{"as_of":"2026-08-13T08:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:af9351740f2f4f73c36fa3b633e4861821651947674c9de2ede318d64d1e1c6e","coverage":[{"denominator":72,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":72,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T15:02:32.508565Z","state":"measured"},{"denominator":72,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":72,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2411.14718/citation-record","integrity":"/paper/2411.14718/integrity","json":"/paper/2411.14718/citation-record.json","paper":"/paper/2411.14718"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2108.10733","last_updated":"2021-09-08T07:18:10Z","snapshot_observed_at":"2026-07-06T11:41:07.033574Z","submitted_at":"2021-08-24T13:46:19Z","title":"Graph Neural Networks: Methods, Applications, and Opportunities","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.10733","snapshot_observed_at":"2026-08-12T15:02:32.134251Z","title":"Graph neural networks: Methods, applications, and opportunities,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.134251Z"},"links":{"cited_paper":"/paper/2108.10733","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:c76fabcb4b29a63da21a2847e090ca449734cf7a4d15c6e19a580afb3bce5475","observation_id":"9821ddf3-bb31-45ba-a5b0-76c1bf4e325e","resolution":{"observed_at":"2026-08-12T15:02:32.134251Z","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":"2026-08-12T15:02:34.649596Z","title":"Local differential private spatio- temporal dynamic graph learning for wireless social networks,","venue":null,"work_id":"437c4218-e980-4ddd-a626-210c60640c40","year":2024},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.143336Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:1bc6bb70fb05edea09f66b5bb73e1460671afd68f655d00e83385f793a65f904","observation_id":"c04cd7bb-9655-4fe9-a2cd-bfb1f0d7d737","resolution":{"observed_at":"2026-08-12T15:02:34.655301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.620687Z","title":"Relevance-aware anomalous users detection in social network via graph neural network,","venue":null,"work_id":"78bc1ce3-3a40-426a-a4f2-50fb3b3de992","year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.148750Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:83f24ed9eea53604d52a2cc16ae17a2fac371325e84accf76afa3d733068f6f6","observation_id":"b9936d15-2af0-42c9-ab1d-be5f44af4e9f","resolution":{"observed_at":"2026-08-12T15:02:34.631309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:32.155955Z","title":"LR-GNN: a graph neural network based on link representation for predicting molecular associations,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.155955Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:be73da2a9f1846d3b34c9bdc6aded8f3f94c3154fd2839b0b2719afc7fd2a8c4","observation_id":"2ba4bfe5-01fe-4a4e-b3a7-058e5f3d8d8f","resolution":{"observed_at":"2026-08-12T15:02:32.155955Z","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":"2026-08-12T15:02:32.160582Z","title":"Pre-training graph neural networks for link prediction in biomedical networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.160582Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:ca9b4e20ac460b7ab60fa5efecd8028e31e78c64c5029a5d8094fd17fbfe8def","observation_id":"fbc56bf3-27ca-4f9a-8d0c-bfa7f365cc89","resolution":{"observed_at":"2026-08-12T15:02:32.160582Z","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":"2026-08-12T15:02:32.166020Z","title":"Consisrec: Enhancing gnn for social recommendation via consistent neighbor aggregation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.166020Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:f4d9aee8fdd431c81e579403bb45e9bfd18c76bef40da07ad4149c2f86b2feb7","observation_id":"21ab3643-cfa9-40ad-b927-2c8c0cb0ace2","resolution":{"observed_at":"2026-08-12T15:02:32.166020Z","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":"2026-08-12T15:02:32.172992Z","title":"Dskreg: Differentiable sampling on knowledge graph for recommendation with relational gnn,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.172992Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:ece6a7ef24ae7ffe3ca89d9cd8d0a63338b8de60e923fd705c87385471d3b71d","observation_id":"e360f4ef-a5c2-4063-b048-c0bbd7b09aba","resolution":{"observed_at":"2026-08-12T15:02:32.172992Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/s41467-018-04948-5","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:32.584616Z","title":"Prioritizing network communities,","venue":null,"work_id":"d8fa0623-b1ce-439a-a422-b451a3802295","year":2018},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.179237Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:c10bf28aa7c077c0ae42b24da535de41a514bb57ec04e43d1769cd0d70c59c0c","observation_id":"da934daa-e9e1-4d3a-bbf5-269a0612c2fa","resolution":{"observed_at":"2026-08-12T15:02:32.589618Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1021/acs.jcim.7b00087","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:32.567369Z","title":"Demystifying multitask deep neural networks for quantitative structure–activity