{"as_of":"2026-08-13T23:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:feabb6d5fe48b31a8169d7c7d567718a7f26d61b079fa840f5893605813c8b07","coverage":[{"denominator":65,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":65,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:44:34.924746Z","state":"measured"},{"denominator":66,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":66,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T03:46:18.553428Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.13989","snapshot_observed_at":"2026-08-01T03:46:18.553428Z","title":"arXiv preprint arXiv:2505.13989 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27665","last_updated":"2026-07-30T04:24:41Z","snapshot_observed_at":"2026-08-08T07:35:16.898400Z","submitted_at":"2026-07-30T04:24:41Z","title":"FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-01T03:46:18.553428Z"},"links":{"cited_paper":"/paper/2505.13989","citing_paper":"/paper/2607.27665"},"observation_digest":"sha256:968bb53b1ac331e6f42a8c3f748f72261f5ee7ea41a1b3db80a194234595d7bd","observation_id":"2cadc34d-15be-4e07-8dfa-9f4c10fb4443","resolution":{"observed_at":"2026-08-01T03:46:18.553428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.13989/citation-record","integrity":"/paper/2505.13989/integrity","json":"/paper/2505.13989/citation-record.json","paper":"/paper/2505.13989"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:53.289673Z","title":"Graph out-of-distribution detection goes neighborhood shaping","venue":null,"work_id":"b594f2a0-f469-4d46-94d4-d97a87c8dfc7","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:26.881157Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:753ab357b1cba7a251de8099c484bd1f309fffe1df3dade7dbd2de139a4f7eea","observation_id":"8a7cfa5c-165a-4256-8f74-608f70e36c0c","resolution":{"observed_at":"2026-08-07T15:44:53.351651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:52.979962Z","title":"Motif prediction with graph neural networks","venue":null,"work_id":"f119763e-f20d-4ca6-abb1-1ead99e3182c","year":2022},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:26.959321Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:deb8e7b8825c41291a47c3fd6a73465556de8d8765f017d1fdb56c70439a0e7b","observation_id":"64288d3d-43c6-4446-8542-c872d34200e2","resolution":{"observed_at":"2026-08-07T15:44:53.115390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:52.623729Z","title":"Decoupled graph energy- based model for node out-of-distribution detection on heterophilic graphs","venue":null,"work_id":"9acaf6b2-47a1-490e-b03f-6d92788ea864","year":2025},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:27.101757Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:e43575830c55de0841f18375abad4e9fccbf5da58517bf9e175f094284fd094b","observation_id":"1b13654f-8eee-4360-9845-5e5c3f360532","resolution":{"observed_at":"2026-08-07T15:44:52.754914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:52.399969Z","title":"Label-free node classification on graphs with large language models (llms)","venue":null,"work_id":"c0f24f25-f926-40c4-9d5b-160dd3d27752","year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:27.249787Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:181bb9ef58544ac12301aa477be3fd92e2ea43916be2aaa1c646dafcd039b183","observation_id":"46b84a4c-fa18-4b7a-8e0f-0c10f342bc54","resolution":{"observed_at":"2026-08-07T15:44:52.465185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:52.125172Z","title":"Dslr: Diversity enhancement and structure learning for rehearsal-based graph continual learning","venue":null,"work_id":"8676ef1c-a390-45e9-a727-aab397426565","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:27.412707Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:6d70067e4870298bbed30f6cdca81e1bbe4827a410ce9bf80b0bbf769b981837","observation_id":"a0f54e02-91d1-42ca-8a68-88560579718b","resolution":{"observed_at":"2026-08-07T15:44:52.232617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:51.818395Z","title":"Spreading out-of-distribution detection on graphs","venue":null,"work_id":"64186881-feee-4295-a32b-cd5865af30c1","year":2025},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:27.555306Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:923891ab653060e509403b8d87e2918ebe640f7582154f39b39ad24cee512813","observation_id":"9e678d3a-5fcb-4633-a1a9-1c9b7591e9e4","resolution":{"observed_at":"2026-08-07T15:44:51.923111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:51.596412Z","title":"Continual learning of knowledge