{"as_of":"2026-08-18T15:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e0502911e0a673def882e20f00d18301e70d33142925cb348178da740fa6740f","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T05:16:56.131672Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:44:32.382722Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T09:39:46.458905Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","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":"2026-08-18T09:34:55.743613Z","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":"sha256:32574bd1cdc07e187db19b622451daa474f93307d179aa1d8849087333155408","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":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","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":"2026-08-03T00:07:43.009648Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.11641","last_updated":"2026-05-31T02:32:04Z","snapshot_observed_at":"2026-08-09T02:42:12.079273Z","submitted_at":"2026-02-12T06:53:35Z","title":"Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T00:07:43.009648Z"},"links":{"cited_paper":"/paper/2504.21198","citing_paper":"/paper/2602.11641"},"observation_digest":"sha256:db0b497725c7278b2e174ebcaaa6d29a67e7240240f00fa5a090a17895823b2d","observation_id":"2f9ebd11-c601-4176-8aa3-405c775d2d8a","resolution":{"observed_at":"2026-08-03T00:07:43.009648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"cited_work":{"arxiv_id":"2504.21198","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.21198","snapshot_observed_at":"2026-07-04T09:39:46.458905Z","title":"arXiv preprint arXiv:2504.21198 , year=","venue":null,"work_id":"d996abb3-fd3d-4751-8e52-ff2f8c8d9d64","year":null},"citing_paper":{"arxiv_id":"2606.22741","last_updated":"2026-06-22T01:03:21Z","snapshot_observed_at":"2026-08-02T09:44:06.503397Z","submitted_at":"2026-06-22T01:03:21Z","title":"GRADE: Graph Representation of LLM Agent Dependency and Execution","version":1},"reference_index":107,"source":"arxiv_source","source_observed_at":"2026-06-26T09:44:37.914985Z"},"links":{"cited_paper":"/paper/2504.21198","citing_paper":"/paper/2606.22741"},"observation_digest":"sha256:fb6de588296cd283c13907152be8f95058c12804e18e4c7310f80dd309d3dbe6","observation_id":"e79a4aae-3f54-4b6b-804f-67c5abfb2a66","resolution":{"observed_at":"2026-07-04T09:39:46.460667Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","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":"2026-07-14T02:33:34.084111Z","title":"Graph synthetic out-of-distribution exposure with large language models, 2025 a","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.11871","last_updated":"2026-07-13T17:55:19Z","snapshot_observed_at":"2026-08-18T13:07:06.175404Z","submitted_at":"2026-07-13T17:55:19Z","title":"Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias","version":1},"reference_index":214,"source":"arxiv_source","source_observed_at":"2026-07-14T02:33:34.084111Z"},"links":{"cited_paper":"/paper/2504.21198","citing_paper":"/paper/2607.11871"},"observation_digest":"sha256:9db2662b0e0e08c996a578351223f194f63fddf3c991c11d4a4eb7dcdb0ae4e2","observation_id":"e41a810d-8a8a-493b-9f61-96df5d33408c","resolution":{"observed_at":"2026-07-14T02:33:34.084111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2504.21198/citation-record","integrity":"/paper/2504.21198/integrity","json":"/paper/2504.21198/citation-record.json","paper":"/paper/2504.21198"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2502.03323","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:56.547218Z","title":"Out-of-distribution detection using synthetic data generation","venue":null,"work_id":"f834fc2f-187b-4bcf-8492-081466b8f500","year":2025},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.938473Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:f3b758a877d760ace7124acd819ff379211a78770b6e7fdbba98c58f2a374a7e","observation_id":"6a833bff-6575-477b-ab96-dc2d23c8553a","resolution":{"observed_at":"2026-08-16T05:16:56.558100Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.00806","last_updated":"2024-06-02T17:09:48Z","snapshot_observed_at":"2026-08-17T08:31:17.357038Z","submitted_at":"2024-06-02T17:09:48Z","title":"Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.00806","snapshot_observed_at":"2026-08-16T05:16:55.943816Z","title":"Envisioning