4dc507d91c738c1b07b9a8947cf10ee3dd0e2ab41a4ea14a3d19e1bb203cb466","observation_id":"727b8a1b-55ec-40cf-9fb9-3f238d695904","resolution":{"observed_at":"2026-05-13T04:52:17.417448Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00315","snapshot_observed_at":"2026-08-03T16:12:17.914741Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28980","last_updated":"2026-07-31T03:12:09Z","snapshot_observed_at":"2026-08-09T03:25:54.058940Z","submitted_at":"2026-07-31T03:12:09Z","title":"Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T16:12:17.914741Z"},"links":{"cited_paper":"/paper/2412.00315","citing_paper":"/paper/2607.28980"},"observation_digest":"sha256:ef55bc14fac45aea2f16d83f615e0094c69f181c39b4ceb04b546dd256fcac2c","observation_id":"0eb7747d-5b31-4d3e-b86a-01a336e28d3a","resolution":{"observed_at":"2026-08-03T16:12:17.914741Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.00315/citation-record","integrity":"/paper/2412.00315/integrity","json":"/paper/2412.00315/citation-record.json","paper":"/paper/2412.00315"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:35:47.290342Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.290342Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:24f86c58e76df8762566ae789a8d78e2fe5bad433e4e9c0e9a45f2909ecb86f8","observation_id":"1fb9cc1b-2f73-4dee-b5fd-bad67c6ac845","resolution":{"observed_at":"2026-08-12T05:35:47.290342Z","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":"2026-08-13T04:20:07.591872Z","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":"2026-08-12T05:35:47.299433Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.299433Z"},"links":{"cited_paper":"/paper/2402.08170","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:83b158ad9c0b6a01ab554d3c591d323fc5fffb5e6ea19236ff877c32bb4d2c44","observation_id":"3b6cbeb4-7880-499b-9bfc-912768e1e72c","resolution":{"observed_at":"2026-08-12T05:35:47.299433Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03393","last_updated":"2024-01-16T16:12:14Z","snapshot_observed_at":"2026-08-06T02:12:40.014268Z","submitted_at":"2023-07-07T05:31:31Z","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03393","snapshot_observed_at":"2026-08-12T05:35:47.304560Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.304560Z"},"links":{"cited_paper":"/paper/2307.03393","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:59fc65da103fbdb777e132bd93ae136c0bc8eb02189d807c29ddc3cdc998a522","observation_id":"59a3bd87-53b1-4eaa-b78c-a3cc50a8cda6","resolution":{"observed_at":"2026-08-12T05:35:47.304560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10727","last_updated":"2024-06-15T19:56:21Z","snapshot_observed_at":"2026-08-12T23:41:59.712001Z","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":"2026-08-12T05:35:47.308988Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.308988Z"},"links":{"cited_paper":"/paper/2406.10727","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:fa91202ccafd5f7814b02c0bcfd819a0a4e973f7a692cd5996001a0a993416dc","observation_id":"20e4e27a-fd57-4ed0-898e-fddd2fd457b5","resolution":{"observed_at":"2026-08-12T05:35:47.308988Z","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":"2026-08-12T05:35:47.313286Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.313286Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:659b6a1873b371a3a1a93ca2a6322f2822d8949cd95523a4140c55c55e6c488d","observation_id":"d8b7dc3b-3069-4518-8345-81d505ee0774","resolution":{"observed_at":"2026-08-12T05:35:47.313286Z","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":"2026-08-12T05:35:48.011199Z","title":null,"venue":null,"work_id":"2e03fcce-892f-4758-9ad4-a0b0ef988d94","year":2023},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.320681Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:1d1d2ef14ab7630aee3e76eb5026258d0b7b8b7f0dbf145f7bd768151877bf54","observation_id":"1ae93b35-46a9-4f46-8e9b-ad4aeb27e302","resolution":{"observed_at":"2026-08-12T05:35:48.015631Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13630","last_updated":"2025-01-20T15:12:02Z","snapshot_observed_at":"2026-08-13T04:13:53.767179Z","submitted_at":"2024-02-21T09:06:31Z","title":"UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13630","snapshot_observed_at":"2026-08-12T05:35:47.324548Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.324548Z"},"links":{"cited_paper":"/paper/2402.13630","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:388e2cf7c10246ed435fb072666d6d2d224b84d4d69a62a2d1e6792c86b82fe7","observation_id":"90b98b18-bc15-48ab-bb2a-2be338a0a27f","resolution":{"observed_at":"2026-08-12T05:35:47.324548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02953","last_updated":"2024-06-05T05:22:32Z","snapshot_observed_at":"2026-08-12T23:49:55.605142Z","submitted_at":"2024-06-05T05:22:32Z","title":"GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature Alignment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02953","snapshot_observed_at":"2026-08-12T05:35:47.328790Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.328790Z"},"links":{"cited_paper":"/paper/2406.02953","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:f3eae3ab79776fbf6188815eaf9c279c591e70bb434fc05dcd850ac97d83f82c","observation_id":"63a4f971-64ed-4bfb-b93e-57b7a8864604","resolution":{"observed_at":"2026-08-12T05:35:47.328790Z","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":"2026-08-12T05:35:47.332605Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.332605Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:78e87708936a6d70efea3357307f7255ad93a94817e6161af8ed67fcbec1b9c4","observation_id":"b4ddf6b5-ef52-41b3-a842-8666b93bd53e","resolution":{"observed_at":"2026-08-12T05:35:47.332605Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12600","last_updated":"2023-05-21T23:16:30Z","snapshot_observed_at":"2026-07-06T15:30:22.612066Z","submitted_at":"2023-05-21T23:16:30Z","title":"PRODIGY: Enabling In-context Learning Over Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12600","snapshot_observed_at":"2026-08-12T05:35:47.337002Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.337002Z"},"links":{"cited_paper":"/paper/2305.12600","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:cd95f5120fe410a022bf9fb56af92bdb52302817751730db5690a9c36665def4","observation_id":"ab84b1f5-c497-4d5e-ad02-be502ab74505","resolution":{"observed_at":"2026-08-12T05:35:47.337002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.05470","last_updated":"2022-03-22T00:48:15Z","snapshot_observed_at":"2026-08-09T00:11:58.863522Z","submitted_at":"2021-06-10T03:09:20Z","title":"Automated Self-Supervised Learning for Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.05470","snapshot_observed_at":"2026-08-12T05:35:47.341075Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.341075Z"},"links":{"cited_paper":"/paper/2106.05470","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:9bb4f81b3edeee02f69976acb262726518b3016787a6613961e29526b44e4e7a","observation_id":"0d4a0f72-c68f-4758-bff3-38208372b42c","resolution":{"observed_at":"2026-08-12T05:35:47.341075Z","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":"2026-08-12T05:35:47.989094Z","title":null,"venue":null,"work_id":"3ad326e9-c173-4898-800f-bda6a510ccbe","year":2023},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.344973Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:4bd250c6711555ecf1cb4df91ea2baad56f484f870e7c4e7695f98263e3177b4","observation_id":"a2abd960-4a97-434e-bab2-90ecad10bcbb","resolution":{"observed_at":"2026-08-12T05:35:47.993077Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-12T05:35:47.350721Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.350721Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:6b2e1659938b70006fca5e2e971e33163b3bb332a625d2d8975f9aa5d81c4d1d","observation_id":"bd6b61c4-65c9-464f-8fcd-501107f35321","resolution":{"observed_at":"2026-08-12T05:35:47.350721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15035","last_updated":"2024-10-19T08:39:21Z","snapshot_observed_at":"2026-08-12T22:19:35.001937Z","submitted_at":"2024-10-19T08:39:21Z","title":"Improving General Text Embedding Model: Tackling Task Conflict and Data Imbalance through Model Merging","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.15035","snapshot_observed_at":"2026-08-12T05:35:47.354576Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.354576Z"},"links":{"cited_paper":"/paper/2410.15035","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:432b805c4e7f430f4afb878afdd7ac864d225ac51b64a40b76a2b764132f53af","observation_id":"f261beca-b4a2-42c2-9cd4-a32df2604490","resolution":{"observed_at":"2026-08-12T05:35:47.354576Z","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":"2026-08-12T05:35:47.359354Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.359354Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:c5fc9df56fbe7ef91280113f3c6e02abcfdfaf198389cf49d905054f76bd9265","observation_id":"e2f0eb5a-3e56-467b-93e2-816931b89be7","resolution":{"observed_at":"2026-08-12T05:35:47.359354Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00149","last_updated":"2024-07-12T23:01:32Z","snapshot_observed_at":"2026-07-06T16:25:46.699214Z","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":"2026-08-12T05:35:47.363230Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