{"as_of":"2026-08-21T19:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:07b156e9d64e74aeb4a03cebd23142709fff7ced5b88ba8430ed1ce538ff2cce","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":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":14,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:28:30.573848Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T03:06:30.208129Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-12T17:34:35.062377Z","title":"Designing bert for convolutional net- works: Sparse and hierarchical masked modeling","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12452","last_updated":"2024-11-19T12:19:45Z","snapshot_observed_at":"2026-08-20T16:01:08.966239Z","submitted_at":"2024-11-19T12:19:45Z","title":"GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T17:34:35.062377Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2411.12452"},"observation_digest":"sha256:82a6ec405486fe1c5e3c9f964c74762b608f76916946113f7ea611b30270a67a","observation_id":"69c524b7-0d97-493a-808a-43afa9726f0f","resolution":{"observed_at":"2026-08-12T17:34:35.062377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-11T11:00:56.450036Z","title":"Designing bert for convolutional networks: Sparse and hierarchical masked mod- eling,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.15917","last_updated":"2024-12-20T14:09:36Z","snapshot_observed_at":"2026-08-14T05:12:36.420115Z","submitted_at":"2024-12-20T14:09:36Z","title":"Self-supervised Spatial-Temporal Learner for Precipitation Nowcasting","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T11:00:56.450036Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2412.15917"},"observation_digest":"sha256:c19919d5110c82a67347a98c4290280c464706a4bee100a83e95b0f65fc62f91","observation_id":"c5cdacac-0d38-4a09-a3b9-d5b1a6bd4e33","resolution":{"observed_at":"2026-08-11T11:00:56.450036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-11T05:53:41.224387Z","title":"Designing bert for convolutional net- works: Sparse and hierarchical masked modeling","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.17041","last_updated":"2025-04-18T13:14:59Z","snapshot_observed_at":"2026-08-15T14:30:34.648230Z","submitted_at":"2024-12-22T14:38:28Z","title":"An OpenMind for 3D medical vision self-supervised learning","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T05:53:41.224387Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2412.17041"},"observation_digest":"sha256:232906925ae6128d0993973a48d531d20f34fdcc7d29526024dd47de38c01f7d","observation_id":"b8999e18-a846-4482-83f2-39515027b45f","resolution":{"observed_at":"2026-08-11T05:53:41.224387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-10T21:47:12.863106Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03880","last_updated":"2025-01-12T15:18:28Z","snapshot_observed_at":"2026-08-17T00:11:07.984228Z","submitted_at":"2025-01-07T15:43:36Z","title":"SELMA3D challenge: Self-supervised learning for 3D light-sheet microscopy image segmentation","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-10T21:47:12.863106Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2501.03880"},"observation_digest":"sha256:cad5806269fb124b7ec61ee3574d4148303624dcc111ee3e0ac8c5bc9f12da50","observation_id":"6f9625ac-66a0-4434-afd2-95ab755176b4","resolution":{"observed_at":"2026-08-10T21:47:12.863106Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-08T05:32:41.922604Z","title":", author Jiang, Y","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08347","last_updated":"2025-02-12T12:14:02Z","snapshot_observed_at":"2026-08-15T18:18:45.491797Z","submitted_at":"2025-02-12T12:14:02Z","title":"Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-08T05:32:41.922604Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2502.08347"},"observation_digest":"sha256:6062b211c3f5bb129b83c552d71c92ea91205e954856d3011c0e31a49625780a","observation_id":"3faf1f73-282a-43fb-91e7-84949d338ac8","resolution":{"observed_at":"2026-08-08T05:32:41.922604Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-16T10:28:30.573848Z","title":"arXiv preprint arXiv:2301.03580 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.18049","last_updated":"2025-04-25T03:38:55Z","snapshot_observed_at":"2026-08-16T14:41:56.793592Z","submitted_at":"2025-04-25T03:38:55Z","title":"A BERT-Style Self-Supervised Learning CNN for Disease Identification from Retinal Images","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T10:28:30.573848Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2504.18049"},"observation_digest":"sha256:f2f73d1eab8268d400f1b5b48fbce3ad9618b65422658101c49277af881a30d1","observation_id":"bb7e1fa5-b681-43a1-af7f-3e7bf8e10591","resolution":{"observed_at":"2026-08-16T10:28:30.573848Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-15T22:11:15.033487Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.08819","last_updated":"2025-05-12T18:40:46Z","snapshot_observed_at":"2026-08-21T00:51:57.740520Z","submitted_at":"2025-05-12T18:40:46Z","title":"Thoughts on Objectives of Sparse and Hierarchical Masked Image Model","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T22:11:15.033487Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2505.08819"},"observation_digest":"sha256:6304cbc850aa351e1fd00ec474a446218ebd98c4301a9c96daa0d951a31fc939","observation_id":"7490fec6-a74b-4c7b-a074-26e13bba8ad5","resolution":{"observed_at":"2026-08-15T22:11:15.033487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-07T05:10:59.607292Z","title":"Designing bert for convolutional networks: Sparse and hierarchical masked modeling","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.08612","last_updated":"2025-06-10T09:21:48Z","snapshot_observed_at":"2026-08-14T13:22:45.754721Z","submitted_at":"2025-06-10T09:21:48Z","title":"Data-Efficient Challenges in Visual Inductive Priors: A Retrospective","version":1},"reference_index":135,"source":"arxiv_source","source_observed_at":"2026-08-07T05:10:59.607292Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2506.08612"},"observation_digest":"sha256:3f4af48ee82dda88a2e3e8951534dcf73474fdf2b62e9c72548961b8ba5c9545","observation_id":"ce0925d8-efd3-47b2-a032-433bee7cab1b","resolution":{"observed_at":"2026-08-07T05:10:59.607292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-06T19:54:34.508875Z","title":"Designing bert for convolutional networks: Sparse and hierarchical masked modeling.arXiv preprint arXiv:2301.03580, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04456","last_updated":"2025-07-06T16:32:37Z","snapshot_observed_at":"2026-08-18T14:17:32.179389Z","submitted_at":"2025-07-06T16:32:37Z","title":"BiVM: Accurate Binarized Neural Network for Efficient Video Matting","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T19:54:34.508875Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2507.04456"},"observation_digest":"sha256:d3362b3f2d15abb6ad5e28b01a2562116a457685f0c5cac38f5850c909acc967","observation_id":"83feca3c-b794-4448-9591-5bb1c96a7167","resolution":{"observed_at":"2026-08-06T19:54:34.508875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-04T15:43:06.629544Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.18919","last_updated":"2026-05-26T11:07:50Z","snapshot_observed_at":"2026-08-12T19:29:57.198776Z","submitted_at":"2025-09-23T12:35:32Z","title":"Advancing Metallic Surface Defect Detection via Anomaly-Guided Pretraining on a Large Industrial Dataset","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T15:43:06.629544Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2509.18919"},"observation_digest":"sha256:3a6a3e18e671ca013c78758a9ba82565e2f5fd21cdc7e0bde9c59da9f4b1a9aa","observation_id":"e1dc82df-c4b2-41d3-bbb5-4915770a3e1f","resolution":{"observed_at":"2026-08-04T15:43:06.629544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":"2301.03580","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-07-02T03:06:30.208129Z","title":"Designing BERT for convolutional networks: Sparse and hierarchical masked modeling","venue":null,"work_id":"6ff7bff9-89b1-4733-9a0f-833274a9c2c6","year":2023},"citing_paper":{"arxiv_id":"2604.08858","last_updated":"2026-04-10T01:45:47Z","snapshot_observed_at":"2026-08-12T21:18:58.549117Z","submitted_at":"2026-04-10T01:45:47Z","title":"BIAS: A Biologically Inspired Algorithm for Video Saliency Detection","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-05-10T18:24:37.810179Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2604.08858"},"observation_digest":"sha256:e39f82c0da993dc7ca8a798ce6e02a2105aa8f5966b331f0af8a172ad1ce13b8","observation_id":"3d21bac3-e89f-441e-8ea5-dc3e67d74bce","resolution":{"observed_at":"2026-05-11T00:41:03.285355Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":"2301.03580","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-07-02T03:06:30.208129Z","title":"Designing BERT for convolutional networks: Sparse and hierarchical masked modeling","venue":null,"work_id":"6ff7bff9-89b1-4733-9a0f-833274a9c2c6","year":2023},"citing_paper":{"arxiv_id":"2606.03508","last_updated":"2026-06-02T11:26:07Z","snapshot_observed_at":"2026-08-15T04:34:56.963678Z","submitted_at":"2026-06-02T11:26:07Z","title":"Structure-Guided Mixed Masked Pretraining and Spatial Continuity Regularization for Printed Circuit Board Defect Detection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-28T10:19:16.668107Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2606.03508"},"observation_digest":"sha256:a05265848d7e9733fa388161e7ea8c8753055f4d46d07ec214d2e80d39049888","observation_id":"0672aff3-4c1d-4eb0-8079-1a1b83f0bc91","resolution":{"observed_at":"2026-07-02T03:06:30.209799Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-07T22:30:01.425484Z","title":"arXiv preprint arXiv:2301.03580 (2023) 3","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.05844","last_updated":"2026-08-07T15:11:56Z","snapshot_observed_at":"2026-08-16T16:24:43.548625Z","submitted_at":"2026-08-06T10:17:23Z","title":"Curia-MAE: Multi-Modal Multi-Anatomy MAE Pre-Training for 3D Medical Image Segmentation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T22:30:01.425484Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2608.05844"},"observation_digest":"sha256:48f8e4f0b4cdd18a1b49fb1c2614b516f1fe4d916cf218bb1d0c802d34218b4e","observation_id":"4f911dab-194e-4da2-8a95-382c7f337a17","resolution":{"observed_at":"2026-08-07T22:30:01.425484Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.03580","snapshot_observed_at":"2026-08-10T04:31:34.475814Z","title":"arXiv preprint arXiv:2301.03580 (2023) 3","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.05844","last_updated":"2026-08-07T15:11:56Z","snapshot_observed_at":"2026-08-16T16:24:43.548625Z","submitted_at":"2026-08-06T10:17:23Z","title":"Curia-MAE: Multi-Modal Multi-Anatomy MAE Pre-Training for 3D Medical Image Segmentation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T04:31:34.475814Z"},"links":{"cited_paper":"/paper/2301.03580","citing_paper":"/paper/2608.05844"},"observation_digest":"sha256:57342511b8e1ea50b83aead005c4b10cf3faa0dc021fbddb1d7fb17cd68c5752","observation_id":"a113148b-a803-4a73-93f3-291e2d1d31b0","resolution":{"observed_at":"2026-08-10T04:31:34.475814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2301.03580/citation-record","integrity":"/paper/2301.03580/integrity","json":"/paper/2301.03580/citation-record.json","paper":"/paper/2301.03580"},"outbound":[],"paper":{"arxiv_id":"2301.03580","last_updated":"2023-01-10T08:02:09Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T16:03:32.509782Z","submitted_at":"2023-01-09T18:59:50Z","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 14 inbound Pith citation observations for arXiv:2301.03580."}