relationships,","venue":null,"work_id":"f11abc4a-33d0-4170-bc9a-11e1802b7a37","year":2017},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.184495Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:6e5f9f20a2f7fabc7bf03302e1af6fb6a7f42a07c5fba0f26a9397754bd39cf5","observation_id":"62bac7e7-7419-4d50-8bf2-9c2dc1cca207","resolution":{"observed_at":"2026-08-12T15:02:32.574871Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08682","last_updated":"2022-01-16T18:28:21Z","snapshot_observed_at":"2026-08-13T08:04:01.751140Z","submitted_at":"2021-04-18T02:20:37Z","title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08682","snapshot_observed_at":"2026-08-12T15:02:32.190370Z","title":"Rethinking network pruning – under the pre-train and fine-tune paradigm,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.190370Z"},"links":{"cited_paper":"/paper/2104.08682","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:b2fc87d65d93070fb1373d89976b782d0433c7f8967977104d96bfa983f4db77","observation_id":"310fb90b-b517-46ec-b81a-2eb9f1beed01","resolution":{"observed_at":"2026-08-12T15:02:32.190370Z","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":"2026-08-12T15:02:32.195847Z","title":"All in one: Multi-task prompting for graph neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.195847Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:ac829790159433c14459bf7ac84014816e81a51e6a94051d204c12fa8a6cf744","observation_id":"3f3e2ae7-3649-4aaa-8454-3165a2570106","resolution":{"observed_at":"2026-08-12T15:02:32.195847Z","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":"2026-08-12T15:02:32.200682Z","title":"Gppt: Graph pre-training and prompt tuning to generalize graph neural networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.200682Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:7f6c672e00c9f78f53767304613378a64ac4318712d8967bdbb8a8ca37de15f7","observation_id":"b0d61029-626b-4183-a744-8140f9e89360","resolution":{"observed_at":"2026-08-12T15:02:32.200682Z","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":"2026-08-12T15:02:34.587833Z","title":"Graphprompt: Unifying pre-training and downstream tasks for graph neural networks,","venue":null,"work_id":"e9c97029-0c43-4be3-ad0a-463f326f3906","year":2023},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.204954Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:59cd6d3737b4c5f3159314e174edf12f2e2d741b7055cc9fd04c86dc3044873d","observation_id":"e47e95a6-f25c-4d15-a413-5a1d2ad69694","resolution":{"observed_at":"2026-08-12T15:02:34.598416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.569847Z","title":"Universal prompt tuning for graph neural networks,","venue":null,"work_id":"2925b07e-68cb-4980-b84f-4e0d16d5a418","year":2023},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.209870Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:75afd1e58e69e9bee89120d22a719f35cf22ac57eee07887b0183703f0a14977","observation_id":"1edfc88d-8a62-42ab-8ee7-dd44a28ed34f","resolution":{"observed_at":"2026-08-12T15:02:34.575327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.549889Z","title":"Hgprompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learn- ing,","venue":null,"work_id":"5aa5e449-9cbf-4e84-969f-b3d2b8a6597d","year":2023},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.216650Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:19ec0f42bb30a1b1dff28d31fb81ccf1d5055c5c2953e79135ea398a8e9ff0b0","observation_id":"fcb199b3-45aa-4ed2-892f-b08268c2d9f3","resolution":{"observed_at":"2026-08-12T15:02:34.557770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.517117Z","title":"Multigprompt for multi-task pre-training and prompting on graphs,","venue":null,"work_id":"106df9c5-abc8-4b1c-86de-b5d32a14633b","year":2024},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.221187Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:a53f6eba8284e838450046fa4eb693c02d95392fda939d6afdf979a2c556d8a1","observation_id":"cff27c8a-aaf7-4322-91d3-02f64bcee8d1","resolution":{"observed_at":"2026-08-12T15:02:34.523249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.05661","last_updated":"2024-07-03T01:29:20Z","snapshot_observed_at":"2026-08-13T05:29:22.160315Z","submitted_at":"2023-11-09T08:00:32Z","title":"Prompt Engineering a Prompt Engineer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.05661","snapshot_observed_at":"2026-08-12T15:02:32.226115Z","title":"Prompt engineering a prompt engineer,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.226115Z"},"links":{"cited_paper":"/paper/2311.05661","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:c96e270d70a12d48a40307b2ead99b397591cc26553d430a8ae62cddeefc9de9","observation_id":"d51d5bf3-521f-4639-bec5-d9930d0682bf","resolution":{"observed_at":"2026-08-12T15:02:32.226115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-06T15:24:34.790850Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-12T15:02:32.233674Z","title":"The power of scale for parameter-efficient prompt tuning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.233674Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:3f52b0221a862279c3d8d02b4aa8eec0f4bac2a1d0beb4fc56b1258014350c0d","observation_id":"bf380c03-3014-4f5c-9c0d-ea0644a89f86","resolution":{"observed_at":"2026-08-12T15:02:32.233674Z","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":"2026-08-12T15:02:32.239319Z","title":"Locally private graph neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.239319Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:05df14451bde6b4f0cf19fb332d212f2b912b451783139badd7f17db7020f14a","observation_id":"366eff6b-ecd9-4e22-b33e-37ab01b0ab5a","resolution":{"observed_at":"2026-08-12T15:02:32.239319Z","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":"2026-08-12T15:02:34.501600Z","title":"Gap: differentially private graph neural networks with aggregation perturbation,","venue":null,"work_id":"882fe44e-d764-4faf-9519-40dbfeba0f51","year":2023},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.243637Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:09040087280a0e17d051902bd279172a8000c7090f3f4209e0bea05d985bca59","observation_id":"e3f4ec47-e79d-4d08-be25-0bc2b72a611d","resolution":{"observed_at":"2026-08-12T15:02:34.506498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.475972Z","title":"Differentially private decoupled graph convolutions for multigranular topology protection,","venue":null,"work_id":"5a4bfa21-1a6c-4760-8169-9bbe202214b9","year":2024},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.247843Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:038e1000d3569afa0593163f2e4e44007ae400da62ccd7c83192ec0962e540b1","observation_id":"a9d73d22-c07a-4c50-ac0e-36652388077b","resolution":{"observed_at":"2026-08-12T15:02:34.484792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:32.252147Z","title":"Linkguard: Link locally privacy-preserving graph neural networks with integrated denoising and private learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.252147Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:22f3ff4964fbb34286c477217e412e7bc27d40f1f0193a6dca6623d271e4db0a","observation_id":"5f30599f-bdd1-49ad-9bb5-e79289874b3d","resolution":{"observed_at":"2026-08-12T15:02:32.252147Z","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":"2026-08-12T15:02:34.456036Z","title":"Lingcn: structural lin- earized graph convolutional network for homomorphically encrypted inference,","venue":null,"work_id":"6a50d13f-afb6-4dbf-9bbd-208df35b6d71","year":2024},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.257611Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:ffd098719a56f89646817f99d675f26ae3eff68b4fba20c8b39df28ae9282d0c","observation_id":"44050ac6-193d-4503-a603-63424cff5c67","resolution":{"observed_at":"2026-08-12T15:02:34.462734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.08271","last_updated":"2021-06-23T17:40:26Z","snapshot_observed_at":"2026-08-07T11:54:00.711153Z","submitted_at":"2020-03-18T15:22:51Z","title":"Pre-trained Models for Natural Language Processing: A Survey","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.08271","snapshot_observed_at":"2026-08-12T15:02:32.273823Z","title":"Pre-trained models for natural language processing: A survey,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.273823Z"},"links":{"cited_paper":"/paper/2003.08271","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:84cb1828fbe10110d5a0983a2deaa317e740f029f6e4b76aca80832809c1245e","observation_id":"9a792ed2-535f-4934-abcb-d90a6087b3e4","resolution":{"observed_at":"2026-08-12T15:02:32.273823Z","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":"2026-08-12T15:02:34.431257Z","title":"SciBERT: A pretrained language model for scientific text,","venue":null,"work_id":"393d733d-7d74-463c-9765-406caea704b3","year":2019},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.279589Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:d8602b9feb8930dce614da6b93f2f48061a5fede6de68859977725e368d74874","observation_id":"333baff3-ee65-45c2-ae15-3d9b028f5e09","resolution":{"observed_at":"2026-08-12T15:02:34.438154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.07356","last_updated":"2022-05-03T21:31:58Z","snapshot_observed_at":"2026-08-10T11:23:41.263502Z","submitted_at":"2022-04-15T07:33:06Z","title":"Vision-and-Language Pretrained Models: A Survey","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.07356","snapshot_observed_at":"2026-08-12T15:02:32.285130Z","title":"Vision-and- language pretrained models: A survey,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.285130Z"},"links":{"cited_paper":"/paper/2204.07356","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:23262443d5cf4f5766ee3fc0ca2079757ab32f4c4c68ce7c22912184bf520514","observation_id":"3d5bbb44-52cd-496e-b4a5-1d1d19be0ba7","resolution":{"observed_at":"2026-08-12T15:02:32.285130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08254","last_updated":"2022-09-03T14:11:33Z","snapshot_observed_at":"2026-07-06T11:19:34.705520Z","submitted_at":"2021-06-15T16:02:37Z","title":"BEiT: BERT Pre-Training of Image Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08254","snapshot_observed_at":"2026-08-12T15:02:32.289558Z","title":"Beit: BERT pre-training of image transformers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.289558Z"},"links":{"cited_paper":"/paper/2106.08254","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:6314b2ead538d4a0a8b54cf6afb84773df5f69b53d903bf1764d376b8b1c0499","observation_id":"1b769cb5-7e55-4e72-9b84-1eb670edcc87","resolution":{"observed_at":"2026-08-12T15:02:32.289558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07893","last_updated":"2022-03-21T01:52:33Z","snapshot_observed_at":"2026-08-12T22:05:45.194431Z","submitted_at":"2022-02-16T07:00:52Z","title":"A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.07893","snapshot_observed_at":"2026-08-12T15:02:32.293362Z","title":"A survey of pretraining on graphs: Taxonomy, methods, and