{"as_of":"2026-08-14T19:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6a42f8eef2347548704f98c16c5389fac31fbe1363535735467493e3c7db5e9c","coverage":[{"denominator":91,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":91,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T00:15:11.963083Z","state":"measured"},{"denominator":91,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":91,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.19628/citation-record","integrity":"/paper/2412.19628/integrity","json":"/paper/2412.19628/citation-record.json","paper":"/paper/2412.19628"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.535520Z","title":"https : / / github","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.535520Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:4c24d4d0171b326e6d0786be5d74cb0a65acaf063f3d6d9dd28ca5b4684cf3d7","observation_id":"dfd51c06-c93f-45ba-aa99-6766f2b3680a","resolution":{"observed_at":"2026-08-11T00:15:11.535520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-08-14T05:15:12.190552Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-11T00:15:11.540376Z","title":"Layer normalization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.540376Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:581fa250119f4a59fc0625f7db7d93eb37ccd8367ea9307ad6a16c7bf7b4c120","observation_id":"df88f87e-bbd3-4db7-bf47-4a4d822ed2b6","resolution":{"observed_at":"2026-08-11T00:15:11.540376Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.545407Z","title":"End-to- end object detection with transformers","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.545407Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:d111104700f04509139360ef2e3e8d98a1467a2a2d663af7956c2c2034167c86","observation_id":"3940b63e-247d-4786-bdb6-a8b94a8dfaab","resolution":{"observed_at":"2026-08-11T00:15:11.545407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07589","last_updated":"2024-03-16T02:55:14Z","snapshot_observed_at":"2026-08-14T16:46:45.710374Z","submitted_at":"2024-03-12T12:19:05Z","title":"PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution","version":2},"cited_work":{"arxiv_id":"2403.07589","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.07589","snapshot_observed_at":"2026-08-11T00:15:12.363311Z","title":"PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution","venue":"cs.CV","work_id":"a0da3a20-2224-4a21-bb3b-6e255b3e5913","year":2024},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.550091Z"},"links":{"cited_paper":"/paper/2403.07589","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:1f7c229c65130d6f439d1d02ba149515064a30660200e0b26f1ecfe59ed04632","observation_id":"799306a7-ecde-4091-bc5f-f5dd400af679","resolution":{"observed_at":"2026-08-11T00:15:12.368771Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.555052Z","title":"Run, don’t walk: Chasing higher flops for faster neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.555052Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:f1b1c88ba3e30298023d630ff3361dece06c0df92840a1aec1496b0f454f81c5","observation_id":"f1a06a58-9704-420f-9ad9-275a602cfe27","resolution":{"observed_at":"2026-08-11T00:15:11.555052Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.559665Z","title":"Drop an octave: Reducing spatial redundancy in con- volutional neural networks with octave convolution","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.559665Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:c51711c81a08839576cf89e8362eed2dcea7140a8881509dd42b94614a156519","observation_id":"65a814b2-0d2f-42bb-b414-367a195d8d26","resolution":{"observed_at":"2026-08-11T00:15:11.559665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.564572Z","title":"Mobile- former: Bridging mobilenet and transformer","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.564572Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:e09d8afa1021fb04ce3a6c999d9c34e10103aeb8b15ea2873c787acd9f8c22fe","observation_id":"c91bc4d2-b909-404c-83f5-352ebbb53998","resolution":{"observed_at":"2026-08-11T00:15:11.564572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.570639Z","title":"Largekernel3d: Scaling up kernels in 3d sparse