{"as_of":"2026-08-20T18:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c729455bb57175f1d26c2abc819b00133a7b5ffbe7ebd8d977ccad0117176078","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T14:52:38.514233Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2607.14102/citation-record","integrity":"/paper/2607.14102/integrity","json":"/paper/2607.14102/citation-record.json","paper":"/paper/2607.14102"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:32.740664Z","title":"Biases in electronic health record data due to processes within the healthcare system: retrospec- tive observational study.Bmj, 361,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:32.740664Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:1db63bb48f83476d5bcc3b991fd5a3871f875369f6078d8db3f42dfc50f19d25","observation_id":"05a83cfe-bb46-4c04-9532-02d179eaf11f","resolution":{"observed_at":"2026-08-02T14:52:32.740664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:38.514233Z","title":null,"venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:38.514233Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:5c5eb4e9f883946a3b18789a61652b64ce28851e80281b4556048c0e87f16d9d","observation_id":"406d8bb9-6ce4-4aef-9b5d-d028cbea03e1","resolution":{"observed_at":"2026-08-02T14:52:38.514233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:33.945428Z","title":"Graph neural networks are dynamic program- mers.ArXiv,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:33.945428Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:d3632476305ec289ee9bf95f155e60d45942d2b00f85373e8abb18777813df32","observation_id":"c1105530-a67a-4015-9160-e9547d208870","resolution":{"observed_at":"2026-08-02T14:52:33.945428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.00476","last_updated":"2024-05-01T12:23:16Z","snapshot_observed_at":"2026-08-19T14:51:08.212543Z","submitted_at":"2024-05-01T12:23:16Z","title":"A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.00476","snapshot_observed_at":"2026-08-02T14:52:34.185889Z","title":"A compre- hensive survey of dynamic graph neural networks: Mod- els, frameworks, benchmarks, experiments and challenges","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:34.185889Z"},"links":{"cited_paper":"/paper/2405.00476","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:1ad6b5aecb67d5cbb6bab54b2cdcd5745edceef657040081bc113f082f7b72d1","observation_id":"22b5c8a8-91c9-448e-9c7c-418dcc6e78f3","resolution":{"observed_at":"2026-08-02T14:52:34.185889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:34.611281Z","title":"Inductive representation learning on large graphs.Advances in neural information processing sys- tems, 30,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:34.611281Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:f0b8a18ae76e97be66910a08e0f9a2414156aa6cbb2ff354cfb8cc9bbfdb7088","observation_id":"c25eece7-9463-48cc-97d9-7c40de8edbae","resolution":{"observed_at":"2026-08-02T14:52:34.611281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:34.665518Z","title":"Evaluating build- ing performance in healthcare facilities using entropy and graph heuristic theories.Scientific Reports, 12(1):8973,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:34.665518Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:ccef379c155668e279fb1a406a99395c684003d1bfa75916ddfb0a9510a78114","observation_id":"8699d17c-9d17-4016-8a0d-95523ab3b273","resolution":{"observed_at":"2026-08-02T14:52:34.665518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:34.789237Z","title":"Approximation capabilities of multilayer feedforward networks.Neural networks, 4(2):251–257,","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:34.789237Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:7e0bf18805136d63c60ea2027f63cf4bf1352a65693287cb348dab7a5243bc33","observation_id":"c6dffe34-54f4-4bd2-824d-2f72bcefa789","resolution":{"observed_at":"2026-08-02T14:52:34.789237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:35.119764Z","title":"A review of content-based and context-based recommendation systems.International Journal of Emerging Technologies in Learning (iJET), 16(3):274–306,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:35.119764Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:da5e7a76bbecc7c96cbe2a9c20cb5b652b827e488c66af699796dca409ed7e67","observation_id":"ff98e425-87c1-4a28-8ed7-0818ad2ea9a8","resolution":{"observed_at":"2026-08-02T14:52:35.119764Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-02T14:52:35.515419Z","title":"Semi-supervised classification with graph convolutional networks.arXiv preprint arXiv:1609.02907,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:35.515419Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:0e4bedce4229423a22d9c39878de884572330c4429044aa4126988cbf2c3b182","observation_id":"5dd9a8ee-0efe-466a-8a22-001502f660c5","resolution":{"observed_at":"2026-08-02T14:52:35.515419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:35.829659Z","title":"Ontological user profiling in recommender systems.ACM Transactions on Information Systems (TOIS), 