{"as_of":"2026-08-09T11:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:04ca1b0c305aae3874253bd12f719a68050d728b06bc5f4b3f1844b58ca645c1","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:26:49.490578Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"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":[],"links":{"evidence":"/evidence","html":"/paper/2506.02451/citation-record","integrity":"/paper/2506.02451/integrity","json":"/paper/2506.02451/citation-record.json","paper":"/paper/2506.02451"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:26:46.262043Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:46.262043Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:6a5bb3ee88dc8789fc8113a8a59252e2c3c86113259f08c139ec5fedda092d45","observation_id":"8bf454c8-e1d5-4ef9-b35e-86d52b4c72d8","resolution":{"observed_at":"2026-08-07T11:26:46.262043Z","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":"2026-08-07T11:26:56.215322Z","title":"Graph attention networks","venue":null,"work_id":"13e3f1b8-430e-4206-ab52-1398d1161b75","year":2018},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:46.313440Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:3c4586fbe360adfeb5f374b0529dab9b4d81cc3ec911ea2538b4a96d430f35d8","observation_id":"4a16b5b6-4d12-45ff-8412-2c07064bea1e","resolution":{"observed_at":"2026-08-07T11:26:56.248110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:56.074231Z","title":"Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes","venue":null,"work_id":"607e8531-b560-4b07-acd9-0e620e541981","year":2020},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:46.409588Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:8b5c5d5c18498c555f7fa7f315b632320067252e0bbc1f5b8af9f9f0aa71bd56","observation_id":"6f37c9ef-9855-4d52-a98d-aab663a408dc","resolution":{"observed_at":"2026-08-07T11:26:56.119060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.02684","last_updated":"2023-03-01T13:12:23Z","snapshot_observed_at":"2026-08-07T21:41:42.864157Z","submitted_at":"2019-10-07T09:21:49Z","title":"Effective Stabilized Self-Training on Few-Labeled Graph Data","version":4},"cited_work":{"arxiv_id":"1910.02684","doi":null,"metadata_source":"pith","pith_arxiv_id":"1910.02684","snapshot_observed_at":"2026-08-07T11:26:49.991595Z","title":"Effective Stabilized Self-Training on Few-Labeled Graph Data","venue":"cs.LG","work_id":"9459e71e-7b23-4226-926a-e03b2ada909f","year":2019},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:46.487525Z"},"links":{"cited_paper":"/paper/1910.02684","citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:4ede85a688ac3b38819fe963780b604070382a17adf87edf9e890c51adf3d298","observation_id":"ca9ab240-4e83-4f40-a85b-03218c7973ff","resolution":{"observed_at":"2026-08-07T11:26:50.050041Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:55.960822Z","title":"T-net: Weakly supervised graph learning for combatting human trafficking","venue":null,"work_id":"d7fc4c37-1e7c-4968-8954-c7715fe5afa8","year":2024},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:46.572674Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:d477615eb073eae2b2296305c645901de63be781458deafd2232b40f8b66f010","observation_id":"4ab1a447-6106-4e7b-bbbb-b27144c026a9","resolution":{"observed_at":"2026-08-07T11:26:56.031539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:55.867375Z","title":"Scaling up fact-checking using the wisdom of crowds","venue":null,"work_id":"14036d73-a1ee-46cd-8bbf-c387b924b20a","year":2021},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:46.660339Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:b39c7bb3f3e0dc3dbf21725159a51646bfa016d996b734327f2803c700b512a3","observation_id":"31a25d81-e7f2-4456-a117-1d1106c720e7","resolution":{"observed_at":"2026-08-07T11:26:55.903293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:55.723474Z","title":"Justice in misinformation detection systems: An analysis of algorithms, stakeholders, and potential harms","venue":null,"work_id":"2f40738e-7dcb-4f49-a7be-6f088bd97ff7","year":2022},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:46.755573Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:d7ad04a6b4b2d567c85be672dd0d7cebb7034fa40a860fa0bd177aa7892acf4a","observation_id":"3053a621-fd1f-40b1-b040-d9236f58a9e6","resolution":{"observed_at":"2026-08-07T11:26:55.771817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:55.604765Z","title":"Data