{"as_of":"2026-08-20T11:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b1efa280b910c58efd4e3b9e100460ef1fe81e1b771d209034058c55ce7e4237","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":73,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":73,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":73,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":73,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:11:15.000111Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":178,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2312.14238","last_updated":"2024-01-15T15:23:55Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-21T18:59:31Z","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","version":3},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-05-13T22:46:09.693156Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2312.14238"},"observation_digest":"sha256:c0085b583620974a50a4f97ddea8492899cf23b33930503477588204ba21a207","observation_id":"17d25f8e-eab0-4a41-b006-85c3d4cf062c","resolution":{"observed_at":"2026-05-13T22:46:10.025076Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-12T20:23:11.097584Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-16T03:34:04.121174Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":236,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:11.097584Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:5c6805544b91d14a83aabd868efde17c2f6ac8c61bb123dac0e8eb8e483e0520","observation_id":"c4e97b23-0c52-4ebe-8738-308488118548","resolution":{"observed_at":"2026-08-12T20:23:11.097584Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-12T18:15:17.997983Z","title":"A convnet for the 2020s, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11738","last_updated":"2024-11-18T17:07:37Z","snapshot_observed_at":"2026-08-16T00:05:32.503668Z","submitted_at":"2024-11-18T17:07:37Z","title":"WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-12T18:15:17.997983Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2411.11738"},"observation_digest":"sha256:406cd3e50ab94378e1e08561f22304f0a4fc55f50dafd160b1dce2ea15f3ff18","observation_id":"a393d440-f6ca-4024-a3da-cc73ec7590a0","resolution":{"observed_at":"2026-08-12T18:15:17.997983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-12T18:16:08.343424Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11940","last_updated":"2024-11-22T21:36:19Z","snapshot_observed_at":"2026-08-20T03:08:00.299087Z","submitted_at":"2024-11-18T17:07:08Z","title":"Introducing Milabench: Benchmarking Accelerators for AI","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T18:16:08.343424Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2411.11940"},"observation_digest":"sha256:8a305b12dcca793183181e24d9ba1470a877ea5e2499c770c37870ef65a29503","observation_id":"21d534b9-509c-428a-bac6-cc16bc079f0b","resolution":{"observed_at":"2026-08-12T18:16:08.343424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-12T17:09:16.588803Z","title":"A ConvNet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12874","last_updated":"2024-11-19T21:42:57Z","snapshot_observed_at":"2026-08-18T10:37:31.473864Z","submitted_at":"2024-11-19T21:42:57Z","title":"Residual Vision Transformer (ResViT) Based Self-Supervised Learning Model for Brain Tumor Classification","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T17:09:16.588803Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2411.12874"},"observation_digest":"sha256:0fe6d4886fd7acc08e6f87f9c156dce1b651dec0c5d05226e937d9e1cf254c5e","observation_id":"335921f9-c7fe-4b73-be88-25a1eef5093d","resolution":{"observed_at":"2026-08-12T17:09:16.588803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-12T14:46:12.344565Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.344565Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:883bd947bb8a1943f7702963f887f9217870aa4e026f4ce9cc745042ee3e4639","observation_id":"9ca60266-d840-44bb-8678-27ade01131d0","resolution":{"observed_at":"2026-08-12T14:46:12.344565Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-12T13:34:05.918542Z","title":"A ConvNet for the 2020s, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.16171","last_updated":"2024-12-12T10:04:33Z","snapshot_observed_at":"2026-08-17T13:15:40.492502Z","submitted_at":"2024-11-25T08:00:21Z","title":"Image Generation Diversity Issues and How to Tame Them","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T13:34:05.918542Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2411.16171"},"observation_digest":"sha256:e0b2e1bcff64bdee4e01a590a7d7f488110e481618614209a7fb2f8019be01a4","observation_id":"ad6bee63-5947-4902-a78c-3b2fc30fbc01","resolution":{"observed_at":"2026-08-12T13:34:05.918542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-12T05:15:07.451970Z","title":"Convnext: Revisiting convolutional neural networks for vision,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00571","last_updated":"2024-12-10T10:23:54Z","snapshot_observed_at":"2026-08-16T01:01:33.190459Z","submitted_at":"2024-11-30T19:53:23Z","title":"From Audio Deepfake Detection to AI-Generated Music Detection -- A Pathway and Overview","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T05:15:07.451970Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2412.00571"},"observation_digest":"sha256:95338c6b0d30a7628e6388e7c1235e2dbe758104a4d0d3e21e47532204c6a1ab","observation_id":"99d1fb14-e9c7-4dfd-af3d-a5c9306f4b5c","resolution":{"observed_at":"2026-08-12T05:15:07.451970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-11T19:23:41.154561Z","title":"A ConvNet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.06760","last_updated":"2025-02-08T03:25:39Z","snapshot_observed_at":"2026-08-18T10:38:27.912312Z","submitted_at":"2024-12-09T18:51:05Z","title":"Ranking-aware adapter for text-driven image ordering with CLIP","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-11T19:23:41.154561Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2412.06760"},"observation_digest":"sha256:294785ab55f6867b1fce0d001f0761ba1d183bf48dd872b1631d2096d3f338f6","observation_id":"a04f393b-913f-407c-84ee-091702763074","resolution":{"observed_at":"2026-08-11T19:23:41.154561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-11T15:52:26.512752Z","title":"A