22(1):54–88,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:35.829659Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:5a2c7dadacf2772e41c918d1d1f475c57f75487278720a1706a92b6c355335f2","observation_id":"ed06b3c7-655a-4569-948b-16ed747719bc","resolution":{"observed_at":"2026-08-02T14:52:35.829659Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:36.541329Z","title":"Sentence-bert: Sentence embeddings using siamese bert-networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:36.541329Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:0a01e7020f09db257374aeb64d1d6454a47ec71009989814b09609bd4e426064","observation_id":"4c047c99-6c05-4de0-8ecc-63a78a4a4ef2","resolution":{"observed_at":"2026-08-02T14:52:36.541329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10637","last_updated":"2020-10-09T11:39:32Z","snapshot_observed_at":"2026-08-19T14:15:32.053566Z","submitted_at":"2020-06-18T16:06:18Z","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10637","snapshot_observed_at":"2026-08-02T14:52:36.870956Z","title":"Temporal graph networks for deep learning on dynamic graphs.arXiv preprint arXiv:2006.10637,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:36.870956Z"},"links":{"cited_paper":"/paper/2006.10637","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:dcecf22eefdf0a675a013bdc18305cba43b01306351d7b09751f9801d02996e2","observation_id":"f3b551f5-c6b5-45f0-8850-3c6029ede553","resolution":{"observed_at":"2026-08-02T14:52:36.870956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:37.202766Z","title":"Freedyg: Frequency enhanced continuous-time dynamic graph model for link prediction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:37.202766Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:8750aedb8ba284d2c70be72f6d2561d46043ecbf97dd4bd24c9167842a517cf3","observation_id":"21e59ffc-f1e8-45b7-b4f4-b118f2072882","resolution":{"observed_at":"2026-08-02T14:52:37.202766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-08-13T22:35:40.714745Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-02T14:52:37.410007Z","title":"Graph attention networks.arXiv preprint arXiv:1710.10903,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:37.410007Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:212311e0b3d8856982ae0eab66f57ea09ea67320daea6bf587b5bdde3545b08b","observation_id":"d25a084d-840f-4dfc-9daa-33826cb98c3d","resolution":{"observed_at":"2026-08-02T14:52:37.410007Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:37.543458Z","title":"Review on mining data from multiple data sources.Pattern Recognition Letters, 109:120–128,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:37.543458Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:7da3f7400172e51597e278e72ea9faf617114a450567032681f3f2f521ca2266","observation_id":"276a50eb-0ee7-4f17-8ead-aa2447b6f14b","resolution":{"observed_at":"2026-08-02T14:52:37.543458Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.06339","last_updated":"2021-05-13T14:50:45Z","snapshot_observed_at":"2026-08-16T18:24:56.787941Z","submitted_at":"2021-05-13T14:50:45Z","title":"Graph Learning based Recommender Systems: A Review","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.06339","snapshot_observed_at":"2026-08-02T14:52:37.631840Z","title":"Graph learning based recommender systems: A review.arXiv preprint arXiv:2105.06339,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:37.631840Z"},"links":{"cited_paper":"/paper/2105.06339","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:92421037b529441330bab466921b8fff3771e9b64e8c0e795bbac6edff79c031","observation_id":"ebc2f609-a003-4cec-ac6a-6dce61129842","resolution":{"observed_at":"2026-08-02T14:52:37.631840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:37.719334Z","title":"A com- prehensive survey on graph neural networks.IEEE trans- actions on neural networks and learning systems, 32(1):4– 24,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:37.719334Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:8f3c7ac677ef982e30568d3872234ada82b15eba64bcc5aaea2c270813134bc1","observation_id":"6e498e69-c308-4759-892e-f65fb011ad8c","resolution":{"observed_at":"2026-08-02T14:52:37.719334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:37.807048Z","title":"A survey of data representation for multi- modality event detection and evolution.Applied Sciences, 12(4):2204,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:37.807048Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:64638217f472b3d0417f58bfd38e075ee52925e5c4c974ae2f6b82c8b82eec36","observation_id":"0d9a39fe-76c3-49ab-9a32-87c5cbb55d13","resolution":{"observed_at":"2026-08-02T14:52:37.807048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07962","last_updated":"2020-02-19T02:05:37Z","snapshot_observed_at":"2026-08-18T19:24:58.405240Z","submitted_at":"2020-02-19T02:05:37Z","title":"Inductive Representation Learning on Temporal Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07962","snapshot_observed_at":"2026-08-02T14:52:37.898405Z","title":"Inductive representation learning on temporal graphs.arXiv preprint arXiv:2002.07962,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:37.898405Z"},"links":{"cited_paper":"/paper/2002.07962","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:27cb5dc2556af17b763596876f6a8deb7bf6444223e8dd63c8c825bf6178c03b","observation_id":"d733a91e-601f-463e-b691-aeca49f51983","resolution":{"observed_at":"2026-08-02T14:52:37.898405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:37.979609Z","title":"How