cnns","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.570639Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:beb6e227b0b0313f396c3ec77d7bb165dd4877deffeb8fb3857d89586f2336d0","observation_id":"e51fb7ba-cb7b-49f3-948f-ad54beb008f0","resolution":{"observed_at":"2026-08-11T00:15:11.570639Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.576041Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.576041Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:96cef48f12c0c1dce9b216d7c4dad971f0436fb951d326f9246c238a5856fca7","observation_id":"749a4078-ffb8-4d05-9575-a41ba5b8ca9f","resolution":{"observed_at":"2026-08-11T00:15:11.576041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.580538Z","title":"Scaling up your kernels to 31x31: Revisiting large kernel design in cnns","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.580538Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:fbf4ca9ea325f12417de0b1916b5f97f5e392eeec09e4cec5652aba120468251","observation_id":"2cf54170-9fba-4a14-99d7-c94ea8011929","resolution":{"observed_at":"2026-08-11T00:15:11.580538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15599","last_updated":"2024-03-18T08:37:24Z","snapshot_observed_at":"2026-08-13T05:17:18.017535Z","submitted_at":"2023-11-27T07:48:50Z","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","version":2},"cited_work":{"arxiv_id":"2311.15599","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.15599","snapshot_observed_at":"2026-08-11T00:15:12.340431Z","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","venue":"cs.CV","work_id":"7f3a6847-2976-4e37-a824-57d3b9835215","year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.585271Z"},"links":{"cited_paper":"/paper/2311.15599","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:da0050ceddb61c869f72877546d040e3e3a27fc1aa7ed07f1fb6422aae8d8358","observation_id":"5010a5fa-34b4-4212-b9a4-5fe270bde68e","resolution":{"observed_at":"2026-08-11T00:15:12.346382Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.590361Z","title":"ModernTCN: A modern pure convolution structure for general time series analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.590361Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:fc2e04344d7857aaec421f4652e2a0f43bfc5c992f45b89aebd84f372457ec64","observation_id":"40882a46-0691-489b-872b-883dbe5ac193","resolution":{"observed_at":"2026-08-11T00:15:11.590361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-13T14:19:26.598265Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-11T00:15:11.594797Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.594797Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:2ea7757c60e2fea515a13902f4c605cf56fbfa9b14365d67373631fe8399e4fb","observation_id":"130e5a62-3932-4684-aa90-a499585bde71","resolution":{"observed_at":"2026-08-11T00:15:11.594797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.599547Z","title":"Torchcam: class activation explorer","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.599547Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:da4355a7d294a261b679330ed6066f1ae2f063fe3a10ef6fffa11e26c10085ef","observation_id":"ce7d8ff2-55f8-43b6-8bdb-2382eaf8c559","resolution":{"observed_at":"2026-08-11T00:15:11.599547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.603997Z","title":"Wavelet convolutions for large receptive fields","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.603997Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:badb45febc39837ce9a6a22fdd23b559fa0609d9b7e116815af1b6e92b095fe6","observation_id":"53685c1e-4b03-4774-a0a6-01ddf5024107","resolution":{"observed_at":"2026-08-11T00:15:11.603997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.209865Z","title":"Partial success in closing the gap between human and machine vision","venue":null,"work_id":"a4db3907-07d7-4e2c-8e65-e07905d2c1ba","year":2021},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.609137Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:0cf30fe8ee21aa519f8c1ebe18e158cef27b9be41b1f31b7edab0fcf2a1b4dbf","observation_id":"a0eb568b-f21b-42da-a44c-2b4d3ccb7e4a","resolution":{"observed_at":"2026-08-11T00:15:13.214983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00752","last_updated":"2024-05-31T17:55:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-01T18:01:34Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00752","snapshot_observed_at":"2026-08-11T00:15:11.613708Z","title":"Mamba: Linear-time sequence modeling with selective state spaces","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.613708Z"},"links":{"cited_paper":"/paper/2312.00752","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:ca976706cd82851c96e653e598f7e762af6689f183a6feadd1eb896f1b30a9e1","observation_id":"8f3e90b4-407e-49d4-bf50-ed753123d74b","resolution":{"observed_at":"2026-08-11T00:15:11.613708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.618666Z","title":"Efficiently