{"as_of":"2026-08-15T19:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ee99f8d4c430fb081a3da63a515e3fa084e9e9bb1e380d61e9f9399a626c8f5b","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T05:44:25.167665Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2411.19946/citation-record","integrity":"/paper/2411.19946/integrity","json":"/paper/2411.19946/citation-record.json","paper":"/paper/2411.19946"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:44:25.576760Z","title":"Understand- ing and improving early stopping for learning with noisy la- bels","venue":null,"work_id":"d339efc5-f464-4a97-9cb5-b0182f51eafd","year":2021},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.003609Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:d78adef90b54ecb13be64477eb1ec0a976e8897aeec2ef77b306a32897caacff","observation_id":"aa970f21-3c1e-413c-97a4-fa0894d72cb5","resolution":{"observed_at":"2026-08-12T05:44:25.580791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10934","last_updated":"2020-04-23T02:10:02Z","snapshot_observed_at":"2026-07-06T09:14:32.318388Z","submitted_at":"2020-04-23T02:10:02Z","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10934","snapshot_observed_at":"2026-08-12T05:44:25.007799Z","title":"Yolov4: Optimal speed and accuracy of object detection","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.007799Z"},"links":{"cited_paper":"/paper/2004.10934","citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:c66b6d7c650943c09e97bd377a2f4257ad6de078b56a463da708403301be02c3","observation_id":"73bbe83f-7e0a-44d0-80f7-f4cc33149939","resolution":{"observed_at":"2026-08-12T05:44:25.007799Z","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":"2026-08-12T05:44:25.567003Z","title":"Dataset distillation by matching training trajectories","venue":null,"work_id":"c466916a-5827-4216-a901-61068e5eb523","year":2022},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.011892Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:d2f131501856769437f86ccd1057ee013f8126ffabeb0e21fa588c1b0e8b56ef","observation_id":"3912a814-b727-40a4-b2f1-51c97e9782c7","resolution":{"observed_at":"2026-08-12T05:44:25.570061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.557180Z","title":"Data distillation can be like vodka: Distilling more times for better quality","venue":null,"work_id":"8430edda-ca4e-4a34-b2f2-f41d364016af","year":2024},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.015565Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:635349076d8951d6625d82ca4ac01e4c61cce0b995f6a275953ce622b936a2b9","observation_id":"657eb411-d3c9-4df7-9304-abd479da1c5d","resolution":{"observed_at":"2026-08-12T05:44:25.560440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.019254Z","title":"Randaugment: Practical automated data augmen- tation with a reduced search space","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.019254Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:9339a186d4922dfa5b113a7301d89dfc12bce02db468841f8a3348e4c0d85269","observation_id":"d8bceb74-bd9f-4def-a8d9-f1f8c872dd5c","resolution":{"observed_at":"2026-08-12T05:44:25.019254Z","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":"2026-08-12T05:44:25.541744Z","title":"Scaling up dataset distillation to imagenet-1k with constant memory","venue":null,"work_id":"8d90f878-13bb-4c09-9362-0f755fe209ca","year":2023},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.022873Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:b0d014b90a03045000839a7d653d4eb15d662a76bc447dcd2e8aac5d6e230134","observation_id":"83207ae4-4e55-4281-a0f9-0a862bd44c3d","resolution":{"observed_at":"2026-08-12T05:44:25.545748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.026667Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.026667Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:0da809cd76768e896c7f41dc8f696a08617d6af9e9e874ae07317df5cb01c8f6","observation_id":"68c10755-2387-42a9-916b-56b98506dc67","resolution":{"observed_at":"2026-08-12T05:44:25.026667Z","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":"2026-08-12T05:44:25.525340Z","title":"Diversity-driven synthesis: Enhancing dataset distillation through directed weight