.363230Z"},"links":{"cited_paper":"/paper/2310.00149","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:6a0b26835e46d65dfed5d47ee323315c75e670a91210e3efacdd2d535d457948","observation_id":"b81024a7-508f-4eab-85d9-51d88783b2fe","resolution":{"observed_at":"2026-08-12T05:35:47.363230Z","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":"2026-08-12T05:35:47.367281Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.367281Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:91eba12778776c61b7b5f9386b472baa92769b3747eaecffbad63feca6897fc5","observation_id":"ea244279-cc63-48b5-8aa8-b83eb1e1cd98","resolution":{"observed_at":"2026-08-12T05:35:47.367281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.06134","last_updated":"2023-07-21T05:02:21Z","snapshot_observed_at":"2026-08-09T23:14:35.131194Z","submitted_at":"2021-06-11T02:44:00Z","title":"Is Homophily a Necessity for Graph Neural Networks?","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.06134","snapshot_observed_at":"2026-08-12T05:35:47.371307Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.371307Z"},"links":{"cited_paper":"/paper/2106.06134","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:fd4ae904aedc9a01dc34812266ea1314ac519b4597c7f84eef10c669527263cd","observation_id":"f50421c2-8231-4c7b-bf1d-6879a5ed1abf","resolution":{"observed_at":"2026-08-12T05:35:47.371307Z","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":"2026-08-12T05:35:47.375480Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.375480Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:f02061bec8b572bb9afd28d67910decba7ac778292340f7be8bd41804b24a398","observation_id":"7be4d9e3-70f9-461d-a360-a1cec6208600","resolution":{"observed_at":"2026-08-12T05:35:47.375480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.01323","last_updated":"2023-10-15T03:50:52Z","snapshot_observed_at":"2026-07-06T15:37:00.698509Z","submitted_at":"2023-06-02T07:46:20Z","title":"Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.01323","snapshot_observed_at":"2026-08-12T05:35:47.379447Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.379447Z"},"links":{"cited_paper":"/paper/2306.01323","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:b5974b608dc6b09e0396b863903607c36341fcd66665d23437df7b7e5cab7ceb","observation_id":"8e896593-1829-4865-8876-406486287dcb","resolution":{"observed_at":"2026-08-12T05:35:47.379447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02216","last_updated":"2024-05-30T22:38:39Z","snapshot_observed_at":"2026-08-13T04:27:41.444087Z","submitted_at":"2024-02-03T17:24:36Z","title":"Position: Graph Foundation Models are Already Here","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.02216","snapshot_observed_at":"2026-08-12T05:35:47.383483Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.383483Z"},"links":{"cited_paper":"/paper/2402.02216","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:3f6cb40f5c2fcd22c3a2db530ec4ccd209cdc58fdb0272d9cbc2c39fe2509d12","observation_id":"85e59ba3-0dd1-4cec-8c6d-762fe5fad030","resolution":{"observed_at":"2026-08-12T05:35:47.383483Z","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":"2026-08-12T05:35:47.945745Z","title":null,"venue":null,"work_id":"2de98aee-5595-4f26-b15d-8de59420b930","year":2022},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.387360Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:2c61dd35cf812ec08451a45a719b3dab29af9e6197f704beb0aaca27a1937384","observation_id":"66e90fd7-4bd7-4caa-87dc-de438caccfdc","resolution":{"observed_at":"2026-08-12T05:35:47.950589Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:35:47.391148Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.391148Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:b3ea4949327abbb7cbc486239fcd578d69e4afb719ae24c4a9c46021a17b26d1","observation_id":"e1aa5c79-98f6-4173-8a78-76784885c209","resolution":{"observed_at":"2026-08-12T05:35:47.391148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10084","last_updated":"2019-08-27T08:50:17Z","snapshot_observed_at":"2026-07-06T08:17:05.681370Z","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10084","snapshot_observed_at":"2026-08-12T05:35:47.394423Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.394423Z"},"links":{"cited_paper":"/paper/1908.10084","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:4f36aa35040ece6d88f552ec1da5f2cdd49204c3a1df461596edbe916359d5d4","observation_id":"24da74d8-8066-4a92-9934-fad327df02de","resolution":{"observed_at":"2026-08-12T05:35:47.394423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1701.06538","last_updated":"2017-01-23T18:10:00Z","snapshot_observed