outlier exposure by large language models for out-of-distribution detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.943816Z"},"links":{"cited_paper":"/paper/2406.00806","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:4f5b6ff939b74374d0280b4a297ec62f99c22934f4ea1ef5fb59858a439f5d7b","observation_id":"f2e01121-b763-45ae-932d-1990d15e8378","resolution":{"observed_at":"2026-08-16T05:16:55.943816Z","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":"2026-08-16T05:16:56.932935Z","title":"Multiood: Scaling out-of-distribution detection for multiple modalities","venue":null,"work_id":"70c33ee4-4298-4d91-b14e-015a84df8042","year":2024},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.949110Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:619533fab9097d1ffc6720fa22565163420eb71255eb30ee540f75f79466ee19","observation_id":"9412b46a-cf25-4ef0-bd7b-ade794cc4675","resolution":{"observed_at":"2026-08-16T05:16:56.938557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03502","last_updated":"2024-02-05T20:36:33Z","snapshot_observed_at":"2026-08-16T14:21:14.983416Z","submitted_at":"2024-02-05T20:36:33Z","title":"How Does Unlabeled Data Provably Help Out-of-Distribution Detection?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03502","snapshot_observed_at":"2026-08-16T05:16:55.954980Z","title":"How does unlabeled data provably help out-of-distribution detection? arXiv preprint arXiv:2402.03502, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.954980Z"},"links":{"cited_paper":"/paper/2402.03502","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:ad9b5832efec9d304f67967119a0e10b83170258d1dfb14aedcf77c5d27986a7","observation_id":"7fcf42b4-4a1a-49d5-b566-2a6e8c717e06","resolution":{"observed_at":"2026-08-16T05:16:55.954980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.01197","last_updated":"2022-05-09T20:12:32Z","snapshot_observed_at":"2026-08-16T17:24:03.718323Z","submitted_at":"2022-02-02T18:43:01Z","title":"VOS: Learning What You Don't Know by Virtual Outlier Synthesis","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.01197","snapshot_observed_at":"2026-08-16T05:16:55.960500Z","title":"V os: Learning what you don’t know by virtual outlier synthesis","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.960500Z"},"links":{"cited_paper":"/paper/2202.01197","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:489dafc96aec8188518f8d831f37048d606db47d23829974f6a0cdf1371c48ae","observation_id":"4fff2b79-dfd8-4b15-b118-8b27ed536ea5","resolution":{"observed_at":"2026-08-16T05:16:55.960500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:55.965975Z","title":"Citeseer: An automatic citation indexing system","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.965975Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:31f7f8d29593a52dc26bd456dd471a0685ad95ae7d99d1e7ecb8cc9b20fb1411","observation_id":"727acb38-155e-492c-9d4c-9fcb5d1421b0","resolution":{"observed_at":"2026-08-16T05:16:55.965975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.02136","last_updated":"2018-10-03T07:32:57Z","snapshot_observed_at":"2026-08-02T06:41:33.803920Z","submitted_at":"2016-10-07T04:06:01Z","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02136","snapshot_observed_at":"2026-08-16T05:16:55.971831Z","title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.971831Z"},"links":{"cited_paper":"/paper/1610.02136","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:80f326cda530d2c6dbe8a8f0a3a3206c0ddfdef51879e078a21badfa2de4b328","observation_id":"7d3afc3f-14fa-4892-906d-782bd0c424c5","resolution":{"observed_at":"2026-08-16T05:16:55.971831Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.04606","last_updated":"2019-01-28T20:34:44Z","snapshot_observed_at":"2026-08-14T17:45:07.132382Z","submitted_at":"2018-12-11T18:49:50Z","title":"Deep Anomaly Detection with Outlier Exposure","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.04606","snapshot_observed_at":"2026-08-16T05:16:55.976751Z","title":"Deep anomaly detection with outlier