applications,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.293362Z"},"links":{"cited_paper":"/paper/2202.07893","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:eab01dc7ec64a0483178041b87800ce532153fb75e22bcff72690d00a3d871e6","observation_id":"fe82c18e-eb9a-4235-bcfd-1ca60e19a403","resolution":{"observed_at":"2026-08-12T15:02:32.293362Z","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":"2026-08-12T15:02:34.409806Z","title":"Strategies for pre-training graph neural networks,","venue":null,"work_id":"1f29274d-537b-4044-8f3f-70590dc3b418","year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.297580Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:6a68d4daecf798b9838f3b9dfd8791d39b47964f2f95fb5eed2150d1de5e3eec","observation_id":"a0613577-2e76-4be6-8444-9b249c065876","resolution":{"observed_at":"2026-08-12T15:02:34.418964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.10341","last_updated":"2018-12-21T15:44:59Z","snapshot_observed_at":"2026-07-06T07:04:37.077852Z","submitted_at":"2018-09-27T04:53:24Z","title":"Deep Graph Infomax","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.10341","snapshot_observed_at":"2026-08-12T15:02:32.305975Z","title":"Deep graph infomax,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.305975Z"},"links":{"cited_paper":"/paper/1809.10341","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:ad18a479c5015fc3f045a311e3a5fb1833f021d364d1de9452d74c96153c8511","observation_id":"b852dbcb-897d-4ab0-92fb-da5b28407b7a","resolution":{"observed_at":"2026-08-12T15:02:32.305975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07308","last_updated":"2016-11-21T11:37:17Z","snapshot_observed_at":"2026-08-06T06:17:37.090691Z","submitted_at":"2016-11-21T11:37:17Z","title":"Variational Graph Auto-Encoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.07308","snapshot_observed_at":"2026-08-12T15:02:32.312214Z","title":"Variational graph auto-encoders,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.312214Z"},"links":{"cited_paper":"/paper/1611.07308","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:b83d9f1a29a48fb092b3f3cd815a79487372305748de8d2cf13debb3b1ca2451","observation_id":"2f23aa93-258e-4cff-a940-acd5973b74d0","resolution":{"observed_at":"2026-08-12T15:02:32.312214Z","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":"2026-08-12T15:02:32.316947Z","title":"Graphmae: Self-supervised masked graph autoencoders,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.316947Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:f657d2bd39137a238244d1a8b8343af31f4daf5f0c36c4d5ea80dbfe96065e05","observation_id":"4be44cbe-af97-44a9-b9aa-62368fc271dd","resolution":{"observed_at":"2026-08-12T15:02:32.316947Z","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":"2026-08-12T15:02:34.389742Z","title":"Graph contrastive learning with augmentations,","venue":null,"work_id":"d9921e3c-eb2e-4f0f-8678-d90c2d9d3d56","year":2020},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.321845Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:f546d215588b616ec2828dc45ddbf96856c9de191534b3a3a455fc2fdf988d61","observation_id":"ef8fa5d4-372d-4b07-9d06-7a8f6502ae0e","resolution":{"observed_at":"2026-08-12T15:02:34.395953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:32.326856Z","title":"Simgrace: A simple framework for graph contrastive learning without data augmentation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.326856Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:7c42bd6238b24a32006f7cd46f9225317c0210581bef48db4c18b5ed9a25a038","observation_id":"5a687bf1-e5b8-4b01-806b-f533917dcbe4","resolution":{"observed_at":"2026-08-12T15:02:32.326856Z","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":"2026-08-12T15:02:34.370294Z","title":"Prog: A graph prompt learning benchmark,","venue":null,"work_id":"e0bbfafa-ff97-4bd9-aef3-cfe74a711665","year":2024},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.332395Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:6060514b0cc624999f7eaf8f9f83cbc8e3922be5202993e9a3b11b026e6de6bd","observation_id":"5e31e98a-2f39-4ea4-9800-0f67db7cf1bc","resolution":{"observed_at":"2026-08-12T15:02:34.377083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.01246","last_updated":"2018-12-14T19:39:43Z","snapshot_observed_at":"2026-08-08T03:39:28.408433Z","submitted_at":"2018-06-04T17:38:42Z","title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.01246","snapshot_observed_at":"2026-08-12T15:02:32.336727Z","title":"Ml- leaks: Model and data independent membership inference attacks and defenses on machine learning models,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.336727Z"},"links":{"cited_paper":"/paper/1806.01246","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:6a4961760f385a8b17e447d3ca36ed6310cf47a06b37b838f23173607e732250","observation_id":"06530568-7d36-4f57-a54d-ec26629f323f","resolution":{"observed_at":"2026-08-12T15:02:32.336727Z","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":"2026-08-12T15:02:34.321264Z","title":"Membership inference attacks against machine learning models,","venue":null,"work_id":"b0124aae-a4f5-48de-8f5e-047098921046","year":2017},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.346339Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:ebcfe4b67c096203ddfce7aaf03805840c9bd672807f4153d566327793fd91a0","observation_id":"3db8ccc3-8c53-4404-a4ce-82cca2f43c5b","resolution":{"observed_at":"2026-08-12T15:02:34.328028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.301120Z","title":"Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences,","venue":null,"work_id":"ffda0b3e-b66f-495d-b13a-04ddb30e40d9","year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.350693Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:da3cc8d05dbf7f4972e2abfa826b772ccb7564e66b3b00019db696443c59da9a","observation_id":"d5232e98-282c-4699-9938-aa8d6bedbcd9","resolution":{"observed_at":"2026-08-12T15:02:34.307235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.267525Z","title":"Random