{"as_of":"2026-08-07T20:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f4db298fe21c18717365c827563164ea124a956a8bc3128c97ff75b974c6fefc","coverage":[{"denominator":70,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":70,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T23:38:57.951047Z","state":"measured"},{"denominator":72,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":72,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T19:16:15.616715Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-01T14:55:47.455600Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"cited_work":{"arxiv_id":"2602.13075","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.13075","snapshot_observed_at":"2026-07-01T14:55:47.455600Z","title":"Unified multi-domain graph pre- training for homogeneous and heterogeneous graphs via domain-specific expert encoding.arXiv preprint arXiv:2602.13075","venue":"cs.LG","work_id":"49de3412-01c3-4018-97db-18829ac61602","year":2026},"citing_paper":{"arxiv_id":"2605.15888","last_updated":"2026-06-05T02:17:47Z","snapshot_observed_at":"2026-08-02T15:57:41.366470Z","submitted_at":"2026-05-15T12:19:18Z","title":"CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-20T20:16:26.671005Z"},"links":{"cited_paper":"/paper/2602.13075","citing_paper":"/paper/2605.15888"},"observation_digest":"sha256:675c6e183ab56b33a408e8ab97413ab9b4346fafa7d50517c375ea0148437575","observation_id":"2a1251d6-db5c-4251-8500-ac091ca143e4","resolution":{"observed_at":"2026-05-28T02:04:14.605745Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"cited_work":{"arxiv_id":"2602.13075","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.13075","snapshot_observed_at":"2026-07-01T14:55:47.455600Z","title":"Unified multi-domain graph pre- training for homogeneous and heterogeneous graphs via domain-specific expert encoding.arXiv preprint arXiv:2602.13075","venue":"cs.LG","work_id":"49de3412-01c3-4018-97db-18829ac61602","year":2026},"citing_paper":{"arxiv_id":"2605.15888","last_updated":"2026-06-05T02:17:47Z","snapshot_observed_at":"2026-08-02T15:57:41.366470Z","submitted_at":"2026-05-15T12:19:18Z","title":"CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-30T19:16:15.616715Z"},"links":{"cited_paper":"/paper/2602.13075","citing_paper":"/paper/2605.15888"},"observation_digest":"sha256:1f2e91c08327b0ca0307c110defa0c56ce3e78f72edae1a114c37982af820a20","observation_id":"ab2857c8-3917-422b-a248-13e024a8ec02","resolution":{"observed_at":"2026-07-01T14:55:47.457287Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2602.13075/citation-record","integrity":"/paper/2602.13075/integrity","json":"/paper/2602.13075/citation-record.json","paper":"/paper/2602.13075"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T23:38:50.338826Z","title":null,"venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:50.338826Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:f4bce00d97e0b01b80b14e9e5d8c8cbffefbc2e9a33bd43083730636afbb7d4f","observation_id":"1f89af6b-60b8-4d46-ba87-114af723b4b8","resolution":{"observed_at":"2026-08-02T23:38:50.338826Z","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":"2026-08-02T23:38:50.540379Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:50.540379Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:7c50725339b7827a3f572d3f56e732279b411a28ed34aa79fc2dea2bb5878e05","observation_id":"4a2e3792-6a8f-4248-8893-856163a48864","resolution":{"observed_at":"2026-08-02T23:38:50.540379Z","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":"2026-08-02T23:38:50.667454Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:50.667454Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:a97bebe822643a52faf32c4b4e217876ffb681c98da58931df0b4bb1e1d15624","observation_id":"d69660b3-312f-40c0-bc63-e076545a2c73","resolution":{"observed_at":"2026-08-02T23:38:50.667454Z","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":"2026-08-02T23:38:50.767957Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:50.767957Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:1700f9936e5fa51f1f11fdf8d75dfabab356d5eaf58f18dcb4303b707fd8803e","observation_id":"36a5dcef-33c1-4681-a260-0322a411edbb","resolution":{"observed_at":"2026-08-02T23:38:50.767957Z","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