graph embeddings","venue":null,"work_id":"5a265d46-7aae-4596-a709-7812e4d6c795","year":2021},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:27.694749Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:bf6dfee11a65d34b0f1a7237157d46e96cf1cf74679d8db644d034d272f61df1","observation_id":"03726dd8-e089-461c-920f-13bb7afcb2ac","resolution":{"observed_at":"2026-08-07T15:44:51.671561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:51.258231Z","title":"Lifelong learning of graph neural networks for open-world node classification","venue":null,"work_id":"21e7f69b-3c2b-4561-9b25-6047c64e7590","year":2021},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:27.844828Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:12196f612a85dfbfc8e5554c163436e708152ddb058acb6680317988aab3a81a","observation_id":"3882af94-0e2a-42ad-b4c3-9e28032d14fe","resolution":{"observed_at":"2026-08-07T15:44:51.423420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:51.024913Z","title":"An energy-centric framework for category-free out-of-distribution node detection in graphs","venue":null,"work_id":"fec79410-1a53-4f84-b7ab-40804b8f4cc3","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:28.002016Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:1fd2447a82ac5fa3f3e280fce9e8a424b234cdc150ea02af9d014384f04b24aa","observation_id":"2a479a1c-23cd-4fe1-b414-6c28e2cdc549","resolution":{"observed_at":"2026-08-07T15:44:51.114842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:50.708760Z","title":"Hamilton, Rex Ying, and Jure Leskovec","venue":null,"work_id":"a4f6908c-6877-4520-9bad-eacf53a2741a","year":2017},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:28.094274Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:cdecb81968d2e294abbf0c65ad21fd7a63889e246f5688fe79669d87a6ad28a8","observation_id":"579b0491-eaea-45e2-b13e-7c06174acbe0","resolution":{"observed_at":"2026-08-07T15:44:50.865327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:50.381350Z","title":"Universal graph continual learning","venue":null,"work_id":"e703afba-7edd-4620-a994-788ab60f9393","year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:28.264849Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:7b4a75d107fddfaaa5ac73b8dbd494ef36f9344d603e993ee6f4b44e904136ac","observation_id":"2a8a8441-0ad2-4064-90c4-cf4b3a137f80","resolution":{"observed_at":"2026-08-07T15:44:50.494833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:50.071282Z","title":"Open-world lifelong graph learning","venue":null,"work_id":"1441f528-4e6e-487e-bcdd-4d91a116ccd8","year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:28.457458Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:ec29e89728ddabdc1c344379929ff7dc5eea5fc30dfb2cf760a8b3745f0e368c","observation_id":"97818c59-1d60-4ad8-8780-84bccf4af17e","resolution":{"observed_at":"2026-08-07T15:44:50.197631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:49.675057Z","title":"Open-world lifelong graph learning","venue":null,"work_id":"3ae63327-97d8-4bae-a491-5f038ff46b55","year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:28.546670Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:4ecabe24cf7fc4e6912bf3da76f8cdcf58cea870b909776da4f8923555104135","observation_id":"178cd87d-c302-4000-8f1e-cd39246fbfc0","resolution":{"observed_at":"2026-08-07T15:44:49.855235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:49.363746Z","title":"Beyond the known: Novel class discovery for open-world graph learning","venue":null,"work_id":"e99a8134-0f60-407b-add6-59873075dfbe","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:28.655099Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:06834d3ce7d9d1f36bad9ffa30ae2876ff25cbad8f801c7062951bff21535978","observation_id":"6fc369c3-1f4d-4524-a690-0dc52e7e5f22","resolution":{"observed_at":"2026-08-07T15:44:49.474842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:49.167342Z","title":"Beyond the known: Novel class discovery for open-world graph