{"as_of":"2026-08-19T00:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f5dffa49adaf61c14c648b0fcd64bc17158e6b2aae50b26459d7337329d2e3b2","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T21:58:47.206610Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:26:20.938452Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-10T05:30:23.456663Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-10T05:30:23.456663Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.03451","snapshot_observed_at":"2026-08-07T00:26:20.933649Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-14T07:25:53.578703Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.933649Z"},"links":{"cited_paper":"/paper/2501.03451","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:d988d6819cb275796e84e4803e92f287a1b7440e89989cb17cbeab40b9df926b","observation_id":"40f61ae3-65f6-45d4-a6e6-825b589bfe89","resolution":{"observed_at":"2026-08-07T00:26:20.933649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"cited_work":{"arxiv_id":"2501.03451","doi":"10.48550/arxiv.2501.03451","metadata_source":"pith","pith_arxiv_id":"2501.03451","snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","venue":"stat.ML","work_id":"cf6f97e8-f95c-421b-bd2e-d0c823effdb7","year":2025},"citing_paper":{"arxiv_id":"2506.14114","last_updated":"2025-06-17T02:12:19Z","snapshot_observed_at":"2026-08-14T07:25:53.578703Z","submitted_at":"2025-06-17T02:12:19Z","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T00:26:20.938452Z"},"links":{"cited_paper":"/paper/2501.03451","citing_paper":"/paper/2506.14114"},"observation_digest":"sha256:096ed827e1d9a6fb7622845c04756396c5d59d542a14449bbd0359eef9d9b0c9","observation_id":"b34df0ed-f01a-4782-92ef-8c3c108d98fe","resolution":{"observed_at":"2026-08-07T00:26:21.016694Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.03451/citation-record","integrity":"/paper/2501.03451/integrity","json":"/paper/2501.03451/citation-record.json","paper":"/paper/2501.03451"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:48.173228Z","title":"Deep learning with differential privacy,","venue":null,"work_id":"f8917086-b1e6-46b1-b7df-90d8afb6d501","year":2016},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:46.967492Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:ae9ab60675ae8870f3828720031f5ac6dda5d87469ee6d5d8dcbec4b555ec7cd","observation_id":"f322e4f3-66f1-49d4-a35f-95ab0853bfb5","resolution":{"observed_at":"2026-08-10T21:58:48.180387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:48.157766Z","title":"Secure deep graph generation with link differential privacy,","venue":null,"work_id":"7bf7929b-c710-4ac2-a20d-5610132f75b1","year":2021},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:46.972615Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:13528c7a415a2df755af774b949a9cc118df4008ec0a41a5485552cc8978d4aa","observation_id":"1d7b4bb1-93a5-45a3-a3b0-4094e72a05e3","resolution":{"observed_at":"2026-08-10T21:58:48.163713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.08907","last_updated":"2023-11-02T05:37:09Z","snapshot_observed_at":"2026-08-18T18:03:06.510336Z","submitted_at":"2021-09-18T11:35:19Z","title":"Releasing Graph Neural Networks with Differential Privacy Guarantees","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.08907","snapshot_observed_at":"2026-08-10T21:58:46.976613Z","title":"Releasing graph neu- ral networks with differential privacy guarantees,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:46.976613Z"},"links":{"cited_paper":"/paper/2109.08907","citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:074c5362a28fdbdb0c0a90e4e1b23cfc45a34eeb45a568ce10135eb0e618fdd1","observation_id":"48ced686-1c32-4d4d-813d-03d748baf39e","resolution":{"observed_at":"2026-08-10T21:58:46.976613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.15521","last_updated":"2022-08-26T19:12:58Z","snapshot_observed_at":"2026-08-18T08:47:10.632811Z","submitted_at":"2021-11-23T16:18:53Z","title":"Node-Level Differentially Private Graph Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.15521","snapshot_observed_at":"2026-08-10T21:58:46.981238Z","title":"Node-level differentially private graph neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:46.981238Z"},"links":{"cited_paper":"/paper/2111.15521","citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:41b77cab75db6fd66193982c3df3c5a33e85c0ccb0acb851fbfeedb403db5fcb","observation_id":"f581742c-dd49-4000-ab66-b7473a9e0cab","resolution":{"observed_at":"2026-08-10T21:58:46.981238Z","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":"2026-08-10T21:58:48.142840Z","title":"DPAR: Decoupled graph neural networks with node-level differential privacy,","venue":null,"work_id":"523839bd-eaed-411c-ae21-63f36c008b59","year":2024},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:46.985514Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:2334c4af175fe96f5ed39f8d4c81fc2cd59f479f3f4eb8120657bdb080f9c314","observation_id":"3bb263e7-48b3-454e-831c-e3c5cca414f8","resolution":{"observed_at":"2026-08-10T21:58:48.147986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:48.128085Z","title":"GAP: Differentially private graph neural networks with aggregation perturbation,","venue":null,"work_id":"63235457-7469-455e-82d3-6424f25fba81","year":2023},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:46.989475Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:b3d27c64cc32e33e9d372da023941cb8f82e966495597f54456f4bfda1c06136","observation_id":"991ca1b2-eac8-4248-a35c-f91ab5296e04","resolution":{"observed_at":"2026-08-10T21:58:48.133638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:48.112576Z","title":"ProGAP: Progressive graph neu- ral networks with differential privacy guarantees,","venue":null,"work_id":"6f12e9f4-0555-442a-bb89-b82e3e545542","year":2024},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:46.994294Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:069c89a4980b5ecb9332ff2ab8fe351a19f13311a487201f1a8217e1baa29931","observation_id":"a65b30e5-9038-44e7-ac6b-dbd63abde14b","resolution":{"observed_at":"2026-08-10T21:58:48.118420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:48.098856Z","title":"Preserving node-level privacy in graph neural networks,","venue":null,"work_id":"fccab9f8-9782-4d91-9a5b-7cca0be2c778","year":2024},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:46.998240Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:ec9b4e9ab24542446e74597e6745f2b0c2c2e4354aed997c5af2d3518622dcc0","observation_id":"7723b9a7-d505-4eb0-895b-5e8afaf9719a","resolution":{"observed_at":"2026-08-10T21:58:48.103741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:48.085218Z","title":"DeepWalk: Online learning of social representations,","venue":null,"work_id":"285156e6-8261-4922-9968-c8b025950c2a","year":2014},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.002970Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:cba6f158b1f6ea721fe0ed2d616ab5999c1ad9adae57e2d79d2eaac0b3c0bd5c","observation_id":"de12d44b-e838-4d50-9c52-ba7886620441","resolution":{"observed_at":"2026-08-10T21:58:48.090028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:48.053623Z","title":"LINE: Large-scale information network embedding,","venue":null,"work_id":"20f2383f-8892-4fb3-9b21-2600d225ce1a","year":2015},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.007787Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:c25e0b939a6ae7f22647fcbc90038044257992e37077c3ed8838a2c48788832a","observation_id":"93432558-14f8-458c-929a-484d475b277c","resolution":{"observed_at":"2026-08-10T21:58:48.058394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:48.039785Z","title":"PTE: Predictive text embedding through large-scale heterogeneous text networks,","venue":null,"work_id":"8074839d-6205-4ec0-b2c3-2121a2292946","year":2015},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.012316Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:1156c224c5dea16fe3374c67f9b094e171f31e91062fdf8f2173d4d7d7485973","observation_id":"718e8b2e-2a08-4fee-865a-0c2ae87c3eb4","resolution":{"observed_at":"2026-08-10T21:58:48.044573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:48.024694Z","title":"node2vec: Scalable feature learning for networks,","venue":null,"work_id":"ce2e9056-88be-4e8f-adf1-70acff2dcf18","year":2016},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.016607Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:8722d053e72edf09f4e8d324eb553bc42d63e4b4b48aad7f8d6490e12ec2d8c8","observation_id":"6f28bd69-ecfe-4090-9d6f-6245fcf56a40","resolution":{"observed_at":"2026-08-10T21:58:48.030205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.999362Z","title":"Dynamic network embedding: An extended approach for skip-gram based network