programming: Creating large training sets, quickly","venue":null,"work_id":"be07f159-62b2-444f-bcf8-eb7a75b2be60","year":2016},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:46.824072Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:1b9fd0f5bf2d658afe6dba6325502f7d1c74dbb17c2ee957c3d42fbb211568f7","observation_id":"20cdf1e5-9468-4807-b45f-c738df2f9a85","resolution":{"observed_at":"2026-08-07T11:26:55.654725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:55.489576Z","title":"Learning hyper label model for programmatic weak supervision","venue":null,"work_id":"32450189-2ca0-4c17-81ac-ba11d63fb70b","year":2023},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:46.919491Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:802387bdaafe91e1101e0e3b3f99be3d7f3675b24a2600707e0cd37de0dd875b","observation_id":"33105a9c-5153-4ce7-9151-39b6f8e30765","resolution":{"observed_at":"2026-08-07T11:26:55.548001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:55.372150Z","title":"Bigbio: a framework for data-centric biomedical natural language processing","venue":null,"work_id":"ccd7d47b-3bf1-42c4-92ae-af020794f2f2","year":2022},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:46.971641Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:ec2375b32ab4e2722b4b2eaf6bcce1ed898a98d6105af6b0dc3d872013219118","observation_id":"0e4f4821-380b-4bb7-8645-caae6ca96d3f","resolution":{"observed_at":"2026-08-07T11:26:55.433543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:55.275604Z","title":"Resonant anomaly detection with multiple reference datasets","venue":null,"work_id":"69a0c421-fba5-4f09-91d2-187aa0855c59","year":2023},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.023780Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:23e668d87d6d631e7066a8c980aad5d6fbce0ec9711f66147b899ea6698c2ec0","observation_id":"42c668c4-c3c9-4b16-8198-7bff85c457e3","resolution":{"observed_at":"2026-08-07T11:26:55.321397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:55.123672Z","title":"Hamilton, Pietro Liò, Yoshua Bengio, and R Devon Hjelm","venue":null,"work_id":"b6026705-eb79-4494-b8f4-41a5bfd48004","year":2019},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.056663Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:0232e9762ecbe0f7d40ce22e0a8d4e12eda148c80d62682f335cb885c0c34de0","observation_id":"a95d902f-7e80-47a7-b1f5-9c8aafaaebf0","resolution":{"observed_at":"2026-08-07T11:26:55.172421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.11362","last_updated":"2021-03-10T19:11:45Z","snapshot_observed_at":"2026-08-07T05:29:45.126060Z","submitted_at":"2020-04-23T17:58:56Z","title":"Supervised Contrastive Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.11362","snapshot_observed_at":"2026-08-07T11:26:47.062630Z","title":"Supervised contrastive learning","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.062630Z"},"links":{"cited_paper":"/paper/2004.11362","citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:4333aceee8730cf0f86095b73752f538b4bcbf8336e8b66fe4365db15ea618a2","observation_id":"6abc4766-31ab-4a58-a167-97408ceee087","resolution":{"observed_at":"2026-08-07T11:26:47.062630Z","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":"2026-08-07T11:26:55.015111Z","title":"Clusterscl: cluster-aware supervised contrastive learning on graphs","venue":null,"work_id":"393db04a-bd99-493a-a139-f81d843de5f8","year":2022},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.188881Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:981f0e8be2557622211c31041ae6b2432faff8427bd1d7aa5bc2a8e1004deabc","observation_id":"a110723f-76f8-44cc-8d1c-3c22a13d06c1","resolution":{"observed_at":"2026-08-07T11:26:55.057570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:54.884120Z","title":"Automating the construction of internet portals with machine learning","venue":null,"work_id":"486e363e-a6d2-4778-ab45-a4dd4eb61ce0","year":2000},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.239888Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:06a2f1b3ae213b6e40059f5acba5d122ccb690152a6415efd443593bb6a42de3","observation_id":"92637ce7-3214-45b1-9394-3832c7390272","resolution":{"observed_at":"2026-08-07T11:26:54.965481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:54.749855Z","title":"liar, liar