{"as_of":"2026-08-18T10:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a75d5a9ce705a1a98fd0757cfb3b827c51bbfa2dedd49d939c8cd9acdba99130","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":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":28,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T20:13:23.857289Z","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":1133,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-12T12:02:57.728447Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.17556","last_updated":"2024-11-26T16:18:48Z","snapshot_observed_at":"2026-08-18T01:50:23.176523Z","submitted_at":"2024-11-26T16:18:48Z","title":"TAFM-Net: A Novel Approach to Skin Lesion Segmentation Using Transformer Attention and Focal Modulation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T12:02:57.728447Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2411.17556"},"observation_digest":"sha256:af716d0a1714a3df6629115658c39eb1e30350176e3401d7fcacd8aa135f26ae","observation_id":"1d54c69c-9ab8-4296-8259-a9b74766b456","resolution":{"observed_at":"2026-08-12T12:02:57.728447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-12T19:06:07.443442Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01622","last_updated":"2024-11-17T11:50:09Z","snapshot_observed_at":"2026-08-14T19:09:54.170264Z","submitted_at":"2024-11-17T11:50:09Z","title":"Image Forgery Localization via Guided Noise and Multi-Scale Feature Aggregation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T19:06:07.443442Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2412.01622"},"observation_digest":"sha256:8dc3ebc56440041bbfcfd08d66be20d6549992196b8ac65bfcc899cec9e93fff","observation_id":"e42e7059-3c70-48ee-8c82-387cf5e0f38e","resolution":{"observed_at":"2026-08-12T19:06:07.443442Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-11T14:52:42.207966Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11574","last_updated":"2024-12-16T09:01:32Z","snapshot_observed_at":"2026-08-16T10:19:28.474489Z","submitted_at":"2024-12-16T09:01:32Z","title":"PyPotteryLens: An Open-Source Deep Learning Framework for Automated Digitisation of Archaeological Pottery Documentation","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-11T14:52:42.207966Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2412.11574"},"observation_digest":"sha256:b956aa2b80ab77652cbe9f8629d6cf9d5faf7a3cc774de8fdcb9b6a31f6ab2d8","observation_id":"203a89db-665e-4b81-8f3d-54db5c924ded","resolution":{"observed_at":"2026-08-11T14:52:42.207966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-11T12:50:11.833181Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.13794","last_updated":"2024-12-18T12:39:01Z","snapshot_observed_at":"2026-08-15T21:27:37.072314Z","submitted_at":"2024-12-18T12:39:01Z","title":"MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-11T12:50:11.833181Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2412.13794"},"observation_digest":"sha256:36d73ff5f3ce298f914641bee7e494421f083d34e27d7d829ba2c099a4942e1c","observation_id":"41743e72-554e-4797-8c6e-8b818da9bc50","resolution":{"observed_at":"2026-08-11T12:50:11.833181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-11T11:24:16.979226Z","title":"V., 2021, EfficientNetV2 : Smaller Models and Faster Training , @doi 10.48550/arXiv.2104.00298 , http://arxiv.org/abs/2104.00298","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.15533","last_updated":"2024-12-20T03:48:12Z","snapshot_observed_at":"2026-08-17T19:37:47.603532Z","submitted_at":"2024-12-20T03:48:12Z","title":"From Galaxy Zoo DECaLS to BASS/MzLS: detailed galaxy morphology classification with unsupervised domain adaption","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-11T11:24:16.979226Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2412.15533"},"observation_digest":"sha256:ee475170e873dfad32ee9d04e6153790fb0be6b74692182058bdc9aa3adb2ae9","observation_id":"1711c75d-b9c0-4a01-a96c-614ffe492889","resolution":{"observed_at":"2026-08-11T11:24:16.979226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-10T17:35:00.776358Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.12085","last_updated":"2025-01-21T12:22:15Z","snapshot_observed_at":"2026-08-11T00:55:23.941758Z","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":15,"source":"pdf_text","source_observed_at":"2026-08-10T17:35:00.776358Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2501.12085"},"observation_digest":"sha256:6ee22f522df56440a8c9095d8fbadf63423d10b34a0b95ab6ecbf53ccead54d1","observation_id":"03a8c4cb-b465-4ad4-a67c-24a668635494","resolution":{"observed_at":"2026-08-10T17:35:00.776358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-10T17:19:59.883125Z","title":"Efficientnetv2: Smaller models and faster training,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.12323","last_updated":"2025-01-24T12:58:30Z","snapshot_observed_at":"2026-08-10T17:14:09.651750Z","submitted_at":"2025-01-21T17:42:06Z","title":"Deep Learning Based Segmentation of Blood Vessels from H&E Stained Oesophageal Adenocarcinoma Whole-Slide Images","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T17:19:59.883125Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2501.12323"},"observation_digest":"sha256:9ae76a8e082e33da9b93f8170fb1bf89ce63e1286a4a2f4c1a34f9ba15833089","observation_id":"3de22eb3-24a4-4eff-8d68-e4fe8e7e823f","resolution":{"observed_at":"2026-08-10T17:19:59.883125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-09T21:57:13.506533Z","title":"EfficientNetV2: Smaller models and faster training,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.506533Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:c63968e7d784db9b09f464833a56e80afb082ff5464296a179340e0ba73864c3","observation_id":"b396912e-7a3d-4a69-bf50-25f1cf43abac","resolution":{"observed_at":"2026-08-09T21:57:13.506533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-08T17:06:10.324496Z","title":"Tancik, M., Srinivasan, P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.06018","last_updated":"2026-05-24T16:33:35Z","snapshot_observed_at":"2026-08-08T16:57:59.773148Z","submitted_at":"2025-02-09T20:21:43Z","title":"Kolmogorov-Arnold Fourier Networks","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T17:06:10.324496Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2502.06018"},"observation_digest":"sha256:5f7400a0d380dd1645085e6765cea4b821780075c5e6a950f17133cb2b3cfb0d","observation_id":"00a93310-c33a-4965-b385-318882a09e24","resolution":{"observed_at":"2026-08-08T17:06:10.324496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-08T12:20:08.099329Z","title":"Efficientnetv2: Smaller models and faster training,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.07855","last_updated":"2025-06-13T12:20:30Z","snapshot_observed_at":"2026-08-13T21:16:14.932934Z","submitted_at":"2025-02-11T14:04:43Z","title":"Vision-Language Models for Edge Networks: A Comprehensive Survey","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T12:20:08.099329Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2502.07855"},"observation_digest":"sha256:d9ce558af828cb92cfe8e7af2e2b27a4a7e7b6ab38bc55bf6625e62e4022e17c","observation_id":"5537b63d-342e-4506-bf55-674b3b5ffff7","resolution":{"observed_at":"2026-08-08T12:20:08.099329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-07T15:36:31.742776Z","title":null,"venue":null,"work_id":null,"year":2021},"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":19,"source":"pdf_text","source_observed_at":"2026-08-07T15:36:31.742776Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2505.14572"},"observation_digest":"sha256:975dbbe2f657516c20438d6140541cc29f6a36c74bb2ab745c235f84f04d9c02","observation_id":"7db232a6-5dd5-442e-b531-2ad530f4d1b8","resolution":{"observed_at":"2026-08-07T15:36:31.742776Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-07T13:08:30.596227Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22609","last_updated":"2025-05-28T17:24:33Z","snapshot_observed_at":"2026-08-16T20:50:28.925100Z","submitted_at":"2025-05-28T17:24:33Z","title":"Chest Disease Detection In X-Ray Images Using Deep Learning Classification Method","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T13:08:30.596227Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2505.22609"},"observation_digest":"sha256:3b00fc0a5fbee2f8ee41ecc5c098aa0cf42761c178811ae9188d575e5fb13bf6","observation_id":"173cc746-d159-4b12-b1c4-0d13f6ef0ad5","resolution":{"observed_at":"2026-08-07T13:08:30.596227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-06T19:03:12.361797Z","title":"EfficientNetV2: Smaller Models and Faster