":"2026-08-02T23:38:50.857312Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:50.857312Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:591f49f870966774c6fc10899b835b6c222b2d4e1afc4b0c0e4a998895616bf2","observation_id":"77887f13-b79a-46a9-a79b-8d4a7eefc20c","resolution":{"observed_at":"2026-08-02T23:38:50.857312Z","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":"2026-08-02T23:38:50.944875Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:50.944875Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:00fbf1e82f506448d4b5f3b49735e437dc67d4ab1e9d6c503be6086076a8f2a5","observation_id":"445855e1-3552-4d36-97aa-234b44c08e48","resolution":{"observed_at":"2026-08-02T23:38:50.944875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.16991","last_updated":"2025-07-27T18:32:07Z","snapshot_observed_at":"2026-08-06T22:50:41.791177Z","submitted_at":"2025-07-22T19:55:09Z","title":"PyG 2.0: Scalable Learning on Real World Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.16991","snapshot_observed_at":"2026-08-02T23:38:51.041188Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:51.041188Z"},"links":{"cited_paper":"/paper/2507.16991","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:897a8c04ba82b735644e50a2b70493333695a7ca867d0676d8a95289afcc06f8","observation_id":"25899afb-4dd5-42cf-a485-24a1453a701f","resolution":{"observed_at":"2026-08-02T23:38:51.041188Z","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":"2026-08-02T23:38:51.136768Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:51.136768Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:8e95d700bb3b6dc93ebd76398788d4c9836f66214d7051178c717470064edade","observation_id":"4616f140-b2de-442b-9b01-068851a8d6a9","resolution":{"observed_at":"2026-08-02T23:38:51.136768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.04043","last_updated":"2018-02-20T16:52:36Z","snapshot_observed_at":"2026-07-06T06:08:54.198229Z","submitted_at":"2017-11-10T23:32:47Z","title":"Few-Shot Learning with Graph Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.04043","snapshot_observed_at":"2026-08-02T23:38:51.301056Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:51.301056Z"},"links":{"cited_paper":"/paper/1711.04043","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:81540c8c08662855cfd38264ec0cbaffa449837e0d7759d2b75d44a8eabf36ab","observation_id":"bcf73e95-916c-4618-b4d9-1733045738d4","resolution":{"observed_at":"2026-08-02T23:38:51.301056Z","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":"2026-08-02T23:38:51.517561Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:51.517561Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:0dcc17403e8f06eeea2703e1890d02b74848eaea680e5af4d5a7b03e0e7e1661","observation_id":"41864818-8917-41a5-81b0-177f21567c61","resolution":{"observed_at":"2026-08-02T23:38:51.517561Z","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":"2026-08-02T23:38:51.660056Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:51.660056Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:fe98a6f4d091513dd812053be38eea2f147318df41493ee1ed0bcd8b2e7c868c","observation_id":"f5330bf3-b9ba-4cad-8310-572a9f855554","resolution":{"observed_at":"2026-08-02T23:38:51.660056Z","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":"2026-08-02T23:38:51.722383Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:51.722383Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:85ea299a7718aab6f548e0aba3347a074389228d85766a9f9d01d4a72cdb35f0","observation_id":"fd354527-8d7e-4de9-a15b-b08e2a9e6204","resolution":{"observed_at":"2026-08-02T23:38:51.722383Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.12265","last_updated":"2020-02-18T19:49:48Z","snapshot_observed_at":"2026-08-04T16:33:25.229105Z","submitted_at":"2019-05-29T08:11:52Z","title":"Strategies for Pre-training