em- bedding,","venue":null,"work_id":"e0f7a731-6efd-455b-b5b7-d7a73f80426e","year":2018},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.020636Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:ecd880375d61c73a3bb31e5e6a171b7fce508c7ee826e54571105a4e0042aa53","observation_id":"f35d8913-e573-4d48-856e-cd384edd506b","resolution":{"observed_at":"2026-08-10T21:58:48.011822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.986594Z","title":"Calibrating noise to sensitivity in private data analysis,","venue":null,"work_id":"17eb0b05-dbb1-49b1-9479-bbfc567e470c","year":2006},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.024472Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:e4d47ccc9a6331f5ee72c56fdc34a1e66226e4682106d7af553863f5eb678478","observation_id":"c588aa5e-e642-4fb5-bd3d-19d1c9b35c82","resolution":{"observed_at":"2026-08-10T21:58:47.991278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.974002Z","title":"Accurate estimation of the degree distribution of private networks,","venue":null,"work_id":"b3897df1-a8af-440c-a7bf-e3d6b11903f6","year":2009},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.028311Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:fee93d683f30f4212f07ac141397c126101b0161bd80de2a1552c8244037bfe8","observation_id":"828d111b-1b4c-4833-b978-483bb55fb290","resolution":{"observed_at":"2026-08-10T21:58:47.978302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.962265Z","title":"Differential privacy,","venue":null,"work_id":"7f7737fc-1490-4c47-a6e2-fa8e2beec972","year":2006},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.032169Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:e449ae6454a71d880469e6b3a06f20fa15f04f0493e8f5efb2b818d08f0e08f1","observation_id":"7a8846f8-9b39-4b09-a8f9-36e804cb4f13","resolution":{"observed_at":"2026-08-10T21:58:47.966149Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.949973Z","title":"R ´enyi differential privacy,","venue":null,"work_id":"fd92569f-fbbf-4c02-90c7-53c78bb8dc9c","year":2017},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.036140Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:51d555753bd02dd30b0040dfef299221de53f38d36c2acf524aba19940199ab7","observation_id":"4b8afcc1-1eda-42bc-a86c-cc530ec44b76","resolution":{"observed_at":"2026-08-10T21:58:47.954337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.039956Z","title":"Emergence of scaling in random net- works,","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.039956Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:ffd449782483bcc0ad99e6d7cd1c2585f063058077096986a85921b37060b42a","observation_id":"76a693ba-229c-48e4-a75f-96f0e744c81b","resolution":{"observed_at":"2026-08-10T21:58:47.039956Z","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":"2026-08-10T21:58:47.043957Z","title":"Predicting missing links via local information,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.043957Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:d8c9a04bb962eab4b3eea8b98006bc41073942e37e84c25e97ae88321b232886","observation_id":"57aba991-ec73-453b-ba2c-7a45c7dbad9a","resolution":{"observed_at":"2026-08-10T21:58:47.043957Z","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":"2026-08-10T21:58:47.047772Z","title":"A new status index derived from sociometric analysis,","venue":null,"work_id":null,"year":1953},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.047772Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:e89b73b5f1d021e566cf6bbc37bb210482beb0b30ee4ad5f5a8c4e85f7185b84","observation_id":"8938e9f8-f7e5-4390-88d4-9a44ab125d39","resolution":{"observed_at":"2026-08-10T21:58:47.047772Z","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":"2026-08-10T21:58:47.915668Z","title":"Topic-sensitive pagerank,","venue":null,"work_id":"db8f33e1-a8bb-47a6-ba65-d510534f690a","year":2002},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.051234Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:a956ae163324064e5a52715dee402355152a6ddace7667e7cf30b6d92302b01a","observation_id":"d740a34b-576a-4b62-9e2f-67fb52d52b10","resolution":{"observed_at":"2026-08-10T21:58:47.920410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.902951Z","title":"Network repre- sentation learning with rich text information,","venue":null,"work_id":"3fa38e84-056b-4b99-9ba4-d8e63d25541d","year":2015},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.055089Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:1f8b6e0dd3e6bf6f8a87aaa48feac693804ba4776776de16b81f66f7e7bc9db5","observation_id":"5ad45082-dbad-4553-9505-e5253f54c26e","resolution":{"observed_at":"2026-08-10T21:58:47.907090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.890396Z","title":"Model