ConvNet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.10597","last_updated":"2025-02-10T21:53:37Z","snapshot_observed_at":"2026-08-12T04:53:04.483357Z","submitted_at":"2024-12-13T22:53:16Z","title":"Err on the Side of Texture: Texture Bias on Real Data","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T15:52:26.512752Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2412.10597"},"observation_digest":"sha256:2c740cd30ddadf3e831e0cfd30bbeffa29103b3f37162f966604c364407754fe","observation_id":"fe9fa969-caf9-499f-993b-3977a3980de6","resolution":{"observed_at":"2026-08-11T15:52:26.512752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-11T15:00:06.911355Z","title":"A convnet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11452","last_updated":"2024-12-16T05:14:08Z","snapshot_observed_at":"2026-08-20T01:42:47.818036Z","submitted_at":"2024-12-16T05:14:08Z","title":"Multilabel Classification for Lung Disease Detection: Integrating Deep Learning and Natural Language Processing","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T15:00:06.911355Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2412.11452"},"observation_digest":"sha256:70db78e378f171270f5882cc8c847e325644ea5cbad0b1586e3a7cb57caeedaa","observation_id":"76960844-ef52-4fcf-838d-7897aeaff9a5","resolution":{"observed_at":"2026-08-11T15:00:06.911355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-11T13:46:47.705361Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.12798","last_updated":"2024-12-17T11:00:56Z","snapshot_observed_at":"2026-08-18T10:37:27.347168Z","submitted_at":"2024-12-17T11:00:56Z","title":"ZoRI: Towards Discriminative Zero-Shot Remote Sensing Instance Segmentation","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-11T13:46:47.705361Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2412.12798"},"observation_digest":"sha256:5539de4087cea5d5511d2e1362e3ebb03d4ef65b3127b41147c3f144dd205a25","observation_id":"eb4d7cdc-9883-4219-984f-4945968d2fab","resolution":{"observed_at":"2026-08-11T13:46:47.705361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-11T14:59:02.337532Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.18619","last_updated":"2024-12-30T03:00:30Z","snapshot_observed_at":"2026-08-19T22:19:56.931776Z","submitted_at":"2024-12-16T05:02:25Z","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","version":2},"reference_index":272,"source":"pdf_text","source_observed_at":"2026-08-11T14:59:02.337532Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2412.18619"},"observation_digest":"sha256:0cb9ff563efc0bf0c119645ecaa30687c6e876d20bfe3a3cecbf562eb1de2170","observation_id":"b48caef7-ddfb-45d7-b744-e6ae75fb226f","resolution":{"observed_at":"2026-08-11T14:59:02.337532Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-10T23:01:24.456928Z","title":"A convnet for the 2020s, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.01453","last_updated":"2025-03-24T23:26:27Z","snapshot_observed_at":"2026-08-17T16:01:57.857119Z","submitted_at":"2024-12-31T00:23:15Z","title":"Geometry Matters: Benchmarking Scientific ML Approaches for Flow Prediction around Complex Geometries","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T23:01:24.456928Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2501.01453"},"observation_digest":"sha256:a92c5e8d5c12e09d3ef638dd199e3ef2776abe9192b62da4e10a5dd600b57d09","observation_id":"ec86c907-b158-4732-a2f0-d70052d5dea1","resolution":{"observed_at":"2026-08-10T23:01:24.456928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-10T20:15:40.062180Z","title":"2022, title A ConvNet for the 2020s , arXiv e-prints, arXiv:2201.03545, 10.48550/arXiv.2201.03545","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.09112","last_updated":"2025-07-31T15:10:35Z","snapshot_observed_at":"2026-08-14T14:39:39.317592Z","submitted_at":"2025-01-15T19:46:23Z","title":"Mantis Shrimp: Exploring Photometric Band Utilization in Computer Vision Networks for Photometric Redshift Estimation","version":2},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-10T20:15:40.062180Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2501.09112"},"observation_digest":"sha256:c09f17154aadedb1b98aadd9bc353a3967c34f8448724cc88c6242a6058e07bb","observation_id":"25503855-c274-4ec1-a51b-5c8984e15991","resolution":{"observed_at":"2026-08-10T20:15:40.062180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-10T19:06:04.159067Z","title":", author Mao, H","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.10733","last_updated":"2025-01-22T10:50:37Z","snapshot_observed_at":"2026-08-15T20:50:56.177567Z","submitted_at":"2025-01-18T11:39:46Z","title":"A CNN-Transformer for Classification of Longitudinal 3D MRI Images -- A Case Study on Hepatocellular Carcinoma Prediction","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-10T19:06:04.159067Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2501.10733"},"observation_digest":"sha256:6d0e86b7be7cc257bb29a073b0c2f4137b6ddb496971719306cd844748256595","observation_id":"657e7e0d-c32a-4efe-bd54-f9c02a317ccd","resolution":{"observed_at":"2026-08-10T19:06:04.159067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-10T17:35:00.769081Z","title":"Convnext: Revisiting convolutional neural networks for visual recognition","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12085","last_updated":"2025-01-21T12:22:15Z","snapshot_observed_at":"2026-08-18T10:38:31.121730Z","submitted_at":"2025-01-21T12:22:15Z","title":"Scalable Whole Slide Image Representation Using K-Mean Clustering and Fisher Vector Aggregation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T17:35:00.769081Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2501.12085"},"observation_digest":"sha256:63befe557f8289aef5cf36a3812ece4e57149141260e852e18f47de84ba7dfd8","observation_id":"5099359b-d2c1-46e7-8b54-7c7085cde81f","resolution":{"observed_at":"2026-08-10T17:35:00.769081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-10T14:14:10.221652Z","title":"A convnet for the 2020s, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15573","last_updated":"2025-01-26T15:58:42Z","snapshot_observed_at":"2026-08-16T09:07:51.877379Z","submitted_at":"2025-01-26T15:58:42Z","title":"Approximate Message Passing for Bayesian Neural