{"as_of":"2026-08-17T22:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4d75da99cbce82516618aa5ee2475ab663ffe43c8f78f3808b6560e852893727","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:32:00.072009Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T15:50:35.304235Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.24125","snapshot_observed_at":"2026-08-03T15:50:35.304235Z","title":"Fadrm: Fast and accurate data residual matching for dataset distillation.arXiv preprint arXiv:2506.24125, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.15647","last_updated":"2026-05-30T01:41:06Z","snapshot_observed_at":"2026-08-15T00:12:33.767058Z","submitted_at":"2025-12-17T17:54:20Z","title":"Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T15:50:35.304235Z"},"links":{"cited_paper":"/paper/2506.24125","citing_paper":"/paper/2512.15647"},"observation_digest":"sha256:f553ee0696d5360b59586d34005e55fb3528ecd45467092b49d80a28c51646ca","observation_id":"31d137a6-8ba7-4d9f-8bac-3e0e44a0275e","resolution":{"observed_at":"2026-08-03T15:50:35.304235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.24125/citation-record","integrity":"/paper/2506.24125/integrity","json":"/paper/2506.24125/citation-record.json","paper":"/paper/2506.24125"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-06T21:31:54.154731Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:54.154731Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:61bd95f7caa95fc1b9c8412242d588f5127c70787262e14a446a78106657c64d","observation_id":"6584032a-5006-4f32-9aae-ad1f2ffc0a67","resolution":{"observed_at":"2026-08-06T21:31:54.154731Z","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":"2026-08-06T21:32:04.216945Z","title":"Rademacher and gaussian complexities: Risk bounds and structural results","venue":null,"work_id":"a6c32155-99b3-47c3-8707-d26ae4b2739a","year":2002},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:54.225684Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:b728e813f7794dba69d330fa5b94b9277ec4556f39d948a1a57a2acd5c2752c6","observation_id":"9102774d-a313-4200-865f-b83213577eb1","resolution":{"observed_at":"2026-08-06T21:32:04.219228Z","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":{"arxiv_id":"1107.0740","last_updated":"2012-09-04T16:43:48Z","snapshot_observed_at":"2026-08-16T12:44:00.939563Z","submitted_at":"2011-07-04T20:34:23Z","title":"An intuitive proof of the data processing inequality","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1107.0740","snapshot_observed_at":"2026-08-06T21:31:54.319874Z","title":"An intuitive proof of the data processing inequality","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:54.319874Z"},"links":{"cited_paper":"/paper/1107.0740","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:9546448fece9eb743be0cbf1fa8858bed73b29741483bd92b5c5f2d82c6329b5","observation_id":"162c5b1e-c443-4537-83a7-b9dba34083c2","resolution":{"observed_at":"2026-08-06T21:31:54.319874Z","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":"2026-08-06T21:32:04.209310Z","title":"Dataset distillation by matching training trajectories","venue":null,"work_id":"736e6da2-4f39-4342-bfa5-eaae89ba1e86","year":2022},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:54.434069Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:940cc778df0eb677d2d6a5e247c8539096162dd8f2f56d0f9658ab569f11a9bb","observation_id":"cb52d259-3614-4557-ba65-b3b1048f8057","resolution":{"observed_at":"2026-08-06T21:32:04.212411Z","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":{"arxiv_id":"2312.08912","last_updated":"2023-12-14T13:19:33Z","snapshot_observed_at":"2026-08-16T14:34:47.636072Z","submitted_at":"2023-12-14T13:19:33Z","title":"Dataset Distillation via Adversarial Prediction Matching","version":1},"cited_work":{"arxiv_id":"2312.08912","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.08912","snapshot_observed_at":"2026-08-06T21:32:00.711068Z","title":"Dataset Distillation via Adversarial Prediction Matching","venue":"cs.CV","work_id":"4befb0f2-224f-42f9-b920-b1cdb432a8de","year":2023},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:54.511869Z"},"links":{"cited_paper":"/paper/2312.08912","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:51d15dcc8711a95605953e97d54839c5cc62d710009840569182d6964d71c630","observation_id":"62ed99b9-8263-4b0c-81ee-35987a5a3469","resolution":{"observed_at":"2026-08-06T21:32:00.751266Z","resolver_source":"local_arxiv","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:31:54.605329Z","title":"Dataset