neural networks extrapolate: From feedforward to graph neural networks.ICLR,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:37.979609Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:b4d05a8720ba186cfb48405ec49871baaad4f00b65d9170a8c2ec097b8111b9d","observation_id":"0f35ff6a-9ea0-4ce8-a75b-07d296b57724","resolution":{"observed_at":"2026-08-02T14:52:37.979609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09034","last_updated":"2023-08-04T05:08:44Z","snapshot_observed_at":"2026-08-16T16:07:52.845690Z","submitted_at":"2022-12-18T08:17:32Z","title":"Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09034","snapshot_observed_at":"2026-08-02T14:52:38.071261Z","title":"Graph neural networks are inherently good generalizers: Insights by bridging gnns and mlps","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:38.071261Z"},"links":{"cited_paper":"/paper/2212.09034","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:a06988b4799ce81d5bed2b37a87e438cfb5e5a20926c826cfb8944c629e9ae71","observation_id":"be2db689-c64a-49eb-9244-5dca0bf0ebd5","resolution":{"observed_at":"2026-08-02T14:52:38.071261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:38.153267Z","title":"How graph neural networks learn: Lessons from training dynamics in function space","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:38.153267Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:d8b4d3b80eb939183dd81fe636166bdef66582e14a9666727d60a555de5b4196","observation_id":"ed2a165f-2ca6-49db-984f-e883176e8f98","resolution":{"observed_at":"2026-08-02T14:52:38.153267Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:38.209091Z","title":"Dynamic graph representation learning with neural networks: A survey.Ieee Access, 12:43460–43484,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:38.209091Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:b854de2f02ed0f25a3956e8f9253d9c14078874cd2291c08b7a2b976b1dadf2e","observation_id":"ff2b516f-284e-4781-9395-1b1255e2b082","resolution":{"observed_at":"2026-08-02T14:52:38.209091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:38.292074Z","title":"Towards better dynamic graph learning: New architec- ture and unified library.Advances in Neural Information Processing Systems, 36:67686–67700,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:38.292074Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:e05d66bc3010977e2734a89f39e2856c05331fb3b82e03e0642aec9b2e585060","observation_id":"9327f190-1b70-4023-aee5-2aa16c950606","resolution":{"observed_at":"2026-08-02T14:52:38.292074Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:38.348568Z","title":"Financial knowledge graph based financial report query system.IEEE Access, 9:69766– 69782,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:38.348568Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:8c2027a1b8adc2995a53719bdb43d6df47f53c8897d022f77e1dfa3ccb80a8ea","observation_id":"b19fa94e-8592-43ff-bf85-ee22f48b45a0","resolution":{"observed_at":"2026-08-02T14:52:38.348568Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:38.403030Z","title":"A dy- namic attributes-driven graph attention network modeling on behavioral finance for stock prediction.ACM Trans- actions on Knowledge Discovery from Data, 18(1):1–29,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:38.403030Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:6652780c8d7cd65587597deec6ad1f4cfd7f667094b970425015ae13f29e83b2","observation_id":"be5dd4c1-83c9-427f-9af6-9fbb36650a11","resolution":{"observed_at":"2026-08-02T14:52:38.403030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:38.457644Z","title":"Graph neural networks: A review of methods and applications.AI open, 1:57–81,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:38.457644Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:f92c46a500dc15186f73968895c9b305013abc2c706ab6c2aee5ffd1972d4996","observation_id":"dac7d94a-fc03-4261-ba6c-c692c5f61c8a","resolution":{"observed_at":"2026-08-02T14:52:38.457644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:33.183191Z","title":"Numerics of gram-schmidt or- thogonalization.Linear Algebra and Its Applications, 197:297–316,","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":1967,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:33.183191Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:64cae606ec753a6ff6e7b6b59ef2b82fad90fa80b69cfafa7f5aaefd6a97fb02","observation_id":"d89d5053-a5a6-4dd3-b1aa-653dae25253d","resolution":{"observed_at":"2026-08-02T14:52:33.183191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:34.900533Z","title":"Socialrec: User activ- ity based post weighted dynamic personalized post recom- mendation system in social media","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":1991,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:34.900533Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:094988d7f3b2a2128868da776b29675cb1f3c6df60d22d2b659789a8c4231660","observation_id":"0f729cf4-f19f-481f-82a7-6f3ec361d2f4","resolution":{"observed_at":"2026-08-02T14:52:34.900533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06784","last_updated":"2025-06-06T19:36:51Z","snapshot_observed_at":"2026-08-18T13:39:08.138744Z","submitted_at":"2025-02-10T18:58:40Z","title":"RelGNN: Composite Message Passing for Relational Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06784","snapshot_observed_at":"2026-08-02T14:52:33.356484Z","title":"Relgnn: Composite message passing for relational deep learning.arXiv preprint arXiv:2502.06784,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":1994,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:33.356484Z"},"links":{"cited_paper":"/paper/2502.06784","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:ff88f01e63dad1fc70993f1eff314fcbfe9f5a6f043ec77c042713039ebacf1f","observation_id":"41018045-400d-444e-acab-3259cbb47f51","resolution":{"observed_at":"2026-08-02T14:52:33.356484Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:36.119487Z","title":"Classifier ensembles: Select real-world applications.In- formation fusion, 9(1):4–20,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2003,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:36.119487Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:be3ed6dfc6fffdc974da6b35cb83cd72a46daa425a5c09f361a3df42d90a3512","observation_id":"7de8fee6-6fff-4561-b772-fbdd2e6293a9","resolution":{"observed_at":"2026-08-02T14:52:36.119487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:35.951538Z","title":"Asset trees and asset graphs in financial markets","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2004,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:35.951538Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:0bcfe27693dd2044b82341d275b81d210d3edbc45ddd1d5e5bc9eebc7d2f11f8","observation_id":"bbe04102-4f9d-409b-a612-3c09e99789d0","resolution":{"observed_at":"2026-08-02T14:52:35.951538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:36.322511Z","title":"A survey on graph database man- agement techniques for huge unstructured data.Interna- tional Journal of Electrical and Computer Engineering, 8(2):1140,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:36.322511Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:6c10c44ddeb50b66d94a275280a81da90f07686abcaec99ed948b024044b9a9b","observation_id":"058aebb0-0dcd-4edf-bdf1-a70e5144eaf8","resolution":{"observed_at":"2026-08-02T14:52:36.322511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:37.110088Z","title":"Foundations and modeling of dy- namic networks using dynamic graph neural networks: A survey.iEEE Access, 9:79143–79168,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:37.110088Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:ba96aad34db1839055631cf89fa4bba30fb9381bdd176c42ccda13238fe085a5","observation_id":"5d03102d-4795-4548-a9d0-2423922f9cd3","resolution":{"observed_at":"2026-08-02T14:52:37.110088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:35.332372Z","title":"Making a graph database from unstruc- tured text","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:35.332372Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:ed070a039fb2a83487ff9fba8b9eeb7712ae58621fab220027300776fd8461bc","observation_id":"6ac3bc5b-93bd-4b9a-8eb0-41af15b80e80","resolution":{"observed_at":"2026-08-02T14:52:35.332372Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:35.399018Z","title":"Lightgbm: A highly efficient gradient boost- ing decision tree.Advances in neural information process- ing systems, 30,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:35.399018Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:b53b6ff7871cd67deb0c97b661ea8a95d130baefb0451bf0d3635de804cb75a8","observation_id":"1eddce29-81b8-4822-8da1-fab762fe1782","resolution":{"observed_at":"2026-08-02T14:52:35.399018Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:33.763193Z","title":"Patient access to medical records and healthcare outcomes: a systematic review.Jour- nal of the American Medical Informatics Association, 21(4):737–741,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:33.763193Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:98b0374d9d2ed0b995994b3adad7a69b30211a04e2219dc372ee100e9273b3c2","observation_id":"a557e488-6107-42ca-8c61-44448e7d140c","resolution":{"observed_at":"2026-08-02T14:52:33.763193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:35.655413Z","title":"Gram-schmidt orthogonalization: 100 years and more.Numerical Linear Algebra with Applications, 20(3):492–532,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:35.655413Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:42ae03964fd5584b2f55b695f393838fbcb4aa4ed6519b7852eff5a2f8512e5c","observation_id":"24fe113f-ca08-4968-9676-f4b07f2a0857","resolution":{"observed_at":"2026-08-02T14:52:35.655413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:33.023805Z","title":"Solving linear least squares problems by gram-schmidt orthogonalization.BIT Numer- ical Mathematics, 7(1):1–21,","venue":null,"work_id":null,"year":1967},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:33.023805Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:58076fc8ac988416f5ee3b9ad2da89285e7d3d1c51d8bf8cbbb20b3ce338f8ad","observation_id":"ed31ba01-a830-4eb0-a23a-c08075c096a4","resolution":{"observed_at":"2026-08-02T14:52:33.023805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:32.856422Z","title":"Graph- based