mod- eling long sequences with structured state spaces","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.618666Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:5c3beae664db396b2ef0a3688a3ffce56d0133e5a7dbdd3039205490ffada5e0","observation_id":"e00fb262-faed-4c42-89e4-be7ac1994f11","resolution":{"observed_at":"2026-08-11T00:15:11.618666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.08575","last_updated":"2022-09-18T14:33:49Z","snapshot_observed_at":"2026-08-13T14:24:23.847576Z","submitted_at":"2022-09-18T14:33:49Z","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.08575","snapshot_observed_at":"2026-08-11T00:15:11.623367Z","title":"Segnext: Rethinking convolutional attention design for semantic segmentation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.623367Z"},"links":{"cited_paper":"/paper/2209.08575","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:c5bd6b43ac129885d6587ae294c2c4f1b6682ec119d545bc490b413bb2755e7c","observation_id":"aaee6ab0-2597-48e9-b77a-5f4ba76dd2cf","resolution":{"observed_at":"2026-08-11T00:15:11.623367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.184121Z","title":"Flatten transformer: Vision transformer using focused linear attention","venue":null,"work_id":"65bf9a68-e929-45e2-af75-fcda1746d3a8","year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.628172Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:b0063a5b36505188ecc39910c9fda683b1b2f7c31ab254632d06a0b9bafa3009","observation_id":"e934fe05-61b5-4471-8412-8884c68bfa64","resolution":{"observed_at":"2026-08-11T00:15:13.189156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.167639Z","title":"Demystify mamba in vision: A linear attention perspective","venue":null,"work_id":"22918fd6-b429-4667-9bac-1fade05b3098","year":2024},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.632515Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:4714e8c383939ff360051e566eba09697e7191bbbef11d95bc5b9677e4ea40ba","observation_id":"151ec777-3f45-424a-a3a1-3c847026f1d9","resolution":{"observed_at":"2026-08-11T00:15:13.173259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.152768Z","title":"Ghostnet: More features from cheap opera- tions","venue":null,"work_id":"58883890-0ae5-4ea0-9283-74d5d8d70857","year":2020},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.636809Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:1ede9c7447e7c16d5b63508827325be3396bf069d00ef9fa240a080495237848","observation_id":"edc39ce0-e17a-4ce5-8e3c-2bb2c39e91e5","resolution":{"observed_at":"2026-08-11T00:15:13.157661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15941","last_updated":"2024-11-24T18:01:05Z","snapshot_observed_at":"2026-08-14T02:28:34.350385Z","submitted_at":"2024-11-24T18:01:05Z","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","version":1},"cited_work":{"arxiv_id":"2411.15941","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.15941","snapshot_observed_at":"2026-08-11T00:15:12.270382Z","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","venue":"cs.CV","work_id":"8feb722f-aa61-48df-9ee9-81e93722bc99","year":2024},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.641205Z"},"links":{"cited_paper":"/paper/2411.15941","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:b395d5eaf0b6c21f571516f93015359c139e04b9c229705db2cb1bce6963de08","observation_id":"c186ffee-78e5-44d3-95a9-afe530034990","resolution":{"observed_at":"2026-08-11T00:15:12.275568Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.136637Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"73960b14-d9da-411c-b78c-fc63555852a1","year":2016},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.645740Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:ccc9b84913ce48d125f975bf191310504729b5871bd34497077714f1ce89382d","observation_id":"dac17103-a628-4311-8f5a-6a6a1de10fa5","resolution":{"observed_at":"2026-08-11T00:15:13.141802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.649873Z","title":"Mask r-cnn","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.649873Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:b812a69dbc316e739db7795194f52112681578b26ed38fcf737113051683b404","observation_id":"6b4c8831-483f-4735-861d-db137717e4fe","resolution":{"observed_at":"2026-08-11T00:15:11.649873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.08415","last_updated":"2023-06-06T01:53:32Z","snapshot_observed_at":"2026-08-13T19:48:28.322536Z","submitted_at":"2016-06-27T19:20:40Z","title":"Gaussian