learning","venue":null,"work_id":"17110271-19dc-4ae7-b8fb-46aaa925f6b8","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:28.745178Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:72c093fa24caf1ddbcb8b95bf7860e68435f930a3ec073275531e6c1f397528d","observation_id":"c9b603e1-11f3-4a8f-b1d2-b326291eff85","resolution":{"observed_at":"2026-08-07T15:44:49.264005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-13T11:38:10.906031Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-07T15:44:28.845026Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:28.845026Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:c12abe01519a69d77870bd6ba86f20f5f0e77a9911d0c48ccfd220b5d1b9e951","observation_id":"65a20db8-1b3a-42ea-9019-23804b87a0ed","resolution":{"observed_at":"2026-08-07T15:44:28.845026Z","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":"2026-08-07T15:44:48.932008Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":"58e3a822-e89b-49e4-a049-5d175c15b527","year":2017},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:28.956660Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:302f46ba9e94bf76944c033fbb98a9847f6f75fc6b9029f3404cbc1735729583","observation_id":"20247eea-5df9-4468-b799-9e760fa7e13d","resolution":{"observed_at":"2026-08-07T15:44:49.062131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:48.644805Z","title":"Gofa: A generative one-for-all model for joint graph language modeling","venue":null,"work_id":"b4fc5c38-2ed4-4dc9-b7bc-70df991e3bde","year":2025},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:29.034880Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:c1f5306f0c7fb533742fecc1ef368437f70e188b0218853175d34e2b88896bb9","observation_id":"359e7d4b-ec93-47c1-a258-0984358ec393","resolution":{"observed_at":"2026-08-07T15:44:48.788638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:48.380046Z","title":"Disentangle-based continual graph representation learning","venue":null,"work_id":"c59d2d67-7b6e-4cc4-955e-ae23dfb21b6b","year":2020},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:29.122439Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:a138368379d81086df9820cca63a3e5bb5c205d6912c60a26912ae4ec1f2a16e","observation_id":"45c3f3d4-7abf-4225-8b59-a0feca8319df","resolution":{"observed_at":"2026-08-07T15:44:48.480186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:48.113444Z","title":"Gated attention with asymmetric regularization for transformer- based continual graph learning","venue":null,"work_id":"5482677e-3b6a-4cbd-9bae-77d10064d8bd","year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:29.245296Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:48c9ed31e82f332521d2a3da0199ab1e052a8c39faa549dce1b94999d8fd66b7","observation_id":"fba2112c-4409-4e29-b9e7-80ea8a89e5c4","resolution":{"observed_at":"2026-08-07T15:44:48.206527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13095","last_updated":"2023-05-22T14:59:50Z","snapshot_observed_at":"2026-08-13T11:37:12.466603Z","submitted_at":"2023-05-22T14:59:50Z","title":"Open-world Semi-supervised Novel Class Discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13095","snapshot_observed_at":"2026-08-07T15:44:29.354964Z","title":"Open-world semi- supervised novel class discovery","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:29.354964Z"},"links":{"cited_paper":"/paper/2305.13095","citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:de09f671aa40c6d51fc6fa5f13ee58e24c1d91df6d6f72cacd6e640f460b9565","observation_id":"f2a44c58-53e3-41a2-8c8a-1dfa1bcca8a3","resolution":{"observed_at":"2026-08-07T15:44:29.354964Z","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":"2026-08-07T15:44:47.859877Z","title":"Good-d: On unsupervised graph out-of-distribution detection","venue":null,"work_id":"8c9506cd-3748-4273-8f96-ccd1e67e8d98","year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:29.465320Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:932459a903fd59660000121398a88eee5c8a3c94ebad2165406ec133abe22de0","observation_id":"2402ce1b-510d-4d0c-9a12-1c8f7cf9b16b","resolution":{"observed_at":"2026-08-07T15:44:47.955327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:47.556333Z","title":"Good-d: On unsupervised graph out-of-distribution detection","venue":null,"work_id":"30c879e8-ce90-497e-bb65-a1141abd8857","year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:29.567259Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:69c2e3fd7a7418112c4f31753b3a26d8df454228b26c3e3cad0a7b3b28d28efe","observation_id":"4f4504ad-d9da-4db3-bff1-935824fe949e","resolution":{"observed_at":"2026-08-07T15:44:47.744740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:47.205887Z","title":"Arc: A generalist graph anomaly detector with in-context learning","venue":null,"work_id":"175e0ffa-3518-4ddc-9f79-5ffa3e317de5","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:29.672520Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:5d873bd80c9ba3c4e1394d5f4adcca3dc5d2641af27129d3413b4faac5173527","observation_id":"55631d75-1043-43b8-86bb-08d11e697db3","resolution":{"observed_at":"2026-08-07T15:44:47.392489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:46.994742Z","title":"Revisiting