pants on fire","venue":null,"work_id":"81e6c0ca-7b4c-4289-bc29-d480c1eba39c","year":2017},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.309604Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:02bf492e993e6a985ab976f312b7f320af0df71cc92128184bef16ab771a33d9","observation_id":"0e1ffc22-5c19-445d-a1f6-11f7945124be","resolution":{"observed_at":"2026-08-07T11:26:54.816190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.05433","last_updated":"2022-02-14T05:45:58Z","snapshot_observed_at":"2026-07-06T12:36:41.820948Z","submitted_at":"2022-02-11T04:05:38Z","title":"A Survey on Programmatic Weak Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.05433","snapshot_observed_at":"2026-08-07T11:26:47.432114Z","title":"A survey on programmatic weak supervision","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.432114Z"},"links":{"cited_paper":"/paper/2202.05433","citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:206f9a23342b727221fb9787c5b3dd47ead6f4dc3e4a5cc2545218705d45e6b5","observation_id":"2e8b8e2d-43f4-4bcc-b6c1-510c5ac2ddbd","resolution":{"observed_at":"2026-08-07T11:26:47.432114Z","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":"2026-08-07T11:26:54.593580Z","title":"Training complex models with multi-task weak supervision","venue":null,"work_id":"9940fbe1-aa7e-49c5-8f7d-f9966c9cad05","year":2019},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.483941Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:fa5728764bb698f2421df50bf76221d483311059e0c6873196afccba4eb940a9","observation_id":"b14f9325-42d4-4684-b068-a061ebd98151","resolution":{"observed_at":"2026-08-07T11:26:54.641332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:54.425701Z","title":"Multi-resolution weak supervision for sequential data","venue":null,"work_id":"7ea490dc-7f99-4948-bc54-c7681aae8454","year":2019},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.536213Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:652c1f70a7579b852c3e8a444ada7c6cb5ca15d3ddaf881fdd5e0b894cdef381","observation_id":"ceb63db0-fe59-448b-a70f-78dbf800b389","resolution":{"observed_at":"2026-08-07T11:26:54.486778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:54.266779Z","title":"Fast and three-rious: Speeding up weak supervision with triplet methods","venue":null,"work_id":"fd26c663-92a5-41ff-9cbd-fc20056d3139","year":2020},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.665593Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:ac79ecda0449f5973e5cc3ec1f25959f03459d98a4a63a34ad722c487a74f75f","observation_id":"fb45f4d7-75b6-40e6-b7eb-7dbdaef7aedc","resolution":{"observed_at":"2026-08-07T11:26:54.363305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.04714","last_updated":"2021-06-08T22:12:44Z","snapshot_observed_at":"2026-07-06T11:17:21.331166Z","submitted_at":"2021-06-08T22:12:44Z","title":"NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs","version":1},"cited_work":{"arxiv_id":"2106.04714","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.04714","snapshot_observed_at":"2026-08-07T11:26:49.795839Z","title":"NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs","venue":"cs.LG","work_id":"1063e1e9-91ea-4b1e-9ea4-fc0d7215f396","year":2021},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.749905Z"},"links":{"cited_paper":"/paper/2106.04714","citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:3c986a336d66790fd46179c6de5a73b5e65b5b98b1d0398d5c2f5b52d3f2198f","observation_id":"9accfc0a-892a-4e7b-8cdc-78fd9ff1e514","resolution":{"observed_at":"2026-08-07T11:26:49.855554Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:54.204925Z","title":"Noise-robust graph learning by estimating and leveraging pairwise interactions","venue":null,"work_id":"0a37bdf5-433f-4772-8f1a-71bcb05d0f7f","year":2023},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.875645Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:92f92c1a89cc38ca34fb4c201243b30293b35ba0d9128a81c64be8af23dde2a1","observation_id":"65b3c965-bfff-4ebc-906f-0ed9bb88e5e9","resolution":{"observed_at":"2026-08-07T11:26:54.229552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:54.141792Z","title":"Learning on graphs under label