Error Linear Units (GELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.08415","snapshot_observed_at":"2026-08-11T00:15:11.654085Z","title":"Gaussian error linear units (gelus)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.654085Z"},"links":{"cited_paper":"/paper/1606.08415","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:16a82a228dbce7b8c24b9801a800b25d97c75772d82ad245cfb31d5686aeec9f","observation_id":"ea72430e-f6e0-4850-8189-46ab10137c0b","resolution":{"observed_at":"2026-08-11T00:15:11.654085Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.110482Z","title":"Searching for mo- bilenetv3","venue":null,"work_id":"c29ab793-3b5f-4d71-8f9c-573fb90d169a","year":2019},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.658703Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:fae9d2747467a4de9b46dfb3dcf5600e338e0c7ff6b144bcb5d0524394813af3","observation_id":"04bedc7d-e83f-48cd-aab7-87da01de086e","resolution":{"observed_at":"2026-08-11T00:15:13.115462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-11T00:15:11.662982Z","title":"Mobilenets: Efficient convolu- tional neural networks for mobile vision applications","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.662982Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:c5ad376ebbf2a2b6b0f93dfee10c26f3aa6a0903799561c1d775ad4973efdffa","observation_id":"710dc1a1-baf4-4c0d-a631-05ba7f7e9261","resolution":{"observed_at":"2026-08-11T00:15:11.662982Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05557","last_updated":"2022-07-12T14:27:57Z","snapshot_observed_at":"2026-08-13T15:05:40.222763Z","submitted_at":"2022-07-12T14:27:57Z","title":"LightViT: Towards Light-Weight Convolution-Free Vision Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.05557","snapshot_observed_at":"2026-08-11T00:15:11.667481Z","title":"Lightvit: Towards light-weight convolution- free vision transformers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.667481Z"},"links":{"cited_paper":"/paper/2207.05557","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:28dbc6aa32e5652da6240d49ac2210d4de8426b83098a05cac5e5ed8ad80b94e","observation_id":"eba18e1d-264e-4821-b4cf-b79e7f3ca132","resolution":{"observed_at":"2026-08-11T00:15:11.667481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.094595Z","title":"Are large kernels better teachers than transformers for convnets?,","venue":null,"work_id":"e0525f1f-8db2-4cf5-8fb0-b02531a12d12","year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.672142Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:8e41cd68c3c85a1838011cfc7a9dc0bf47b45c611c217d9bc19b0aa7439e365b","observation_id":"250bb4f4-d9f2-4273-8bc0-a8288aeea249","resolution":{"observed_at":"2026-08-11T00:15:13.099862Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.676587Z","title":"Batch normalization: Accelerating deep network training by reducing internal co- variate shift","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.676587Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:2b68b6ab35eeef1655593e3f4040781af3669268cb6ab88da01a2160546a6fd7","observation_id":"f6c69702-a596-4115-9d5f-74969687f4c5","resolution":{"observed_at":"2026-08-11T00:15:11.676587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.069302Z","title":"Wavemix: A resource-efficient neural network for im- age analysis, 2023","venue":null,"work_id":"9ac06944-8eb5-4f4a-8ffb-183333037a20","year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.681861Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:e5481ca832602018d81f3d140edf3976ea9948d2d74c079535044cef7ce852cf","observation_id":"fd1bbfd3-56f4-4993-97cc-13b634c3441a","resolution":{"observed_at":"2026-08-11T00:15:13.074107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.053352Z","title":"Transformers are rnns: Fast autoregressive transformers with linear attention","venue":null,"work_id":"2d4eeb1b-2f45-4dff-8646-7b4ecba31d9b","year":2020},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.686271Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:8c1b13acd3f72125d7789126b061eed546548377fe0960da33b77c18048a9085","observation_id":"8365ab4b-fa98-40ab-975d-a795b89df361","resolution":{"observed_at":"2026-08-11T00:15:13.058920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.037626Z","title":"Panoptic