exposure","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.976751Z"},"links":{"cited_paper":"/paper/1812.04606","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:6f19022e7e09b94b2d7682dd01628cf38ecb9f8b5ef428ed9e33bb94a383b67d","observation_id":"49061e70-ae62-4592-b7be-db17b3040cae","resolution":{"observed_at":"2026-08-16T05:16:55.976751Z","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":"2026-08-16T05:16:56.901472Z","title":"Pixmix: Dreamlike pictures comprehensively improve safety measures","venue":null,"work_id":"908627b9-36fd-468e-93ac-cf9468c77717","year":2022},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.981841Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:c039154e665239e2bdc32e089df3eafdd8df1ff8759148282a044ea04bd5bca9","observation_id":"926a6afc-390b-4d5c-8f44-47742e984dad","resolution":{"observed_at":"2026-08-16T05:16:56.907420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:16:56.882448Z","title":"Training sar-atr models for reliable operation in open-world environments","venue":null,"work_id":"437e8ef7-e71e-44e2-8c38-4792e33ee2bc","year":2021},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.986710Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:4efbbded613d7234ff2710a881c4b358abbe6b4df0f9a3c161012bcd949ca412","observation_id":"a075fff8-cefa-4459-8917-07c3e4d28982","resolution":{"observed_at":"2026-08-16T05:16:56.888239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:16:56.864692Z","title":"Autoaudit: Mining accounting and time-evolving graphs","venue":null,"work_id":"63033bc0-3c0f-4a0f-afea-7aa0b8f93fa6","year":2020},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.991849Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:dedf8c219b6e6a3bb06395adffc41b302fe68b9922291764add4c2dccfcd209c","observation_id":"72fc8ad6-c262-4e89-bdef-6a36c2e12a6f","resolution":{"observed_at":"2026-08-16T05:16:56.870352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:16:56.845932Z","title":"Dpu: Dynamic prototype updating for multimodal out-of-distribution detection","venue":null,"work_id":"29075a4d-55ce-4d14-8af9-d2214b11da73","year":2025},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:55.997018Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:9ea98513e50dac3436a2b7c738972b881d544587720a1d78ea90d6669ef36d97","observation_id":"49b058d8-821c-4574-908a-b46e0731b16e","resolution":{"observed_at":"2026-08-16T05:16:56.852061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:16:56.827138Z","title":"Energy-based out-of-distribution detection","venue":null,"work_id":"54e8ea9f-7066-417d-bead-214e77443e6a","year":2020},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.002696Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:18d1eecfec4f1b9568f9cc86b62e39e270cf793b66def5a46ef397e523c4a023","observation_id":"ee74f278-59ce-415f-9882-929d6468a2de","resolution":{"observed_at":"2026-08-16T05:16:56.833312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:56.009003Z","title":"Revisiting score propagation in graph out-of-distribution detection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.009003Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:e802b3aa3b39305f08985170c200b77f9ecec3bc6149b287c2d6ff72e3a62af3","observation_id":"b7eb6d90-62c4-4da5-8210-ff5db4b44493","resolution":{"observed_at":"2026-08-16T05:16:56.009003Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:56.014204Z","title":"Automating the construction of internet portals with machine learning","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.014204Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:3209058f312ea0665e52e8607e4b3e8edac0223814430817c8ad12add58c186e","observation_id":"237ab98f-5c88-4fdc-bc03-4951be892929","resolution":{"observed_at":"2026-08-16T05:16:56.014204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.02901","last_updated":"2022-01-09T23:19:38Z","snapshot_observed_at":"2026-08-09T07:12:13.529182Z","submitted_at":"2020-07-06T17:25:47Z","title":"Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.02901","snapshot_observed_at":"2026-08-16T05:16:56.019102Z","title":"Wiki-cs: A wikipedia-based benchmark for graph neural