Graph Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.12265","snapshot_observed_at":"2026-08-02T23:38:51.842857Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:51.842857Z"},"links":{"cited_paper":"/paper/1905.12265","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:d7c894bfb88ec847c19267a5c7d1c464fc7f0cfc3dab5c56fb84fba9a66f2dae","observation_id":"9963018d-b226-4a51-9645-2ad46f9b846d","resolution":{"observed_at":"2026-08-02T23:38:51.842857Z","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":"2026-08-02T23:38:51.981658Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:51.981658Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:c986985572d74db521b2a37b3e78e726880910b662656c1e50b261cdcfc3d0cd","observation_id":"f30f0a2d-427e-468d-9fb2-701fbd6e44da","resolution":{"observed_at":"2026-08-02T23:38:51.981658Z","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":"2026-08-02T23:38:52.084745Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.084745Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:cf59273a863c195b4059fdf2a90bc206d99595ec7a81bf9a0f7544859e335a64","observation_id":"d518793d-ad45-490d-b760-5c66d721834f","resolution":{"observed_at":"2026-08-02T23:38:52.084745Z","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":"2026-08-02T23:38:52.166827Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.166827Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:153091edcc07b8fc88aebf945e6d3e95813578e4d4eddd400116d7225f690a2c","observation_id":"96b9aabd-bed6-4952-bf0e-db7761d618cf","resolution":{"observed_at":"2026-08-02T23:38:52.166827Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07308","last_updated":"2016-11-21T11:37:17Z","snapshot_observed_at":"2026-08-06T06:17:37.090691Z","submitted_at":"2016-11-21T11:37:17Z","title":"Variational Graph Auto-Encoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.07308","snapshot_observed_at":"2026-08-02T23:38:52.234744Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.234744Z"},"links":{"cited_paper":"/paper/1611.07308","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:a1c0d204b5e27175e6c9cb0af4aee0b763785de4f2c57e8e96653d946f6a6ecc","observation_id":"fe7e1419-7f92-41b4-b64c-c0c0084939b7","resolution":{"observed_at":"2026-08-02T23:38:52.234744Z","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":"2026-08-02T23:38:52.313300Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.313300Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:7c40a5fb257bb54bcffa918c007f7d1b88f5c2110af501b9b0761cb985411162","observation_id":"97cb709a-9924-4c3b-ad46-fee2678f94b5","resolution":{"observed_at":"2026-08-02T23:38:52.313300Z","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":"2026-08-02T23:38:52.414750Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.414750Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:a12bd8accb0901e1037a28f8c7a022b7e50941a101330fb0cbe8553bf951b829","observation_id":"786dfe6d-2f37-4fe8-917f-e8dc2aaa5171","resolution":{"observed_at":"2026-08-02T23:38:52.414750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11829","last_updated":"2025-03-10T16:14:30Z","snapshot_observed_at":"2026-07-06T16:34:54.717394Z","submitted_at":"2023-10-18T09:31:21Z","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11829","snapshot_observed_at":"2026-08-02T23:38:52.474515Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.474515Z"},"links":{"cited_paper":"/paper/2310.11829","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:fc60414c7b7a0c2e259209c1aadb756bcf242d4c1cd86f74563e64e9be20fe4f","observation_id":"3e185516-6d21-44a5-b667-a658ea7e00bc","resolution":{"observed_at":"2026-08-02T23:38:52.474515Z","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":"2026-08-02T23:38:52.519930Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.519930Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:7b6303dfdf7fcb6a4e8e4ad4e46481ac02e96dbb166ae90ecc4452a036bd0677","observation_id":"2f024560-5561-444a-a78a-1c76e3a6236c","resolution":{"observed_at":"2026-08-02T23:38:52.519930Z","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":"2026-08-02T23:38:52.652358Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.652358Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:8e74cff5ed1df87686256c2bea76fc8487522c03ca2533c021390a0502b3c394","observation_id":"1c320703-07ef-48f0-9def-cffcf4ad52dc","resolution":{"observed_at":"2026-08-02T23:38:52.652358Z","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":"2026-08-02T23:38:52.710996Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.710996Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:e93a4ff5bae868398539f17235b96fef9c98dd53ffd4bf52eaf519efcec0e551","observation_id":"