score propagation in graph out-of- distribution detection","venue":null,"work_id":"b901f93d-f024-4e58-b4da-5e6470f925f9","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:29.776759Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:76d9213f51537ce145110ca9ea61801f1e8c4657778a3b8d6148c434ac898e55","observation_id":"5c45ff0d-f5bc-450b-84ac-ae1c5d600eaa","resolution":{"observed_at":"2026-08-07T15:44:47.086725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:46.664392Z","title":"Entropic out- of-distribution detection","venue":null,"work_id":"2aca908b-7979-45ed-8fdf-840075c55e46","year":2021},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:29.896525Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:d89aa6186c66f359818ffd59bfdf0e56184640c696e57ab0817fab4800a2608f","observation_id":"9ebc10b3-4425-45c7-b8b4-1cee5bf19fd9","resolution":{"observed_at":"2026-08-07T15:44:46.836912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:46.385023Z","title":"Graph continual learning with debiased lossless memory replay","venue":null,"work_id":"b2dd9c27-5e21-4b87-94f1-d09333dda5e2","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:30.025617Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:58f711b1dcde68936fb40b5a6ba765afc9bfd291b5a5c897e2d2efdf2961ecf4","observation_id":"804ee9df-9367-4e1d-bc11-a6574d87c92f","resolution":{"observed_at":"2026-08-07T15:44:46.546127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:46.114801Z","title":"Ftf-er: Feature-topology fusion-based experience replay method for continual graph learning","venue":null,"work_id":"c3c28fcf-431f-4bc2-a52f-eb2b8e1ade57","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:30.135153Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:5855b043bb8199e3a50a9c4938bf6114462f97dab48d862b8c90e0a2b11c9823","observation_id":"845a09f9-ee78-4d84-8fed-bededf7276ed","resolution":{"observed_at":"2026-08-07T15:44:46.187733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:45.734806Z","title":"Contrastive augmented graph2graph memory interaction for few shot continual learning","venue":null,"work_id":"0d867bcd-9ba5-4fff-b519-a9c4654e83af","year":2025},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:30.255237Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:3babb8a987fc0c47e32115332aab823f55960e87555c9938f86cc8573d6e4e17","observation_id":"b50e3487-ef92-49b0-9a50-a087a6a826e1","resolution":{"observed_at":"2026-08-07T15:44:45.914827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:45.313520Z","title":"Reinforced continual learning for graphs","venue":null,"work_id":"f7d04fca-5448-417c-992c-aa798b8b9d0f","year":2022},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:30.352901Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:a7b46d07baafe5bb585cfe21c4b9520d829ec379b61be3fe78a5e90fd1a7f422","observation_id":"dc2857d0-a189-426f-9bee-cd76d381dfb5","resolution":{"observed_at":"2026-08-07T15:44:45.442861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:45.133805Z","title":"Learning on graphs with out-of-distribution nodes","venue":null,"work_id":"e39de18c-c972-4aba-b8a5-f966cace5243","year":2022},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:30.444934Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:3db5fb10e60075bd61a70306b467cff1ce84487bfdc06826051af2ff710e1789","observation_id":"fc85ae6b-f94b-4365-b468-573939811365","resolution":{"observed_at":"2026-08-07T15:44:45.222207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:44.799017Z","title":"Learning on graphs with out-of-distribution nodes","venue":null,"work_id":"c4623c23-5c59-4129-aafa-9e4a8d79b6d4","year":2022},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:30.577695Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:d7abf5f898adfa9a59f22aaabfcdd92ede318702492f7769b5c074cb9ce857a3","observation_id":"2d5c7d58-3629-4168-90af-3ed77203da8c","resolution":{"observed_at":"2026-08-07T15:44:44.945921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:44.531328Z","title":"Graph posterior network: Bayesian predictive uncertainty for node classification","venue":null,"work_id":"e2cbd277-6b88-46a6-bc3c-33a61383063b","year":2021},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:30.666049Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:313b58db1021d2425f5832f357d612a49275f676887f444e014b23b8a71b3d02","observation_id":"c05a1e0a-8350-41fa-b835-1aae5eb360f8","resolution":{"observed_at":"2026-08-07T15:44:44.615987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:44.311271Z","title":"Graph-based