adjustment","venue":null,"work_id":"380586d5-877d-4e6a-93cf-0211e369dcee","year":2024},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.029595Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:99c9acba44aff57e3f755e2acd1e97282085271053eceb930ff6d5c2a2fac9af","observation_id":"c9655ef3-231d-471d-ab77-d228916d80b6","resolution":{"observed_at":"2026-08-12T05:44:25.530592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.032545Z","title":"Fastai/imagenette: A smaller subset of 10 easily clas- sified classes from imagenet, and a little more french","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.032545Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:bdd519318f9f1cef1ea9e224b50518c8b02c2b00fc9d5285294d4da7eda3b209","observation_id":"654b84b2-b138-4e3e-b115-36bf45ec0436","resolution":{"observed_at":"2026-08-12T05:44:25.032545Z","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":"2026-08-12T05:44:25.509536Z","title":"Dynamic few-shot visual learning without forgetting","venue":null,"work_id":"c6946e45-37df-424a-a87a-11e01df0edc6","year":2018},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.035553Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:0f9d3cc9bab35875862766fea951f2386927cdbebdfc87e474573ed74981fcc4","observation_id":"6a03bfdb-de59-48d1-904e-73c9d347d158","resolution":{"observed_at":"2026-08-12T05:44:25.513757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.499476Z","title":"Efficient dataset distillation via minimax diffusion","venue":null,"work_id":"c1e30e80-ebc3-445c-8f46-374eefcdcc24","year":2024},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.038817Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:d570418931a88f6f7e56b33af6315ddd6b58bcf2c389a20998e71ac4e66572dc","observation_id":"0fa535a2-6f0d-4623-9a77-737a241d607e","resolution":{"observed_at":"2026-08-12T05:44:25.503427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.490831Z","title":"Towards lossless dataset distillation via difficulty-aligned trajectory matching","venue":null,"work_id":"29e49afa-5b5f-4a9d-ae38-e19dea0c32f2","year":2024},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.042655Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:2f7219877a9038dbfe38a28c6d96f642be044583327e86209a9627942db71cfc","observation_id":"a722bb80-668c-477a-b786-23b1f8331588","resolution":{"observed_at":"2026-08-12T05:44:25.493971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.046308Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.046308Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:f5e50c79584a38d47b921ca6b850aeb3c8c9ca06c0d46eedeb0f51cb2380766d","observation_id":"78b55875-634a-4a68-809c-771c24a445b3","resolution":{"observed_at":"2026-08-12T05:44:25.046308Z","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":"2026-08-12T05:44:25.477279Z","title":"Multisize dataset condensation","venue":null,"work_id":"f423f267-648b-457e-a386-1ba553a75175","year":2024},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.049173Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:e9899494f3712ad8a09efbd8f13f8d52c5c875b23699b29b935b863cf59bc345","observation_id":"d677ae88-a90f-4727-bb06-2297b6404356","resolution":{"observed_at":"2026-08-12T05:44:25.480340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.467372Z","title":"Dataset condensation via efficient synthetic- data parameterization","venue":null,"work_id":"b68ecf56-a84e-4b33-bf5c-2e931614bcc8","year":2022},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.052057Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:ea34ee47693be15588507d7d206ebc74189cee12d98ea19b089dfbbcd35f4e0a","observation_id":"b2006a84-d1dc-472e-9d09-f1777bfbf68e","resolution":{"observed_at":"2026-08-12T05:44:25.471356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.055534Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.055534Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:62d524668a22b931aa8b5f269c15d1be03db8b5d93b2a521dca8bd9bcf9c7474","observation_id":"10158edc-d394-44f2-b87a-926813073f40","resolution":{"observed_at":"2026-08-12T05:44:25.055534Z","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":"2026-08-12T05:44:25.058308Z","title":"Tiny imagenet visual recognition challenge","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.058308Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:31e397eea4aae41b650ea8d46519646c96409d022293c1063282a3c46b580366","observation_id":"be2800c8-0d0a-434d-82dc-4655507bd19a","resolution":{"observed_at":"2026-08-12T05:44:25.058308Z","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":"2026-08-12T05:44:25.447298Z","title":"Dataset