networks","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.019102Z"},"links":{"cited_paper":"/paper/2007.02901","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:2606337eafd4ac1bf7a855e2062381fbd8ac9ba7ff33de664354e073c412170c","observation_id":"2fe270f6-cf80-4e9e-900d-c18854e84296","resolution":{"observed_at":"2026-08-16T05:16:56.019102Z","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":"2026-08-16T05:16:56.783265Z","title":"Outlier exposure with confidence control for out-of-distribution detection","venue":null,"work_id":"6cecd1e1-387d-4f96-a773-f600823421a8","year":2021},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.023891Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:ea7a089fea1fe4f40afb78a41bfa6c25a32d0d9c66d782e55338300582d04a39","observation_id":"f8893ed4-e3a3-4133-93d9-40a951bbf3ec","resolution":{"observed_at":"2026-08-16T05:16:56.789279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:56.028797Z","title":"Metaood: Automatic selection of ood detection models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.028797Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:77c2460dff83fce5c245d52e51af801131d85c3a037494be6d8df05c2494d09d","observation_id":"c4ea8416-91f7-411a-945a-3ac7ead9497a","resolution":{"observed_at":"2026-08-16T05:16:56.028797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10084","last_updated":"2019-08-27T08:50:17Z","snapshot_observed_at":"2026-08-14T05:02:11.716316Z","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10084","snapshot_observed_at":"2026-08-16T05:16:56.034094Z","title":"Sentence-bert: Sentence embeddings using siamese bert-networks","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.034094Z"},"links":{"cited_paper":"/paper/1908.10084","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:5f5b9ee904cd980b373e6a501eb488106858499e866f2a4fad23d36074cab490","observation_id":"6b7a1b4f-1eb8-4642-9ad2-492738c5a6a9","resolution":{"observed_at":"2026-08-16T05:16:56.034094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:56.038998Z","title":"Collective classification in network data","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.038998Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:15996f8044d784b50d0099ecc697067d7f9a8a31499c9fa58981f5e600863150","observation_id":"8c24fb5a-f2f3-4621-ac9f-9cb8e6aa09cb","resolution":{"observed_at":"2026-08-16T05:16:56.038998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:56.044247Z","title":"Learning on graphs with out-of-distribution nodes","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.044247Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:987be77943072d697b1d7f01dd157f33abb75a2e4b96594949290a8448da5517","observation_id":"14f50c42-9f82-44ef-9c5c-282c8bebdecc","resolution":{"observed_at":"2026-08-16T05:16:56.044247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02966","last_updated":"2023-03-06T08:51:00Z","snapshot_observed_at":"2026-08-16T15:50:33.540896Z","submitted_at":"2023-03-06T08:51:00Z","title":"Non-Parametric Outlier Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.02966","snapshot_observed_at":"2026-08-16T05:16:56.049061Z","title":"Non-parametric outlier synthesis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.049061Z"},"links":{"cited_paper":"/paper/2303.02966","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:4b3ef6c812022ada0930320a96c3c6c4bb811e9cf0f0640bd648670904c1f779","observation_id":"80d5e9c5-903a-49c0-bde3-7bb2544c6629","resolution":{"observed_at":"2026-08-16T05:16:56.049061Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.04241","last_updated":"2019-10-09T20:38:56Z","snapshot_observed_at":"2026-08-18T07:26:18.703145Z","submitted_at":"2019-10-09T20:38:56Z","title":"Out-of-distribution Detection in Classifiers via Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.04241","snapshot_observed_at":"2026-08-16T05:16:56.054220Z","title":"Out-of-distribution detection in classifiers via generation","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.054220Z"},"links":{"cited_paper":"/paper/1910.04241","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:be23d29c22af702dde9666b6caf51dd32fe29ecb84d4e7e6da3d7b62d452983c","observation_id":"d7be6759-acef-465f-9c0d-094cb54774eb","resolution":{"observed_at":"2026-08-16T05:16:56.054220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.05780","last_updated":"2025-04-10T11:41:23Z","snapshot_observed_at":"2026-08-17T17:24:05.798869Z","submitted_at":"2025-02-09T05:19:53Z","title":"GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.05780","snapshot_observed_at":"2026-08-16T05:16:56.059247Z","title":"Gold: Graph out-of-distribution detection via implicit adversarial latent generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.059247Z"},"links":{"cited_paper":"/paper/2502.05780","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:5eba93a63a60ee31362c0239441e9ad222b109e0375229858952fd411a7fe99e","observation_id":"82e48206-829e-4325-a8ef-f6a8c863599f","resolution":{"observed_at":"2026-08-16T05:16:56.059247Z","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":"2026-08-16T05:16:56.727500Z","title":"Further analysis of outlier detection with deep generative models","venue":null,"work_id":"99a067ce-9d9c-4209-975c-cab94b588477","year":2020},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.064486Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:90c5b0deb6f114d0f2229823f97effe5b2ffb44c1cf09953271ac26da9c0b79b","observation_id":"a7c2f369-e4b5-48b1-90e7-c1c2c7b1fc96","resolution":{"observed_at":"2026-08-16T05:16:56.735486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.02914","last_updated":"2023-03-09T06:24:02Z","snapshot_observed_at":"2026-08-16T15:57:21.408661Z","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":"2026-08-16T05:16:56.069136Z","title":"Energy-based out-of-distribution detection for graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.069136Z"},"links":{"cited_paper":"/paper/2302.02914","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:9f35ee381cb109b9cad619506658495832031c1a6dbc27298dfd1cfecdf49dcd","observation_id":"7d31895c-0248-4ddf-a84c-0773edfe9353","resolution":{"observed_at":"2026-08-16T05:16:56.069136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:56.074597Z","title":"Timme: Twitter ideology-detection via multi-task multi-relational embedding","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.074597Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:7aa35d42f3b8e5ebe6c679906f2c02bdbe3a7b19fc2f48a2ed971696639ead4c","observation_id":"2a654b5c-c4a8-4978-a180-a067a10b20ba","resolution":{"observed_at":"2026-08-16T05:16:56.074597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.07115","last_updated":"2022-08-17T02:20:15Z","snapshot_observed_at":"2026-08-03T14:23:36.976812Z","submitted_at":"2020-05-14T16:33:13Z","title":"CoSimGNN: Towards Large-scale Graph Similarity Computation","version":7},"cited_work":{"arxiv_id":"2005.07115","doi":null,"metadata_source":"pith","pith_arxiv_id":"2005.07115","snapshot_observed_at":"2026-08-16T05:16:56.206075Z","title":"CoSimGNN: Towards Large-scale Graph Similarity Computation","venue":"cs.LG","work_id":"36d682aa-af25-4442-9f3a-e22b19ac757d","year":2020},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.079513Z"},"links":{"cited_paper":"/paper/2005.07115","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:d25f4f0626f2d6b762a4118f18566c894c7dba8f6fc09cda3d67a05263959b87","observation_id":"c2855a2a-c1d5-4354-b54c-5bdb3c91d114","resolution":{"observed_at":"2026-08-16T05:16:56.215816Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:16:56.695788Z","title":"Graph partitioning and graph neural network based hierarchical graph matching for graph similarity computation","venue":null,"work_id":"9ba8193a-9dee-4d64-8bb6-a2b88e414a98","year":2021},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.085468Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:83132d18f88728bd584e3da7957c660bc8f8789aa3dc479ab859d387f6064700","observation_id":"ff62a100-9aa7-4671-ba7e-f1be0138ac9b","resolution":{"observed_at":"2026-08-16T05:16:56.702453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:16:56.677094Z","title":"Lego-learn: Label-efficient graph open-set learning","venue":null,"work_id":"552f626c-660f-44cb-9387-7120a3f88589","year":2025},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.090583Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:e0b68860250b32c49db856d05b35a750e3474de512563d5451f4b818a53f5a8e","observation_id":"3a0d9d89-75af-4e9e-8181-5284ed7f8f39","resolution":{"observed_at":"2026-08-16T05:16:56.682176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.22097","last_updated":"2025-03-28T02:37:18Z","snapshot_observed_at":"2026-08-16T12:46:05.917379Z","submitted_at":"2025-03-28T02:37:18Z","title":"Few-Shot