continual learning","venue":null,"work_id":"c27304fd-4173-4c5c-9428-75925a6b930b","year":2020},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:30.776103Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:096900ba6cb7d6734cc9f7b413f3a442d7ed48a6528736a80e35c0ec25df2d82","observation_id":"1177c6e4-5156-4632-87b7-9a88e0672cda","resolution":{"observed_at":"2026-08-07T15:44:44.397819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:43.972270Z","title":"Spreading out-of-distribution detection on graphs","venue":null,"work_id":"44278817-78e8-4b32-a26c-6364f43b82cd","year":2025},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:30.846848Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:86cc068647749feda14bc9c6f557d7b449b0c8fc5f3ca86ea5ca0f2d3be03ae8","observation_id":"559ee592-fca8-40e2-8c5b-bf0578d4c94f","resolution":{"observed_at":"2026-08-07T15:44:44.150551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-08-13T22:35:40.714745Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-07T15:44:30.994849Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:30.994849Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:786a90f9afa3f1c0601e0becb5e219e1cedbfd9a1dea98177b72cd2be799235a","observation_id":"c523e73d-322e-40db-9afe-436e06c04abc","resolution":{"observed_at":"2026-08-07T15:44:30.994849Z","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":"2026-08-07T15:44:43.794157Z","title":"Smug: Sand mixing for unobserved class detection in graph few-shot learning","venue":null,"work_id":"bc2d8af2-f1bc-4f04-b5d3-c9537dbb9e12","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:31.110338Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:1a579c274d7d11739fd021ea277b9eadefbb3cdde0ab24261e10575cdee277ad","observation_id":"e7700d91-f42b-4972-8d93-4bfcf58fcc64","resolution":{"observed_at":"2026-08-07T15:44:43.874818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:43.595328Z","title":"Gold: Graph out-of-distribution detection via implicit adversarial latent generation","venue":null,"work_id":"0265964b-80c0-47cc-98b1-b94dcbafe5c7","year":2025},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:31.214832Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:c7801311204b0c5a2e0a13190d210136682f58cf1475734a301b8dabf1d3bf2d","observation_id":"6856b15a-b2f8-4680-a594-7ffa4d2f730e","resolution":{"observed_at":"2026-08-07T15:44:43.658306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:43.374749Z","title":"Streaming graph neural networks via continual learning","venue":null,"work_id":"d26c0b43-88b3-48b9-89f7-dae99899efcb","year":2020},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:31.346934Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:d1de2d3f85087b453ba5a9ae7a530719a61646261557c0e9a53acfa3dc2d8737","observation_id":"49b91f17-aca3-47ec-8b89-527ad477fc7d","resolution":{"observed_at":"2026-08-07T15:44:43.481765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:43.085423Z","title":"Open-world semi-supervised learning for node classification","venue":null,"work_id":"68d00028-6478-454a-808d-37c44ac9cc98","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:31.448074Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:992e453bb3f54065dafc2870623ec91f245fa19ca1ca016d931d99cbeb7a8102","observation_id":"e35a3fa4-5b03-4515-92c1-485fd21619d2","resolution":{"observed_at":"2026-08-07T15:44:43.179642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:42.692865Z","title":"Open-world semi-supervised learning for node classification","venue":null,"work_id":"641c336e-a139-40dd-9766-09a1d7d01ff4","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:31.519574Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:a219ba5dfd88061aaed0fb4e69790c99476207b15c73ab0717705219e76efa9a","observation_id":"4662eb27-2f2d-4e74-95b4-86ece85f7a10","resolution":{"observed_at":"2026-08-07T15:44:42.875081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:42.409270Z","title":"Augmenting low-resource text classification with graph-grounded pre-training and prompting","venue":null,"work_id":"978e5eb7-39f3-4e1c-94e1-80430a4a5a0a","year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:31.677457Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:a374f617d5db43a0d229a4a1aee59ada8f833ac2832a3ae5f4330a020420bf04","observation_id":"2acbe9e1-f408-4a78-8e06-e842b040d8c6","resolution":{"observed_at":"2026-08-07T15:44:42.527947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:42.103852Z","title":"Openwgl: Open-world graph learning","venue":null,"work_id":"fc84b0a9-8f11-48c7-b10b-55e3ac5c9a12","year":2020},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:31.811623Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:5c3b602188ec834a70330a3a3215a2d6057074a85a9135aefaa4b04c92055d1b","observation_id":"9a14de88-8a66-450c-85d0-97ebfd5596d0","resolution":{"observed_at":"2026-08-07T15:44:42.212332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:41.824929Z","title":"Openwgl: Open-world graph learning","venue":null,"work_id":"83dab205-8f4e-4746-b05a-4ba11277d7ce","year":2020},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:32.001143Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:eb3e3c228770a44cd091fbe541ed75505745039b14c5e59383bf9f2ffef2f856","observation_id":"0c5bae26-0527-46cc-bf23-fe1a4e9755da","resolution":{"observed_at":"2026-08-07T15:44:41.964836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:41.556346Z","title":"Energy-based out-of-distribution detection for graph neural networks","venue":null,"work_id":"7bfbe062-e28c-4069-b01f-234615af0d9f","year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:32.114486Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:099f196f637dfd00ebe611741844d44e67122347a849a50b5ac3d52ff71ed5b3","observation_id":"86c4eaf4-167d-40f2-9f12-fae39d090492","resolution":{"observed_at":"2026-08-07T15:44:41.645090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.02914","last_updated":"2023-03-09T06:24:02Z","snapshot_observed_at":"2026-08-13T12:50:04.628459Z","submitted_at":"2023-02-06T16:38:43Z","title":"Energy-based Out-of-Distribution Detection for Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.02914","snapshot_observed_at":"2026-08-07T15:44:32.198619Z","title":"Energy-based out-of-distribution detection for graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:32.198619Z"},"links":{"cited_paper":"/paper/2302.02914","citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:a791d9f6da0f38de03b88bc406c6393e2d01f468c5828d9891b46939bf9a4f37","observation_id":"1634a428-96e9-43e2-b777-2c4da0631dcb","resolution":{"observed_at":"2026-08-07T15:44:32.198619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.16386","last_updated":"2025-05-09T06:53:36Z","snapshot_observed_at":"2026-08-12T22:18:13.229282Z","submitted_at":"2024-10-21T18:01:11Z","title":"LEGO-Learn: Label-Efficient Graph Open-Set Learning","version":2},"cited_work":{"arxiv_id":"2410.16386","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.16386","snapshot_observed_at":"2026-08-07T15:44:35.789539Z","title":"LEGO-Learn: Label-Efficient Graph Open-Set Learning","venue":"cs.LG","work_id":"757639b7-8f1d-4711-b405-1dbfd60ffd38","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:32.253887Z"},"links":{"cited_paper":"/paper/2410.16386","citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:d333b2c26242c9d677bfc17291bc37e8863341789e9efb840f6878a93a0b84d1","observation_id":"29aae3ba-d5ae-47a2-967b-12aa1fec80a6","resolution":{"observed_at":"2026-08-07T15:44:35.877013Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-11T19:49:25.775908Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.21198","snapshot_observed_at":"2026-08-07T15:44:32.382722Z","title":"Graph synthetic out-of-distribution exposure with large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:32.382722Z"},"links":{"cited_paper":"/paper/2504.21198","citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:80107845d626c8682e65ef69c543bb8927d210ba1e60ca0dcbd82aa21b687b4a","observation_id":"50c2009e-4d50-4fc6-89b3-86452bd68d78","resolution":{"observed_at":"2026-08-07T15:44:32.382722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.21186","last_updated":"2025-05-17T01:21:19Z","snapshot_observed_at":"2026-08-07T15:58:02.171207Z","submitted_at":"2025-04-29T21:42:54Z","title":"GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.21186","snapshot_observed_at":"2026-08-07T15:44:32.512606Z","title":"Glip-ood: Zero-shot graph ood detection with foundation model","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:32.512606Z"},"links":{"cited_paper":"/paper/2504.21186","citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:4d624720883fe6b5e8010d9ead3d3977816fbc1c54f2c92054cf70d74997a5e4","observation_id":"fb89445d-b8dd-4451-95be-e9c60ea1578c","resolution":{"observed_at":"2026-08-07T15:44:32.512606Z","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":"2026-08-07T15:44:41.216038Z","title":"Open-world graph active learning for node classification","venue":null,"work_id":"ebb8cb0e-9e36-472f-ad73-019aaf1a863d","year":2023},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:32.687575Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:6e9873f1db6abbdc3c5a3f679ae9b3bc5d373bf9f221adb92512877409fcc8fc","observation_id":"67917220-fa6e-4ba3-81cd-0207f2741c07","resolution":{"observed_at":"2026-08-07T15:44:41.375386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:40.937496Z","title":"How powerful are graph neural networks? 