Training,","venue":null,"work_id":null,"year":2021},"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":34,"source":"pdf_text","source_observed_at":"2026-08-06T19:03:12.361797Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2507.06687"},"observation_digest":"sha256:1bfd4b81d2b824d5451bd7cd758ecd19d1e4730e601edd8840011073d02f1ec5","observation_id":"16340daa-e2be-4f96-b20e-cf644f51a53d","resolution":{"observed_at":"2026-08-06T19:03:12.361797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-06T16:16:22.932147Z","title":"https://doi.org/10.48550/arXiv.2104.00298","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.13974","last_updated":"2025-07-18T14:38:25Z","snapshot_observed_at":"2026-08-18T01:41:21.094693Z","submitted_at":"2025-07-18T14:38:25Z","title":"Leveraging Pathology Foundation Models for Panoptic Segmentation of Melanoma in H&E Images","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T16:16:22.932147Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2507.13974"},"observation_digest":"sha256:a81ac8ea4c5b83975924a15d2b618e7d41ee5b79bf862dc0cffa50740789ae86","observation_id":"64e90de0-2da6-438f-b538-66bbe434a421","resolution":{"observed_at":"2026-08-06T16:16:22.932147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":"2104.00298","doi":"10.48550/arxiv.2104.00298","metadata_source":"arxiv_reference","pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Le , title =","venue":"arXiv (Cornell University)","work_id":"3f1080e6-ab18-48ed-8ca4-a21a97c6887a","year":2021},"citing_paper":{"arxiv_id":"2507.23315","last_updated":"2025-10-16T13:29:58Z","snapshot_observed_at":"2026-07-06T22:05:38.642936Z","submitted_at":"2025-07-31T07:47:30Z","title":"Analysis of Hyperparameter Optimization Effects on Lightweight Deep Models for Real-Time Image Classification","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-19T02:40:10.578804Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2507.23315"},"observation_digest":"sha256:6b67ae3ba1eef91055fbe88db85f3667874bdc03cca567a569c4d510ca95c0d3","observation_id":"5a5ca558-fb7f-4e22-89d5-8d19b13e1b10","resolution":{"observed_at":"2026-05-19T02:41:59.846447Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-04T19:24:21.507572Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.09311","last_updated":"2025-09-11T09:54:25Z","snapshot_observed_at":"2026-08-16T02:44:26.539551Z","submitted_at":"2025-09-11T09:54:25Z","title":"Image Recognition with Vision and Language Embeddings of VLMs","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-04T19:24:21.507572Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2509.09311"},"observation_digest":"sha256:31533636cf66ddef06afc65964792634cc0ab6248454e44b1d407f1f9a33311a","observation_id":"1e4496f4-70f1-4cd2-ab1c-2ca998b2b319","resolution":{"observed_at":"2026-08-04T19:24:21.507572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-04T11:17:36.319958Z","title":"EfficientNetV2: Sm aller Models and Faster Training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.06299","last_updated":"2025-10-07T14:29:37Z","snapshot_observed_at":"2026-08-07T17:29:52.545790Z","submitted_at":"2025-10-07T14:29:37Z","title":"Scalable deep fusion of spaceborne lidar and synthetic aperture radar for global forest structural complexity mapping","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T11:17:36.319958Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2510.06299"},"observation_digest":"sha256:2ee982a9f1e1455128d5c2a2c33a0f5753e17341882e02bb353871566a2e43cf","observation_id":"d6ea1a99-e98a-4343-b199-e34a45013092","resolution":{"observed_at":"2026-08-04T11:17:36.319958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":"2104.00298","doi":"10.48550/arxiv.2104.00298","metadata_source":"arxiv_reference","pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Le , title =","venue":"arXiv (Cornell University)","work_id":"3f1080e6-ab18-48ed-8ca4-a21a97c6887a","year":2021},"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":34,"source":"pdf_text","source_observed_at":"2026-05-15T20:46:43.938789Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2602.20028"},"observation_digest":"sha256:69e47e1f53513575238b8937435fa1c54ce2c4caab1e42f0471ddf669fd5bdc1","observation_id":"9ff2b9d9-f63e-4788-9580-31cd748679f5","resolution":{"observed_at":"2026-05-15T20:50:17.403778Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":"2104.00298","doi":"10.48550/arxiv.2104.00298","metadata_source":"arxiv_reference","pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Le , title =","venue":"arXiv (Cornell University)","work_id":"3f1080e6-ab18-48ed-8ca4-a21a97c6887a","year":2021},"citing_paper":{"arxiv_id":"2604.03203","last_updated":"2026-04-03T17:25:17Z","snapshot_observed_at":"2026-08-11T05:04:07.160192Z","submitted_at":"2026-04-03T17:25:17Z","title":"PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-13T20:42:13.955407Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2604.03203"},"observation_digest":"sha256:c22631de0942e56a12bafa4d0d4611e114046dbea71b7461845aed54579b3777","observation_id":"17f03da3-f2ae-4a4b-9fa0-521a4bf4b288","resolution":{"observed_at":"2026-05-13T20:43:14.826860Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":"2104.00298","doi":"10.48550/arxiv.2104.00298","metadata_source":"arxiv_reference","pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Le , title =","venue":"arXiv (Cornell University)","work_id":"3f1080e6-ab18-48ed-8ca4-a21a97c6887a","year":2021},"citing_paper":{"arxiv_id":"2605.01075","last_updated":"2026-05-01T20:17:33Z","snapshot_observed_at":"2026-07-06T23:14:24.758147Z","submitted_at":"2026-05-01T20:17:33Z","title":"Neighbor2Inverse: Self-Supervised Denoising for Low-Dose Region-of-Interest Phase Contrast CT","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-09T19:17:11.807520Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2605.01075"},"observation_digest":"sha256:d75f7415ce9765abeeb2811da1cd9512e93c6bec34e6d252cd3032bf2f210de1","observation_id":"de41d1b0-8a7a-4878-b0fb-38e8f538aa62","resolution":{"observed_at":"2026-05-11T15:46:41.435273Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":"2104.00298","doi":"10.48550/arxiv.2104.00298","metadata_source":"arxiv_reference","pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Le , title =","venue":"arXiv (Cornell University)","work_id":"3f1080e6-ab18-48ed-8ca4-a21a97c6887a","year":2021},"citing_paper":{"arxiv_id":"2605.02614","last_updated":"2026-05-04T14:02:45Z","snapshot_observed_at":"2026-07-31T09:04:41.341111Z","submitted_at":"2026-05-04T14:02:45Z","title":"Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-08T18:22:40.334293Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2605.02614"},"observation_digest":"sha256:debaf273eb7a0fe5a519df1490717ea36509a46eb99163b28c5f99e7a59266ac","observation_id":"bcd388ae-9b68-4649-b75f-6059d954283d","resolution":{"observed_at":"2026-05-08T18:23:55.790157Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":"2104.00298","doi":"10.48550/arxiv.2104.00298","metadata_source":"arxiv_reference","pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Le , title =","venue":"arXiv (Cornell University)","work_id":"3f1080e6-ab18-48ed-8ca4-a21a97c6887a","year":2021},"citing_paper":{"arxiv_id":"2605.15484","last_updated":"2026-05-15T00:01:11Z","snapshot_observed_at":"2026-08-15T05:40:09.581364Z","submitted_at":"2026-05-15T00:01:11Z","title":"When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-05-19T16:21:02.198882Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2605.15484"},"observation_digest":"sha256:8789d3f9f2ca51d85c7685633d6da4551c1fe917bab416ef8fd4948fb564d719","observation_id":"6c9f89bf-55d7-4676-91ef-2ca4cf5dd11e","resolution":{"observed_at":"2026-05-19T16:22:39.118619Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":"2104.00298","doi":"10.48550/arxiv.2104.00298","metadata_source":"arxiv_reference","pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Le , title =","venue":"arXiv (Cornell University)","work_id":"3f1080e6-ab18-48ed-8ca4-a21a97c6887a","year":2021},"citing_paper":{"arxiv_id":"2605.19856","last_updated":"2026-05-19T13:49:30Z","snapshot_observed_at":"2026-08-15T19:30:13.003381Z","submitted_at":"2026-05-19T13:49:30Z","title":"StableGrad: Backward Scale Control without Batch Normalization","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-05-20T06:48:43.034925Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2605.19856"},"observation_digest":"sha256:ddc969c12b0c0065313825c56241f7146df978c7edc7066ad53933d48a78dad5","observation_id":"4f1ded5e-37df-4e7c-a3d9-281e5c5cba8d","resolution":{"observed_at":"2026-05-20T06:53:06.023836Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":"2104.00298","doi":"10.48550/arxiv.2104.00298","metadata_source":"arxiv_reference","pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Le , title =","venue":"arXiv (Cornell University)","work_id":"3f1080e6-ab18-48ed-8ca4-a21a97c6887a","year":2021},"citing_paper":{"arxiv_id":"2605.26370","last_updated":"2026-05-25T22:37:11Z","snapshot_observed_at":"2026-08-03T22:58:07.636698Z","submitted_at":"2026-05-25T22:37:11Z","title":"Joint Instance Segmentation and Geometric Attribute Regression for Roof Structures in Aerial Imagery","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-29T22:23:49.322588Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2605.26370"},"observation_digest":"sha256:0f778d25aa3c8895d66a0c1df4d95180c1c3483ce3beada69bbc37dfa9caa457","observation_id":"7a02ff58-4d6c-470e-92b8-28dc312e6014","resolution":{"observed_at":"2026-06-29T22:23:59.762408Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":"2104.00298","doi":"10.48550/arxiv.2104.00298","metadata_source":"arxiv_reference","pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Le , title =","venue":"arXiv (Cornell University)","work_id":"3f1080e6-ab18-48ed-8ca4-a21a97c6887a","year":2021},"citing_paper":{"arxiv_id":"2606.10372","last_updated":"2026-06-09T03:34:11Z","snapshot_observed_at":"2026-08-17T20:32:15.222900Z","submitted_at":"2026-06-09T03:34:11Z","title":"ClinReadNet: A clinical reading-inspired network for low-dose abdominal CT image quality assessment","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-27T14:05:04.834108Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2606.10372"},"observation_digest":"sha256:667b089945a9bf8fa7f21ba2a61ee64a05be8813184d744b06e24150680e6ab5","observation_id":"7933799c-2dab-498a-9a2d-2282f0e6d2ee","resolution":{"observed_at":"2026-07-03T04:17:36.826707Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-01T14:16:03.065590Z","title":"Efficientnetv2: Smaller models and faster training.arXiv preprint arXiv:2104.00298, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18819","last_updated":"2026-07-21T07:55:07Z","snapshot_observed_at":"2026-08-06T23:55:01.270909Z","submitted_at":"2026-07-21T07:55:07Z","title":"In-Context Learning for Wound Classification with Small Multimodal Language Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-01T14:16:03.065590Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2607.18819"},"observation_digest":"sha256:57daae0eb4f4f640fd8bab8a38627f51ee1b65afacdc72a3a194fcbac8021e60","observation_id":"4f8632e2-5691-4dcb-a298-4bd9a8ee0424","resolution":{"observed_at":"2026-08-01T14:16:03.065590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-07-31T23:23:03.934926Z","title":"Efficientnetv2: Smaller mod- els and faster training.arXiv preprint arXiv:2104.00298,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.23997","last_updated":"2026-07-27T04:49:14Z","snapshot_observed_at":"2026-08-15T03:16:18.987910Z","submitted_at":"2026-07-27T04:49:14Z","title":"Exploring Budgeted Image Classification with Content-Sensitive Resource Allocation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-31T23:23:03.934926Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2607.23997"},"observation_digest":"sha256:b754a7c61ff450e7d901d22077dbf6bdc94e1512fd04dfc77e5ad58bc91e5060","observation_id":"367d3818-69a3-4202-8faa-b7bb21c85f0d","resolution":{"observed_at":"2026-07-31T23:23:03.934926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-12T20:13:23.857289Z","title":"EfficientNetV2: Smaller models and faster training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10649","last_updated":"2026-08-11T08:33:17Z","snapshot_observed_at":"2026-08-16T13:45:59.949544Z","submitted_at":"2026-08-11T08:33:17Z","title":"PolypVision: A Three-Stage Hierarchical Deep Learning Framework for Classification and Segmentation of Colorectal Polyps","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T20:13:23.857289Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2608.10649"},"observation_digest":"sha256:6a04fee1f34d6ea44dec3bd28880f5ed65be89630ac1584b23f6618a5985235f","observation_id":"dc5f7bb7-ec13-444f-9b4c-4548d3d87c85","resolution":{"observed_at":"2026-08-12T20:13:23.857289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2104.00298/citation-record","integrity":"/paper/2104.00298/integrity","json":"/paper/2104.00298/citation-record.json","paper":"/paper/2104.00298"},"outbound":[],"paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 28 inbound Pith citation observations for arXiv:2104.00298."}