Graph Out-of-Distribution Detection with LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.22097","snapshot_observed_at":"2026-08-16T05:16:56.096944Z","title":"Few-shot graph out-of-distribution detection with llms","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.096944Z"},"links":{"cited_paper":"/paper/2503.22097","citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:f47ea572ef76abd86c281d046a4ab60aa441eb9e9fab9ec153ca6e91c5e1d5d2","observation_id":"ec5a9451-1d45-470a-8f60-e582f8912eae","resolution":{"observed_at":"2026-08-16T05:16:56.096944Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:56.104196Z","title":"A comprehensive study on text-attributed graphs: Benchmarking and rethinking","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.104196Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:8aef8d73bae5574d9174484e22795c19723db8cc4d3695dc197523118610e053","observation_id":"cd618ed8-3e6a-40ef-a185-f51b1c5127ed","resolution":{"observed_at":"2026-08-16T05:16:56.104196Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:56.109647Z","title":"Generalized out-of-distribution detection: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.109647Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:295e57eee8ce35edc78d466b11fe5f94e4cd87f748918508becfc9d6c702e8ea","observation_id":"29a0a524-f33e-44de-8982-616586b85f33","resolution":{"observed_at":"2026-08-16T05:16:56.109647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:16:56.114664Z","title":"Graphformers: Gnn-nested transformers for representation learning on textual graph","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.114664Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:214c9baef1038771df3673ba6111f07c351a26edf47da2db7fd819290c46426f","observation_id":"cfa53175-643f-4ff3-b7c7-336143142658","resolution":{"observed_at":"2026-08-16T05:16:56.114664Z","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":"2026-08-16T05:16:56.619817Z","title":"Mix- ture outlier exposure: Towards out-of-distribution detection in fine-grained environments","venue":null,"work_id":"04cc78ba-8378-4e45-8205-90ba68af0966","year":2023},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.120638Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:fa3fa48111632e60d8b6df7d83cac0a4e3ed3bb3bee63a8810ffd4dd3e32cf42","observation_id":"df8d0081-a75a-431e-bc81-f1b78e1124d4","resolution":{"observed_at":"2026-08-16T05:16:56.626751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:16:56.598619Z","title":"Uncertainty aware semi-supervised learning on graph data","venue":null,"work_id":"7ff1c9d0-9524-4e8c-b363-97520976f774","year":2020},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.125977Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:b80726a664eb564970f53c589858ad87c2f22dcefb2e7a9b4c989d5c9afbeecf","observation_id":"9b493e3f-cf85-4c0c-a8f0-fc1f50b4fc8e","resolution":{"observed_at":"2026-08-16T05:16:56.604736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:16:56.577565Z","title":"A survey on deep graph generation: Methods and applications","venue":null,"work_id":"d6e53e8f-15da-4d52-b42a-6b50048b32fb","year":2022},"citing_paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T05:16:56.131672Z"},"links":{"citing_paper":"/paper/2504.21198"},"observation_digest":"sha256:45a57bb5cec76894477a2c024aef9f7a530c81692abb0bf4f1e813934b6e8ae9","observation_id":"c6232d0a-f2e2-43a4-8add-1af9dd84dcaf","resolution":{"observed_at":"2026-08-16T05:16:56.585468Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.21198","last_updated":"2025-05-17T05:06:02Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T05:08:19.217194Z","submitted_at":"2025-04-29T22:04:30Z","title":"Graph Synthetic Out-of-Distribution Exposure with Large Language Models"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":2,"verified_fuzzy":12},"total_outbound_references":37},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 4 inbound Pith citation observations for arXiv:2504.21198."}