forests,","venue":null,"work_id":"da9b7586-c972-4a35-8daa-d148f5c0e116","year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.359466Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:8fc655407d79d6dbec0121fce5ce1b56ffeca564d07b48c47f62807371571745","observation_id":"eb3ac8cf-f634-4df4-8d63-482a77378463","resolution":{"observed_at":"2026-08-12T15:02:34.274090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.05429","last_updated":"2021-02-10T13:51:54Z","snapshot_observed_at":"2026-08-12T10:03:11.480813Z","submitted_at":"2021-02-10T13:51:54Z","title":"Node-Level Membership Inference Attacks Against Graph Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.05429","snapshot_observed_at":"2026-08-12T15:02:32.367591Z","title":"Node-level membership inference attacks against graph neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.367591Z"},"links":{"cited_paper":"/paper/2102.05429","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:36fb9a815fd8f95e882d1e9cb80ea29821035bb659f2e7f1779f77b2ec60a13f","observation_id":"22b2e3c5-9651-4778-8535-5288bb61c293","resolution":{"observed_at":"2026-08-12T15:02:32.367591Z","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":"2026-08-12T15:02:34.229356Z","title":"Deep Graph Infomax,","venue":null,"work_id":"cfb633cc-318f-416b-a3b6-1d68f82053e9","year":2019},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.372591Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:f357925cef6d6ca72751a4f710d8b3d343fd33e7a6e53e6ec7f513f0a77f1e3a","observation_id":"3e6c0bd4-b303-4402-a63e-ead9fada1ef1","resolution":{"observed_at":"2026-08-12T15:02:34.233865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.02131","last_updated":"2020-10-05T20:38:16Z","snapshot_observed_at":"2026-08-11T02:22:03.911690Z","submitted_at":"2020-05-05T13:22:35Z","title":"Stealing Links from Graph Neural Networks","version":2},"cited_work":{"arxiv_id":"2005.02131","doi":null,"metadata_source":"pith","pith_arxiv_id":"2005.02131","snapshot_observed_at":"2026-08-12T15:02:33.151952Z","title":"Stealing Links from Graph Neural Networks","venue":"cs.CR","work_id":"b5363028-b658-4487-9579-508bdba25ee7","year":2020},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.377089Z"},"links":{"cited_paper":"/paper/2005.02131","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:f8390122e9b4df64711ae0bb3ca753cbb1f3334533c71c4ca48d3e862998bb45","observation_id":"bced7818-a747-4601-a040-40aa7ecdaad8","resolution":{"observed_at":"2026-08-12T15:02:33.159053Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.215789Z","title":"Data fine-tuning,","venue":null,"work_id":"de6bcd3f-dee3-4d25-a837-2324b812f5de","year":2019},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.381732Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:3de4914ce259224d115648518d3f9dca54cf8099764ded4e0abf76f55b3987ae","observation_id":"d570ffa9-8a21-4b86-8bc4-7be574c3df41","resolution":{"observed_at":"2026-08-12T15:02:34.220054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.06146","last_updated":"2018-05-23T09:23:47Z","snapshot_observed_at":"2026-08-12T22:43:22.928789Z","submitted_at":"2018-01-18T17:54:52Z","title":"Universal Language Model Fine-tuning for Text Classification","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.06146","snapshot_observed_at":"2026-08-12T15:02:32.386289Z","title":"Universal language model fine- tuning for text classification,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.386289Z"},"links":{"cited_paper":"/paper/1801.06146","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:544fbddae3aa1e02a3e21b119e4f646baef3ddcea98d8802826c024d0cc6be72","observation_id":"3e3af275-13d1-451b-9cb3-51230962e1f9","resolution":{"observed_at":"2026-08-12T15:02:32.386289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.08737","last_updated":"2018-11-21T14:02:03Z","snapshot_observed_at":"2026-08-07T10:00:08.817459Z","submitted_at":"2018-11-21T14:02:03Z","title":"SpotTune: Transfer Learning through Adaptive Fine-tuning","version":1},"cited_work":{"arxiv_id":"1811.08737","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.08737","snapshot_observed_at":"2026-08-12T15:02:33.090682Z","title":"SpotTune: Transfer Learning through Adaptive Fine-tuning","venue":"cs.CV","work_id":"1a92d05f-d6e3-4794-abf0-1eeeccf9bcfa","year":2018},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.390787Z"},"links":{"cited_paper":"/paper/1811.08737","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:06d5a01f941b357afcb2fd126b9de0a2e76291fe70e5536c9f5baacd183b734a","observation_id":"04d7a552-8212-4e79-850c-579dd0e75b62","resolution":{"observed_at":"2026-08-12T15:02:33.107035Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07927","last_updated":"2025-03-16T06:23:34Z","snapshot_observed_at":"2026-08-05T17:55:26.008016Z","submitted_at":"2024-02-05T19:49:13Z","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07927","snapshot_observed_at":"2026-08-12T15:02:32.395523Z","title":"A systematic survey of prompt engineering in large language models: Techniques and