{"as_of":"2026-08-13T16:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:18349d2204fb411f58aabeff6237ea50ffeee92579d3a9d3aa522363ddd46ac4","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T14:15:39.416806Z","state":"measured"},{"denominator":19,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":19,"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/2502.01865/citation-record","integrity":"/paper/2502.01865/integrity","json":"/paper/2502.01865/citation-record.json","paper":"/paper/2502.01865"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:15:39.696272Z","title":null,"venue":null,"work_id":"1db6e719-c8fd-4ea2-994e-5f66a9c7734a","year":2023},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.381243Z"},"links":{"citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:b4d92cad4fe4dbd622a2657e907e25843f336b7a8fb71ab5ad40ba50b3838dcb","observation_id":"ad3dbc7e-a428-4d38-9e7d-2238b7d3b7f3","resolution":{"observed_at":"2026-08-09T14:15:39.700776Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2205.09329","last_updated":"2023-02-27T04:55:14Z","snapshot_observed_at":"2026-08-13T15:41:00.861027Z","submitted_at":"2022-05-19T05:36:35Z","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.09329","snapshot_observed_at":"2026-08-09T14:15:39.371692Z","title":"Dataset pruning: Reducing training data by examining generalization influence","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.371692Z"},"links":{"cited_paper":"/paper/2205.09329","citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:3faf20732f4e83f05050522c7736369ada24b35a0f2c606b5d34c6a611f97b95","observation_id":"073918db-e43d-4bb2-b256-1c3e67c3a9f0","resolution":{"observed_at":"2026-08-09T14:15:39.371692Z","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":"2026-08-09T14:15:39.710534Z","title":"0 2000 4000 6000 Training Iteration 0.010 0.015 0.020 0.025 0.030 0.035 0.040 0.045 Learning Rate Dynamic of Learning Rate Learning First Order Second Order Figure","venue":null,"work_id":"33c195fd-ba97-4a98-bb9f-289054b7a8e0","year":2000},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.376920Z"},"links":{"citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:ca2e88e04069f4979d962cba73549f76687ec772fa788e4550e5c81875afb049","observation_id":"49589aea-2fbf-4f1c-b4f9-42262cc92e92","resolution":{"observed_at":"2026-08-09T14:15:39.715482Z","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":"2026-08-09T14:15:39.680645Z","title":null,"venue":null,"work_id":"cbab278c-b967-4ef6-90c4-a342b29d2834","year":2020},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.385724Z"},"links":{"citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:e5b73589f95f6ffb21cd7244e8187283a857a178ab0b25f5d879eaf006e725b9","observation_id":"45c82680-faae-441e-953d-d99825727d0a","resolution":{"observed_at":"2026-08-09T14:15:39.685257Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-09T14:15:39.665873Z","title":"For a fair comparison, the hyperparameters of each method are properly tuned for the adaption to all the tasks including Cifar100 with 1 IPC and Tiny ImageNet with 3 IPC","venue":null,"work_id":"3dab1d34-4130-42f8-ab2d-048d3d9cca4e","year":2022},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.390458Z"},"links":{"citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:d37902873c0f0a11083ea3e57ebf1d22f71449eeb3d7c2379542b4f97fd7c3bc","observation_id":"3048d948-9a6c-4755-9ca7-946465a91229","resolution":{"observed_at":"2026-08-09T14:15:39.670678Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"2026-08-09T14:15:39.650514Z","title":null,"venue":null,"work_id":"0e66ac2f-59bf-4567-814c-bad013981cae","year":2009},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.394583Z"},"links":{"citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:f15018a5f9ed55d7e7a602dbdb60cb18f6961b1c74875116138f3cdc7f7216ce","observation_id":"96e81bf9-5a66-4f08-8100-6d62141b66c3","resolution":{"observed_at":"2026-08-09T14:15:39.655430Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-09T14:15:39.634102Z","title":"Cifar10 categorises 50,000 images with the size 32 × 32 into 10 classes while Cifar100 further categorises each of those 10 classes into 10 fine-grained