distillation via committee voting","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:54.605329Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:587d45f40c74f87268b484561475ab392a4400935705ebb3cb97a6d723c2bb09","observation_id":"902cbd81-c7c2-4c75-893b-4e50921a800c","resolution":{"observed_at":"2026-08-06T21:31:54.605329Z","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":"2026-08-06T21:32:04.201881Z","title":"Scaling up dataset distillation to imagenet- 1k with constant memory","venue":null,"work_id":"5ea72850-2c1f-4c3d-81a9-d40b59282a93","year":2023},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:54.709514Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:ecadd365c05df85be94a438fc34be17235ad9f1eea1eaba0abb97140ae1032e7","observation_id":"0a828a6d-a2d7-4d75-91a0-1068c1c59c03","resolution":{"observed_at":"2026-08-06T21:32:04.204809Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:31:54.847155Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:54.847155Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:810e82d34be0db03530a8a2179fbb2407983a38e4a0f343285b81606fd54778c","observation_id":"c4504ae4-c5d1-4626-ae1d-382d64e1a0a5","resolution":{"observed_at":"2026-08-06T21:31:54.847155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.02916","last_updated":"2022-11-19T03:48:09Z","snapshot_observed_at":"2026-08-16T16:54:55.216581Z","submitted_at":"2022-06-06T21:32:26Z","title":"Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks","version":2},"cited_work":{"arxiv_id":"2206.02916","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.02916","snapshot_observed_at":"2026-08-06T21:32:00.481240Z","title":"Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks","venue":"cs.LG","work_id":"4226808c-4f2a-449a-a16f-084deadea613","year":2022},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:54.950578Z"},"links":{"cited_paper":"/paper/2206.02916","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:fc45a8058bacdb382609d0eaed3286a828ecba169cdc98bca37de561003bf6bb","observation_id":"b232e7cc-4b81-485b-b4bd-3f7783467630","resolution":{"observed_at":"2026-08-06T21:32:00.528796Z","resolver_source":"local_arxiv","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":"2026-08-06T21:32:04.190272Z","title":"To- wards lossless dataset distillation via difficulty-aligned trajectory matching","venue":null,"work_id":"4299b319-d49a-4efe-a933-119f7044dbab","year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:55.091000Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:e531096ee40706eb449afd6a355ce660769c44dfea25b286987ff47459677a64","observation_id":"f3e2a548-bac3-4493-9024-7dd0ef6a49e4","resolution":{"observed_at":"2026-08-06T21:32:04.192761Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:31:55.228722Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:55.228722Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:f129aacb487ca9356bfd27100672d362cc8693ae956e447dc1026c66fafbf978","observation_id":"6e8d37d4-39f1-4d38-bf64-986a051553d1","resolution":{"observed_at":"2026-08-06T21:31:55.228722Z","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":"2026-08-06T21:32:04.178338Z","title":"Multisize dataset condensation","venue":null,"work_id":"87028e8a-043a-415f-8d1a-a80588545b57","year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:55.307988Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:ce31e1183c2155a0306a4d372dfce2b360d6387653d75b35f9c93baa70e798db","observation_id":"d3ac94c9-b4bb-445d-8177-b43848029fe8","resolution":{"observed_at":"2026-08-06T21:32:04.180594Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:31:55.415678Z","title":"Densely connected convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:55.415678Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:129c60c97ba7400950dade6e76dd3bcc21388281ec796b016c77c4e71d8a37a3","observation_id":"0b0ef0ee-759a-42cd-8730-38782df79228","resolution":{"observed_at":"2026-08-06T21:31:55.415678Z","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":"2026-08-06T21:32:04.166113Z","title":"Dataset condensation via efficient synthetic-data