{"as_of":"2026-08-18T01:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:84383c342367b41b9892c8475c82fabc3f3d180faf32d881d4362a629711cde2","coverage":[{"denominator":16,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-14T19:49:10.067376Z","state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2605.13418/citation-record","integrity":"/paper/2605.13418/integrity","json":"/paper/2605.13418/citation-record.json","paper":"/paper/2605.13418"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"6749.297831","doi":"10.1145/2976749.2978313","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Goodfellow, H","venue":null,"work_id":"518424d2-1085-4f06-9f9f-1c3aa7913ecb","year":2016},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:387c2607e421c8335aeee59d3f2857c39585bcd50744c5f2e4da697768b1d783","observation_id":"c5eecee8-8277-448c-8e90-93f39be33bf1","resolution":{"observed_at":"2026-05-14T19:49:23.642363Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.01129","last_updated":"2025-07-01T18:44:35Z","snapshot_observed_at":"2026-08-15T20:18:55.407024Z","submitted_at":"2025-07-01T18:44:35Z","title":"On Design Principles for Private Adaptive Optimizers","version":1},"cited_work":{"arxiv_id":"2507.01129","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.01129","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ganesh, A., McMahan, B., and Thakurta, A","venue":null,"work_id":"315be0a1-0660-4ee0-92b2-b31236185e6f","year":2025},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"cited_paper":"/paper/2507.01129","citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:b9053e2990f3ce3c04ac4d42688b0f4cb72edb0b6c1f37afa00a4724af693dd4","observation_id":"d2a50b67-273b-410a-86e7-15c50941d88e","resolution":{"observed_at":"2026-05-14T19:49:25.489440Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1109/csf","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T04:00:28.798490Z","title":"Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting","venue":null,"work_id":"5b06efce-068d-4d94-b184-beacaeed4e53","year":2019},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:fa9b00f69cfc69966d8a497bd0034dc68386988a55ff2d6607624d4173c32f4c","observation_id":"9d053373-5a56-45c0-94a6-bcb8c5e6d56f","resolution":{"observed_at":"2026-05-14T19:49:23.632585Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1609/aaai.v38i14.29451","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thakkar, O., Andrew, G., and McMahan, H","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","work_id":"d25e4851-7365-40a7-86b0-15c7648d26d9","year":1905},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:1d988f630e1fa80aa09a1d6b39fbeb1dc3b770ba0b0c228eb6a7ad1e305d0499","observation_id":"7e5d6ccc-bb63-41d9-b896-245b129a14c1","resolution":{"observed_at":"2026-05-14T19:49:23.651737Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"764de8ca-f8ba-49fc-9a1c-c089fdbd46ac","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:833c75673e152bec71ed55c9d9ccf54c9cc704a026b97deb2949cc24cc2b50e5","observation_id":"a85d8fc5-49f6-4ea8-99aa-40bfd8dd5050","resolution":{"observed_at":"2026-05-14T19:49:26.265239Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":"By Assumption A.2, the privacy noise ξt is statistically independent of the gradient estimate¯gt and the fixed preconditionerP t","venue":null,"work_id":"561a64b5-72bf-4dea-aaa7-8a0d3a73f6b8","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:2b3084446de9925d302b69bc3db8b68b128563fcb45f82b509c6d662c8825b76","observation_id":"ec84e33e-ce4f-47aa-bbbf-db9de9841776","resolution":{"observed_at":"2026-05-14T19:49:26.261153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"a33a2d77-cb4c-4ac7-ab03-893313ba3df8","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:7fffe6cdcd597a4cfbd9b8aab22d17f1ce081a1a35488e1eabcc839ff6bf7e2c","observation_id":"660e67fd-1446-4890-92ad-d1df2c8fbb44","resolution":{"observed_at":"2026-05-14T19:49:26.273928Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":"This confirms that the algorithm converges to a stationary point despite the injected privacy