{"as_of":"2026-08-22T02:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c0135826c8e21de9e84e66d4ad70617b300ecbdeed0bb48491367795c5786445","coverage":[{"denominator":23,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":23,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T15:18:52.891579Z","state":"measured"},{"denominator":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2501.14197/citation-record","integrity":"/paper/2501.14197/integrity","json":"/paper/2501.14197/citation-record.json","paper":"/paper/2501.14197"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:18:53.316362Z","title":"Can abnormality be detected by graph neural networks? In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI),","venue":null,"work_id":"2796ac96-1487-4b9d-96be-c6fe4e9f4425","year":2022},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.772997Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:9ec2186a9394906a2690b09b075334cf2b819e37b1a0ab31c5cd05523099789c","observation_id":"ee0c3ab5-9495-4f83-822e-9116b15577f1","resolution":{"observed_at":"2026-08-10T15:18:53.322482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-17T10:49:36.026134Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-10T15:18:52.813635Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.813635Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:a87f3cfce2bf3f6c1b4af4e901f5c580344ed19f1d56bbf62ac3f59f79f288c8","observation_id":"841f9709-950d-494d-bc34-a54b5c39e0c8","resolution":{"observed_at":"2026-08-10T15:18:52.813635Z","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":"2026-08-10T15:18:53.164137Z","title":"Sheng, Hui Xiong, and Le- man Akoglu","venue":null,"work_id":"9c6ad87b-7a07-40bb-ade6-a478db936978","year":2023},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.831194Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:8ee8f4726913b5417bf88cb3cd50a215d40b3515c53cc2cf6d2d37adb39fab30","observation_id":"242a9c0e-12da-45b0-9ac3-179fc71a96b5","resolution":{"observed_at":"2026-08-10T15:18:53.169040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.145703Z","title":"Weidele Daniel, Bellei Claudio, Robinson Tom, and E","venue":null,"work_id":"6a7d9c61-c1ff-424a-b183-3bbb8b6337f7","year":2019},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.837477Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:40da4b8028a1326037bfad62647aef3cb0df8df747b5d7d8fab698353db682b7","observation_id":"f198e80c-93c6-4f44-99b7-8c71d38cc789","resolution":{"observed_at":"2026-08-10T15:18:53.151658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.09957","last_updated":"2025-06-18T13:42:20Z","snapshot_observed_at":"2026-08-21T15:15:52.988203Z","submitted_at":"2024-09-16T03:05:11Z","title":"Deep Graph Anomaly Detection: A Survey and New Perspectives","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.09957","snapshot_observed_at":"2026-08-10T15:18:52.843323Z","title":"Deep graph anomaly detection: A survey and new perspectives","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.843323Z"},"links":{"cited_paper":"/paper/2409.09957","citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:e43795634f5e1904576d1b61c9d4bf4da7a29774322d126a59a4141648d9c37e","observation_id":"5388813d-b553-49ce-aa21-ba5e2805bfc7","resolution":{"observed_at":"2026-08-10T15:18:52.843323Z","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":"2026-08-10T15:18:53.075925Z","title":"Rethinking graph neural networks for anomaly de- tection","venue":null,"work_id":"ff2184a0-c8a7-463f-958c-3bcc01178f66","year":2022},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.861552Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:fcd68a911305321d583fae65b7e2d4ff8f0d8774899f84625471850c5d7fed56","observation_id":"6a7a78fc-c409-4715-86b2-835a7c1431fb","resolution":{"observed_at":"2026-08-10T15:18:53.081914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:52.865712Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.865712Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:c71293a67d30a09e714c8834cd10d40d5c605d20ef63ad78392e107f7c2c9808","observation_id":"7eb3f585-5d4b-4fc2-bf67-2653c079c4ae","resolution":{"observed_at":"2026-08-10T15:18:52.865712Z","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":"2026-08-10T15:18:53.030122Z","title":"[Wang et al., 2025] Conghao Wang, Gaurav Asok Kumar, and Jagath