param- eterization","venue":null,"work_id":"1d1a82d9-e04e-4304-8051-2f3ade7f31db","year":2022},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:55.506235Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:ce2bfbfa19d0b737939b220a76001dc7b928bb404996520a2633bac6c9dbc916","observation_id":"af914229-3750-4f7e-bb44-112c4d2e1630","resolution":{"observed_at":"2026-08-06T21:32:04.169304Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:31:55.608355Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:55.608355Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:9330754dad01420b43b14105c8d3f0f6edcac96485d7dca3ed784bb240c55912","observation_id":"2fabd374-1c30-4426-8318-cb93cc0c50d2","resolution":{"observed_at":"2026-08-06T21:31:55.608355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.10494","last_updated":"2022-08-21T18:14:08Z","snapshot_observed_at":"2026-08-16T16:37:52.929600Z","submitted_at":"2022-08-21T18:14:08Z","title":"Dataset Condensation with Latent Space Knowledge Factorization and Sharing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.10494","snapshot_observed_at":"2026-08-06T21:31:55.720003Z","title":"Dataset condensation with latent space knowledge factorization and sharing","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:55.720003Z"},"links":{"cited_paper":"/paper/2208.10494","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:59b2618f9d8d89e5c339ecc043d47e11f422befbfe29b7424cbb674a159aa76d","observation_id":"b2ff6812-64c4-45a3-9cbd-1a78cc4ed176","resolution":{"observed_at":"2026-08-06T21:31:55.720003Z","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":"2026-08-06T21:32:04.154475Z","title":"Dataset condensation with contrastive signals","venue":null,"work_id":"021e914e-9c12-460e-a477-8cd2625b3350","year":2022},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:55.850154Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:99b5014d9b105db98ab43b34d850d3aebcdea6de89f3c3f955f35a08dd6915da","observation_id":"27a7f0a3-1e26-4e4d-bfa8-aceb54cf093c","resolution":{"observed_at":"2026-08-06T21:32:04.156944Z","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":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-06T21:31:55.988254Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:55.988254Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:03338115ea89b45f654854566e695fbc3f87ce981e666f56825bdce757df9d27","observation_id":"990a5991-ab43-4efc-b6e9-1fd29ee9f846","resolution":{"observed_at":"2026-08-06T21:31:55.988254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.05673","last_updated":"2025-07-03T14:56:22Z","snapshot_observed_at":"2026-08-16T00:09:28.454533Z","submitted_at":"2025-02-08T19:37:33Z","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.05673","snapshot_observed_at":"2026-08-06T21:31:56.126010Z","title":"The evolution of dataset distillation: Toward scalable and generalizable solutions","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:56.126010Z"},"links":{"cited_paper":"/paper/2502.05673","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:93c2ad4961338b5c6464da8660f971779f60ddc0f090308dbfdb250ae9f62a3d","observation_id":"0928311c-70aa-44cf-b0c4-317bf647285b","resolution":{"observed_at":"2026-08-06T21:31:56.126010Z","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":"2026-08-06T21:32:04.147045Z","title":"Dataset distillation via factorization","venue":null,"work_id":"b13b1ae8-f566-4376-8966-70dec37177cc","year":2022},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:56.227316Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:bb63732fc34bc108bedff0a3eeca0834af0b0403155c223fe7218d20f5b8bfa4","observation_id":"d5c39e0d-e890-41a5-b1ee-b23e2ad4ec8a","resolution":{"observed_at":"2026-08-06T21:32:04.149395Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:31:56.329009Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:56.329009Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:452d03d57f3096168d28739cceebc8105681f196304abc9b018ceffb072a1e5a","observation_id":"3321f48b-6c0f-435b-8be4-98b2f4eba89f","resolution":{"observed_at":"2026-08-06T21:31:56.329009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.12067","last_updated":"2022-10-21T15:56:13Z","snapshot_observed_at":"2026-08-17T18:54:40.294435Z","submitted_at":"2022-10-21T15:56:13Z","title":"Efficient Dataset Distillation