condensation with con- trastive signals","venue":null,"work_id":"98958621-7515-4535-85cc-44a87400af23","year":2022},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.061184Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:79b3fce5192298eedd96bf26ce55aba1b027cd048f055940607ab529adfe36aa","observation_id":"4bc482ba-d38e-41bf-a0b1-c14a161e8e02","resolution":{"observed_at":"2026-08-12T05:44:25.451373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.18531","last_updated":"2025-07-02T04:25:43Z","snapshot_observed_at":"2026-08-13T22:14:18.354753Z","submitted_at":"2023-11-30T13:15:28Z","title":"Dataset Distillation via the Wasserstein Metric","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.18531","snapshot_observed_at":"2026-08-12T05:44:25.064326Z","title":"Dataset distillation via the wasserstein metric","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.064326Z"},"links":{"cited_paper":"/paper/2311.18531","citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:7be5775e664f44016872fbbddf023314af981e57e7478257fca561bebd498d51","observation_id":"1541e025-2405-4e0d-9947-ab93dc36e37c","resolution":{"observed_at":"2026-08-12T05:44:25.064326Z","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":"2026-08-12T05:44:25.438156Z","title":"Investigating bi-level optimization for learn- ing and vision from a unified perspective: A survey and be- yond","venue":null,"work_id":"a214294a-d520-4df6-ae47-c480487392f9","year":2021},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.068553Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:c07d1321415d6fcd35e13ef6f039c5d89b58155194c78cd3cedcf7a95e43fe06","observation_id":"33afb1d7-9266-45b8-8f8e-857de534eda9","resolution":{"observed_at":"2026-08-12T05:44:25.441711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.429230Z","title":"Dataset distillation via factorization","venue":null,"work_id":"88d5902a-9316-45a2-925f-5f6a5e786898","year":null},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.072475Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:6b8e3e70cd814f57eafaa0a483d4b65946fbc107112402a580f98b71a4939944","observation_id":"e3226c04-2762-4245-963b-f368d081bcd6","resolution":{"observed_at":"2026-08-12T05:44:25.432446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.419542Z","title":"Learning efficient convolutional networks through network slimming","venue":null,"work_id":"d571ec8c-fec7-48de-b2ad-cf93031114b1","year":2017},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.076472Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:a470fb23a6e866b99006417b375ecd4f4205ebd41152ffc4baaa44ee4616367e","observation_id":"3c0c7a93-fc28-4b94-b7b4-cbe0738ecfbf","resolution":{"observed_at":"2026-08-12T05:44:25.422821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.080747Z","title":"Pytorch: An im- perative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.080747Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:841de61af81da91c1ff0e368c8a2336ff242b1818833dd57fa12e8369f24e0b5","observation_id":"118490ba-eaf2-4b28-8c1b-92f4676467e0","resolution":{"observed_at":"2026-08-12T05:44:25.080747Z","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":"2026-08-12T05:44:25.406349Z","title":"Early stopping-but when? In Neural Net- works: Tricks of the trade, pages 55–69","venue":null,"work_id":"666ad38f-5749-4cd0-bedb-45d0d33905e9","year":2002},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.084693Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:421f28dd50d419b51c34895fa801f95e1f3d13018912338cfe54202ef1a8d8dc","observation_id":"16911afd-970d-404d-b482-66985d4da8e4","resolution":{"observed_at":"2026-08-12T05:44:25.409540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.00999","last_updated":"2024-03-01T21:49:34Z","snapshot_observed_at":"2026-08-13T04:05:16.270566Z","submitted_at":"2024-03-01T21:49:34Z","title":"Distributional Dataset Distillation with Subtask Decomposition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.00999","snapshot_observed_at":"2026-08-12T05:44:25.088832Z","title":"Distribu- tional dataset distillation with subtask decomposition","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.088832Z"},"links":{"cited_paper":"/paper/2403.00999","citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:ecfb3958a06c46d1f54bf3ee9f3d599b16420e0f7cae40ed874abbc2802b6e1e","observation_id":"8bf5cfd8-65d0-4e11-a383-6b2f3e834d2f","resolution":{"observed_at":"2026-08-12T05:44:25.088832Z","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":"2026-08-12T05:44:25.092220Z","title":"Designing