Networks","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T14:14:10.221652Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2501.15573"},"observation_digest":"sha256:d4ac2b9844f765d69b87aa0ab75ec742322d5bc548f0604644ef85366c6741f4","observation_id":"0faed823-d7ed-4061-bcb6-49f203227531","resolution":{"observed_at":"2026-08-10T14:14:10.221652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-09T19:32:18.724411Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.00321","last_updated":"2025-02-23T15:40:03Z","snapshot_observed_at":"2026-08-15T15:42:35.045531Z","submitted_at":"2025-02-01T05:06:21Z","title":"MIM: Multi-modal Content Interest Modeling Paradigm for User Behavior Modeling","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T19:32:18.724411Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2502.00321"},"observation_digest":"sha256:0edc60a867a69121288524c19a71e1473036c40b0e7f5d1c5986f1b2d47c8845","observation_id":"faf122d7-ddba-449c-a021-0ce0c4c6b4f9","resolution":{"observed_at":"2026-08-09T19:32:18.724411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-09T15:22:13.296722Z","title":"A convnet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.01710","last_updated":"2025-05-05T08:31:11Z","snapshot_observed_at":"2026-08-18T10:38:30.638528Z","submitted_at":"2025-02-03T15:18:54Z","title":"DAGNet: A Dual-View Attention-Guided Network for Efficient X-ray Security Inspection","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T15:22:13.296722Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2502.01710"},"observation_digest":"sha256:23b40644297d3c95b08019b9e84479a2384245ed3370a425011ad21ff456cd3a","observation_id":"a9ef7989-9973-487f-b4e9-f3495ef344ab","resolution":{"observed_at":"2026-08-09T15:22:13.296722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-08T05:28:50.199017Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.09663","last_updated":"2025-02-12T12:46:58Z","snapshot_observed_at":"2026-08-18T10:40:10.725438Z","submitted_at":"2025-02-12T12:46:58Z","title":"DiffEx: Explaining a Classifier with Diffusion Models to Identify Microscopic Cellular Variations","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-08T05:28:50.199017Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2502.09663"},"observation_digest":"sha256:1f29b15686b42794bd5225dd17584e36931b1e036cc30bff1abae9ad223549d5","observation_id":"b9dac5e2-0918-403a-9e46-c53c17004c7b","resolution":{"observed_at":"2026-08-08T05:28:50.199017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-15T22:11:15.000111Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.08819","last_updated":"2025-05-12T18:40:46Z","snapshot_observed_at":"2026-08-18T10:38:25.822600Z","submitted_at":"2025-05-12T18:40:46Z","title":"Thoughts on Objectives of Sparse and Hierarchical Masked Image Model","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T22:11:15.000111Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2505.08819"},"observation_digest":"sha256:8ae864b91e6d954181fa3cf7bc2b5c2220544137350c72255cae8af8364a9dbf","observation_id":"b8a5d268-69cd-4e51-ad13-c4edfa28e134","resolution":{"observed_at":"2026-08-15T22:11:15.000111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-07T15:42:31.228385Z","title":"& Beyer, L","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.14204","last_updated":"2025-05-20T11:04:14Z","snapshot_observed_at":"2026-08-15T20:47:23.757939Z","submitted_at":"2025-05-20T11:04:14Z","title":"Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:31.228385Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2505.14204"},"observation_digest":"sha256:22af0a519aee03c7e9c26b20882361e03a34c4a12499102ba84cb20f7d375147","observation_id":"7923eccb-8790-434e-917a-b6462101f1df","resolution":{"observed_at":"2026-08-07T15:42:31.228385Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-07T15:36:31.310494Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.14572","last_updated":"2025-05-20T16:31:09Z","snapshot_observed_at":"2026-08-16T07:48:37.871965Z","submitted_at":"2025-05-20T16:31:09Z","title":"Automated Fetal Biometry Assessment with Deep Ensembles using Sparse-Sampling of 2D Intrapartum Ultrasound Images","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:36:31.310494Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2505.14572"},"observation_digest":"sha256:e2aedf2af31318666378a34f5a7c1e125a4fec486aa64d3a8b10a1124339344e","observation_id":"dfbc3def-e85b-4a64-9556-d82efa799f81","resolution":{"observed_at":"2026-08-07T15:36:31.310494Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-07T13:15:36.761669Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.22209","last_updated":"2025-05-28T10:37:52Z","snapshot_observed_at":"2026-08-13T08:48:36.820126Z","submitted_at":"2025-05-28T10:37:52Z","title":"A Survey on Training-free Open-Vocabulary Semantic Segmentation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:36.761669Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2505.22209"},"observation_digest":"sha256:7e811e7b3b0d67b93a3da280177b2240f93ddf3e5b210dde7175e470e9611969","observation_id":"510b10e2-07fe-4037-b339-f970f122ad57","resolution":{"observed_at":"2026-08-07T13:15:36.761669Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-07T05:42:14.303924Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07327","last_updated":"2025-06-15T17:02:01Z","snapshot_observed_at":"2026-08-17T05:33:57.559279Z","submitted_at":"2025-06-08T23:57:37Z","title":"CASE: Contrastive Activation for Saliency Estimation","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T05:42:14.303924Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2506.07327"},"observation_digest":"sha256:73c48f9eaa00659b3ff84f037b2405ff803b577adc4f831af72d6ef0e036b3e7","observation_id":"b5f2145f-e440-45f8-8c5e-b66943120abd","resolution":{"observed_at":"2026-08-07T05:42:14.303924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-07T00:47:19.602746Z","title":"arXiv preprint arXiv:2201.03545 (2022), https://arxiv.org/abs/2201.03545","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.12798","last_updated":"2025-06-15T10:15:42Z","snapshot_observed_at":"2026-08-18T10:37:29.340185Z","submitted_at":"2025-06-15T10:15:42Z","title":"Predicting Genetic Mutations from Single-Cell Bone Marrow Images in Acute Myeloid Leukemia Using Noise-Robust Deep