Using Random Feature Approximation","version":1},"cited_work":{"arxiv_id":"2210.12067","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.12067","snapshot_observed_at":"2026-08-06T21:32:00.339472Z","title":"Efficient Dataset Distillation Using Random Feature Approximation","venue":"cs.LG","work_id":"a8e12106-bd78-43fb-aff8-62fce9aa4876","year":2022},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:56.400854Z"},"links":{"cited_paper":"/paper/2210.12067","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:1e9514abb7c4de3d93e298e830ff39c7cd864bf095dc4131b7cacc2d8d209971","observation_id":"d2d097ca-de7c-4c51-a5b0-7ff12e002af3","resolution":{"observed_at":"2026-08-06T21:32:00.386620Z","resolver_source":"local_arxiv","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":{"arxiv_id":"1710.03740","last_updated":"2018-02-15T20:04:02Z","snapshot_observed_at":"2026-08-12T13:00:33.339808Z","submitted_at":"2017-10-10T17:42:04Z","title":"Mixed Precision Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.03740","snapshot_observed_at":"2026-08-06T21:31:56.506055Z","title":"Mixed precision training","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:56.506055Z"},"links":{"cited_paper":"/paper/1710.03740","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:16559deee05451a7b5b77e157142079615e38ac3851bd901269c6f44b08a4b12","observation_id":"a398d585-fcbd-4cf2-90d2-9c9c13836bbc","resolution":{"observed_at":"2026-08-06T21:31:56.506055Z","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":"2026-08-06T21:32:04.134498Z","title":"Dataset distillation with infinitely wide convolutional networks","venue":null,"work_id":"f1eb2d50-4693-4bc9-a4d8-9c1061d26326","year":2021},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:56.644821Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:b36da1c3bee810a1508237edea7e66fef698749057fd8b6be405ef54d3543ede","observation_id":"e09e12b0-644e-4690-9c2a-84813c529d87","resolution":{"observed_at":"2026-08-06T21:32:04.137699Z","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":"2026-08-06T21:32:04.127212Z","title":"Improving language understanding by generative pre-training","venue":null,"work_id":"1f5aadc7-06ce-4707-80b0-2e1ce82bfd7a","year":2018},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:56.848469Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:890269d88e759142921f5fffa0b5fdcf32d83b6812248e3f81da0bcb2d1f87d8","observation_id":"86db2fae-edd9-43a9-9d59-7ee3e74dcd41","resolution":{"observed_at":"2026-08-06T21:32:04.129997Z","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":"2026-08-06T21:32:04.120196Z","title":"Liu, Yuri A","venue":null,"work_id":"13a65587-b5bc-440d-9b0e-2738ffe04df7","year":2023},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:57.007128Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:7629af51fb06673dd31d550cf26e455f7df8d666a43c14fdc1f271674d1e0458","observation_id":"a9229910-dd2d-453c-9936-eb50789a0271","resolution":{"observed_at":"2026-08-06T21:32:04.122452Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:31:57.142896Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:57.142896Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:de6f0faf082ba53e24d919d96295320fbbdd236357fe3d7a777714f09a4c0cca","observation_id":"7be36bca-f495-43a3-9f99-5b95218de64b","resolution":{"observed_at":"2026-08-06T21:31:57.142896Z","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":"2026-08-06T21:32:04.016710Z","title":"Dataset distillation in the era of large-scale data: Methods, analysis, and future directions","venue":null,"work_id":"fdd7937a-22be-4660-a5b9-3114d7d6f515","year":2025},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:57.343368Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:b39c08e4013e11f9e5a9c7995fc36343f6b6f60a535a489d0e40c96f0beca87e","observation_id":"ce49c717-36d5-40fa-ad35-d5ad71bd11c7","resolution":{"observed_at":"2026-08-06T21:32:04.110805Z","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":"2026-08-06T21:32:03.786289Z","title":"Generalized large-scale data condensation via various backbone and statistical