noise","venue":null,"work_id":"5f1d9ecd-dae6-4d83-a03a-c815f0e58f2c","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:b8e2625e31bac41738a9f45608b6ea867812da59c8971d0103ef50d79a1aa383","observation_id":"18baf0b6-8755-4764-9136-50037303a89c","resolution":{"observed_at":"2026-05-14T19:49:26.277997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"d437d724-cd78-46de-a35b-89f654f43163","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:6af145de81dd7c5160e25b21aa240cae39ba3e1411b3d5514b38b77e64120d6e","observation_id":"2f59db69-878f-49f0-a78c-b54138588ec2","resolution":{"observed_at":"2026-05-14T19:49:26.269876Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":"We scale the amplitude of the noise by the inverse frequency: ˜Zu =Z u · 1 ∥u∥α/2 2 +ϵ (42) whereϵprevents division by zero at the DC component","venue":null,"work_id":"43ed0d14-9799-4ea2-80f0-31f36e3fab83","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:492bbcaece70224a2c1508dfdc46690d8c734d7e332dde4b71a35b23a332cace","observation_id":"21b87667-6297-47ac-b21b-4691a979efc9","resolution":{"observed_at":"2026-05-14T19:49:26.237621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"f5d69a52-7d47-4811-b578-2d516222fe59","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:36dac7c853de3c72d2bafb014d08f2df187794f1bfe9e45c743d5df05094ce41","observation_id":"fb3914a9-a61b-4234-b4ec-05f200fd28f3","resolution":{"observed_at":"2026-05-14T19:49:26.252514Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":"Algorithm 3 details the implementation","venue":null,"work_id":"96a8f730-18fb-4eeb-9074-41561708f421","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:61f8f05579ce442edf85906b9dca110590d3884ca4eb8629522a0af375934c54","observation_id":"69c72459-765b-4ed2-b93a-04a69af9a9db","resolution":{"observed_at":"2026-05-14T19:49:26.232476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":"For each synthetic batch, we sample a random active lengthL act ∼ U(L min, Lmax)","venue":null,"work_id":"cbec4df7-6859-46e9-bb81-7ef5daa58cc4","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:f9b5f6da2956e3596e0871d3fe668665750d22a1209a468366549de98f12d12e","observation_id":"78077843-3622-483c-8349-0c242dbcccc8","resolution":{"observed_at":"2026-05-14T19:49:26.242545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":"This ensures that when projected through the model’s embedding layer, the inputs activate the lookup table with the correct varianceq 0 =Var(W embed)","venue":null,"work_id":"a0997cc5-f085-431e-955a-114ff840f578","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:68e31016aaf4c861d3c7b523e26266138cfbfa7505340e6ee93cd9f772f9be8a","observation_id":"a9d99bb8-2c0f-4130-8aa3-6469076d20fd","resolution":{"observed_at":"2026-05-14T19:49:26.257060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":"19 Data-Free Preconditioning for Private Deep Learning Algorithm 3Synthetic Pink Noise Generator (1/f α) Input:Batch sizeB, ChannelsC, HeightH, WidthW, Decayα(default 1.0)","venue":null,"work_id":"3bf08cf3-2024-4014-b5ec-4dc45ef83652","year":null},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:7e7aace920042b8277a750e74466730e2e46614d654e199bec69cc7012639d43","observation_id":"fd6f2816-0f52-431f-b547-dd679f57ac2d","resolution":{"observed_at":"2026-05-14T19:49:26.247872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-05T21:23:00.469572Z","title":"Positions i > L act are set to 0 (padded)","venue":null,"work_id":"e7f4764b-3ca2-4122-a224-77347d4e93e1","year":2015},"citing_paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-14T19:49:10.067376Z"},"links":{"citing_paper":"/paper/2605.13418"},"observation_digest":"sha256:a4c4a5666f2840f3fc2605b793ec1a8af065bbd05263324f0a07f2a0ac40c305","observation_id":"5ea5a4d8-101e-4bd9-84df-b815853ab5db","resolution":{"observed_at":"2026-05-14T19:49:26.233134Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.13418","last_updated":"2026-05-13T12:14:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T05:29:32.805410Z","submitted_at":"2026-05-13T12:14:00Z","title":"DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning"},"reference_resolution":{"displayed":16,"state_counts":{"malformed_identifier":3,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":4,"verified_exact":1,"verified_fuzzy":7},"total_outbound_references":16},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2605.13418."}