_at":"2026-08-12T04:14:58.866318Z","submitted_at":"2017-01-23T18:10:00Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.06538","snapshot_observed_at":"2026-08-12T05:35:47.398464Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.398464Z"},"links":{"cited_paper":"/paper/1701.06538","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:4dd3d38acc94aee20fac2cf2335d77d9c1f61a7b4ff2ef3ff98a509bc567d0e0","observation_id":"bc8f9295-91e8-4612-b7e1-ba8f8914d035","resolution":{"observed_at":"2026-08-12T05:35:47.398464Z","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":"2026-08-12T05:35:47.402856Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.402856Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:186fa9712aed3331f0056876e0578fc480e9d15745bbf3349bbbbafc8193027b","observation_id":"32956843-8d74-44b1-a4ee-0c4ff4086ab2","resolution":{"observed_at":"2026-08-12T05:35:47.402856Z","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":"2026-08-12T05:35:47.922512Z","title":null,"venue":null,"work_id":"31e232c2-d2b7-42e2-b2b4-0a4d61d1ac85","year":2023},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.406474Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:52af1df3f95c82bd7969c32941f36cebb7738ced67cf8c39d48a72c4f3171c2a","observation_id":"3ffd76d1-e4d6-4d30-8674-3b38518eeef2","resolution":{"observed_at":"2026-08-12T05:35:47.926973Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13023","last_updated":"2024-05-07T10:10:14Z","snapshot_observed_at":"2026-08-03T12:59:24.218283Z","submitted_at":"2023-10-19T06:17:46Z","title":"GraphGPT: Graph Instruction Tuning for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.13023","snapshot_observed_at":"2026-08-12T05:35:47.410028Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.410028Z"},"links":{"cited_paper":"/paper/2310.13023","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:45f927aa19de3768780df3b2bcfb27332a6eb42f1fcc73852a45e97a47422e7b","observation_id":"b44b458d-2d96-4a8e-9a86-82d0c2b392bb","resolution":{"observed_at":"2026-08-12T05:35:47.410028Z","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":"2026-08-12T05:35:47.909631Z","title":null,"venue":null,"work_id":"f416367e-e562-42a2-8969-f16bfd14fa3e","year":2020},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.413598Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:9a48bd58c735c2e27182a65f95292809c777aff4d3944cb05a651e1172796eb7","observation_id":"207857e8-91f2-462a-8ca7-2988bc9bf268","resolution":{"observed_at":"2026-08-12T05:35:47.914013Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:35:47.417183Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.417183Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:54eeb8cb0188a16e023d6b44708800a790d513c11d52db3c0a6bb7b94312a47b","observation_id":"60a69018-900e-428a-9986-82a9360da3b2","resolution":{"observed_at":"2026-08-12T05:35:47.417183Z","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":"2026-08-12T05:35:47.420728Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.420728Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:f7986ae7bdc100d3f646ad7192321617f1e4f7a34b4b0f69592d5853e2a0a2aa","observation_id":"295c0103-e0cb-411d-a992-17cee786ffc8","resolution":{"observed_at":"2026-08-12T05:35:47.420728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10700","last_updated":"2024-08-20T09:57:13Z","snapshot_observed_at":"2026-08-12T23:00:50.930213Z","submitted_at":"2024-08-20T09:57:13Z","title":"AnyGraph: Graph Foundation Model in the Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.10700","snapshot_observed_at":"2026-08-12T05:35:47.424356Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.424356Z"},"links":{"cited_paper":"/paper/2408.10700","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:7021de3b9ba5a0a24c55b2098aa8f5e8e9ca2953811898976354f66c5cca1bff","observation_id":"721dd8bb-1be7-495b-a7b0-fa12acb93651","resolution":{"observed_at":"2026-08-12T05:35:47.424356Z","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":"2026-08-12T05:35:47.883893Z","title":null,"venue":null,"work_id":"4748d1d8-95fa-4231-8349-eb45b43238a1","year":2023},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.428001Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:c2551781a8533fffcaafc800e0f451bfca15029d5e42de7345c8e856bdf3f74f","observation_id":"82158f1b-b641-43f1-ad9c-6ecda3a3d611","resolution":{"observed_at":"2026-08-12T05:35:47.887925Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:35:47.431868Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.431868Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:cdd574a4db3d222212c431a323c9a99ee6094b2795e408efee9017eecfb870a7","