C","venue":null,"work_id":"73224fd3-c80d-4d00-9521-0b8d364a6aa9","year":2025},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.876532Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:d88e2788ecd3e595be490ae5466621c59c8b7a7ffa7833829f0c49429759ed6a","observation_id":"e6118c17-0e04-4125-ac9e-09b0486cbddf","resolution":{"observed_at":"2026-08-10T15:18:53.035710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.011670Z","title":"Clnode: Cur- riculum learning for node classification","venue":null,"work_id":"05e594b3-f78f-4db3-bacb-a4ba9f54308e","year":2022},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.881346Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:6a70de1c1f9c8103bc1386361ad5e518c8123cbfe2dea9e2c6a281f0655b714e","observation_id":"c44ceddb-f0ae-478d-8a7e-7b80e61fb878","resolution":{"observed_at":"2026-08-10T15:18:53.016881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:52.993822Z","title":"Splitgnn: Spectral graph neural network for fraud detection against heterophily","venue":null,"work_id":"bc761f3b-571b-4872-9b36-a595f27c5124","year":2023},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.886462Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:cd9acc8ac44c61798ffb6f616e4888fa519bcd7d2927d6a8ba32ee1ce3c086bd","observation_id":"b5ecace0-b365-45d5-89f8-2c1cbb5ff312","resolution":{"observed_at":"2026-08-10T15:18:52.999346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.18735","last_updated":"2023-10-28T15:35:34Z","snapshot_observed_at":"2026-08-19T20:37:55.475977Z","submitted_at":"2023-10-28T15:35:34Z","title":"Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First","version":1},"cited_work":{"arxiv_id":"2310.18735","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.18735","snapshot_observed_at":"2026-08-10T15:18:52.933633Z","title":"Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First","venue":"cs.LG","work_id":"4c9c4b4b-dc44-4cda-a5df-749e9cdc62dd","year":2023},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.891579Z"},"links":{"cited_paper":"/paper/2310.18735","citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:57c81fa5a4de75df5b43c4118d3d25d02104924cac5e58275ad4ad83d26c6afd","observation_id":"e1d74ca0-c5e0-48f8-a917-cd76f9ed9cac","resolution":{"observed_at":"2026-08-10T15:18:52.941646Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.093609Z","title":"Predicting dynamic embedding trajectory in temporal interaction networks","venue":null,"work_id":"20bfcc52-9b61-4dbc-baa7-9513b768d7d9","year":2019},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":1958,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.857348Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:efc8db139626ec5ebd5aa7e8f5727defd2c7fb4d14f15dd7355a872a418cfa04","observation_id":"6a5553cc-d016-4120-a999-6335f5f209f3","resolution":{"observed_at":"2026-08-10T15:18:53.098751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.110882Z","title":"The perceptron: a probabilistic model for information storage and organiza- tion in the brain","venue":null,"work_id":"019a59ef-0692-4d28-867e-ceacfc56933f","year":1958},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.853025Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:808a5176c76fc22a22c34169a43cc6b3705079912b9625b46a4276e705cd9216","observation_id":"168ab8b2-b44f-4a25-8ace-fc93c9a26a32","resolution":{"observed_at":"2026-08-10T15:18:53.116364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.196049Z","title":"A universal adaptive algorithm for graph anomaly detection","venue":null,"work_id":"0ddbe37d-8353-4dc8-aba7-529697d82933","year":2025},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.819091Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:41027dc21a3cb1ff1297343574d1957043d1e26e97d9d451e7dc5238c005d1ce","observation_id":"d279060d-5a64-41d8-95a2-df73842b502c","resolution":{"observed_at":"2026-08-10T15:18:53.202221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.213957Z","title":"F, and Singaraju Srinivasulu","venue":null,"work_id":"68602d24-129b-4044-a976-37ae6ed92092","year":2021},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.806909Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:63e15f5b341ff86caf3cab3c042146c33779aaf524d92eea5e58b7d1630c8ec1","observation_id":"1bfb3276-25be-4665-9e73-c4a726073ff2","resolution":{"observed_at":"2026-08-10T15:18:53.219073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.049177Z","title":"Curgraph: Curriculum learning for graph