Learning Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:47:19.602746Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2506.12798"},"observation_digest":"sha256:f8a0b956d3d3a2e565fde5087716ad36b9f565d79872fac9bc91d9db0107ea4a","observation_id":"b6edb404-f1fb-49bb-849e-f4ad07166f14","resolution":{"observed_at":"2026-08-07T00:47:19.602746Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-15T20:08:09.328537Z","title":"A ConvNet for the 2020s, March 2022 b","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.13335","last_updated":"2025-06-16T10:25:23Z","snapshot_observed_at":"2026-08-18T20:17:18.959819Z","submitted_at":"2025-06-16T10:25:23Z","title":"Advancing Image-Based Grapevine Variety Classification with a New Benchmark and Evaluation of Masked Autoencoders","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-15T20:08:09.328537Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2506.13335"},"observation_digest":"sha256:f664b88d3a5c5e79a9e5562391a0c33b64b4351c253b823f66e614ff6c7c4ffe","observation_id":"7d51d0cf-dc00-484c-85be-c0ec0416e7d1","resolution":{"observed_at":"2026-08-15T20:08:09.328537Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-07T00:28:35.692907Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.13964","last_updated":"2025-06-16T20:14:37Z","snapshot_observed_at":"2026-08-18T10:38:29.538300Z","submitted_at":"2025-06-16T20:14:37Z","title":"Comparison of ConvNeXt and Vision-Language Models for Breast Density Assessment in Screening Mammography","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T00:28:35.692907Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2506.13964"},"observation_digest":"sha256:b9ad4815be478b0dcd2a2a3431433082c25965508b45366b93feb9f87e25773c","observation_id":"6d87b6c0-6800-4d39-b1c9-10a92d3a2a24","resolution":{"observed_at":"2026-08-07T00:28:35.692907Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-15T18:49:12.212442Z","title":"-Y., Feichtenhofer, C., Darrell, T., & Xie, S","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.18683","last_updated":"2025-06-23T14:25:40Z","snapshot_observed_at":"2026-08-19T21:17:34.665741Z","submitted_at":"2025-06-23T14:25:40Z","title":"SIM-Net: A Multimodal Fusion Network Using Inferred 3D Object Shape Point Clouds from RGB Images for 2D Classification","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T18:49:12.212442Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2506.18683"},"observation_digest":"sha256:a7ab25d2ffcb3591476fbdbcdeabf86d8a405e96ad60150efab4efd055dfe852","observation_id":"1d315bc2-e21a-4d04-a218-6cf078e7ed76","resolution":{"observed_at":"2026-08-15T18:49:12.212442Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-06T19:03:11.481155Z","title":"A ConvNet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.06687","last_updated":"2025-07-09T09:30:07Z","snapshot_observed_at":"2026-08-16T11:40:23.318807Z","submitted_at":"2025-07-09T09:30:07Z","title":"StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T19:03:11.481155Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2507.06687"},"observation_digest":"sha256:188a8a7de67b3bcf0f6050019dd44e78dd5dba7f478dd1d6a0ec5e6f39f9cf02","observation_id":"9d771b6d-f481-40e7-84cf-b33cb4af27b5","resolution":{"observed_at":"2026-08-06T19:03:11.481155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-06T18:42:43.986081Z","title":"A convnet for the 2020s, in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.07638","last_updated":"2025-07-10T11:07:13Z","snapshot_observed_at":"2026-08-16T14:41:22.473629Z","submitted_at":"2025-07-10T11:07:13Z","title":"Bridging the gap in FER: addressing age bias in deep learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T18:42:43.986081Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2507.07638"},"observation_digest":"sha256:03b4b7cc7a0f7bcb9a57ceb01208894ca5ac9f71996e70a04d51538da19d6a04","observation_id":"110c084c-b95a-4607-8725-ee33d2b66475","resolution":{"observed_at":"2026-08-06T18:42:43.986081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-06T17:40:19.737979Z","title":", author Mao, H","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.10642","last_updated":"2025-07-14T16:37:20Z","snapshot_observed_at":"2026-08-18T10:37:28.001906Z","submitted_at":"2025-07-14T16:37:20Z","title":"First-of-its-kind AI model for bioacoustic detection using a lightweight associative memory Hopfield neural network","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-06T17:40:19.737979Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2507.10642"},"observation_digest":"sha256:62c30f760586dd2935ebbb722130ca8b51325e547fc4151453f676ae80b027fb","observation_id":"a3f9a9b3-2050-48a3-95dd-049d355a7008","resolution":{"observed_at":"2026-08-06T17:40:19.737979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-06T16:59:54.816055Z","title":"A ConvNet for the 2020s, 1 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.12144","last_updated":"2025-07-18T08:05:51Z","snapshot_observed_at":"2026-08-09T02:46:35.827559Z","submitted_at":"2025-07-16T11:22:18Z","title":"FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T16:59:54.816055Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2507.12144"},"observation_digest":"sha256:9b4adbb9ccbecbcb6fa58ee23636e84ea8680c9a393fde6919bdc0cde923749a","observation_id":"29b0d897-e7ea-4173-ba9d-1012a8c0de57","resolution":{"observed_at":"2026-08-06T16:59:54.816055Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-06T15:23:48.172128Z","title":"2022, A ConvNet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.16088","last_updated":"2025-07-24T14:46:14Z","snapshot_observed_at":"2026-08-14T01:55:22.554768Z","submitted_at":"2025-07-21T21:55:14Z","title":"Applying multimodal learning to Classify transient Detections Early (AppleCiDEr) I: Data set, methods, and infrastructure","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-06T15:23:48.172128Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2507.16088"},"observation_digest":"sha256:31a9b6fd2303559279fdb5c02719e1f0c2400aae8423d1f6aed140b39a067e4e","observation_id":"2c488006-6da8-4211-ac33-343461458fbf","resolution":{"observed_at":"2026-08-06T15:23:48.172128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-06T15:05:55.955262Z","title":"A ConvNet for the 