{"as_of":"2026-08-14T02:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c6d8fbefc41a3f72d19badb647302289a97763562c3ee3ab088521a02e405557","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:06:30.120001Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"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/2505.20026/citation-record","integrity":"/paper/2505.20026/integrity","json":"/paper/2505.20026/citation-record.json","paper":"/paper/2505.20026"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:06:33.586576Z","title":"Distributed learning: developing a predictive model based on data from multiple hospitals without data leaving the hospital–a real life proof of concept","venue":null,"work_id":"f5d187b0-652b-4967-917b-693edc440d4f","year":2016},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:27.284811Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:22aaeac8471a6360207f53b77439748ce7f1259421ac70c0f559e84d36477f45","observation_id":"feae195a-1416-4e98-9331-a1e7ce276949","resolution":{"observed_at":"2026-08-07T14:06:33.671712Z","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":"2026-08-07T14:06:27.366988Z","title":"Communication- efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:27.366988Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:1d658d937981d3dc50c12cdf16b564d0356091d6f97b7a57a9d6a33e78921250","observation_id":"a724989a-a1eb-4a6d-83da-e7373cf5bdff","resolution":{"observed_at":"2026-08-07T14:06:27.366988Z","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":"2026-08-07T14:06:33.415268Z","title":"Ffd: A federated learning based method for credit card fraud detection","venue":null,"work_id":"86f91a3f-efad-47ba-9b4a-d1bb9c9e6913","year":2019},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:27.463312Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:2b965375c391278811e9a9f52d531a6dd298082450f8f98e5a30ed1acacc8cbb","observation_id":"d15bb50a-7049-4dce-afb3-7d26d56046db","resolution":{"observed_at":"2026-08-07T14:06:33.481987Z","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":"2026-08-07T14:06:33.267367Z","title":"Evaluating gradient inversion attacks and defenses in federated learning","venue":null,"work_id":"ba276860-3254-4a74-8243-c6a5b8be97e1","year":2021},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:27.561957Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:a9e33a4666590e518ff5632ae2979c15fc8871416453558d9cea4893f9bb5290","observation_id":"77f84dc3-4393-42e1-8874-5e91574c03f6","resolution":{"observed_at":"2026-08-07T14:06:33.339386Z","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":"2026-08-07T14:06:33.058608Z","title":"Privacy-preserving deep learning: Revisited and enhanced","venue":null,"work_id":"b7f48b1d-3cfc-4390-8275-c61ae24ea12b","year":2017},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:27.631724Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:841e077fe734eed7f49254497291f01b8662eeac42debb37b69c626492e6810e","observation_id":"fc27139c-ac2e-4110-b16e-26205354ef56","resolution":{"observed_at":"2026-08-07T14:06:33.116197Z","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":"2026-08-07T14:06:32.881103Z","title":"Deep leakage from gradients","venue":null,"work_id":"55001256-8cad-4423-bd24-a4fd58673e92","year":2019},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:27.719967Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:362f6cb10161f617df05411a6d09bfa25b4a60bc9df6ff1741d43bf0b84cac88","observation_id":"548d251a-4939-4972-aaa1-baa552e41abc","resolution":{"observed_at":"2026-08-07T14:06:32.966565Z","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":"2001.02610","last_updated":"2020-01-08T16:45:09Z","snapshot_observed_at":"2026-08-12T01:33:52.396724Z","submitted_at":"2020-01-08T16:45:09Z","title":"iDLG: Improved Deep Leakage from Gradients","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.02610","snapshot_observed_at":"2026-08-07T14:06:27.811626Z","title":"idlg: Improved deep leakage from gradients","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:27.811626Z"},"links":{"cited_paper":"/paper/2001.02610","citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:56a2e3d309c15c376daa355b2a5194362eb871f6fc37e3a60de6d81f9233369e","observation_id":"c339bb25-a87d-48e9-9333-c7eea890e729","resolution":{"observed_at":"2026-08-07T14:06:27.811626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10397","last_updated":"2020-04-23T04:31:26Z","snapshot_observed_at":"2026-08-02T05:12:09.916792Z","submitted_at":"2020-04-22T05:15:03Z","title":"A Framework for