subcategories","venue":null,"work_id":"c32f0011-391d-4054-9056-8537c45160a8","year":2015},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.398897Z"},"links":{"citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:3423ee1086c0fa5e0431886d7d6e0a200aa50f70d9d81f2bb97481d2fa052ab1","observation_id":"3897babf-6b2c-4adf-be1a-d4f6cec82525","resolution":{"observed_at":"2026-08-09T14:15:39.639278Z","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":"2026-08-09T14:15:39.605363Z","title":null,"venue":null,"work_id":"09b05b24-708c-45a7-b355-30cd24bf1cb6","year":2015},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.407508Z"},"links":{"citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:01e8c4f268567b264c642fbca400d5893b1f508b4a30550b6f678347ffc03fb7","observation_id":"88bd9bd6-664b-4fbb-a6f4-53dc94e2f869","resolution":{"observed_at":"2026-08-09T14:15:39.609786Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-09T14:15:39.591028Z","title":null,"venue":null,"work_id":"b6415304-0da1-4e3d-a949-7a8cf3012139","year":2012},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.412504Z"},"links":{"citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:f4d7968b54876a651cc1bf0000140d796e346bc0989670668cccef23b8259a2e","observation_id":"fcc6afcf-664d-4a80-909c-cd06235e2a60","resolution":{"observed_at":"2026-08-09T14:15:39.595841Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-09T14:15:39.619323Z","title":"We evaluate our methods on four main image datasets, Cifar10 (Krizhevsky et al., 2009), Cifar100 (Krizhevsky et al., 2009), TinyImageNet (Le & Yang,","venue":null,"work_id":"5d15ca22-0b27-4b1f-84ad-c2ae9708c35c","year":2023},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.403164Z"},"links":{"citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:2504445fdbbc481b669e771206cdc47c15fa400969a20af0d1d8923dfc042fe2","observation_id":"6a8fd474-c37f-468a-a6bd-025204d24f71","resolution":{"observed_at":"2026-08-09T14:15:39.623671Z","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":"2026-08-09T14:15:39.574323Z","title":"The trained neural networks are evaluated on the real test sets for generalization ability comparison of the synthetic datasets","venue":null,"work_id":"108f026f-be1e-46f8-838f-b735fc4cd114","year":2016},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.416806Z"},"links":{"citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:4eab58eb5c6e66fb1945ad1d26d36445e43b07b09054cf538a3a8ecb71e8d6a8","observation_id":"6d01bcdd-c133-4715-b33c-3eee267ffa3a","resolution":{"observed_at":"2026-08-09T14:15:39.580933Z","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":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-12T14:19:29.389332Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-09T14:15:39.357642Z","title":"and Zisserman, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.357642Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:466bb254229bdd7e07bb1b3f4012eac7ccd50c1a4be3ccdaafcfc82fc3cc7272","observation_id":"eb98d921-e446-43aa-8b6c-f226706b3866","resolution":{"observed_at":"2026-08-09T14:15:39.357642Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.10822","last_updated":"2019-06-26T02:54:26Z","snapshot_observed_at":"2026-07-06T08:02:51.583780Z","submitted_at":"2019-06-26T02:54:26Z","title":"Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.10822","snapshot_observed_at":"2026-08-09T14:15:39.342590Z","title":"Gradient noise convolution (gnc): Smoothing loss function for distributed large-batch sgd","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.342590Z"},"links":{"cited_paper":"/paper/1906.10822","citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:1dc706098e74d5fa571f98477b8cca75fb27d268d060b353336c16fa8502bf59","observation_id":"57290f38-606d-4f78-9cdf-c3b26038eec7","resolution":{"observed_at":"2026-08-09T14:15:39.342590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01412","last_updated":"2021-04-29T16:44:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-03T19:02:10Z","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01412","snapshot_observed_at":"2026-08-09T14:15:39.331786Z","title":"Sharpness-aware minimization for efficiently improving