9a0b5c58-df1e-4d91-b205-1e7a2f2f8940","resolution":{"observed_at":"2026-08-02T23:38:52.710996Z","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":"2026-08-02T23:38:52.954820Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.954820Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:0173979bcf8522cbaae69f242a0a4e80358337f37f2d18db68ce8c49d9e4bb67","observation_id":"cdf0ebb2-d70c-4d8b-9009-b9e85f5908db","resolution":{"observed_at":"2026-08-02T23:38:52.954820Z","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":"2026-08-02T23:38:53.055148Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:53.055148Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:f9108e37d6b932b4989aae18d0467d4784b5803a654aa967fd256f214d5a2745","observation_id":"e68de5a7-a700-4198-8a5d-affa0b9ef428","resolution":{"observed_at":"2026-08-02T23:38:53.055148Z","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":"2026-08-02T23:38:53.220164Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:53.220164Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:b43ef921f5561bab280085a9f7ba4da9459304bf78618d8bcf444a0b5f0001da","observation_id":"bf0e5598-4216-491c-91d4-74d8c23206db","resolution":{"observed_at":"2026-08-02T23:38:53.220164Z","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":"2026-08-02T23:38:53.325892Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:53.325892Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:2220762d049bc0a74141be36ded837662a62cf2708822cf83c20fc716916c64b","observation_id":"4296aaa7-3123-4d7a-a461-7a38fbae14d1","resolution":{"observed_at":"2026-08-02T23:38:53.325892Z","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":"2026-08-02T23:38:53.500838Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:53.500838Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:ae4debd2472ca2b621113fbc6ae3b69c3c0b247869f62c031662e65d9c0cee83","observation_id":"696b7840-8299-4cb0-a6cc-4931cd6c8d6d","resolution":{"observed_at":"2026-08-02T23:38:53.500838Z","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":"2026-08-02T23:38:53.745485Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:53.745485Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:21dc2ceda25d04d850bafdf55a94d9be276a9e460dee56501b7f3852578ab7a2","observation_id":"1d605573-0940-4305-883b-93a75cd2b52a","resolution":{"observed_at":"2026-08-02T23:38:53.745485Z","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":"2026-08-02T23:38:53.831110Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:53.831110Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:99a5f4a07667f90efcc328af55dc9a332b506c0a0bbe3d212d3e3a658c181fff","observation_id":"a6ee715b-754d-46ed-81dc-30f943054187","resolution":{"observed_at":"2026-08-02T23:38:53.831110Z","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":"2026-08-02T23:38:53.870904Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:53.870904Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:920640d0a14481cdd1b878f83e5bf79a8a6213548a1a186d424aa9ac97d5f9d6","observation_id":"03369de7-412e-43ba-bd09-b970be02b59c","resolution":{"observed_at":"2026-08-02T23:38:53.870904Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.05868","last_updated":"2019-06-18T13:15:39Z","snapshot_observed_at":"2026-07-06T07:14:41.761512Z","submitted_at":"2018-11-14T15:53:19Z","title":"Pitfalls of Graph Neural Network Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.05868","snapshot_observed_at":"2026-08-02T23:38:53.963766Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:53.963766Z"},"links":{"cited_paper":"/paper/1811.05868","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:b9e4685b36eb70c405ff93a7797b0f604fa671f9cc245a009b5d373b9bde2c20","observation_id":"7ce0c67c-35ba-40f3-8828-1712af8f5945","resolution":{"observed_at":"2026-08-02T23:38:53.963766Z","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":"2026-08-02T23:38:54.037327Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:54.037327Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:0f4830697177a03ccb6393d955328bb03b1c3d3d8bdfbe7268300b7a99cd86be","observation_id":"7ef0bc22-bb98-4874-8ba8-afb78cb99e02","resolution":{"observed_at":"2026-08-02T23:38:54.037327Z","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":"2026-08-02T23:38:54.217935Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:54.217935Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:57a256adff4077b836acfb172fad8335ddae0236254ede7d80268b00dc7225c5","observation_id":"c049909e-131e-4e47-9344-828b89350434","resolution":{"observed_at":"2026-08-02T23:38:54.217935Z","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":"2026-08-02T23:38:54.332626Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:54.332626Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:d82a3a27650939254af1881baf0ccda6d2652fa9f11fd54be9ac246a0b6c0036","observation_id":"8755b315-dc77-4994-ad31-3f2bf90a1005","resolution":{"observed_at":"2026-08-02T23:38:54.332626Z","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":"2026-08-02T23:38:54.452627Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:54.452627Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:eb138ac184f74057703b8e876dd233d75d0f372136af2b75a8bd36be619b25ee","observation_id":"0e856911-34ee-437e-af76-801e715460b8","resolution":{"observed_at":"2026-08-02T23:38:54.452627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16534","last_updated":"2023-11-28T05:36:59Z","snapshot_observed_at":"2026-07-06T16:53:35.776613Z","submitted_at":"2023-11-28T05:36:59Z","title":"Graph Prompt Learning: A Comprehensive Survey and Beyond","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.16534","snapshot_observed_at":"2026-08-02T23:38:54.632538Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:54.632538Z"},"links":{"cited_paper":"/paper/2311.16534","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:fd6adf383dcfda6fa9e29d013fa679e4eb7e6edfb884858f46ccf813d3fcabc8","observation_id":"df204f12-8368-4d0b-9e1f-920204e7a56c","resolution":{"observed_at":"2026-08-02T23:38:54.632538Z","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":"2026-08-02T23:38:54.756714Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:54.756714Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:eccc161b3e4feb83c78d24fb5bba717691da3625b83c72ca64243e51a6e9062f","observation_id":"084d48a1-b825-4831-9304-d645c5cb4f3e","resolution":{"observed_at":"2026-08-02T23:38:54.756714Z","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":"2026-08-02T23:38:54.827391Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:54.827391Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:542ab46d630bb4f6f5597286b97fb6d9cfbdbcaa9fd7625fc49ab89687efc571","observation_id":"f15bb82e-e594-4412-be49-cfe24571b60a","resolution":{"observed_at":"2026-08-02T23:38:54.827391Z","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":"2026-08-02T23:38:54.961916Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:54.961916Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:ae935de7a76ca07c5b8270c0a65e3f2bc71b7212f7a908fb715a4c86cd48ba24","observation_id":"34a464a6-00a0-444d-9bb7-6962a46beee1","resolution":{"observed_at":"2026-08-02T23:38:54.961916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.10341","last_updated":"2018-12-21T15:44:59Z","snapshot_observed_at":"2026-07-06T07:04:37.077852Z","submitted_at":"2018-09-27T04:53:24Z","title":"Deep Graph Infomax","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.10341","snapshot_observed_at":"2026-08-02T23:38:55.052451Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:55.052451Z"},"links":{"cited_paper":"/paper/1809.10341","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:635e4aab94ac90cf9e1b1fd59c8e96fa45855c2286df7be3647fb818f63af9e8","observation_id":"74bf4762-3e98-41e2-8b67-f7433d8b32fb","resolution":{"observed_at":"2026-08-02T23:38:55.052451Z","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":"2026-08-02T23:38:55.129817Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:55.129817Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:66a3e28485450b85fcc9826dced3a234334c173ae794b33343ce72473d2bcc8c","observation_id":"8be34b99-a5c0-4a3d-8bc0-2bc6e8ec03bd","resolution":{"observed_at":"2026-08-02T23:38:55.129817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.02017","last_updated":"2025-05-30T06:45:49Z","snapshot_observed_at":"2026-07-06T20:30:45.542351Z","submitted_at":"2025-02-04T05:09:23Z","title":"Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.02017","snapshot_observed_at":"2026-08-02T23:38