Evaluating Gradient Leakage Attacks in Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10397","snapshot_observed_at":"2026-08-07T14:06:27.887385Z","title":"A framework for evaluating gradient leakage attacks in federated learning","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:27.887385Z"},"links":{"cited_paper":"/paper/2004.10397","citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:c4473e15f9e6f187caab3f32a7f6a5440145bd8660ec222a1fd2c78dc1d8e55f","observation_id":"3cbc31c3-5fd6-4f4b-8c29-215e6d3adb96","resolution":{"observed_at":"2026-08-07T14:06:27.887385Z","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":"2026-08-07T14:06:32.676810Z","title":"Inverting gradients-how easy is it to break privacy in federated learning? Advances in neural information processing systems, 33:16937–16947, 2020","venue":null,"work_id":"ce07fe54-3420-4bf8-817b-4513bd68be9f","year":2020},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:27.967008Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:a9bf02606ab5d4c9dd673246c209a30aaae53e28ad93567d522b12dd1d5b7004","observation_id":"d6627546-2540-4285-bc83-843acda0632e","resolution":{"observed_at":"2026-08-07T14:06:32.788212Z","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":"2010.07733","last_updated":"2021-03-16T11:16:25Z","snapshot_observed_at":"2026-08-08T23:11:08.785736Z","submitted_at":"2020-10-15T13:22:40Z","title":"R-GAP: Recursive Gradient Attack on Privacy","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.07733","snapshot_observed_at":"2026-08-07T14:06:28.062115Z","title":"R-gap: Recursive gradient attack on privacy","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:28.062115Z"},"links":{"cited_paper":"/paper/2010.07733","citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:10517714db243654781cdae4049a825ff477e50a27a2b86afca4c6d201d2af07","observation_id":"a2f05dba-2408-48c4-aad4-9d3db28e9330","resolution":{"observed_at":"2026-08-07T14:06:28.062115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.06228","last_updated":"2020-09-14T07:04:02Z","snapshot_observed_at":"2026-08-11T17:13:59.286684Z","submitted_at":"2020-09-14T07:04:02Z","title":"SAPAG: A Self-Adaptive Privacy Attack From Gradients","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.06228","snapshot_observed_at":"2026-08-07T14:06:28.160205Z","title":"Sapag: A self-adaptive privacy attack from gradients","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:28.160205Z"},"links":{"cited_paper":"/paper/2009.06228","citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:dd0d1f01824dfb5dfe663050feeeeceec5366d12ee646f33ea89937a5258fe1a","observation_id":"66a3d0db-911c-40e5-a9e9-ebb9ecdc70fa","resolution":{"observed_at":"2026-08-07T14:06:28.160205Z","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":"2026-08-07T14:06:32.548909Z","title":"See through gradients: Image batch recovery via gradinversion","venue":null,"work_id":"d51f1bcc-ccfd-40a0-878c-50b03ed2a75e","year":2021},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:28.230335Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:8cd9c7856a5e33418b3ff3ce8fda9c8f0e41b84b564f50daeb58c9b9a2848727","observation_id":"d8c9554b-9639-42a4-87b7-c267ef817456","resolution":{"observed_at":"2026-08-07T14:06:32.606312Z","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":"2026-08-07T14:06:28.354308Z","title":"Reconstructing training data from model gradient, provably","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:28.354308Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:cd1a33cf9c99e46186f95de551d44c13e2ffeabcd872a538fcc67766d52f441a","observation_id":"00e65b3b-b8d4-4e22-8a5c-f0407880485f","resolution":{"observed_at":"2026-08-07T14:06:28.354308Z","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":"2026-08-07T14:06:32.386175Z","title":"Gradient inversion with generative image prior","venue":null,"work_id":"0ec9f4c2-619d-46ca-b9ff-cb07e2d2088b","year":2021},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:28.435264Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:35afff43168e238568faecf0c5c7092ac66f7cdc6679157279b2c15418d86722","observation_id":"ccb52a7e-a433-4af1-9dcb-8834c2732f80","resolution":{"observed_at":"2026-08-07T14:06:32.457899Z","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":"2026-08-07T14:06:32.201965Z","title":"Auditing privacy defenses in federated learning via generative gradient