2019","venue":null,"work_id":"1883c241-5c2f-4ac2-988c-752b71487dfb","year":2019},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:32.779233Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:98af427a4530a3a65fa3e37b0e0455b3b0c4d4f55c14a27bbbdd42595d8dc776","observation_id":"45819032-bc31-4e8b-afa5-30b965cc6fc1","resolution":{"observed_at":"2026-08-07T15:44:41.046115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:40.639463Z","title":"Bounded and uniform energy-based out-of-distribution detection for graphs","venue":null,"work_id":"dc997859-ef91-4e9d-8b8e-fc9eb066a9c8","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:32.952528Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:dde002d4d5d632a7474bb99ae38cd33ea1469b00d947f06b6e492724a32f08f2","observation_id":"b64fb420-77be-40c3-a5f1-b9e0fef299dd","resolution":{"observed_at":"2026-08-07T15:44:40.816951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:40.348250Z","title":"Samgpt: Text-free graph foundation model for multi-domain pre-training and cross-domain adaptation","venue":null,"work_id":"3ef89784-342e-4f1b-9a0b-a0a9e8783a99","year":2025},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:33.119331Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:e4c5469d40c15350c58e401d244b9598a1588af75c5153fab221639e5c7bba21","observation_id":"a246bc65-2158-4648-af32-c71a3fc87d93","resolution":{"observed_at":"2026-08-07T15:44:40.434827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.11983","last_updated":"2025-05-16T06:58:58Z","snapshot_observed_at":"2026-08-12T20:42:48.962860Z","submitted_at":"2024-12-16T17:04:40Z","title":"Leveraging Large Language Models for Effective Label-free Node Classification in Text-Attributed Graphs","version":3},"cited_work":{"arxiv_id":"2412.11983","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.11983","snapshot_observed_at":"2026-08-07T15:44:35.165064Z","title":"Leveraging Large Language Models for Effective Label-free Node Classification in Text-Attributed Graphs","venue":"cs.LG","work_id":"04df0f29-16d8-4d4f-bc56-4b109c2de0fc","year":2024},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:33.314848Z"},"links":{"cited_paper":"/paper/2412.11983","citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:9d9d758476d9ff5f5d3fde4f6f2347b791cc9f2fe3da462fe3839e3253a39dd8","observation_id":"bfceef40-e20f-4819-a50a-bd872cf75659","resolution":{"observed_at":"2026-08-07T15:44:35.310847Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:40.041212Z","title":"Hierarchical prototype networks for continual graph representation learning","venue":null,"work_id":"aa5b2258-6cf9-4ce0-8ceb-7d602a661335","year":2022},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:33.524598Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:275baa9a64c44e557eed8ce708aaeb721aaf7853d02d56fc5f5eedf0988ea71f","observation_id":"3c6ef23d-5ee5-415e-bc11-e34520cad15a","resolution":{"observed_at":"2026-08-07T15:44:40.154759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:39.776444Z","title":"Uncertainty aware semi-supervised learning on graph data","venue":null,"work_id":"bed215d8-0443-4c0a-8418-ddf4b353fdd5","year":2020},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:33.656381Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:9c691ef84b47a64916e477290c2b7bbe528ed5452739c02e8b2bb2470c5222a4","observation_id":"f62aa303-0dd5-4d6d-b622-8cdcd14dc963","resolution":{"observed_at":"2026-08-07T15:44:39.885944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:39.547418Z","title":"Overcoming catastrophic forgetting in graph neural networks with experience