generalization","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.331786Z"},"links":{"cited_paper":"/paper/2010.01412","citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:99cd83a8bf44403765eedfd475cdfc597063bd3d125a6ebec274cd21eeab0e07","observation_id":"ce270825-4db1-498a-b4e8-d821cf076f8b","resolution":{"observed_at":"2026-08-09T14:15:39.331786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.07898","last_updated":"2018-12-02T15:20:07Z","snapshot_observed_at":"2026-08-06T23:04:15.507433Z","submitted_at":"2018-05-21T05:28:22Z","title":"SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.07898","snapshot_observed_at":"2026-08-09T14:15:39.367061Z","title":"Improving task-free continual learning by distributionally robust memory evolution","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.367061Z"},"links":{"cited_paper":"/paper/1805.07898","citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:db4038959df6785d5b13b13c69a7069ea9c5daabfd202353209025116bddab89","observation_id":"03a0a71c-2c44-4786-998c-0d1e5b432cfe","resolution":{"observed_at":"2026-08-09T14:15:39.367061Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.03088","last_updated":"2019-03-07T18:26:46Z","snapshot_observed_at":"2026-08-13T03:48:18.040262Z","submitted_at":"2019-03-07T18:26:46Z","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.03088","snapshot_observed_at":"2026-08-09T14:15:39.352564Z","title":"Self-tuning networks: Bilevel optimization of hyperparameters using structured best-response functions","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.352564Z"},"links":{"cited_paper":"/paper/1903.03088","citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:2e8f201c1fa0208688c9b3d8639bef71ec048ecf6035beac6549b828e3ebd1c1","observation_id":"1258c755-5eb4-4c35-9a57-465abd2bd93b","resolution":{"observed_at":"2026-08-09T14:15:39.352564Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06522","last_updated":"2024-09-17T14:30:04Z","snapshot_observed_at":"2026-08-13T05:53:07.215849Z","submitted_at":"2023-10-10T11:08:31Z","title":"Watt For What: Rethinking Deep Learning's Energy-Performance Relationship","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06522","snapshot_observed_at":"2026-08-09T14:15:39.337693Z","title":"N., Hao, X., Li, G., Sevilla-Lara, L., and Gowda, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.337693Z"},"links":{"cited_paper":"/paper/2310.06522","citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:d7ce4ce4450c166411a6969258d3872578f79aecba5950335af5007c8f0afd50","observation_id":"47836786-996a-4978-91f8-aed2002e0b8c","resolution":{"observed_at":"2026-08-09T14:15:39.337693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.04836","last_updated":"2017-02-09T20:38:16Z","snapshot_observed_at":"2026-07-06T05:10:58.923264Z","submitted_at":"2016-09-15T20:03:06Z","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.04836","snapshot_observed_at":"2026-08-09T14:15:39.347636Z","title":"S., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.347636Z"},"links":{"cited_paper":"/paper/1609.04836","citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:84babaf47d986130b5fb450c874b9d409e55ce15254c101437ad77b092286cf2","observation_id":"88fb222f-af32-46d0-9e94-bdd1542cadf6","resolution":{"observed_at":"2026-08-09T14:15:39.347636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.10959","last_updated":"2020-02-24T23:25:50Z","snapshot_observed_at":"2026-07-06T07:17:20.813296Z","submitted_at":"2018-11-27T13:17:45Z","title":"Dataset Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.10959","snapshot_observed_at":"2026-08-09T14:15:39.362326Z","title":"Cafe: Learning to condense dataset by aligning features","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-09T14:15:39.362326Z"},"links":{"cited_paper":"/paper/1811.10959","citing_paper":"/paper/2502.01865"},"observation_digest":"sha256:b3c65d200a7b2c3e6759c59ce432f0941e54a32654d0674fc22f036f8cc7e100","observation_id":"292de2b9-1578-4723-b006-14c1fdd5dc52","resolution":{"observed_at":"2026-08-09T14:15:39.362326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.01865","last_updated":"2025-02-03T22:30:06Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T14:12:45.870481Z","submitted_at":"2025-02-03T22:30:06Z","title":"Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":4},"total_outbound_references":19},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2502.01865."}