leakage","venue":null,"work_id":"d9c71324-ce08-45a2-ac17-795db1da4601","year":2022},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:28.527139Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:6ece0001ef6757442f3901ae0f8616fa0a3c60bc3252b83efbbcfedf772b9440","observation_id":"bedd3438-6171-47cb-842f-feeb15d14f71","resolution":{"observed_at":"2026-08-07T14:06:32.291423Z","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":"2026-08-07T14:06:32.033683Z","title":"Gifd: A generative gradient inversion method with feature domain optimization","venue":null,"work_id":"6b115338-4e21-4e5e-9fb2-70862dfc85cd","year":2023},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:28.635787Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:b87fabd60f67f9ac25b96c4e9ba79267bb4680505129cfcd993b862ee5f6efd3","observation_id":"d6cb671a-5d76-43fe-b1ac-69a511bb1e23","resolution":{"observed_at":"2026-08-07T14:06:32.125362Z","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":"2026-08-07T14:06:31.771159Z","title":"Learning to invert: Simple adaptive attacks for gradient inversion in federated learning","venue":null,"work_id":"dad68305-f179-4904-8910-460d9f0998c4","year":2023},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:28.745339Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:883b0f5d619dcb0cec2b96c8f2549e23c32c27821798f1128f19d98a82448f7f","observation_id":"a4be98e7-129b-476b-9342-06f8ddee041a","resolution":{"observed_at":"2026-08-07T14:06:31.925448Z","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":"2405.00955","last_updated":"2024-05-02T02:33:15Z","snapshot_observed_at":"2026-08-13T00:17:15.252116Z","submitted_at":"2024-05-02T02:33:15Z","title":"Recovering Labels from Local Updates in Federated Learning","version":1},"cited_work":{"arxiv_id":"2405.00955","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.00955","snapshot_observed_at":"2026-08-07T14:06:30.259529Z","title":"Recovering Labels from Local Updates in Federated Learning","venue":"cs.LG","work_id":"91511fde-1ab8-4099-bb80-090b6a011715","year":2024},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:28.855535Z"},"links":{"cited_paper":"/paper/2405.00955","citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:936aaa706916442fb9e65d9d73b98eff416db436ac1f2ce55a609ca55fa90613","observation_id":"0e281faa-3b5c-439c-b0a3-67e644b272fa","resolution":{"observed_at":"2026-08-07T14:06:30.321191Z","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":"2026-08-07T14:06:31.447605Z","title":"Dggi: Deep generative gradient inversion with diffusion model","venue":null,"work_id":"f79d9bd3-2778-4d7d-9cf7-be5dbf0f5c42","year":2025},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:28.997002Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:299c2b151310c03ce5371aeceb35850a06e3c75b8114868cade63b623be844ea","observation_id":"8c26d8f4-c6d3-49bd-ae37-27ec969c6c2b","resolution":{"observed_at":"2026-08-07T14:06:31.589187Z","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":"2026-08-07T14:06:31.125463Z","title":"The perceptron: a probabilistic model for information storage and organization in the brain","venue":null,"work_id":"7245e9a1-96f6-44e0-b85c-af7896abedf7","year":1958},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:29.075722Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:05029df6693d08ab7f742aa961b7ea8d226b3ee7db160f4652db9361e3e569c8","observation_id":"30c5e910-074d-4d82-a0fe-fa86eb9871cb","resolution":{"observed_at":"2026-08-07T14:06:31.295202Z","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":"2026-08-07T14:06:29.178669Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:29.178669Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:a47fa457b0d7c48b67b694b2e11b66a5c97f0829b365d09cbf3b80c55e1f5a50","observation_id":"36789cda-e3ac-48b4-b919-d1f4e1350afd","resolution":{"observed_at":"2026-08-07T14:06:29.178669Z","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":"2026-08-07T14:06:30.872407Z","title":"Reconstructing training data from trained neural networks","venue":null,"work_id":"ebcbfbc6-b0ce-4d21-bfed-a1e954450601","year":2022},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:29.257241Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:74156c650fd346d7baf49151bc2615892ecefdd4ae042231a842e58cdfda5dbe","observation_id":"281bbce8-dc9c-4527-b3eb-4a07d4e9d6c8","resolution":{"observed_at":"2026-08-07T14:06:30.960199Z","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":"2026-08-07T14:06:30.709509Z","title":"Instance-wise batch label restoration via gradients in federated