inversion attacks against collaborative inference,","venue":null,"work_id":"dcdfe36d-63e3-412a-b625-06b31029d340","year":2019},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.058624Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:99002b99b3f8016ad35194405cd5a7284b2099cae5f7d0ff45ffa01b425f3cf7","observation_id":"13bbac3b-386c-46f4-816d-b528a8b56b0a","resolution":{"observed_at":"2026-08-10T21:58:47.894482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.878257Z","title":"Network embedding as matrix factorization: Unifying DeepWalk, LINE, PTE, and node2vec,","venue":null,"work_id":"500e532d-d56d-434b-afd3-1eeaa26d9c1a","year":2018},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.062204Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:85be5b7b3c3fec51a1c4ce4ddc9f4f98581319ec6d8d1a5060ed2e388dcba739","observation_id":"38a82a04-8d51-4f60-97bd-755f12454686","resolution":{"observed_at":"2026-08-10T21:58:47.882158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.865911Z","title":"Subsampled r ´enyi differential privacy and analytical moments accountant,","venue":null,"work_id":"97751cf8-3fba-4466-b839-9b8ad50230f7","year":2019},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.065715Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:5dc933782e4dc1963482e59fe55a6633309f4a169c6f7e7f2c2f05bdf56a78c7","observation_id":"b0c482a7-c675-4b90-89e8-ec6330dcb206","resolution":{"observed_at":"2026-08-10T21:58:47.870214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.854668Z","title":"Poission subsampled r´enyi differential privacy,","venue":null,"work_id":"4da824a0-a1c8-4151-b7f0-e5b672f7b9cd","year":2019},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.069437Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:3924d67b4d2f95af9876543c2b0bec5e9ea3888aafc38f20ff1efaeb5d7f00a1","observation_id":"12662f01-b759-41a6-bf14-640782ccdf64","resolution":{"observed_at":"2026-08-10T21:58:47.858465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10530","last_updated":"2019-08-28T03:03:25Z","snapshot_observed_at":"2026-08-17T16:19:30.418133Z","submitted_at":"2019-08-28T03:03:25Z","title":"R\\'enyi Differential Privacy of the Sampled Gaussian Mechanism","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10530","snapshot_observed_at":"2026-08-10T21:58:47.072915Z","title":"R ´enyi differential privacy of the sampled gaussian mechanism,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.072915Z"},"links":{"cited_paper":"/paper/1908.10530","citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:5ec77ef57077ca4468460b5d960c9ad51556ecf402024c23ccf869d2cebc44bd","observation_id":"020740e0-9b50-4e36-859e-c436a623eb65","resolution":{"observed_at":"2026-08-10T21:58:47.072915Z","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":"2026-08-10T21:58:47.842939Z","title":"Differentially private opti- mization on large model at small cost,","venue":null,"work_id":"1c60e61d-e266-4206-87cc-df2c0770e82a","year":2023},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.077375Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:73fe9521a23febea1bb47896a3a298a86dd2c136f684e510cccc4c232c4f953a","observation_id":"bc257285-0a16-44f2-a463-1ff59e9c9191","resolution":{"observed_at":"2026-08-10T21:58:47.847952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.831398Z","title":"Toward understanding and evaluating structural node embeddings,","venue":null,"work_id":"7c12ba32-c4a5-4166-9b81-018caa875802","year":2021},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.080717Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:6a053cbb3ba1aca15dfaf0b5935d8c205b184875faffb9b9c18a59ec4dad4028","observation_id":"68dbdd67-f645-47ac-ba2c-6b737373b924","resolution":{"observed_at":"2026-08-10T21:58:47.835403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.819825Z","title":"BioGRID: A general repository for interaction datasets,","venue":null,"work_id":"d1a44610-5165-4891-8adb-91610ee1ab9b","year":2006},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.084306Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:23ff726090e44cd049d6db25cf31eff186f61769aa136d20de27eae9a1984db4","observation_id":"7736c840-a8d7-43ce-8109-8538ce3f5f32","resolution":{"observed_at":"2026-08-10T21:58:47.824206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.807108Z","title":"Link