noise","venue":null,"work_id":"b8230d03-9905-4a7e-a1dd-5664684a5fda","year":2023},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:47.964267Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:7037dcf46eba9831af08a1b39b62888b731b2da315f8beccabaff38cac8882c9","observation_id":"19e3312e-80f7-41cd-a021-941bf67f8e7a","resolution":{"observed_at":"2026-08-07T11:26:54.166914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:54.090726Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":"82d0dcf2-1262-43b7-b7f0-7d21da558dda","year":2020},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.035600Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:9b11dfbce319a805274f152735f6d6f75a73d678ebeb49f18b249302b8f76cd4","observation_id":"755e6f53-6186-42ed-b2c2-91bf3f347540","resolution":{"observed_at":"2026-08-07T11:26:54.115730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:53.980339Z","title":"Graph contrastive learning with augmentations","venue":null,"work_id":"46d5870d-6e54-475b-bde1-ee6d01a72b1b","year":2020},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.094604Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:0228c59241577bb84cdc3a678a8f6ae7fd7862134dd7008ffc20c0214b9888f1","observation_id":"9218f044-8bc2-4a08-8362-84c4a97b7322","resolution":{"observed_at":"2026-08-07T11:26:54.031577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:53.756803Z","title":"Contrastive multi-view representation learning on graphs","venue":null,"work_id":"f1e74049-8efe-461d-be58-bf291e4dda34","year":2020},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.165510Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:143f423880daac3df396130159fa3322350e19c22ab5c5fc81a3d3349db4f204","observation_id":"0e6b676e-b58c-46ff-90dd-ae78e9721aa7","resolution":{"observed_at":"2026-08-07T11:26:53.886534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:53.560840Z","title":"Deep graph contrastive representation learning","venue":null,"work_id":"da72d517-81ce-48fd-87b0-9ce14fa1c13a","year":2020},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.243330Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:4dfaef5e152e93f6b7801b2cff43951d6e541633f359c17f0a813a830ddf4a49","observation_id":"04b7a613-b6ca-4987-bbeb-00db2904449e","resolution":{"observed_at":"2026-08-07T11:26:53.641196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.04658","last_updated":"2023-05-08T12:21:24Z","snapshot_observed_at":"2026-08-04T11:17:44.234521Z","submitted_at":"2023-05-08T12:21:24Z","title":"CSGCL: Community-Strength-Enhanced Graph Contrastive Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.04658","snapshot_observed_at":"2026-08-07T11:26:48.298293Z","title":"Csgcl: Community-strength- enhanced graph contrastive learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.298293Z"},"links":{"cited_paper":"/paper/2305.04658","citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:f89c347dbaba50b6b643cf713be96534c76f7d1515dff34dda1583c26f9bff2e","observation_id":"34737c25-8f0b-4ed4-a191-aca539c687aa","resolution":{"observed_at":"2026-08-07T11:26:48.298293Z","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":"2026-08-07T11:26:53.330265Z","title":"Graph contrastive learning with adaptive augmentation","venue":null,"work_id":"5daae425-2c19-45b7-9c39-7d43cf18db3a","year":2021},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.360113Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:4bc95d759e060335e2ebd123ca8695ddfce7ba73fb78c5e536c4cd0a2b52e7cd","observation_id":"dd38ee4c-fe2c-4d1a-a0ac-6a5d052c07b2","resolution":{"observed_at":"2026-08-07T11:26:53.435040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:53.160203Z","title":"Large-scale representation learning on graphs via bootstrapping","venue":null,"work_id":"f04f3642-1323-4dbf-9d48-09c6a51aed3e","year":2022},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.422462Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:d683b4f81465dcf442f55fe2f616a62b97b29481c27702ea6e2cd2461e086272","observation_id":"7374fc40-f4b0-418b-bb55-74a587bf9b47","resolution":{"observed_at":"2026-08-07T11:26:53.235080Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:52.973578Z","title":"Graph Representation Learning via Graphical Mutual Information