classification","venue":null,"work_id":"65651db5-1e17-4585-9506-11b0df93106d","year":2021},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.870902Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:d46c3d31dfd1020d0e893f12c08cf6ab2bd030188906d35cf47832b9f572ced3","observation_id":"37908ccb-ae80-46bc-a307-a9c664a0fa21","resolution":{"observed_at":"2026-08-10T15:18:53.053785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.247701Z","title":"Ad- dressing heterophily in graph anomaly detection: A per- spective of graph spectrum","venue":null,"work_id":"48167103-ac1f-47e1-ad5f-b6a1478afa2f","year":2023},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.794577Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:e80410c2cc013f91d1d0ebf6d735826647720c38b756897a88a898c53c26aaf8","observation_id":"2c3cb812-7c92-435c-bf19-663e7f4c6ffe","resolution":{"observed_at":"2026-08-10T15:18:53.253958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.265402Z","title":"Elhadad, Kin Fun Li, and Fayez Gebali","venue":null,"work_id":"f1df3ccf-4c69-4e66-951a-3871502eb71d","year":2019},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.788776Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:f1c04feda7a0e6116a388dee11f2122d1e3d79cb2e5f763779257ef4907edba9","observation_id":"8d8d7058-bab7-4e1f-8f0b-3e12a6690d43","resolution":{"observed_at":"2026-08-10T15:18:53.270444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.281598Z","title":"Enhancing graph neural network-based fraud detectors against camouflaged fraudsters","venue":null,"work_id":"8e0f7a3a-44a8-463a-b1cd-3283b6ac71ea","year":2020},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.783449Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:14022c23192505a87dacde035c7d15c02f0403c29d49c28945d5c5cd3a191dc5","observation_id":"291a18ed-9cc6-4746-b4fa-fd0e1fefc756","resolution":{"observed_at":"2026-08-10T15:18:53.286949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.299030Z","title":"Cuco: Graph representation with cur- riculum contrastive learning","venue":null,"work_id":"5b79cfdb-99d4-4fb7-8bfc-2867f053b257","year":2021},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.778811Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:d815667f3d01de03789f7ba5c069c332dc43c6014302e8b6aed50a408d1b6d2d","observation_id":"cb788e36-4cc5-416c-b777-771befbb734a","resolution":{"observed_at":"2026-08-10T15:18:53.305445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.231178Z","title":"Hamilton, Rex Ying, and Jure Leskovec","venue":null,"work_id":"8d7de69c-7f18-48de-af53-2aac0bb93bc9","year":2017},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.800998Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:8cce944e3fa0746e74bfe28a4f5a75dc6d7c5890edaeffb1888c9e360307c24e","observation_id":"99b5cc91-3808-4602-8dbf-e79c41bc10ce","resolution":{"observed_at":"2026-08-10T15:18:53.236810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.128846Z","title":"Collective opinion spam detection: Bridging re- view networks and metadata","venue":null,"work_id":"8e3216ca-3190-49c7-87a0-9dd043eda7a7","year":2015},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.848716Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:6ba4fd83d76df0448e7b86ec5265fb7a541604cda4b0fb952a116f0e0bbafc46","observation_id":"7c884a50-a4dc-48ab-bbae-be8ebcb682da","resolution":{"observed_at":"2026-08-10T15:18:53.134315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T15:18:53.179826Z","title":"Pick and choose: A gnn-based imbalanced learning approach for fraud detection","venue":null,"work_id":"6e83ee23-0786-42a6-861d-f5868fe9e323","year":2021},"citing_paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-10T15:18:52.825060Z"},"links":{"citing_paper":"/paper/2501.14197"},"observation_digest":"sha256:9f2606055756cf589d79f685cc229792691c22d2da4dc1e3d616c52188398d5b","observation_id":"dbab0a90-f243-4650-a1c8-683432335627","resolution":{"observed_at":"2026-08-10T15:18:53.184838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.14197","last_updated":"2025-01-24T03:01:16Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-21T15:16:10.711722Z","submitted_at":"2025-01-24T03:01:16Z","title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity"},"reference_resolution":{"displayed":23,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":1,"verified_fuzzy":19},"total_outbound_references":23},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2501.14197."}