network design spaces","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.092220Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:814766daf2b54313788e68ebc0c19c3714426c8f1b2d442d60430e5b1ff911e9","observation_id":"3d2c61ae-7294-4a64-9fd7-6b74fc22d05a","resolution":{"observed_at":"2026-08-12T05:44:25.092220Z","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":"2026-08-12T05:44:25.391992Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":"a5fee71b-ed37-44e6-abd4-a4b88f837bae","year":2018},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.095875Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:496f7a864ecb85188ca0f83cdff232f3895ba40cf8f3e5da5af2e6d9d4d88d4c","observation_id":"ccb4ebcf-e15b-46e6-bab9-9ef595ccaab1","resolution":{"observed_at":"2026-08-12T05:44:25.395615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.382004Z","title":"Generalized large-scale data condensa- tion via various backbone and statistical matching","venue":null,"work_id":"7155aa1b-051f-4de1-bf13-3819bd9fcebd","year":null},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.098877Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:52f67998173731436aff2493a1a74dddad1746ece8bad38693a249fe5e813f37","observation_id":"8796a1c6-685e-4f54-b384-7230666586d4","resolution":{"observed_at":"2026-08-12T05:44:25.386291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.372963Z","title":"A fast knowledge distillation framework for visual recognition","venue":null,"work_id":"2815f5a4-ea83-4e06-8f92-533c73a0b449","year":2022},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.102260Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:4f6abb4abcd07ccea7caf3ccbfbdf3d2c49fc487629d52c1a22808d9d9949bb7","observation_id":"3d939d33-fbb1-46ce-9341-c22d9ce86fe4","resolution":{"observed_at":"2026-08-12T05:44:25.376190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-14T23:20:42.336514Z","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":"2026-08-12T05:44:25.105645Z","title":"Very deep convo- lutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.105645Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:30112c59e3f4b66f02660a07cf5bac9cce32116ff554a14befe8c2b713c30594","observation_id":"3c9dbf4e-78e7-4bf8-89b1-841272835937","resolution":{"observed_at":"2026-08-12T05:44:25.105645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1507.06149","last_updated":"2015-07-22T12:18:21Z","snapshot_observed_at":"2026-08-14T22:39:27.646865Z","submitted_at":"2015-07-22T12:18:21Z","title":"Data-free parameter pruning for Deep Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1507.06149","snapshot_observed_at":"2026-08-12T05:44:25.109051Z","title":"Data-free param- eter pruning for deep neural networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.109051Z"},"links":{"cited_paper":"/paper/1507.06149","citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:81a5b3f0cc83c857c26fe042aefc413328cac829349fe3e228129939b7a67aa3","observation_id":"70d5c845-dbce-41e5-b119-7aef1edf40ad","resolution":{"observed_at":"2026-08-12T05:44:25.109051Z","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":"2026-08-12T05:44:25.363516Z","title":"On the diversity and realism of distilled dataset: An efficient dataset distilla- tion paradigm","venue":null,"work_id":"76f94b99-4202-40e7-9c91-031496bb0468","year":2024},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.113018Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:2a3b04b0030fa3089443595f8337ee5d305b5d96b1d109ba734823831fc21c0f","observation_id":"3fd82cbf-9728-441f-8ec6-7f0e9dc05626","resolution":{"observed_at":"2026-08-12T05:44:25.366967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.115963Z","title":"Efficientnet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.115963Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:9652c9389daab3d3ae961a23517cbece976d912744d13dd5423f7b1fdf70a95a","observation_id":"759f2c3d-edb2-452c-b010-57f17141e984","resolution":{"observed_at":"2026-08-12T05:44:25.115963Z","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":"2026-08-12T05:44:25.349885Z","title":"Mnas- net: Platform-aware neural architecture search for