Maximization","venue":null,"work_id":"af8530db-e02a-49d7-9da1-1183817e4b6e","year":2020},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.488207Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:8d4685549a7806a99dd9b3df9c55f36275ed9a35c99387aadfa97adc61d186dd","observation_id":"af15549d-85c4-4ab3-afac-5bc75b98758d","resolution":{"observed_at":"2026-08-07T11:26:53.083184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:52.751739Z","title":"Simple unsupervised graph representation learning","venue":null,"work_id":"8ee85501-3569-42fa-93c3-fdcc5b705b5b","year":2022},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.556250Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:c18e0169eb7fc7ddd0dbe8dbcc5b80ba34cb7d212f6e21bebfa5319c5037fd63","observation_id":"341bbd93-b9e2-4817-a525-ee04108c921e","resolution":{"observed_at":"2026-08-07T11:26:52.886757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:52.486028Z","title":"Augmentation-free graph contrastive learning of invariant-discriminative representations.IEEE Transactions on Neural Networks and Learning Systems, 2023","venue":null,"work_id":"1b3b23a6-55a3-46a0-bec4-2ad5bf8389f1","year":2023},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.643156Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:a8587905ccdf98133276b2ad1f65c25e93c6f9f203e73c0c8ce8217d2c872a55","observation_id":"b7617a91-bded-4ee3-b741-4e9ee06df7c9","resolution":{"observed_at":"2026-08-07T11:26:52.631432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:52.276134Z","title":"Kefato and Sarunas Girdzijauskas","venue":null,"work_id":"0ef4fa2b-1771-4889-b473-008663cb26a6","year":2021},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.731092Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:67ab894287d7255cc009801663d550b3541921e51f647fb3ee7fc6b67f890273","observation_id":"93588fd6-3645-479d-bed5-6465c7a10220","resolution":{"observed_at":"2026-08-07T11:26:52.376420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:51.948293Z","title":"Jgcl: Joint self-supervised and supervised graph contrastive learning","venue":null,"work_id":"74853042-94d6-4d8d-b698-4fdcd15d5474","year":2022},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.837939Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:f0cd8c13e8ed537bc6d24f0d192086f5b0c29f07aa7d4b85a2e9042edfee806d","observation_id":"5da0234f-9359-40c3-890e-0fbb7c35b385","resolution":{"observed_at":"2026-08-07T11:26:52.112615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:51.672848Z","title":"Weakly supervised contrastive learning","venue":null,"work_id":"401614c1-7bf6-4857-9502-4913886cfd4a","year":2021},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.895701Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:cee7b390a7ed81677cd308a161d5ad45bddf335c804935087f651c4945c6a6a8","observation_id":"1341c78b-194e-4e2d-910c-2c42fab46102","resolution":{"observed_at":"2026-08-07T11:26:51.784031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.04160","last_updated":"2023-06-07T05:18:27Z","snapshot_observed_at":"2026-07-06T15:39:33.825891Z","submitted_at":"2023-06-07T05:18:27Z","title":"Rethinking Weak Supervision in Helping Contrastive Learning","version":1},"cited_work":{"arxiv_id":"2306.04160","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.04160","snapshot_observed_at":"2026-08-07T11:26:49.598987Z","title":"Rethinking Weak Supervision in Helping Contrastive Learning","venue":"cs.LG","work_id":"a8d919ea-fc1e-448b-9ee9-1adc78c9288c","year":2023},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:48.950170Z"},"links":{"cited_paper":"/paper/2306.04160","citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:214f1c453028599610eff195ce53efd7b84fc1310d9567bb0b5ddc1b7bf5607b","observation_id":"28c207a5-7d6b-42d8-a924-619208136816","resolution":{"observed_at":"2026-08-07T11:26:49.664556Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03748","last_updated":"2019-01-22T18:47:12Z","snapshot_observed_at":"2026-07-06T06:49:24.960992Z","submitted_at":"2018-07-10T16:52:11Z","title":"Representation Learning with Contrastive Predictive Coding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03748","snapshot_observed_at":"2026-08-07T11:26:49.034679Z","title":"Representation learning with contrastive predictive coding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:49.034679Z"},"links":{"cited_paper":"/paper/1807.03748","citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:34eb2f8415739135fbb3ca8acd6682eeb3c31c4e773fba77239e71a5bc262804","observation_id":"799645f8-90dd-45f9-a1c2-6247721260c8","resolution":{"observed_at":"2026-08-07T11:26:49.034679Z","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":"2026-08-07T11:26:51.355838Z","title":"Combating