semantic web service composition for healthcare data integration.Journal of healthcare engineering, 2017(1):4271273,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:32.856422Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:6fef5374d66524b9683f38af7f63f4094e717975fc9250e27a323753b83ab08a","observation_id":"36928088-4891-44fc-8016-747bd8fa79d0","resolution":{"observed_at":"2026-08-02T14:52:32.856422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:36.745891Z","title":"Relbench: A benchmark for deep learning on relational databases.Advances in Neural Information Processing Systems, 37:21330–21341,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:36.745891Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:2d5b8e44080620cddd1f78a78b5a39fbf8f40833d989b6408dd33f3650e0e9dc","observation_id":"581346d8-bd06-48dc-b61c-c57be49186cb","resolution":{"observed_at":"2026-08-02T14:52:36.745891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:36.972950Z","title":"Transaction logs.Applications of social research methods to questions in information and library science, pages 166–177,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:36.972950Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:5a8491a18c8295e8a47d20cec54e568ce7c67025e75c937c0fbcfaf3399102ba","observation_id":"d9ec1e73-13ce-42bc-83cf-a10e24c76efd","resolution":{"observed_at":"2026-08-02T14:52:36.972950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:35.236230Z","title":"Towards structured log analysis","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:35.236230Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:5a36b81bf28a1e6537be4c57303ff1cfd05045baa81365be6ab397c9caa35b3a","observation_id":"e38a1d32-8fbd-4b1b-ad89-c626d4879d17","resolution":{"observed_at":"2026-08-02T14:52:35.236230Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.16654","last_updated":"2025-06-19T23:51:38Z","snapshot_observed_at":"2026-08-18T07:28:50.927294Z","submitted_at":"2025-06-19T23:51:38Z","title":"Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.16654","snapshot_observed_at":"2026-08-02T14:52:34.064678Z","title":"Relational deep learning: Challenges, foundations and next-generation architectures.arXiv preprint arXiv:2506.16654,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:34.064678Z"},"links":{"cited_paper":"/paper/2506.16654","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:6558c96e86f66528f8b41bef6151bd790b6ccd5c315c7c7266fc6dd50373472a","observation_id":"3393861e-d46e-4287-a35c-e61155833986","resolution":{"observed_at":"2026-08-02T14:52:34.064678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T14:52:34.441359Z","title":"Exiting the risk as- sessment maze: A meta-survey.ACM Computing Surveys (CSUR), 51(1):1–30,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:34.441359Z"},"links":{"citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:0f58c6bbdf605ef8ec9927d02903c1794975705779676a102ed314686698e045","observation_id":"7830b0e5-37de-4fe6-8bf8-1e4743094b7a","resolution":{"observed_at":"2026-08-02T14:52:34.441359Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.04615","last_updated":"2023-12-07T18:51:41Z","snapshot_observed_at":"2026-08-17T12:05:36.545797Z","submitted_at":"2023-12-07T18:51:41Z","title":"Relational Deep Learning: Graph Representation Learning on Relational Databases","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.04615","snapshot_observed_at":"2026-08-02T14:52:34.303291Z","title":"Relational deep learning: Graph representation learning on relational databases.arXiv preprint arXiv:2312.04615,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:34.303291Z"},"links":{"cited_paper":"/paper/2312.04615","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:bad4e2bf98bf076d5d42dfb46d21bffa2098b746401ce66e95c2319cbbd8f547","observation_id":"aef72cfc-56b2-4bdd-b5c0-829e97c9aad2","resolution":{"observed_at":"2026-08-02T14:52:34.303291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.3555","last_updated":"2014-12-11T06:46:53Z","snapshot_observed_at":"2026-08-20T00:41:09.240026Z","submitted_at":"2014-12-11T06:46:53Z","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.3555","snapshot_observed_at":"2026-08-02T14:52:33.533958Z","title":"Empirical evalua- tion of gated recurrent neural networks on sequence mod- eling.arXiv preprint arXiv:1412.3555,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T14:52:33.533958Z"},"links":{"cited_paper":"/paper/1412.3555","citing_paper":"/paper/2607.14102"},"observation_digest":"sha256:a5e95185f54388fd472af6a52c4f2f06efcd7f06645420c1928d05f8beb419d5","observation_id":"18e280b3-233b-44e7-af49-1fa0d6900657","resolution":{"observed_at":"2026-08-02T14:52:33.533958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.14102","last_updated":"2026-05-06T07:48:48Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-18T12:02:19.232186Z","submitted_at":"2026-05-06T07:48:48Z","title":"UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":47,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":47},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2607.14102."}