mobile","venue":null,"work_id":"4ae9947e-ce71-491a-87bc-cf043781cba2","year":2019},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.118901Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:088ce4fb20fe146f6594aa4ec0a170c7fe22732c1b594b5cd1c887d0881d5180","observation_id":"46e48fe9-b998-414b-bd3c-b5d983620907","resolution":{"observed_at":"2026-08-12T05:44:25.353060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.122252Z","title":"Con- trastive multiview coding","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.122252Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:a2dc193baa37b6c1834afbb7abd2347994d8746dbdd537b2fed832f8fd57057d","observation_id":"65759490-bda8-486e-9696-4500553789e0","resolution":{"observed_at":"2026-08-12T05:44:25.122252Z","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":"2026-08-15T02:56:10.149790Z","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":"2026-08-12T05:44:25.126205Z","title":"Dataset distillation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.126205Z"},"links":{"cited_paper":"/paper/1811.10959","citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:e55745013f2c7bb0b1bdbaf5e94bd00b82e49f64ea606e8f48b805fc64b97433","observation_id":"f76dd3ec-64d7-487d-aec7-2af0fcc18ee4","resolution":{"observed_at":"2026-08-12T05:44:25.126205Z","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":"2026-08-12T05:44:25.335531Z","title":"Mean squared error: Love it or leave it? a new look at signal fidelity measures","venue":null,"work_id":"a5fd304f-2957-4024-939a-ffd493f84b32","year":2009},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.130172Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:d679bec3c99f30b8bcb3cc0f7defe5690a641cd495da63aeaf84a7b942177343","observation_id":"8d6452a9-7fd3-447d-bfe1-a812daa9bacd","resolution":{"observed_at":"2026-08-12T05:44:25.338825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.325644Z","title":"Are large-scale soft labels nec- essary for large-scale dataset distillation? In Advances in neural information processing systems, 2024","venue":null,"work_id":"84253f2c-ecd4-48e3-b171-3f4e77fe8e2b","year":2024},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.133084Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:1c08401519cb62a652253d2dad9429b525f72b0ed761334b9351caec8ed9abc5","observation_id":"2bbe7bbd-3a23-4e30-81e5-3e661a0c194d","resolution":{"observed_at":"2026-08-12T05:44:25.330055Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.317305Z","title":"Dataset distillation via cur- riculum data synthesis in large data era","venue":null,"work_id":"4dd79a2f-c3a2-4a59-9704-2986661d58d2","year":null},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.135969Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:7f69b9e66e52a21780fe2213dd42908f8b115fdb0efd4c44ee88aa78e729670a","observation_id":"39b9133c-20c4-4551-8be6-dd490ab52246","resolution":{"observed_at":"2026-08-12T05:44:25.320307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.308370Z","title":"Squeeze, recover and relabel: Dataset condensation at imagenet scale from a new perspective","venue":null,"work_id":"e48f888e-f598-4956-bc08-700b4ad6a9b8","year":2023},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.139304Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:de2c6571f428ffeeb04e773f32d76653d397c34828d3e5223711ee831e7c5113","observation_id":"30be7e3a-2eff-468c-a9f9-fd06e297c3ab","resolution":{"observed_at":"2026-08-12T05:44:25.311443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.00788","last_updated":"2023-12-20T20:30:24Z","snapshot_observed_at":"2026-08-13T17:53:01.642802Z","submitted_at":"2023-08-01T18:59:07Z","title":"An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.00788","snapshot_observed_at":"2026-08-12T05:44:25.142689Z","title":"An introduc- tion to bi-level optimization: Foundations and applications in signal processing and machine learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.142689Z"},"links":{"cited_paper":"/paper/2308.00788","citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:286919583cf8ff14f87ec3b28c14c7582803a99a774ca1a3f64feee02ba6f8ec","observation_id":"3d315857-4166-4624-b8a8-6412b5f7ab93","resolution":{"observed_at":"2026-08-12T05:44:25.142689Z","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":"2026-08-12T05:44:25.299240Z","title":"Dataset condensation with dis- tribution