matching","venue":null,"work_id":"21a6ce97-e871-474e-98bf-0e022b0a38d7","year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:57.507200Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:1a3f577c8efc453fd5a67a0b73c16daa2d7d59b2c47501e76c59f2524014762f","observation_id":"0372b1ad-09c5-483a-874c-4fa31f8fcf22","resolution":{"observed_at":"2026-08-06T21:32:03.878882Z","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":{"arxiv_id":"2404.13733","last_updated":"2025-01-17T07:15:16Z","snapshot_observed_at":"2026-08-16T13:59:06.331739Z","submitted_at":"2024-04-21T18:19:27Z","title":"Elucidating the Design Space of Dataset Condensation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.13733","snapshot_observed_at":"2026-08-06T21:31:57.646322Z","title":"Elucidating the design space of dataset condensation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:57.646322Z"},"links":{"cited_paper":"/paper/2404.13733","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:7f006cd4246f32830f0fdc862df75fe9a1c44a6d64d73717751f29c699fe7f8c","observation_id":"ddd13eab-7c54-431c-9404-28782260ddbb","resolution":{"observed_at":"2026-08-06T21:31:57.646322Z","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":"2026-08-06T21:32:03.525247Z","title":"Frequency domain-based dataset distilla- tion","venue":null,"work_id":"047350aa-97fd-4706-a39b-c2a13c74d988","year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:57.767176Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:d03489ed9b03bf276c98651bae5fa460eb8b8506effafbdace367c9717ef65d0","observation_id":"bd73bd32-50b6-45e7-ab74-a7d4a82c56b4","resolution":{"observed_at":"2026-08-06T21:32:03.668996Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:31:57.899918Z","title":"On the diversity and realism of distilled dataset: An efficient dataset distillation paradigm","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:57.899918Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:283f3d739649afc4bab8af1916394fa5447c18b6a476cbc72bf3687173d40d43","observation_id":"a9ab5eda-5c9b-4136-adf7-b8552c96080f","resolution":{"observed_at":"2026-08-06T21:31:57.899918Z","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":"2026-08-06T21:31:58.071095Z","title":"Inception-v4, inception-resnet and the impact of residual connections on learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:58.071095Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:d41b8efe65e05a50045f5770de6593c8165c0a89a418676bab25e5aa0f544842","observation_id":"d01ab754-793c-4162-ab7a-f0c25321109c","resolution":{"observed_at":"2026-08-06T21:31:58.071095Z","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":"2026-08-06T21:31:58.272235Z","title":"Efficientnetv2: Smaller models and faster training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:58.272235Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:e722a013f1cfa773325763aaa59c8beb6acf153b31c13cc0f7304ee8ee9a99b7","observation_id":"0ea06d0f-3c82-4abe-9c7f-23c1b532e1a9","resolution":{"observed_at":"2026-08-06T21:31:58.272235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-06T21:31:58.410768Z","title":"Gemini: a family of highly capable multimodal models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:58.410768Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:dbceea924e95364dd59092eb68b199c08fdf4fb1d801c6e7addb8a26b85f80a2","observation_id":"86f332b6-9f69-4235-bc9b-330224127a8e","resolution":{"observed_at":"2026-08-06T21:31:58.410768Z","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":"2026-08-06T21:31:58.573418Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:58.573418Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:937fb290e113050139380dff3a9e5761c2619cb2e9c5066e10e0abab4a003462","observation_id":"0600af16-61eb-4ff9-ad86-38babd3ea6e5","resolution":{"observed_at":"2026-08-06T21:31:58.573418Z","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":"2026-08-06T21:32:03.110716Z","title":"Cafe: Learning to condense dataset by aligning features","venue":null,"work_id":"84c27d86-c42d-4731-9e91-2e96b208383e","year":2022},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:58.739250Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:9174d6737655b59d479ce0d4674a0f349b5c537142c0fe24d4ecfcbd1b35dc71","observation_id":"1547b4b6-eaa1-4643-972d-a396eb5d01b2","resolution":{"observed_at":"2026-08-06T21:32:03.278417Z","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":{"arxiv_id":"1811.10959","last_updated":"2020-02-24T23:25:50Z","snapshot_observed_at":"2026-08-15T02:56:10.149790Z","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":"2026-08-06T21:31:58.893318Z","title":"Dataset