observation_id":"dfce1194-e216-4b5e-b04d-6947f0353b67","resolution":{"observed_at":"2026-08-12T05:35:47.431868Z","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":"2026-08-12T05:35:47.857414Z","title":null,"venue":null,"work_id":"d422c07e-c7aa-4a02-8418-dfee7992131d","year":2021},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.435394Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:af4b9a9b523e12cc177e379295dd9c258648a1dec9b5c93f01a2f9127ef04c97","observation_id":"171e2c5a-2405-4ca8-8cf5-3ee73a208aee","resolution":{"observed_at":"2026-08-12T05:35:47.862236Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:35:47.439117Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.439117Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:f6cd057e652d46c8465fe90c6683ba8afecb4de67eb9b09583ee6d29ba5b353f","observation_id":"e8f26437-3632-4f34-b620-6814752df577","resolution":{"observed_at":"2026-08-12T05:35:47.439117Z","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":"2026-08-12T05:35:47.446581Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.446581Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:89e75dba7dc524d00671191b354efb019ad08ae985bcf9b94dd6d5ef48b98058","observation_id":"a157ae48-45a4-4aa3-aea8-ee5160a350da","resolution":{"observed_at":"2026-08-12T05:35:47.446581Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.20445","last_updated":"2025-04-08T00:15:02Z","snapshot_observed_at":"2026-08-12T23:53:46.684312Z","submitted_at":"2024-05-30T19:43:29Z","title":"Fully-inductive Node Classification on Arbitrary Graphs","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20445","snapshot_observed_at":"2026-08-12T05:35:47.449932Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.449932Z"},"links":{"cited_paper":"/paper/2405.20445","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:2f298492e61ae3dd474e3fc2f8b0bbe2b1dfac5e5dcec1dace5712bfa8353e3f","observation_id":"79c2d30f-6f57-4c73-b1fc-e7974468ebd9","resolution":{"observed_at":"2026-08-12T05:35:47.449932Z","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":"2026-08-12T05:35:47.828596Z","title":null,"venue":null,"work_id":"82d50baa-8f72-4478-b220-90f04fff82dd","year":2021},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.453724Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:4b2554f395f7b45c1e0c861d4f63ecf729fe4f7e8a95371401f5a14a40939125","observation_id":"eb2a22f1-71af-47d6-b76b-153d6ae658af","resolution":{"observed_at":"2026-08-12T05:35:47.832813Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:35:47.457679Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.457679Z"},"links":{"cited_paper":"/paper/2006.04131","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:c765f4292cbee128290ab4a6fb9daf2d3b642866f8ed84075756eb00f8724075","observation_id":"af79cf46-361a-441f-9bb5-125629e3e669","resolution":{"observed_at":"2026-08-12T05:35:47.457679Z","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":"2026-08-12T05:35:47.316999Z","title":"In The world wide web conference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.316999Z"},"links":{"citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:7b576a3ca19b0b296f33581868c1b8303dbaa48915cee8c41f6b4c810bae28a2","observation_id":"f771d3d9-b92f-45dc-b4cb-34a00c9226c1","resolution":{"observed_at":"2026-08-12T05:35:47.316999Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11139","last_updated":"2024-02-17T00:10:33Z","snapshot_observed_at":"2026-08-13T04:17:12.411717Z","submitted_at":"2024-02-17T00:10:33Z","title":"LiGNN: Graph Neural Networks at LinkedIn","version":1},"cited_work":{"arxiv_id":"2402.11139","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.11139","snapshot_observed_at":"2026-08-12T05:35:47.809209Z","title":"LiGNN: Graph Neural Networks at LinkedIn","venue":"cs.LG","work_id":"f676ba75-bedc-4def-bd67-d9fc195bbf8b","year":2024},"citing_paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:47.294895Z"},"links":{"cited_paper":"/paper/2402.11139","citing_paper":"/paper/2412.00315"},"observation_digest":"sha256:f7e4dcff4ee70dd2840ca95607fbb7a145a397606efa4b28491d82dc88e095cc","observation_id":"8d421d84-2f25-473a-b5ee-9bd1b631663e","resolution":{"observed_at":"2026-08-12T05:35:47.817542Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.00315","last_updated":"2025-05-29T03:35:49Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T01:09:46.581400Z","submitted_at":"2024-11-30T01:49:45Z","title":"One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":41,"verified_exact":1,"verified_fuzzy":0},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 3 inbound Pith citation observations for arXiv:2412.00315."}