replay","venue":null,"work_id":"b77ff97c-4f7d-4e5d-8f84-253670fc6337","year":2021},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:33.775199Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:cbe7ff74f04eaead174a969ea649ebef6c0775f7d3df80561f3c6a05703d0e49","observation_id":"a3b989c1-2c14-4055-bd48-4a6fed51ece2","resolution":{"observed_at":"2026-08-07T15:44:39.668908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:39.270416Z","title":null,"venue":null,"work_id":"0a6d8d10-a301-437e-844f-44bd38376ff0","year":null},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:33.888774Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:ae7665f01b5f062c8af1a5ec17b025f2f0c2069081fd887b9b4efeed30b74fcf","observation_id":"250ee122-d907-4559-aee2-eea3a2fc34b9","resolution":{"observed_at":"2026-08-07T15:44:39.416096Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:38.884739Z","title":null,"venue":null,"work_id":"45d7ca9d-8741-4f35-862d-5d16dc8eb854","year":null},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:34.015005Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:14a5af4394e26bd04dc1906dcf8a564bdee4963ca3a9b223b75caf1a48998d51","observation_id":"b95bab55-6aa9-40d0-9798-936fe7996801","resolution":{"observed_at":"2026-08-07T15:44:39.058357Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:38.617857Z","title":"Use this supplementary information, but prioritize semantic similarity when merging","venue":null,"work_id":"86a3d3f5-5391-4255-9f75-0862af436354","year":null},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:34.175004Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:c3b02424512d2f4e19a2ca1c2d9b16d2e1b3c21965df06dbba2786c1aa5ba09e","observation_id":"3b5bf22b-53da-4cac-b211-9656fd11022f","resolution":{"observed_at":"2026-08-07T15:44:38.725448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:37.954760Z","title":"Output Format: The output should be a comma-separated list of merged labels, each enclosed in parenthe- ses, in the same order as the input community-level labels","venue":null,"work_id":"60c4f42d-9c14-4fd7-9daa-2d193c16f17d","year":null},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:34.264826Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:912b2826df546937dd2d1111bcf638a1347341db99d88253f7b0bf0de2b124d1","observation_id":"9a520146-cd55-4b40-9dc7-405ad2259edd","resolution":{"observed_at":"2026-08-07T15:44:38.342820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:37.439953Z","title":null,"venue":null,"work_id":"f3569d3b-8584-4d9c-9cb6-85cf861434c7","year":null},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:34.446535Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:01086d101181fa7151bfdcb2262bf5e3e09ebeb9ef8264a21cb228fbe63b6854","observation_id":"ec36aeaf-de4c-46e7-89db-ce13e906a3f5","resolution":{"observed_at":"2026-08-07T15:44:37.586211Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:37.070301Z","title":null,"venue":null,"work_id":"719b9a6c-f885-4141-bea7-5e221c21ab42","year":null},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:34.634750Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:bb55d2ed58790a1319d5c9a9e9a111a62c2647743e5b9b5187ac853006db9e95","observation_id":"b813f866-fd9b-4a18-9a4b-7b11789b2147","resolution":{"observed_at":"2026-08-07T15:44:37.235300Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:36.855391Z","title":"However, prioritize semantic similarity over contextual proximity","venue":null,"work_id":"e36a1331-3ae9-4c7f-94ef-802e84f16e6d","year":null},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:34.756799Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:5fbdbfda24617f5aaa29e83fa99cf1db0b2d5baea0d8442e0e3c55f11b114d8d","observation_id":"1f43afbe-ef90-42b6-9e9f-f25afbaa2508","resolution":{"observed_at":"2026-08-07T15:44:36.945315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:44:36.563315Z","title":"Output Format: Return a comma-separated list of the merged labels, with each label enclosed in parenthe- ses, following the original order of the input","venue":null,"work_id":"f15dbf82-7158-467a-ac1d-fc95765caa64","year":null},"citing_paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T15:44:34.924746Z"},"links":{"citing_paper":"/paper/2505.13989"},"observation_digest":"sha256:7e4317ef6d9201669bb6352b3b87c1d611f5bdadfa4155da4ff89ec0777ded9d","observation_id":"d5ed76de-3e1d-43d2-bd9c-d0313a083da9","resolution":{"observed_at":"2026-08-07T15:44:36.664491Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.13989","last_updated":"2025-05-21T04:23:56Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T19:49:10.084378Z","submitted_at":"2025-05-20T06:37:18Z","title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty"},"reference_resolution":{"displayed":65,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":2,"verified_fuzzy":52},"total_outbound_references":65},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 1 inbound Pith citation observation for arXiv:2505.13989."}