applications,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.395523Z"},"links":{"cited_paper":"/paper/2402.07927","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:837dee9f1092822195eb3ac1762208b9a89769684aa7885acc03a0560911e7fe","observation_id":"32d475c1-772f-44fc-86fb-646735dd1da6","resolution":{"observed_at":"2026-08-12T15:02:32.395523Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-08-12T12:37:28.207761Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-12T15:02:32.400200Z","title":"Prefix-tuning: Optimizing continuous prompts for generation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.400200Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:1ef94d50b972aa20dc33403040ad1e7427d4716387998d5db1904f0e272b4d5b","observation_id":"1327ebb9-c7a3-4664-b520-627f83ce239f","resolution":{"observed_at":"2026-08-12T15:02:32.400200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.13586","last_updated":"2021-07-28T18:09:46Z","snapshot_observed_at":"2026-07-06T11:33:25.933445Z","submitted_at":"2021-07-28T18:09:46Z","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.13586","snapshot_observed_at":"2026-08-12T15:02:32.405286Z","title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.405286Z"},"links":{"cited_paper":"/paper/2107.13586","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:5fc17f5aa1a5ac125a27e83f81ba8ff5a487d1c8f4e7758dab52183a18bf0698","observation_id":"3aef8a5a-e3ec-46d0-9550-16c6da3fd219","resolution":{"observed_at":"2026-08-12T15:02:32.405286Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-08-12T09:14:21.453940Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-12T15:02:32.410155Z","title":"Exploring visual prompts for adapting large-scale models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.410155Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:310a5860b7760a88e381cde26fb5efa0b55741137d17bc0b1d329692567c96c7","observation_id":"984c5862-a7fe-48fc-8962-af041bad7a2c","resolution":{"observed_at":"2026-08-12T15:02:32.410155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.00647","last_updated":"2022-09-01T17:59:33Z","snapshot_observed_at":"2026-08-12T04:31:42.830497Z","submitted_at":"2022-09-01T17:59:33Z","title":"Visual Prompting via Image Inpainting","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.00647","snapshot_observed_at":"2026-08-12T15:02:32.415020Z","title":"Visual prompting via image inpainting,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.415020Z"},"links":{"cited_paper":"/paper/2209.00647","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:5d0780f6129aa37b80d168dfd9d641f5b78b418310f8de7b234c77319038f845","observation_id":"73123378-8686-48e2-a650-4791a5f534db","resolution":{"observed_at":"2026-08-12T15:02:32.415020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08138","last_updated":"2023-03-14T17:59:59Z","snapshot_observed_at":"2026-07-06T15:03:20.851932Z","submitted_at":"2023-03-14T17:59:59Z","title":"Diversity-Aware Meta Visual Prompting","version":1},"cited_work":{"arxiv_id":"2303.08138","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.08138","snapshot_observed_at":"2026-08-12T15:02:32.965724Z","title":"Diversity-Aware Meta Visual Prompting","venue":"cs.CV","work_id":"d40077bb-0ccd-44fe-badb-67934bd6ba07","year":2023},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.419553Z"},"links":{"cited_paper":"/paper/2303.08138","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:62b814e590e2e7f6e5d93c1276609481ebeba5fa44469ec39c47baeaef6397cc","observation_id":"2c6541eb-2209-417b-a315-a805464e27bf","resolution":{"observed_at":"2026-08-12T15:02:32.970671Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12449","last_updated":"2023-08-15T08:11:16Z","snapshot_observed_at":"2026-08-10T02:41:21.086048Z","submitted_at":"2023-02-24T04:31:18Z","title":"SGL-PT: A Strong Graph Learner with Graph Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12449","snapshot_observed_at":"2026-08-12T15:02:32.424930Z","title":"Sgl-pt: A strong graph learner with graph prompt tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.424930Z"},"links":{"cited_paper":"/paper/2302.12449","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:ba500f3edc32a46888625f08131d97a3520040f53457a6fcef6699ee75c300f6","observation_id":"87e39325-a6c6-4bc5-9692-84847305fa11","resolution":{"observed_at":"2026-08-12T15:02:32.424930Z","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":"2026-08-12T15:02:32.429731Z","title":"Hetgpt: Harnessing the power of prompt tuning in pre-trained heterogeneous graph neural networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.429731Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:227a766b41a0df9f72f1bffbf91df6a4d389d0a59c42062b90929d2dcbf94d31","observation_id":"49cd226c-1032-455d-98e0-d568cb20074f","resolution":{"observed_at":"2026-08-12T15:02:32.429731Z","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":"2026-08-12T15:02:34.199569Z","title":"Ultra-dp: Unifying graph pre-training with multi-task graph dual prompt,","venue":null,"work_id":"ba6c05e2-1b9e-40e2-9d31-d98dd4d17e30","year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.436398Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:cd3f73f14f0450f5dc11cfb9b1b33115e80051258e0f15523508b959136158b5","observation_id":"48e0946c-de39-4a7a-8b37-de487f9bd636","resolution":{"observed_at":"2026-08-12T15:02:34.203823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10362","last_updated":"2024-06-04T08:31:15Z","snapshot_observed_at":"2026-08-13T05:48:31.034822Z","submitted_at":"2023-10-16T12:58:04Z","title":"Self-Pro: A Self-Prompt and Tuning Framework for Graph Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10362","snapshot_observed_at":"2026-08-12T15:02:32.447972Z","title":"Prompt tuning for multi-view graph contrastive learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.447972Z"},"links":{"cited_paper":"/paper/2310.10362","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:9dc29f8c26070ad87024753adfe0c58dcb40b998cc0637b7a6f47aca6a19d6d0","observation_id":"df7f8718-3fa7-47ad-be34-7b176c246a96","resolution":{"observed_at":"2026-08-12T15:02:32.447972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17394","last_updated":"2024-06-01T06:31:26Z","snapshot_observed_at":"2026-08-13T05:39:52.588603Z","submitted_at":"2023-10-26T13:46:18Z","title":"PSP: Pre-Training and Structure Prompt Tuning for Graph Neural Networks","version":2},"cited_work":{"arxiv_id":"2310.17394","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.17394","snapshot_observed_at":"2026-08-12T15:02:32.808532Z","title":"PSP: Pre-Training and Structure Prompt Tuning for Graph Neural Networks","venue":"cs.LG","work_id":"87456270-800c-4d90-ac54-897cc4e35ae9","year":2023},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.453897Z"},"links":{"cited_paper":"/paper/2310.17394","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:90f8b3811e6943be4356988876bc7b70c6f9b2ae6b21a7fc26f2f4f1485fec8b","observation_id":"190748b9-0e80-454b-9a11-4fa9857f9751","resolution":{"observed_at":"2026-08-12T15:02:32.814383Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.184363Z","title":"Inference attacks against graph neural networks,","venue":null,"work_id":"95f65739-8cf0-425a-a6f0-121587c9d736","year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.459394Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:d5a6b3e5f7675b5945d9e8b798c1359e1ec1752e30ff0de471d73df584543902","observation_id":"123b1db7-02fb-42c3-b62f-01eb79d3bc90","resolution":{"observed_at":"2026-08-12T15:02:34.189417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.164021Z","title":"Group property inference attacks against graph neural networks,","venue":null,"work_id":"3ee0ad45-390f-4d2e-b7bc-ae067a126f0f","year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.463952Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:0168853386a405a34e906a2b098501971f00fd2324cf179535fb92c3775cc570","observation_id":"66ce1809-f1ce-4d0d-bf1f-22b8232aa3db","resolution":{"observed_at":"2026-08-12T15:02:34.170794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.147185Z","title":"node2vec: Scalable feature learning for networks,","venue":null,"work_id":"b90416f3-90b1-42ae-a8cd-b3d2788e6052","year":2016},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.468232Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:7dc6f081c0609547c16b4f795ffe176c8b0409c8f8154f613d209a2e42f91ff3","observation_id":"43fcca73-a83c-4ea1-a001-3843cb2e2331","resolution":{"observed_at":"2026-08-12T15:02:34.153213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.131491Z","title":"Link prediction based on graph neural networks,","venue":null,"work_id":"f6cf1131-9911-4f65-bab3-44dbd0a8d076","year":2018},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.472127Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:0fd56487968ae948710a1aec86fa8487e913b6ff2fa870fdbdeb231cd645f660","observation_id":"da7ea430-42cf-4799-a342-5a0635b4c53f","resolution":{"observed_at":"2026-08-12T15:02:34.136175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.115114Z","title":"walk2friends: Inferring social links from mobility profiles,","venue":null,"work_id":"e484cc48-c601-4d9a-bf04-3141e67656e8","year":2017},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.475982Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:e195114248d3be177c4ae199d1854a1fa1984533e71c2d044ea36cd3dc8e16b6","observation_id":"d9a04a3c-13c5-448c-886f-5e49adeb5e31","resolution":{"observed_at":"2026-08-12T15:02:34.120777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.096992Z","title":"Linkteller: Recovering private edges from graph neural networks via influence analysis,","venue":null,"work_id":"455cdc9a-cc4b-49ba-ab60-a1fbf269f6fc","year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.479884Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:12feb4fcf7a9d804cce0a89e82b278be42706570cf29312600d4b0f5fa6c4c2b","observation_id":"35ee879d-e87d-4e6e-8df8-edbc7c9a265d","resolution":{"observed_at":"2026-08-12T15:02:34.103878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.075837Z","title":"Inference attacks against graph neural networks,","venue":null,"work_id":"7bed3cdc-77d6-41a8-9afd-0ca50795458e","year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.490115Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:a4ed25b61b84febf36b7ce587af42a74f72fab6c6bf94db141ef96fcf23d4af7","observation_id":"4097159f-1895-49d7-8420-6a157e024fff","resolution":{"observed_at":"2026-08-12T15:02:34.080601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:32.495398Z","title":"Quantifying privacy leakage in graph embedding,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.495398Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:0a4171b70765b0a757a26ebe2e96f83c8b9b8f62d812d8c8ecaf06c237ce0d40","observation_id":"c1a4f4bb-5b81-45b5-8b1d-8c05b32ab7b6","resolution":{"observed_at":"2026-08-12T15:02:32.495398Z","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":"2026-08-12T15:02:32.499520Z","title":"Model