:55.221271Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:55.221271Z"},"links":{"cited_paper":"/paper/2502.02017","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:15c009b12f6b7c356b590c7b0a8fbe937e1e403f46ca86e46417e7269bbff401","observation_id":"57ba74e1-2000-4384-83e9-88aa1f686b39","resolution":{"observed_at":"2026-08-02T23:38:55.221271Z","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":"2026-08-02T23:38:55.320019Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:55.320019Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:5b2e8c4a11b0f9e6ea1d6714c3b0a2220b87e6abbbbc9e187b577566acfd3511","observation_id":"a51246a0-90a5-4ecc-8b99-a3d0730b780b","resolution":{"observed_at":"2026-08-02T23:38:55.320019Z","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":"2026-08-02T23:38:55.522455Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:55.522455Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:3e857ed35b892664b19a1dcc6cef3486a56cb849648b99fa631cc5ac9bb56cff","observation_id":"ef36798e-f0cc-4958-98ba-e0fa47f313df","resolution":{"observed_at":"2026-08-02T23:38:55.522455Z","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":"2026-08-02T23:38:55.584086Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:55.584086Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:b9bd2416f8ea4649796cfd6e910b1b98d804d212b08ab93e98ad5b2d01705811","observation_id":"ae49752d-5651-44fb-bba0-24548a24ffff","resolution":{"observed_at":"2026-08-02T23:38:55.584086Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.07275","last_updated":"2023-05-31T03:49:26Z","snapshot_observed_at":"2026-07-06T15:02:40.704180Z","submitted_at":"2023-03-13T16:49:43Z","title":"A Survey of Graph Prompting Methods: Techniques, Applications, and Challenges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.07275","snapshot_observed_at":"2026-08-02T23:38:55.662828Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:55.662828Z"},"links":{"cited_paper":"/paper/2303.07275","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:f8bf4f8d3f8b3f4ad3829ceb3cba4bb4cf36b2abc62e7af02c45d815164657f0","observation_id":"96466d5d-a98c-46c4-b68e-882ed4e24f03","resolution":{"observed_at":"2026-08-02T23:38:55.662828Z","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":"2026-08-02T23:38:55.787473Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:55.787473Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:ad7846ad376b59aaf7a0dbb4bec848f5b5cd6d4faa51bfca5dc65ab5de7fcc2b","observation_id":"bf62fd2e-ec5a-4bb6-897f-3fa9b44448a4","resolution":{"observed_at":"2026-08-02T23:38:55.787473Z","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":"2026-08-02T23:38:55.870940Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:55.870940Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:656ed39616d7c38cb7df69ec22c49ef3e8e311ccc8b3362c87876aa81a653d3f","observation_id":"1ccd6bc6-d83c-4ac3-8128-1c04fea9fee5","resolution":{"observed_at":"2026-08-02T23:38:55.870940Z","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":"2026-08-02T23:38:56.074399Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:56.074399Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:237e8e09a86789cb130eebe96099d77aa99239b2db92634ed4ea20c9a44ca90f","observation_id":"5cc9ca22-076c-4c27-aa81-08d061c1e61f","resolution":{"observed_at":"2026-08-02T23:38:56.074399Z","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":"2026-08-02T23:38:56.240645Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:56.240645Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:c2d50351b8ab43ea59929d626b1e55b85e6e2dcbfa859f7a58a50fc302b620c7","observation_id":"95104705-68b5-431f-94e0-921c1ece7a27","resolution":{"observed_at":"2026-08-02T23:38:56.240645Z","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":"2026-08-02T23:38:56.407412Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:56.407412Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:3f083c551a24a9542e409a18dbb281bf8320769240fb3ef7fccc440dc48c69e6","observation_id":"5c1b79fa-7581-4043-a369-2d43edf04d61","resolution":{"observed_at":"2026-08-02T23:38:56.407412Z","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":"2026-08-02T23:38:56.508733Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:56.508733Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:1ebf085e17a07a87acc8b07d8d6516fe6fb5021dfa3f214f8a265cb6adf7a58e","observation_id":"ca271ec7-8ec6-4abe-a0be-cb9e0478ba28","resolution":{"observed_at":"2026-08-02T23:38:56.508733Z","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":"2026-08-02T23:38:56.636619Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:56.636619Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:9daa2a8d2c69bd2c219e684d6f471a2cdc803af5c7f4f9d4f8f37af3c75c8109","observation_id":"a2dc7703-2d1e-49d6-bbfc-e60ada36f5d0","resolution":{"observed_at":"2026-08-02T23:38:56.636619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.13934","last_updated":"2024-09-22T03:47:19Z","snapshot_observed_at":"2026-08-01T15:39:52.519512Z","submitted_at":"2024-05-22T19:06:39Z","title":"Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.13934","snapshot_observed_at":"2026-08-02T23:38:56.742968Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:56.742968Z"},"links":{"cited_paper":"/paper/2405.13934","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:422a3c30eb1016986952c373ca9a0c4ce6595ea91f0feff33fc74aff1c508700","observation_id":"c8e94bb1-f054-405b-b149-f1174243db69","resolution":{"observed_at":"2026-08-02T23:38:56.742968Z","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":"2026-08-02T23:38:56.851691Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:56.851691Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:ed5c5aaccf6370277e7d8917e016f024052fdc2ecb34dd3ccf3a6925e3ec027c","observation_id":"542da222-324a-486b-ba8d-7ad9a5b7e167","resolution":{"observed_at":"2026-08-02T23:38:56.851691Z","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":"2026-08-02T23:38:56.992096Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:56.992096Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:204293e978a5c68b448cb4a8170fe93ffb9ecc302e80747fe89c6b671cd28bc5","observation_id":"ee2da1a4-6033-4919-9e4e-177e9b3a2aa5","resolution":{"observed_at":"2026-08-02T23:38:56.992096Z","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":"2026-08-02T23:38:57.124263Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:57.124263Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:eb397982b210225981fe024ce046d95021ca9f4fbc84ad66ccf40e3cd5d94243","observation_id":"07126a92-26b9-44fd-974f-a1a92cbf3f8d","resolution":{"observed_at":"2026-08-02T23:38:57.124263Z","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":"2026-08-02T23:38:57.179442Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:57.179442Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:443b38b6faae6f05f1e3cadf0ecbb59b3c0e153510e0fb8cb2a47a08445ab9c0","observation_id":"50cff7f1-5508-4a22-93d6-6321429b54e3","resolution":{"observed_at":"2026-08-02T23:38:57.179442Z","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":"2026-08-02T23:38:57.283699Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:57.283699Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:55bcec014ad03cc9baa095d4fc047d4c9f05ff34fd0eb7538f50b587a2bd8a74","observation_id":"57b108b5-76e4-4cbf-9c6f-1b705e93833a","resolution":{"observed_at":"2026-08-02T23:38:57.283699Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12449","last_updated":"2023-08-15T08:11:16Z","snapshot_observed_at":"2026-07-06T14:55:19.727805Z","submitted_at":"2023-02-24T04:31:18Z","title":"SGL-PT: A Strong Graph Learner with Graph Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12449","snapshot_observed_at":"2026-08-02T23:38:57.436114Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:57.436114Z"},"links":{"cited_paper":"/paper/2302.12449","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:5965cb4637c0a640b5a233d255820f2382557998dc689e8747d6ed6fc903565c","observation_id":"e6d74d8b-0edd-417d-8049-1ad46f2adfed","resolution":{"observed_at":"2026-08-02T23:38:57.436114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.04131","last_updated":"2020-07-13T16:32:20Z","snapshot_observed_at":"2026-08-05T13:22:44.473317Z","submitted_at":"2020-06-07T11:50:45Z","title":"Deep Graph Contrastive