learning","venue":null,"work_id":"d2b3b264-db07-47ea-ab8a-8cb80b09bf4f","year":2023},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:29.362082Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:ffc99f4ec4765210d97d9f22cd855dd92573e56abbd4c733f502e36b17926599","observation_id":"526a46e8-98a3-47f1-ba3a-793aa2c094d9","resolution":{"observed_at":"2026-08-07T14:06:30.773624Z","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":"2026-08-07T14:06:30.590327Z","title":"Spear: Exact gradient inversion of batches in federated learning","venue":null,"work_id":"40062426-a552-4669-bb7e-41a4c43f22c7","year":2024},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:29.471712Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:309e8100609f3d6c16e6b74fead7cdb7b4b08c5763bb05426ed667c4e98136c4","observation_id":"d9f0e4c3-fa4a-415e-ab85-bb4857765b7b","resolution":{"observed_at":"2026-08-07T14:06:30.631206Z","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":"2026-08-07T14:06:29.585116Z","title":"Generative adversarial nets","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:29.585116Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:1f50f792818531faab7aa9b4a7e99ca24ef349d241530b27d24e8750b2ac65a1","observation_id":"712f1ec3-a6a0-4347-896a-29800ea844ff","resolution":{"observed_at":"2026-08-07T14:06:29.585116Z","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":"2026-08-07T14:06:29.697225Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:29.697225Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:e6f22a97feaa2c94b7ee6d7eb2b9ea1c677380622001ef253d9ae2087a3d0f91","observation_id":"600d00ac-c814-45af-8d67-a203bf84e980","resolution":{"observed_at":"2026-08-07T14:06:29.697225Z","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":"2026-08-07T14:06:29.808530Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:29.808530Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:6c955ded1ae0019e07418d45189d8dc8d07a4352c3589a80724a361134ee72e1","observation_id":"2a360c63-1a3e-4f53-9804-a61415f53304","resolution":{"observed_at":"2026-08-07T14:06:29.808530Z","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":"2026-08-07T14:06:29.908738Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:29.908738Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:791470a6d66889bc65cb493c1351bc1453dd8d9bd4d0db5e80db959b654872a5","observation_id":"d74ed9eb-5f3f-40fc-afef-2ee345e90714","resolution":{"observed_at":"2026-08-07T14:06:29.908738Z","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":"2026-08-07T14:06:30.434646Z","title":"The japanese female facial expression (jaffe) dataset","venue":null,"work_id":"f4353bd5-80ae-4f30-9a31-b61d7ea1ccc5","year":1998},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:29.995663Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:5757a338e381c44bf4f2e85f765f600aa538c2d14e47ada80dd26fd9602ae7c6","observation_id":"0418412e-14cb-4dac-968b-2c8f52c32d34","resolution":{"observed_at":"2026-08-07T14:06:30.488362Z","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":"2026-08-07T14:06:30.065489Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:30.065489Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:fcf7c53d5a3406c3c3a2ab161b00fafdc6eec39ec4dc8a47936ec19e2f0428b6","observation_id":"81a4de9a-2217-42f0-92f0-0931fff0d4c4","resolution":{"observed_at":"2026-08-07T14:06:30.065489Z","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":"2026-08-07T14:06:30.093990Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:30.093990Z"},"links":{"citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:6dde84afae510d74032e50abb43b8a3300bad0b5a2d5248b0d4271e51f3fef7c","observation_id":"2da8990c-0cb4-4a0d-b2ba-1c0c96f1222c","resolution":{"observed_at":"2026-08-07T14:06:30.093990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-13T14:19:26.598265Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-07T14:06:30.120001Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:06:30.120001Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2505.20026"},"observation_digest":"sha256:87ce8ca7540b3d1637de72e5480b1da210934ec04cbb1248a1c4b8c2cf2b7e2e","observation_id":"2b733a65-6860-465c-a57f-e5c8ec2af145","resolution":{"observed_at":"2026-08-07T14:06:30.120001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.20026","last_updated":"2025-05-26T14:17:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T16:05:13.234855Z","submitted_at":"2025-05-26T14:17:00Z","title":"Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":1,"verified_fuzzy":17},"total_outbound_references":32},"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 14 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2505.20026."}