2020s, Mar","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.16761","last_updated":"2025-07-24T14:58:44Z","snapshot_observed_at":"2026-08-15T05:50:40.170056Z","submitted_at":"2025-07-22T16:56:02Z","title":"Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T15:05:55.955262Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2507.16761"},"observation_digest":"sha256:a5383a053b06cc8e8ede5fc7bb1639df80b20addcaf3ad0609823a6e9e0df698","observation_id":"3f0b1c43-b696-485f-97a8-c2cd5e75cfd0","resolution":{"observed_at":"2026-08-06T15:05:55.955262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-06T12:30:26.652027Z","title":"A ConvNet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21739","last_updated":"2025-07-29T12:16:56Z","snapshot_observed_at":"2026-08-17T13:40:01.618136Z","submitted_at":"2025-07-29T12:16:56Z","title":"RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computing","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T12:30:26.652027Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2507.21739"},"observation_digest":"sha256:335b1b860086ad7520dc55d89f3da29f8fcbcee874e2d4144d718da9de76c535","observation_id":"eb06d2d1-ccbc-4a20-996d-efdc68ac2bcd","resolution":{"observed_at":"2026-08-06T12:30:26.652027Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-06T10:49:50.585497Z","title":"arXiv preprint arXiv:2201.03545 (2022) 8","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.23436","last_updated":"2025-07-31T11:16:00Z","snapshot_observed_at":"2026-08-11T00:24:57.364027Z","submitted_at":"2025-07-31T11:16:00Z","title":"Beyond Linear Bottlenecks: Spline-Based Knowledge Distillation for Culturally Diverse Art Style Classification","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T10:49:50.585497Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2507.23436"},"observation_digest":"sha256:c8cc5820d4d1f86633a0af93ce9dcdcd2dcba11b044b6179f9c2896a99c9e1c1","observation_id":"c82c90a5-5095-46a8-85c4-87af003664ea","resolution":{"observed_at":"2026-08-06T10:49:50.585497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T14:45:53.673996Z","title":"A ConvNet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.20919","last_updated":"2025-08-28T15:50:27Z","snapshot_observed_at":"2026-08-18T10:37:26.729027Z","submitted_at":"2025-08-28T15:50:27Z","title":"Classifying Mitotic Figures in the MIDOG25 Challenge with Deep Ensemble Learning and Rule Based Refinement","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:53.673996Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2508.20919"},"observation_digest":"sha256:8548d3a70a8e19fdf672372ffd1bd5d9bd1a3fce47d025db69fd3a7f74bad09d","observation_id":"439311cc-71c4-444c-bed9-040cf4646e45","resolution":{"observed_at":"2026-08-05T14:45:53.673996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T12:24:26.353023Z","title":"A ConvNet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.01642","last_updated":"2025-09-01T17:36:09Z","snapshot_observed_at":"2026-08-18T10:38:28.579566Z","submitted_at":"2025-09-01T17:36:09Z","title":"REVELIO -- Universal Multimodal Task Load Estimation for Cross-Domain Generalization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T12:24:26.353023Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2509.01642"},"observation_digest":"sha256:6b44e739fa8e00f72de6ffa723074f01a5a35d0c181bd830bde9585f880ee321","observation_id":"25be2599-90ca-45f2-9fac-322f77c9ab93","resolution":{"observed_at":"2026-08-05T12:24:26.353023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T10:24:26.064327Z","title":"A ConvNet for the 2020s, Mar","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.04150","last_updated":"2025-09-04T12:23:59Z","snapshot_observed_at":"2026-08-18T10:37:28.372963Z","submitted_at":"2025-09-04T12:23:59Z","title":"Revisiting Simple Baselines for In-The-Wild Deepfake Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T10:24:26.064327Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2509.04150"},"observation_digest":"sha256:4409c5ee0c96f85498c706566041af5b1f528412a0bb167751ab664b1e9a8498","observation_id":"60c2dacc-899b-48ec-b402-0f8dd76514a6","resolution":{"observed_at":"2026-08-05T10:24:26.064327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T04:40:48.000332Z","title":"A convnet for the 2020s.CoRR, abs/2201.03545, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.06006","last_updated":"2025-09-07T10:43:29Z","snapshot_observed_at":"2026-08-18T22:34:00.973762Z","submitted_at":"2025-09-07T10:43:29Z","title":"Khana: A Comprehensive Indian Cuisine Dataset","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T04:40:48.000332Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2509.06006"},"observation_digest":"sha256:5656a132a2d285077aa575ca4fa91a0de402cff0c0de68ef3854025a3e3de755","observation_id":"4a8c0f3a-8a1a-4d24-8a3a-4dc8521aa18f","resolution":{"observed_at":"2026-08-05T04:40:48.000332Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2602.09524","last_updated":"2026-05-09T08:05:39Z","snapshot_observed_at":"2026-08-13T03:43:22.368443Z","submitted_at":"2026-02-10T08:27:20Z","title":"HLGFA: High-Low Resolution Guided Feature Alignment for Unsupervised Anomaly Detection","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-16T03:05:37.320403Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2602.09524"},"observation_digest":"sha256:4621730411870fdd37e9e3baed75553edde68c958814b24983798c40298b496a","observation_id":"bc31fdd0-e459-4c15-95f7-cc720853ae47","resolution":{"observed_at":"2026-05-16T03:07:11.871760Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-03T02:51:55.440595Z","title":"Loshchilov, I","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.09689","last_updated":"2026-06-18T12:30:19Z","snapshot_observed_at":"2026-08-18T09:41:25.313071Z","submitted_at":"2026-02-10T11:44:19Z","title":"Model soups need only one ingredient","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-03T02:51:55.440595Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2602.09689"},"observation_digest":"sha256:ab1fd817dd505de6891e7e53f9b9e4c7ed8053d3a5ffef24e06438117d45e159","observation_id":"54be3cdb-b1ad-412f-8948-62f1591afa58","resolution":{"observed_at":"2026-08-03T02:51:55.440595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2602.20028","last_updated":"2026-04-29T12:37:35Z","snapshot_observed_at":"2026-08-12T16:41:21.218465Z","submitted_at":"2026-02-20T15:13:14Z","title":"Descriptor: Parasitoid Wasps and Associated Hymenoptera Dataset (DAPWH)","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-15T20:46:43.938789Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2602.20028"},"observation_digest":"sha256:306369d859d70773635a715a4c7e7468b104137c69efba7c4e5179dd054a6525","observation_id":"e2fa6f20-5524-48eb-bb0b-99a0ea6d4540","resolution":{"observed_at":"2026-05-15T20:50:17.391033Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-02T19:09:10.298281Z","title":", author Mao, H","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.03503","last_updated":"2026-03-03T20:23:11Z","snapshot_observed_at":"2026-08-15T02:23:53.916453Z","submitted_at":"2026-03-03T20:23:11Z","title":"Geographically-Weighted Weakly Supervised Bayesian High-Resolution Transformer for 200m Resolution Pan-Arctic Sea Ice Concentration Mapping and Uncertainty Estimation using Sentinel-1, RCM, and AMSR2 Data","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-02T19:09:10.298281Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2603.03503"},"observation_digest":"sha256:ad9e1d8c1cb7791673aa940c770bdd8af73fbfddc621bfafa082d8465559d107","observation_id":"9f8ebb29-5e1e-41b9-bf62-e6a8e388f0bb","resolution":{"observed_at":"2026-08-02T19:09:10.298281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2604.10634","last_updated":"2026-05-13T15:38:39Z","snapshot_observed_at":"2026-08-15T00:51:21.357802Z","submitted_at":"2026-04-12T13:22:23Z","title":"NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-10T16:37:56.306745Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2604.10634"},"observation_digest":"sha256:5d7c9dacefbf6e6f206acfaf4fd658aa5b8142b82e5e159fa0d31751a201cc8e","observation_id":"db7b5099-6f42-4fb5-99ac-df697ff1b283","resolution":{"observed_at":"2026-05-11T08:26:01.877624Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2604.10634","last_updated":"2026-05-13T15:38:39Z","snapshot_observed_at":"2026-08-15T00:51:21.357802Z","submitted_at":"2026-04-12T13:22:23Z","title":"NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-14T21:25:14.527838Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2604.10634"},"observation_digest":"sha256:6c8a978a4bc67af183c2ba86697610a58dab0bd568cf446867c411adce04144a","observation_id":"98bf2743-f6ea-435e-ba60-5b61b2b8e019","resolution":{"observed_at":"2026-05-14T21:27:59.823871Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2604.18067","last_updated":"2026-04-21T08:28:13Z","snapshot_observed_at":"2026-08-16T08:49:07.490781Z","submitted_at":"2026-04-20T10:35:33Z","title":"Towards Real-Time ECG and EMG Modeling on $\\mu$NPUs","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-10T05:57:26.793743Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2604.18067"},"observation_digest":"sha256:daccd4d6ab8a2c31f3980b828f17920650e5116c396448cd37ee290fb27b9a76","observation_id":"a9c6ad38-07c9-41d5-b551-1730212a4408","resolution":{"observed_at":"2026-05-10T06:01:13.519407Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2604.21780","last_updated":"2026-04-23T15:38:11Z","snapshot_observed_at":"2026-08-13T15:12:07.608270Z","submitted_at":"2026-04-23T15:38:11Z","title":"Only Brains Align with Brains: Cross-Region Alignment Patterns Expose Limits of Normative Models","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-05-08T13:13:03.129195Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2604.21780"},"observation_digest":"sha256:58e51850426662ae04b3fb47bd214d650c663b64be685b7595c32a990941f8b2","observation_id":"90cb6202-70ab-474a-a514-73359034531e","resolution":{"observed_at":"2026-05-11T18:56:07.556663Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2604.24913","last_updated":"2026-04-27T18:48:40Z","snapshot_observed_at":"2026-08-14T18:41:36.230215Z","submitted_at":"2026-04-27T18:48:40Z","title":"Generative diffusion models for spatiotemporal influenza forecasting","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-08T04:08:29.810085Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2604.24913"},"observation_digest":"sha256:bc14a32bd76cd49b1033c897a81cc7e8658246f1a7f43de166d6d759d2eb5865","observation_id":"1c85eb31-f50c-4904-9058-a57776ab5401","resolution":{"observed_at":"2026-05-09T00:09:29.491623Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2604.26324","last_updated":"2026-04-29T06:12:09Z","snapshot_observed_at":"2026-08-16T07:24:44.521612Z","submitted_at":"2026-04-29T06:12:09Z","title":"Federated Medical Image Classification under Class and Domain Imbalance exploiting Synthetic Sample Generation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-07T13:52:23.634115Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2604.26324"},"observation_digest":"sha256:ad618cc0e75e723f400625053ae0cc9260ae3a0589f624e137faa75197eba09f","observation_id":"de7b82c2-a009-45c5-b337-da841777c053","resolution":{"observed_at":"2026-05-12T08:46:25.634533Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2605.05549","last_updated":"2026-05-07T00:53:47Z","snapshot_observed_at":"2026-08-15T06:31:08.079014Z","submitted_at":"2026-05-07T00:53:47Z","title":"A Novel Graph-Regulated Disentangling Mamba Model with Sparse Tokens for Enhanced Tree Species Classification from MODIS Time Series","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-05-09T16:38:51.074609Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2605.05549"},"observation_digest":"sha256:d00a1f16fd730405172c3f3e8c334db453f4a45ece8f7a08831fce723413c4f0","observation_id":"2793abd3-ef87-4572-810a-fad63eeb79be","resolution":{"observed_at":"2026-05-09T21:48:37.038855Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2605.06944","last_updated":"2026-07-23T17:55:20Z","snapshot_observed_at":"2026-08-15T00:59:55.620207Z","submitted_at":"2026-05-07T21:04:05Z","title":"AIMIP Phase 1: systematic evaluations of AI weather and climate models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-20T23:06:35.598118Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2605.06944"},"observation_digest":"sha256:c67fc499911eeaff91a6c1238491d56b7dd17aad823dabab5817be79e270121c","observation_id":"54ebab35-7450-4a65-8f07-0c74e2e26e04","resolution":{"observed_at":"2026-05-20T23:09:12.365161Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-07-15T11:15:52.552742Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.06944","last_updated":"2026-07-23T17:55:20Z","snapshot_observed_at":"2026-08-15T00:59:55.620207Z","submitted_at":"2026-05-07T21:04:05Z","title":"AIMIP Phase 1: systematic evaluations of AI weather and climate models","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-15T11:15:52.552742Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2605.06944"},"observation_digest":"sha256:100014a5cd60c46f8b9ef6ccb63347f7a62740a67d23eb0effe5e2143edeba21","observation_id":"bff39c7d-bdb2-4c12-b5b4-1667410bcdbe","resolution":{"observed_at":"2026-07-15T11:15:52.552742Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-02T14:43:41.032219Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.06944","last_updated":"2026-07-23T17:55:20Z","snapshot_observed_at":"2026-08-15T00:59:55.620207Z","submitted_at":"2026-05-07T21:04:05Z","title":"AIMIP Phase 1: systematic evaluations of AI weather and climate models","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T14:43:41.032219Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2605.06944"},"observation_digest":"sha256:c73e0b29ab634faafa2056c0e645127b6a456bfc18dbf390ef06478d9ccb5f20","observation_id":"cde1fa1c-fd0f-4a84-87bd-4347bb661f17","resolution":{"observed_at":"2026-08-02T14:43:41.032219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2605.11107","last_updated":"2026-05-11T18:13:05Z","snapshot_observed_at":"2026-08-11T03:45:15.335189Z","submitted_at":"2026-05-11T18:13:05Z","title":"Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-13T07:26:02.947081Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2605.11107"},"observation_digest":"sha256:ae823db23cfec08785c0fbbf550bb0292f3ea0a27c89a567612bb4d39f829b50","observation_id":"df0210fc-678a-4010-8bba-05e55f90c12e","resolution":{"observed_at":"2026-05-13T07:27:29.666150Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2605.13555","last_updated":"2026-05-13T13:59:03Z","snapshot_observed_at":"2026-08-13T15:09:42.557382Z","submitted_at":"2026-05-13T13:59:03Z","title":"Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-05-14T18:14:26.793684Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2605.13555"},"observation_digest":"sha256:dbd00ce6283ab44108385b899898a543b2ad0a234d1f3d915a853b4eff54dcef","observation_id":"369cb43c-dab6-4411-b311-ab2af1fbcd07","resolution":{"observed_at":"2026-05-14T18:17:35.190295Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2605.20250","last_updated":"2026-05-18T08:02:28Z","snapshot_observed_at":"2026-08-15T15:40:27.028915Z","submitted_at":"2026-05-18T08:02:28Z","title":"Physics-informed convolutional neural networks for fluid flow through porous media","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-05-21T08:21:16.460521Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2605.20250"},"observation_digest":"sha256:e4374ad7724424fd60470af547679a9753204957fcd08d7dbd7b5627bfc1f795","observation_id":"79b4ccc7-d078-403b-9e64-70e957da8e2c","resolution":{"observed_at":"2026-05-21T08:24:03.522222Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2606.01819","last_updated":"2026-06-01T07:34:10Z","snapshot_observed_at":"2026-08-03T07:16:33.801181Z","submitted_at":"2026-06-01T07:34:10Z","title":"Hist2Style: Histogram-Guided Stylization with Bilateral Grids","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-28T15:23:57.653734Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2606.01819"},"observation_digest":"sha256:c99d7fedd2339ca9278de6bdc3632371604b8f9630c309a358b5718d87b4cd79","observation_id":"01eaec12-0e37-4a6c-8434-5df976e30860","resolution":{"observed_at":"2026-07-01T22:26:17.663163Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2606.03512","last_updated":"2026-06-02T11:29:00Z","snapshot_observed_at":"2026-08-16T22:09:54.313997Z","submitted_at":"2026-06-02T11:29:00Z","title":"SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T10:12:08.238917Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2606.03512"},"observation_digest":"sha256:b07a2f92b66e3fef3c4f12564092e8bf9b9012a3d3074988a693c51a0b069644","observation_id":"7ac24bb5-4567-4a58-babf-fe11e7cd616d","resolution":{"observed_at":"2026-07-02T03:16:34.503050Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2606.11315","last_updated":"2026-06-09T18:01:16Z","snapshot_observed_at":"2026-07-06T23:50:25.158108Z","submitted_at":"2026-06-09T18:01:16Z","title":"Spiral arms across cosmic time: JWST measurements of the pitch angles of spiral galaxies at $z<3.5$","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-27T12:28:30.714369Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2606.11315"},"observation_digest":"sha256:d62e519abde857ebfbe551fce9587a2870642e02fdb1925be694a31e629d66ef","observation_id":"ad595387-7614-4c1e-8553-5cd5f2b29f19","resolution":{"observed_at":"2026-06-27T12:30:55.070520Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2606.20561","last_updated":"2026-06-18T17:59:48Z","snapshot_observed_at":"2026-08-15T21:36:13.012997Z","submitted_at":"2026-06-18T17:59:48Z","title":"TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-06-26T18:22:13.147215Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2606.20561"},"observation_digest":"sha256:6abc5f2ae9733ecfb5d72840d05fe72a2ddf2064ef93842f5936799f4fde845f","observation_id":"f963b167-fb0c-4087-8d15-af3c27863af8","resolution":{"observed_at":"2026-07-04T03:09:30.198638Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2606.26894","last_updated":"2026-06-25T11:26:57Z","snapshot_observed_at":"2026-07-07T00:01:10.711037Z","submitted_at":"2026-06-25T11:26:57Z","title":"Modeling Local, Global, and Cross-Modal Context in Multimodal 3D MRI","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-06-26T05:28:43.159404Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2606.26894"},"observation_digest":"sha256:8aae6326672b21b49ac0dca78f2811fdcef9ef445189b0af7cf643426ed4c01b","observation_id":"c7cecaa6-c869-4f75-87b0-adc22814f2d7","resolution":{"observed_at":"2026-07-04T13:09:50.655080Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2606.29723","last_updated":"2026-06-29T03:00:54Z","snapshot_observed_at":"2026-08-14T13:46:27.519650Z","submitted_at":"2026-06-29T03:00:54Z","title":"ScaleAware-JEPA: Latent Representation for Discovery in Multiscale Physical