prediction based on graph neural networks,","venue":null,"work_id":"1e2fa3a5-a951-4cb7-9370-0a763f743763","year":2018},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.087895Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:89a54f8dfff0faebb8f06df9a4c10be56833c1252fa3191b13d29f86a05bf35a","observation_id":"b2407964-0d7a-4a31-ab6b-87b42f81491f","resolution":{"observed_at":"2026-08-10T21:58:47.811454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.792694Z","title":"Understanding and improvement of adversarial training for network embedding from an optimization perspective,","venue":null,"work_id":"7eeccd30-aff1-4203-b859-e71b1be70ab4","year":2022},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.091212Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:049f65f07d82ae732e0a0bec19ec19d13eb86e3af93f5114867c371b7a65839c","observation_id":"ae3bf576-3b19-4f5d-be48-edaf7526a419","resolution":{"observed_at":"2026-08-10T21:58:47.797322Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.778958Z","title":"PRUNE: Preserving proximity and global ranking for network embedding,","venue":null,"work_id":"954ab05a-cbe6-4557-8f83-f98e03b14b67","year":2017},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.094958Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:eacd2b2a9378455d2f0f75da3327b46010de33793a4f7ae5e8e10c4b8dd1faf9","observation_id":"1ae52ef8-3eb4-4913-9a69-ea96110f4e36","resolution":{"observed_at":"2026-08-10T21:58:47.784008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.765975Z","title":"A unified framework for community detection and network representation learning,","venue":null,"work_id":"905b4ab4-8f0b-4cf6-82fb-8d21277205e7","year":2018},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.098606Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:e941971fff13c3079d43aa6fdc817f37942de08c1348d303d1a3511cc4380894","observation_id":"79e4e000-78b4-4486-931f-ecde8a6e8673","resolution":{"observed_at":"2026-08-10T21:58:47.770559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.753115Z","title":"k-anonymity: A model for protecting privacy,","venue":null,"work_id":"508b7d75-3bce-4f78-af61-4f4f57b39057","year":2002},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.102349Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:92423f04eddde40027e1957707f06f32a58da64516bcfdb2498f08d1a262f268","observation_id":"68c79315-507b-4da0-9d9d-15b18164f1a7","resolution":{"observed_at":"2026-08-10T21:58:47.757458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.739462Z","title":"l-diversity: Privacy beyondk-anonymity,","venue":null,"work_id":"2f81400e-4b23-423a-a648-3f114c2d93d1","year":2007},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.106252Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:806fcc38e30a00bdf9e39dd2468f238e99810698b38c8af19187039a56f63ea1","observation_id":"bbb3aa44-3d3c-4c04-a00e-9d98e0a5ef60","resolution":{"observed_at":"2026-08-10T21:58:47.744495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.725057Z","title":"Private search on key-value stores with hierarchical indexes,","venue":null,"work_id":"e0637832-5a6d-4979-a86a-30760ac9bc3f","year":2014},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.109773Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:e16515e2cac8fcb33fd5157b62419323231948e3c701b461851e869c6c0c582b","observation_id":"4541e4b5-8ddd-4c2b-905e-a57296b14daa","resolution":{"observed_at":"2026-08-10T21:58:47.729781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.710764Z","title":"Differentially private empirical risk minimization,","venue":null,"work_id":"3f309460-a577-49f5-9e8d-48331bb134cc","year":2011},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.113665Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:33583045228c72bab95a4f3d137c84895999801a2ac1411f9f2b4f87c73307dc","observation_id":"eb14a931-cba4-441f-b23c-207f65d943aa","resolution":{"observed_at":"2026-08-10T21:58:47.715197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.697339Z","title":"Private empirical risk mini- mization: Efficient algorithms and tight error bounds,","venue":null,"work_id":"cd5c8bb9-7529-47ed-9fc0-c64bf1f1e14b","year":2014},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.117496Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:8cdbf7978ee2d1dd668598e3ad9f1544aa63a86848a8a4ebbd1565f4dea450a5","observation_id":"41c9a5ba-99aa-450e-a125-1fec46b38748","resolution":{"observed_at":"2026-08-10T21:58:47.701853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.683319Z","title":"CALM: Consistent adaptive local marginal for marginal release under local differential pri- vacy,","venue":null,"work_id":"e725d27a-018d-489f-9c2f-48c30a9c4e3c","year":2018},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.121425Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:f65d8bf4d8a33431462c537f4a49c002269a8ba7bc7081de94d5703eec474dae","observation_id":"0f735d58-41c1-42e0-bf9b-79a96003c3f1","resolution":{"observed_at":"2026-08-10T21:58:47.687977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.669226Z","title":"Beyond Value Perturbation: Local differential privacy in the temporal setting,","venue":null,"work_id":"cae95a91-8a54-400c-bc18-027660f07551","year":2021},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.125320Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:9e6e5a68aed443586ebf5e93af442d518547834e79d4e6e716c0461ab8bcaf69","observation_id":"65a0aa0e-0065-4f15-a7cf-8a7604353980","resolution":{"observed_at":"2026-08-10T21:58:47.673806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.655777Z","title":"PrivSyn: Differentially private data synthesis,","venue":null,"work_id":"c8b79043-1fe3-4328-8549-c781ade9be7b","year":2021},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.129226Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:b8c2d642633c5ba311b17c5df0f9a44fabef699978f1a5472a141f8636f9b2e1","observation_id":"e18f7846-c91b-4ff1-accc-a72c7c80834c","resolution":{"observed_at":"2026-08-10T21:58:47.660064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.641578Z","title":"Stateful Switch: Optimized time series release with local differential privacy,","venue":null,"work_id":"837baf8f-8b4b-47a9-9698-2fda9e029acb","year":2023},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.133047Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:52aa5d359e80a54f810d1b044ac5c59bb68ed00448765c2b74fb72bdf093818a","observation_id":"2bf25ffb-34f8-473b-844c-477052c08069","resolution":{"observed_at":"2026-08-10T21:58:47.646137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.625772Z","title":"Trajectory data collection with local differential privacy,","venue":null,"work_id":"0adbfe03-628e-4563-b971-96e71e58fb98","year":2023},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.137264Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:bd2c46339f643dec52f4ee99468d5c806b1a4a33ce2d3cbcf1e7584dbe15ccb8","observation_id":"30ae8d20-7b0a-48bc-897a-12a9049b8c95","resolution":{"observed_at":"2026-08-10T21:58:47.631505Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06963","last_updated":"2018-02-24T00:40:30Z","snapshot_observed_at":"2026-08-14T20:22:22.512463Z","submitted_at":"2017-10-18T23:46:57Z","title":"Learning Differentially Private Recurrent Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06963","snapshot_observed_at":"2026-08-10T21:58:47.141226Z","title":"Learning differentially private language models without losing accuracy,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.141226Z"},"links":{"cited_paper":"/paper/1710.06963","citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:c025d4d6252d8b47d2a249b8c5892b41db67b5852845ceedd42a48b46d971ffb","observation_id":"e873e818-0311-40da-b069-30042480c873","resolution":{"observed_at":"2026-08-10T21:58:47.141226Z","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":"2026-08-10T21:58:47.609639Z","title":"Stochastic gradient descent with differentially private updates,","venue":null,"work_id":"a92d15f9-63d9-45d6-8e9d-becba715e1ec","year":2013},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.145549Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:78d30968acdea0bdb831795f8d628a713f0ba944c82b66924e0a8f393f306c80","observation_id":"1fa82927-d033-43c3-9c28-1644b9798419","resolution":{"observed_at":"2026-08-10T21:58:47.614952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.595482Z","title":"Boosting and differential privacy,","venue":null,"work_id":"9cdd8d32-cd0d-4231-870b-b03fe11f5d8a","year":2010},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.149415Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:d53c8f1589fc8c9e8e21f2e9e248ae92eec87e052f0413adac1873128a871942","observation_id":"a7a11935-a1d7-43c6-ae2e-fd64bc3bd10d","resolution":{"observed_at":"2026-08-10T21:58:47.599681Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.581417Z","title":"Stochastic