distillation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:58.893318Z"},"links":{"cited_paper":"/paper/1811.10959","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:ac05dd72b457c40ea7354b453f1b05a625a8c66c1bbd9b716eaed4f92767a543","observation_id":"325bf653-1b86-4e6e-a549-e7c8e1de3257","resolution":{"observed_at":"2026-08-06T21:31:58.893318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15919","last_updated":"2024-11-03T16:39:09Z","snapshot_observed_at":"2026-08-16T13:07:26.442224Z","submitted_at":"2024-10-21T11:49:10Z","title":"Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.15919","snapshot_observed_at":"2026-08-06T21:31:59.073420Z","title":"Are large-scale soft labels necessary for large-scale dataset distilla- tion? arXiv preprint arXiv:2410.15919, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.073420Z"},"links":{"cited_paper":"/paper/2410.15919","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:e7314081e84a936e7c13f7146c0e884259827ff2cacff634e25f18a7aa642b38","observation_id":"a5c0af80-824d-4f89-8169-c1f96e232e7e","resolution":{"observed_at":"2026-08-06T21:31:59.073420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.10045","last_updated":"2025-04-04T20:27:58Z","snapshot_observed_at":"2026-08-16T14:09:34.825858Z","submitted_at":"2024-03-15T06:31:03Z","title":"Towards Adversarially Robust Dataset Distillation by Curvature Regularization","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.10045","snapshot_observed_at":"2026-08-06T21:31:59.199921Z","title":"Towards adversarially robust dataset distillation by curvature regularization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.199921Z"},"links":{"cited_paper":"/paper/2403.10045","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:608ab3fc6abc9eefeba3e8c8810b6f3abd09c9c0581c8b4b34fb6b3ee26aaf58","observation_id":"4bad430f-0dab-41fc-98a1-2fdd7989ed32","resolution":{"observed_at":"2026-08-06T21:31:59.199921Z","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":"2026-08-06T21:32:02.852908Z","title":"Image classification using deep convolutional neural net- works","venue":null,"work_id":"9b0bb7de-65bb-4410-b204-05898872515e","year":2015},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.348041Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:e512f42757f651073d22a3777de64acc893d19fd14fea1e8a73af3b36323c925","observation_id":"676af3ce-5059-4990-8a04-15956b6f4257","resolution":{"observed_at":"2026-08-06T21:32:02.969053Z","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":"2026-08-06T21:32:02.500532Z","title":"Dataset distillation via curriculum data synthesis in large data era","venue":null,"work_id":"bae2a81e-c20d-4e9e-8c72-a6801ce1ec4c","year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.432340Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:67e7c34de48b55e3a79ff1e3a21284810282e8c95ec74f85077bd94d1fa62ef0","observation_id":"7429bc8c-6f34-4f84-9b74-5fea84a4e57e","resolution":{"observed_at":"2026-08-06T21:32:02.654184Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:31:59.514114Z","title":"Squeeze, recover and relabel: Dataset condensation at imagenet scale from a new perspective","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.514114Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:f694aa2ee8a1ee93f53c4e2722f3f629915a8fea4bf0c87b0b96559a99913e16","observation_id":"7cb31c9b-7b40-4863-a8b3-4b26d2af9aef","resolution":{"observed_at":"2026-08-06T21:31:59.514114Z","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":"2026-08-06T21:32:02.136948Z","title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices","venue":null,"work_id":"c5f5d137-e626-40e3-9cad-350a1a8db683","year":2018},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.590635Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:0934877fb0b6b92cf6ee5608a77eae9480250e0aacc77ae674975a57d8086e01","observation_id":"d72fe51e-5253-4e11-ac61-7e814511f904","resolution":{"observed_at":"2026-08-06T21:32:02.324364Z","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":"2026-08-06T21:32:01.812320Z","title":"Dataset condensation with differentiable siamese