matching","venue":null,"work_id":"8c3220c3-2086-4c9f-8f0d-0b2e64bb6834","year":2023},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.146575Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:1e45fca75cecdd5cf8e6a27ebc22819d818a5ee50cbef2454161fb301d757846","observation_id":"c5dc41cc-b8de-4998-8408-a4cd2d70dfe4","resolution":{"observed_at":"2026-08-12T05:44:25.302364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05929","last_updated":"2021-03-08T13:31:22Z","snapshot_observed_at":"2026-08-09T10:26:02.821053Z","submitted_at":"2020-06-10T16:30:52Z","title":"Dataset Condensation with Gradient Matching","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.05929","snapshot_observed_at":"2026-08-12T05:44:25.149462Z","title":"Dataset condensation with gradient matching","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.149462Z"},"links":{"cited_paper":"/paper/2006.05929","citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:00c8efaa94f0431a85038373fc878525756457267c3ba4a85d1140e5b586cf1d","observation_id":"c1f43320-36dd-4de1-a906-16b1b374ac48","resolution":{"observed_at":"2026-08-12T05:44:25.149462Z","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":"2026-08-12T05:44:25.289201Z","title":"Decoupled knowledge distillation","venue":null,"work_id":"9a606f1d-240d-4b32-bd1e-07cd39c0fbd5","year":2022},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.152752Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:3008cd3c053cd6755f2191113f0361002b1ec01813ad0fc3099c87d09fd27e62","observation_id":"8baa2740-c68a-4b51-b7cb-30f6a4b51467","resolution":{"observed_at":"2026-08-12T05:44:25.292253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.279574Z","title":"Im- proved distribution matching for dataset condensation","venue":null,"work_id":"476f1e36-0413-40cb-836a-7575c45c9f8b","year":2023},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.155616Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:53bcc287e11dcfc2cd0d68205ac3622b43a195ff985c87bad6324b1f4dff63ac","observation_id":"9d5a3c8c-de70-4bca-adf4-8ba8e562d86e","resolution":{"observed_at":"2026-08-12T05:44:25.282764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07976","last_updated":"2024-04-11T17:56:40Z","snapshot_observed_at":"2026-08-13T00:32:26.956088Z","submitted_at":"2024-04-11T17:56:40Z","title":"Self-supervised Dataset Distillation: A Good Compression Is All You Need","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07976","snapshot_observed_at":"2026-08-12T05:44:25.159437Z","title":"Self-supervised dataset distillation: A good compression is all you need","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.159437Z"},"links":{"cited_paper":"/paper/2404.07976","citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:e19760d66c2319dcfdf1abb9eb385db4dda726222298f5e48449e05b83793564","observation_id":"7fa50bc6-4118-460b-aa83-1746b31c2b73","resolution":{"observed_at":"2026-08-12T05:44:25.159437Z","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":"2026-08-12T05:44:25.269664Z","title":"Dataset distillation using neural feature regression.Advances in Neu- ral Information Processing Systems, 35:9813–9827, 2022","venue":null,"work_id":"ddde8122-0798-4c49-9049-edd92245a2a6","year":2022},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.163520Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:18df889fd853a12145125091cc01af3b41ec2e20ba3de5f2f948934ae7263fc0","observation_id":"0bdc9013-31be-42be-912d-eb7dab4f4584","resolution":{"observed_at":"2026-08-12T05:44:25.273661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-12T05:44:25.259809Z","title":"Hyper-parameter settings","venue":null,"work_id":"bb8c4d45-2c91-4784-a092-e69a63fa7f38","year":null},"citing_paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:25.167665Z"},"links":{"citing_paper":"/paper/2411.19946"},"observation_digest":"sha256:e2d2e33eac96d81ee97d8fc9515502e11143f9a2cf7e7e674813923486863ebe","observation_id":"38dd8abc-28da-4472-bc3e-997e59a664c2","resolution":{"observed_at":"2026-08-12T05:44:25.263863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.19946","last_updated":"2025-06-06T19:05:04Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T13:54:50.103916Z","submitted_at":"2024-11-29T18:59:46Z","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":0,"verified_fuzzy":29},"total_outbound_references":48},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2411.19946."}