Representation Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.04131","snapshot_observed_at":"2026-08-02T23:38:57.556834Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:57.556834Z"},"links":{"cited_paper":"/paper/2006.04131","citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:c14980899aac04751b1f5f8ae80a8425e79d9c6c6ea097555b407e4837766927","observation_id":"91b252fd-fe17-4b00-8de2-c21330a296c1","resolution":{"observed_at":"2026-08-02T23:38:57.556834Z","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":"2026-08-02T23:38:57.675452Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:57.675452Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:7f692cdc4d8d5b5d54fc895773c536430eb5378c23fe1f38d075af4b935c3cf6","observation_id":"bae73db4-dadf-4ef4-bb39-757e7113ffcb","resolution":{"observed_at":"2026-08-02T23:38:57.675452Z","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":"2026-08-02T23:38:57.801163Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:57.801163Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:3f215bf55790c1a13f91c3ec64afeb66c9fd65f43d6a77b9e0fb780e1898eba8","observation_id":"523c1b63-03c0-47d3-a7a2-c72695133a0e","resolution":{"observed_at":"2026-08-02T23:38:57.801163Z","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":"2026-08-02T23:38:53.588593Z","title":"Information Retrieval3, 2 (2000), 127–163","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":2000,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:53.588593Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:b0a139282c63a9f0914ab3f6cab2c7f85e2ac2b99f4c49f6214a1a4b6b35625e","observation_id":"00ed333e-3786-4c2f-9f2c-e0b38fcfdb15","resolution":{"observed_at":"2026-08-02T23:38:53.588593Z","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":"2026-08-02T23:38:53.415716Z","title":"InProceedings of the 38th international ACM SIGIR conference on research and development in information retrieval","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:53.415716Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:41369b24e346969fda5ab2dde7ca477a39665ef6c8f0afb4dcd4e9ec7c2d6516","observation_id":"f78157d7-5afb-4a28-8a26-16be4fc35797","resolution":{"observed_at":"2026-08-02T23:38:53.415716Z","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":"2026-08-02T23:38:55.395701Z","title":"InThe world wide web conference","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:55.395701Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:78477fad05459df8d5e96dfee909b6ab046479ffc50837a77b62b9af1e6676ec","observation_id":"2b71f5f9-59e8-4c82-91e1-414b3a087ddb","resolution":{"observed_at":"2026-08-02T23:38:55.395701Z","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":"2026-08-02T23:38:52.819029Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:52.819029Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:33fda337bec8104bac962b51d0b2586bbec172cddfce36f6e095efd83e44e414","observation_id":"ba40a25a-09e3-4444-982a-008400641ead","resolution":{"observed_at":"2026-08-02T23:38:52.819029Z","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":"2026-08-02T23:38:54.876726Z","title":"InProceedings of the AAAI conference on artificial intelligence, Vol","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:54.876726Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:ed37365e05f7f8126c60770a2acb92dcaf086f4fe225e1cb2a94231bb13d4910","observation_id":"036f09c8-21b0-4c27-a908-8491488ce934","resolution":{"observed_at":"2026-08-02T23:38:54.876726Z","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":"2026-08-02T23:38:57.951047Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T23:38:57.951047Z"},"links":{"citing_paper":"/paper/2602.13075"},"observation_digest":"sha256:37646127a3a14453be41fd4ce426f2c387b1a559e6c4e118424e71b8b3147392","observation_id":"cb6a3933-f585-4b71-909d-6b179172f8b4","resolution":{"observed_at":"2026-08-02T23:38:57.951047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2602.13075","last_updated":"2026-05-27T04:21:31Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T23:38:48.433563Z","submitted_at":"2026-02-13T16:34:55Z","title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding"},"reference_resolution":{"displayed":70,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":70,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":70},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 2 inbound Pith citation observations for arXiv:2602.13075."}