Fields","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-06-30T07:47:27.281103Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2606.29723"},"observation_digest":"sha256:baa29d8995a0208fbf834d038ece5616329984dec1116908187c35f07a3c82a9","observation_id":"0c814418-d099-4089-9edd-1f8c864f30e8","resolution":{"observed_at":"2026-06-30T08:04:28.631742Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2606.30108","last_updated":"2026-06-29T10:44:51Z","snapshot_observed_at":"2026-08-15T01:22:40.083293Z","submitted_at":"2026-06-29T10:44:51Z","title":"LETT-NeXt: A Lightweight RECIST-Guided Model for 3D CT Lesion Segmentation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-30T06:51:20.059187Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2606.30108"},"observation_digest":"sha256:61cdc56f6e7fa38263872bc3a23c413568910aa9b9be63e015fdca7e4177d03f","observation_id":"6dda23b5-3bfe-4769-a12c-c8061311bc06","resolution":{"observed_at":"2026-06-30T06:54:20.427932Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":"2201.03545","doi":"10.48550/arxiv.2201.03545","metadata_source":"arxiv_reference","pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"author Mao, H","venue":"arXiv (Cornell University)","work_id":"b4cbe008-c235-4449-9c2b-cacb84d779e1","year":2022},"citing_paper":{"arxiv_id":"2607.00228","last_updated":"2026-06-30T22:15:54Z","snapshot_observed_at":"2026-08-07T17:45:09.124348Z","submitted_at":"2026-06-30T22:15:54Z","title":"Leveraging Multimodality for Real-Time Classification of Transients and Variables found by the Zwicky Transient Facility","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-02T17:02:45.133692Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2607.00228"},"observation_digest":"sha256:9701afaa4749888db01f17a2cb11c46d76659a2cf11976651397e4f8c8abab98","observation_id":"8506bd27-ce87-4289-9bc3-61334ad0294c","resolution":{"observed_at":"2026-07-02T17:07:12.037722Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-02T05:51:36.253921Z","title":"A convnet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.13234","last_updated":"2026-07-14T19:53:09Z","snapshot_observed_at":"2026-08-13T12:20:16.706977Z","submitted_at":"2026-07-14T19:53:09Z","title":"Continuously Evolving Deepfake Detection: An Architecture and Public-Benchmark Evaluation of a Dynamic Detection System","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T05:51:36.253921Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2607.13234"},"observation_digest":"sha256:f7cc00c483160d03e21243ce2676d30a2c7569d9802f74db10ebbdc8dce1a17f","observation_id":"982ff3da-c32d-4859-ad33-6c28703c644d","resolution":{"observed_at":"2026-08-02T05:51:36.253921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-01T19:37:04.190732Z","title":"2201.03545 , archivePrefix=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.16929","last_updated":"2026-07-18T18:46:49Z","snapshot_observed_at":"2026-08-18T00:48:40.301757Z","submitted_at":"2026-07-18T18:46:49Z","title":"C3DIR: A Deep Learning 3-Dimensional Cloud Property Retrieval Scheme for Passive Satellite Imagers","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-01T19:37:04.190732Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2607.16929"},"observation_digest":"sha256:8603af1f0383b1d2e9b30eaeb8b155952d63a0204a4aec5d8d2135b2e79f9a73","observation_id":"18656830-ad78-4286-b6d1-5b1b818c44ec","resolution":{"observed_at":"2026-08-01T19:37:04.190732Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-01T12:48:17.176805Z","title":"A convnet for the 2020s, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.19332","last_updated":"2026-07-21T17:51:38Z","snapshot_observed_at":"2026-08-16T07:04:05.820221Z","submitted_at":"2026-07-21T17:51:38Z","title":"ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T12:48:17.176805Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2607.19332"},"observation_digest":"sha256:02a22d2f766299fe70ba49a05de9a60b5a7083a494ce838ffd6bcb2ce0845a62","observation_id":"c89745b7-2163-4248-913c-8946aac223c8","resolution":{"observed_at":"2026-08-01T12:48:17.176805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-01T07:56:36.865756Z","title":"A convnet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21290","last_updated":"2026-07-23T13:12:51Z","snapshot_observed_at":"2026-08-18T14:02:49.278618Z","submitted_at":"2026-07-23T13:12:51Z","title":"Multi-Task Learning for Heterogeneous Prediction from Video Game State with Transfer Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T07:56:36.865756Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2607.21290"},"observation_digest":"sha256:efc802a77598cb026e32dd86b6909d40f8d80fff282246d0d377a2e776fb312e","observation_id":"f6db68fc-7cb5-49bf-bb70-9c6d183484dc","resolution":{"observed_at":"2026-08-01T07:56:36.865756Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-01T05:16:02.196682Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22793","last_updated":"2026-07-24T13:31:22Z","snapshot_observed_at":"2026-08-18T10:39:26.814217Z","submitted_at":"2026-07-24T13:31:22Z","title":"Small, Bias-Free, Blind and Convolutional Denoiser: A compact ConvNeXt U-Net for blind Gaussian color-image denoising","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-01T05:16:02.196682Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2607.22793"},"observation_digest":"sha256:eff8efaf8bf363de67f774ea14c6b04bffb3f2c1f656a11a8e236f614caabd34","observation_id":"de8564f3-9817-43c8-b185-e4f8ba04dc1d","resolution":{"observed_at":"2026-08-01T05:16:02.196682Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-07-30T17:15:02.301627Z","title":"A convnet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23633","last_updated":"2026-07-26T12:38:06Z","snapshot_observed_at":"2026-08-14T23:26:11.378228Z","submitted_at":"2026-07-26T12:38:06Z","title":"A Controlled Visual-Backbone Benchmark for Multimodal Short-Term Solar Irradiance Forecasting","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-30T17:15:02.301627Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2607.23633"},"observation_digest":"sha256:81764d87ff71b21e0d558fe4e916ba526780aadd36b257cb467354a58865773c","observation_id":"dc4c7987-b6e1-41e3-836e-38f18e285193","resolution":{"observed_at":"2026-07-30T17:15:02.301627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2201.03545/citation-record","integrity":"/paper/2201.03545/integrity","json":"/paper/2201.03545/citation-record.json","paper":"/paper/2201.03545"},"outbound":[],"paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 73 inbound Pith citation observations for arXiv:2201.03545."}