adaptive line search for differentially private optimization,","venue":null,"work_id":"516b9de1-5431-4bb2-94a1-ede024014378","year":2020},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.153307Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:a74c19fe041663d66f80df178a4e1deb99fad4012aa7a88fa3ae09b645c6c959","observation_id":"e0078622-6f90-4869-b8c6-528a7f7b2f62","resolution":{"observed_at":"2026-08-10T21:58:47.586472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.11524","last_updated":"2020-07-22T16:33:14Z","snapshot_observed_at":"2026-08-04T15:18:26.501887Z","submitted_at":"2020-07-22T16:33:14Z","title":"Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.11524","snapshot_observed_at":"2026-08-10T21:58:47.157127Z","title":"Improving deep learning with differential privacy using gradient encoding and denoising,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.157127Z"},"links":{"cited_paper":"/paper/2007.11524","citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:136ae2817ef47f57f8e0e6c8dbf6f7b78409d4ac854c68ba79f2e3e8adb06e4f","observation_id":"1037680e-d577-47ec-9609-3464cc731502","resolution":{"observed_at":"2026-08-10T21:58:47.157127Z","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":"2026-08-10T21:58:47.567425Z","title":"Tem- pered sigmoid activations for deep learning with differential privacy,","venue":null,"work_id":"36b17155-8d62-44c3-8643-7a5feb909c48","year":2021},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.161608Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:18bc6460bf178d4f8a39afd6514fff349513daa5728c0fd76c9fc9a567c07e85","observation_id":"ee9be2dd-94b8-4196-9760-1272af009136","resolution":{"observed_at":"2026-08-10T21:58:47.572393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.11660","last_updated":"2021-02-18T02:56:42Z","snapshot_observed_at":"2026-08-16T19:03:51.699473Z","submitted_at":"2020-11-23T19:00:52Z","title":"Differentially Private Learning Needs Better Features (or Much More Data)","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.11660","snapshot_observed_at":"2026-08-10T21:58:47.165539Z","title":"Differentially private learning needs better features (or much more data),","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.165539Z"},"links":{"cited_paper":"/paper/2011.11660","citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:d2d03f4db6bc65e100b710fe79c1ab59bd0aa9e24e3c4088865d005955322b7f","observation_id":"96975b6a-afab-4a79-98e3-7aa552df70bc","resolution":{"observed_at":"2026-08-10T21:58:47.165539Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.07643","last_updated":"2019-10-23T19:02:00Z","snapshot_observed_at":"2026-08-15T11:50:16.329843Z","submitted_at":"2019-08-20T23:19:21Z","title":"AdaCliP: Adaptive Clipping for Private SGD","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.07643","snapshot_observed_at":"2026-08-10T21:58:47.169984Z","title":"AdaCliP: Adaptive clipping for private SGD,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.169984Z"},"links":{"cited_paper":"/paper/1908.07643","citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:c2fb1e445e45338e47ebc65f7fe2a1b631b2a9dd9d0964deff945f68e2f3a29c","observation_id":"3cb3fb6f-87c0-4fb6-9001-ecc0d99c604e","resolution":{"observed_at":"2026-08-10T21:58:47.169984Z","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":"2026-08-10T21:58:47.553077Z","title":"Differentially-private deep learning from an optimization perspective,","venue":null,"work_id":"4619a9c0-d94d-4f56-acc0-5996ed88694c","year":2019},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.174546Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:a38e38571efd78a9adc3bce9bd72c4f1be60a091e5fc84fbe7fd12433168b829","observation_id":"7961c317-b3c9-4c78-bb1e-baa0daee953f","resolution":{"observed_at":"2026-08-10T21:58:47.558070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.538083Z","title":"Differentially private model publishing for deep learning,","venue":null,"work_id":"1414ecdf-16b8-4b41-a023-d5fcd1250f24","year":2019},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.178390Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:4ff2df36acb7230518f8772cac50060d177d513780e838c58107958c4937963e","observation_id":"fe16152f-aa8d-43dc-b207-55a168220f07","resolution":{"observed_at":"2026-08-10T21:58:47.543692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.523525Z","title":"DPSUR: Accelerating differentially private stochastic gradient descent using selective update and release,","venue":null,"work_id":"565bb582-f41e-4e92-8614-bba10ce1fdbc","year":2024},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.182309Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:cbfc46adaf7391ef3cb91b3e926fa96d7ae3353d2b3755a43720d635ef0cb95d","observation_id":"47020fcd-d161-4231-9b6e-198bf71c0c03","resolution":{"observed_at":"2026-08-10T21:58:47.528125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1301.3781","last_updated":"2013-09-07T00:30:40Z","snapshot_observed_at":"2026-07-06T03:04:11.148340Z","submitted_at":"2013-01-16T18:24:43Z","title":"Efficient Estimation of Word Representations in Vector Space","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1301.3781","snapshot_observed_at":"2026-08-10T21:58:47.186208Z","title":"Efficient estimation of word representations in vector space,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.186208Z"},"links":{"cited_paper":"/paper/1301.3781","citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:6a2f558652527cc4eb7b97ddbc366aa6ecf0a887bfb65bb593c04f252aefae1b","observation_id":"67f01072-32f4-4684-89de-9e4e9fa950a7","resolution":{"observed_at":"2026-08-10T21:58:47.186208Z","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":"2026-08-10T21:58:47.504051Z","title":"Distributed representations of words and phrases and their composi- tionality,","venue":null,"work_id":"09a77c9a-c9ff-4d19-949a-2dbe36ccb1a7","year":2013},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.190355Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:cbe10e548aa55259b9cd4e5ac07c4edd1d95de2a2c689d5062ebfd2657d7826c","observation_id":"b64d184b-17aa-4780-aa8e-459204cd1dec","resolution":{"observed_at":"2026-08-10T21:58:47.513370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.489021Z","title":"Differentially-private next- location prediction with neural networks,","venue":null,"work_id":"8e51293f-a8f8-4114-a1b1-c207836881a3","year":2020},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.194388Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:bb830652748ac55828fa3aefd915d56b22da105c0171200e43536efce21affae","observation_id":"5d29d0b2-e04b-4898-b2c9-ffa970226c62","resolution":{"observed_at":"2026-08-10T21:58:47.493892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.474830Z","title":"Differentially private fed- erated knowledge graphs embedding,","venue":null,"work_id":"ed201575-fd37-4227-86f5-88d09c804b40","year":2021},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.198444Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:4a50ce70c78168b351bf791e0013815a64834c4f40180070c2c8c19ce8a8eb0c","observation_id":"fe4ba573-4e66-40d4-8962-f4be99b314ae","resolution":{"observed_at":"2026-08-10T21:58:47.479305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.461347Z","title":"A framework for differentially-private knowledge graph embeddings,","venue":null,"work_id":"26572621-3f2a-4806-8ff8-ade891815abd","year":2022},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.202804Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:a413264c763ba6f66f3931c54a0e167e1c2f2f03d8d9fe98be92336491febe1f","observation_id":"5aa8626e-d800-49be-a213-9942756e6020","resolution":{"observed_at":"2026-08-10T21:58:47.465947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:58:47.442514Z","title":"FedWalk: Communication efficient federated unsu- pervised node embedding with differential privacy,","venue":null,"work_id":"f2c68ab6-c572-42f2-870b-5bb9db3ed9cc","year":2022},"citing_paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-10T21:58:47.206610Z"},"links":{"citing_paper":"/paper/2501.03451"},"observation_digest":"sha256:5f0118dd8cf8f254854fdb2803e221a4dc635581866b837bbfbced31f1015d8a","observation_id":"bc8b70dc-00f7-4b09-9bb8-98d94f31e86b","resolution":{"observed_at":"2026-08-10T21:58:47.450458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.03451","last_updated":"2025-01-07T00:43:18Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-15T07:03:13.543013Z","submitted_at":"2025-01-07T00:43:18Z","title":"Structure-Preference Enabled Graph Embedding Generation under Differential Privacy"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":50},"total_outbound_references":61},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 2 inbound Pith citation observations for arXiv:2501.03451."}