misinformation in the age of llms: Opportunities and challenges","venue":null,"work_id":"e435aed8-89f8-4ae8-80f9-633e41cd999e","year":2023},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:49.107716Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:9f0b40b9b9b32f5719ac4f021a6ab7e57ee3fa12fabc6bd04f35a674efe9236e","observation_id":"68c918df-ff57-40f1-9f67-aaf1d21ef192","resolution":{"observed_at":"2026-08-07T11:26:51.508600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14928","last_updated":"2023-10-31T07:19:01Z","snapshot_observed_at":"2026-08-01T16:15:24.643387Z","submitted_at":"2023-05-24T09:10:20Z","title":"Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14928","snapshot_observed_at":"2026-08-07T11:26:49.145945Z","title":"Towards reliable misinformation mitigation: Generalization, uncertainty, and gpt-4","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:49.145945Z"},"links":{"cited_paper":"/paper/2305.14928","citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:234bf625aede141b499aeacd0937c9ebc2407ff6a2f2a54014adeb79a4bceded","observation_id":"58c35708-d600-4be0-852e-d786bb22f997","resolution":{"observed_at":"2026-08-07T11:26:49.145945Z","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":"2026-08-07T11:26:51.071045Z","title":"Citeseer: An automatic citation indexing system","venue":null,"work_id":"94c7f31c-798f-47df-879c-4893e5b28172","year":1998},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:49.216560Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:1d9bf207196ae8cfc1e2f9cfedb12effc48450a61f0474c7bb901429dbec9486","observation_id":"f0ef18c1-e582-4dbd-bdec-890197d3edab","resolution":{"observed_at":"2026-08-07T11:26:51.186034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:50.770664Z","title":"Hyperbolic graph convolutional neural networks","venue":null,"work_id":"c1c72df5-2938-4570-8ccc-0babe71d512c","year":2019},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:49.274955Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:23157308b70beef6cb93e76188caeeec6d66a34df43ffb6dd29031d8a34ea4d7","observation_id":"34db01c6-e89d-4461-8da9-beb48d52d925","resolution":{"observed_at":"2026-08-07T11:26:50.910141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:50.516487Z","title":"Microsoft academic graph: When experts are not enough","venue":null,"work_id":"e7d997dc-1189-44c3-afa6-ed7a03f85f1a","year":2020},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:49.348383Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:c12b02a19729f644868defb6c6da209fabd376b53f148a55926c08c0eda9b519","observation_id":"23b256fb-a389-4b84-8871-a771190e973d","resolution":{"observed_at":"2026-08-07T11:26:50.608674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:50.329281Z","title":"Image-based recommendations on styles and substitutes","venue":null,"work_id":"ed6a274c-3323-4eb3-bbac-a52b5af7a795","year":2015},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:49.415111Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:8dca2d99cb05b8747c8e5fa03c59cc4da65f1ecc185f63d7d816872d8a55566a","observation_id":"816cf4c0-34be-4c5e-9883-1d5a9db1ee9f","resolution":{"observed_at":"2026-08-07T11:26:50.404468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:26:50.156567Z","title":"Graphmix: Improved training of gnns for semi-supervised learning","venue":null,"work_id":"7464ec97-9b70-436a-81fa-d7c929f33857","year":2021},"citing_paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:49.490578Z"},"links":{"citing_paper":"/paper/2506.02451"},"observation_digest":"sha256:adaf61addb54adf99da5ad9060bcf9d2af675ec7343d51c747e0cb568b47173a","observation_id":"91122ac3-2fa2-4488-9fff-77e88fff57f5","resolution":{"observed_at":"2026-08-07T11:26:50.218641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.02451","last_updated":"2025-06-03T05:16:18Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T06:31:01.009568Z","submitted_at":"2025-06-03T05:16:18Z","title":"Weak Supervision for Real World Graphs"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":3,"verified_fuzzy":36},"total_outbound_references":45},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2506.02451."}