augmentation","venue":null,"work_id":"90ded848-b332-4578-8df9-df345be64faf","year":2021},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.701939Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:4605dcc07207f2cb57c21a414061c86021da9096e11b943c38ee0d9cad69f506","observation_id":"cfc1ca97-1ac5-4476-a7ff-806719587c9a","resolution":{"observed_at":"2026-08-06T21:32:01.965002Z","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":"2026-08-06T21:32:01.520616Z","title":"Dataset condensation with distribution matching","venue":null,"work_id":"4ecb04cb-8666-4cab-a8bb-b2112e8ef20a","year":2023},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.765171Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:bddb75fd35793a6d26b8c562ac80d2acfbccf9da612b67a10f10bb6df38835e9","observation_id":"79292212-561c-4dfd-8eb4-0dcf858c6de5","resolution":{"observed_at":"2026-08-06T21:32:01.650624Z","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":"2026-08-06T21:32:01.198278Z","title":"Dataset condensation with gradient matching","venue":null,"work_id":"4b178bb5-8154-4560-a444-ab30ad36ffbe","year":2021},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.825062Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:739666225e707b76e7c20c8a36ca40f3ae4981edd0a4006ead283a635b6dfb1f","observation_id":"7d26a42d-a2e7-4345-a980-d5639aa39ee5","resolution":{"observed_at":"2026-08-06T21:32:01.342023Z","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":{"arxiv_id":"2402.13007","last_updated":"2024-02-20T13:42:36Z","snapshot_observed_at":"2026-08-16T14:16:57.294927Z","submitted_at":"2024-02-20T13:42:36Z","title":"Improve Cross-Architecture Generalization on Dataset Distillation","version":1},"cited_work":{"arxiv_id":"2402.13007","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.13007","snapshot_observed_at":"2026-08-06T21:32:00.163044Z","title":"Improve Cross-Architecture Generalization on Dataset Distillation","venue":"cs.LG","work_id":"e3058eb2-a185-4562-9211-ca9bd41d957f","year":2024},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.887032Z"},"links":{"cited_paper":"/paper/2402.13007","citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:9472b7f0be28736a0efac12b3c1217ad368b7048ecea6d7dbd5566581110ae51","observation_id":"10346d2c-c2e7-416d-a894-1c6bcbe0ab7a","resolution":{"observed_at":"2026-08-06T21:32:00.219850Z","resolver_source":"local_arxiv","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":"2026-08-06T21:32:01.091524Z","title":"Dataset distillation using neural feature regression","venue":null,"work_id":"deb9c33b-2a1b-46ed-9c6f-df1f715e0ead","year":2022},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T21:31:59.948456Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:e623dbd8ee8fb5cf36ee998b974d0d330f79cc9fc43e827f81654012ae98c2fd","observation_id":"cac3a918-7090-45c6-b7d5-95fc704adaf6","resolution":{"observed_at":"2026-08-06T21:32:01.168375Z","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":"2026-08-06T21:32:00.925508Z","title":null,"venue":null,"work_id":"004a9b47-828f-4bd9-afb9-7ad82ec765aa","year":null},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:00.008324Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:97c3c93057760d54d6ece8b0106afcdd9b58699181974ff77bc2a1800506a8a9","observation_id":"e6381798-649b-47ae-9c19-4ca639284b09","resolution":{"observed_at":"2026-08-06T21:32:00.981282Z","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":"2026-08-06T21:32:00.815906Z","title":"theℓ∞ norm with L = 1 T","venue":null,"work_id":"9d58ec0f-daf7-49ff-9d62-31b09b17671d","year":null},"citing_paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:00.072009Z"},"links":{"citing_paper":"/paper/2506.24125"},"observation_digest":"sha256:6509ec4020e6bde51955882a410cd4d83039c7d2eda9045cc097c2999f007c0c","observation_id":"a1ac54e4-0d79-4fa5-a997-1e29bdef76f7","resolution":{"observed_at":"2026-08-06T21:32:00.871193Z","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"}}],"paper":{"arxiv_id":"2506.24125","last_updated":"2025-06-30T17:59:34Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T17:59:26.781836Z","submitted_at":"2025-06-30T17:59:34Z","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":4,"verified_fuzzy":23},"total_outbound_references":51},"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 17 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 1 inbound Pith citation observation for arXiv:2506.24125."}