extraction attacks on graph neural networks: Taxonomy and realisation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.499520Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:0593ac27bed2ac0fe564d56f184d1f5c8554a44e5952d153faa5b8d7d5bd4557","observation_id":"c45d0a45-5e98-4bbc-b96f-24c4e7284905","resolution":{"observed_at":"2026-08-12T15:02:32.499520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-08-12T15:02:32.508565Z","title":"Available: https://arxiv.org/abs/2108.04417 Appendix A Notations The key notations frequently used throughout this paper are summarized in Table 4","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.508565Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:2c90939f8280959c9103684eb31fed90ef3fd80e05afe5877af18c9d7c9f324e","observation_id":"275c42b7-3707-498b-8744-cd19dd410882","resolution":{"observed_at":"2026-08-12T15:02:32.508565Z","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":"2026-08-12T15:02:34.285168Z","title":"Available: https://www.sciencedirect.com/science/ article/pii/S1352231097004470","venue":null,"work_id":"d26239d0-fde8-466a-8509-43620d5be5b5","year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":1998,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.355405Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:e9af1eea3a221f24252af2f843d5524488e6d9189e87f0383f8c6fb17ed7279d","observation_id":"37724444-7f36-4202-97bf-6c225433ec56","resolution":{"observed_at":"2026-08-12T15:02:34.290588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.247925Z","title":"Available: https://api.semanticscholar.org/CorpusID: 89141","venue":null,"work_id":"88aec9d7-35eb-4648-be94-fc096ea08374","year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":2001,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.363480Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:0e3428c03601775fa4ffe91fe2ffe48ce2e1ed0ff881d2afd68cb91864c857ee","observation_id":"c162fe32-cadd-4f56-9f50-bfdeca7f68b3","resolution":{"observed_at":"2026-08-12T15:02:34.254976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:02:34.343312Z","title":"Available: https://api.semanticscholar.org/CorpusID: 46933970","venue":null,"work_id":"2c6571a8-56ad-40e7-a34d-b8d6de4aa4f8","year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.341614Z"},"links":{"citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:38f2c9c9b666e1c89ebd3d497cd0b787569a3d499b43ea7c9d0ca556e1bd3c72","observation_id":"e204a143-256a-4647-9219-5e5296f10956","resolution":{"observed_at":"2026-08-12T15:02:34.351278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.12265","last_updated":"2020-02-18T19:49:48Z","snapshot_observed_at":"2026-08-04T16:33:25.229105Z","submitted_at":"2019-05-29T08:11:52Z","title":"Strategies for Pre-training Graph Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.12265","snapshot_observed_at":"2026-08-12T15:02:32.301729Z","title":"Available: https://arxiv.org/abs/1905.12265","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.301729Z"},"links":{"cited_paper":"/paper/1905.12265","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:395a64ddbc32076241c9998b9e490af1d3fe8e7bc85e0cdfd11137eb8de477ab","observation_id":"bff32879-0fe1-4cba-ae18-ba41c0b27ff2","resolution":{"observed_at":"2026-08-12T15:02:32.301729Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07139","last_updated":"2021-08-11T06:48:47Z","snapshot_observed_at":"2026-08-12T09:28:52.787268Z","submitted_at":"2021-06-14T02:40:32Z","title":"Pre-Trained Models: Past, Present and Future","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07139","snapshot_observed_at":"2026-08-12T15:02:32.268449Z","title":"Available: https://arxiv.org/abs/2106.07139","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.268449Z"},"links":{"cited_paper":"/paper/2106.07139","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:f96790971750d58e0ba24185099b44a720e479c754d158817402466513ca213f","observation_id":"0782baa3-75b4-42f6-a881-2b50ca48a2ad","resolution":{"observed_at":"2026-08-12T15:02:32.268449Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14845","last_updated":"2023-12-17T08:16:44Z","snapshot_observed_at":"2026-08-13T05:43:11.947611Z","submitted_at":"2023-10-23T12:11:13Z","title":"ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14845","snapshot_observed_at":"2026-08-12T15:02:32.442131Z","title":"Available: https://arxiv.org/abs/2310.14845","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-12T15:02:32.442131Z"},"links":{"cited_paper":"/paper/2310.14845","citing_paper":"/paper/2411.14718"},"observation_digest":"sha256:ab7ac43125d93c162f5f646a4d5f7d27f334a9e5a0480db52c1de2e8ac90c104","observation_id":"55604f77-6bae-4c56-9a2e-2bf25d8edf34","resolution":{"observed_at":"2026-08-12T15:02:32.442131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.14718","last_updated":"2024-11-22T04:10:49Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-13T03:55:20.116454Z","submitted_at":"2024-11-22T04:10:49Z","title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning"},"reference_resolution":{"displayed":72,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":6,"verified_fuzzy":29},"total_outbound_references":72},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 72 of 72 outbound references and 0 inbound Pith citation observations for arXiv:2411.14718."}