feature pyramid networks","venue":null,"work_id":"93387320-ea40-44db-993a-7c8845caabc8","year":2019},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.690582Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:b896166df8dc023c245506802479d5d23933c71db67ebbddfcb10fc35805540e","observation_id":"f5545b3f-09ab-40f6-912e-04aa90063296","resolution":{"observed_at":"2026-08-11T00:15:13.042789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:13.022070Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":"c1b2f3df-dc85-47ac-8058-3fb8964f44e9","year":2012},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.695277Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:dd3c90878341cd24b5d2c0147701db08e47886caa7ebebceb5d5c7dd3fb81d31","observation_id":"35138178-1e73-4b43-b4c0-5aed6f3595d9","resolution":{"observed_at":"2026-08-11T00:15:13.027368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07648","last_updated":"2017-05-26T18:53:56Z","snapshot_observed_at":"2026-08-08T19:03:12.030897Z","submitted_at":"2016-05-24T20:28:53Z","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07648","snapshot_observed_at":"2026-08-11T00:15:11.699886Z","title":"Fractalnet: Ultra-deep neural networks without residuals","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.699886Z"},"links":{"cited_paper":"/paper/1605.07648","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:eb496ed41257eae4b9bca80daf2d0f96ff2c849c133b3d060bf2602a2386f94d","observation_id":"196ec7f6-d398-4111-8a5d-28d4c547dc65","resolution":{"observed_at":"2026-08-11T00:15:11.699886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.704848Z","title":"Backpropagation applied to handwrit- ten zip code recognition.Neural computation, 1(4):541–551,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.704848Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:a28d3440835a29afbea02e864ff4cb283fcf8a4bdbfa7f738a97faf16caf0d4a","observation_id":"2992cf7a-e825-475e-953e-ce74075df87a","resolution":{"observed_at":"2026-08-11T00:15:11.704848Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.710372Z","title":"Visualizing the loss landscape of neural nets","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.710372Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:8b46f6fa1e5182906285ca4d4de696b0a73a352142cec94a6d3e5b46dc16fa24","observation_id":"907ed8db-31cd-48aa-bdef-a3b8369e90cd","resolution":{"observed_at":"2026-08-11T00:15:11.710372Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.986174Z","title":null,"venue":null,"work_id":"e91fa1dc-9128-47f0-a71b-93869fb7fc0e","year":2024},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.714722Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:133d7a41ad3226bde4f36d641117e93e2b7c5cc4d579f80336145c950036c2ce","observation_id":"3a7ca80f-2a0c-48eb-8821-5e11c7af72ad","resolution":{"observed_at":"2026-08-11T00:15:12.990840Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.969395Z","title":"Selec- tive kernel networks","venue":null,"work_id":"b3c03f62-2d17-4e09-9216-e9e979d9777c","year":2019},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.719222Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:8918ad71c7be8ee6771ceddc86841b1aca1f008db9f3f1dfbf3eac6754c25ee6","observation_id":"e76d4961-197c-421f-a8a6-edc43c54bcc5","resolution":{"observed_at":"2026-08-11T00:15:12.974914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.952767Z","title":"Efficientformer: Vision transformers at mobilenet speed","venue":null,"work_id":"6e7f4939-ac72-4311-9afa-698d0b2e75cb","year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.723601Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:4a7bd7673422dd94ffba509340375f00fc2a261d909fa55e417fbe529616507f","observation_id":"75ce6090-4ebd-45c8-af89-e7f4db348abf","resolution":{"observed_at":"2026-08-11T00:15:12.957754Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.937493Z","title":"Large selective kernel network for remote sensing object detection","venue":null,"work_id":"b62fd723-9704-4047-a544-8c92b1eb17e3","year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.729080Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:dac93ad592b1e2a0a38abefd67065eabc09fea0c4a0031372282485086828b8d","observation_id":"65c9635d-b5ff-4e87-b5ce-5f879a10276a","resolution":{"observed_at":"2026-08-11T00:15:12.942546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.921932Z","title":"Re- thinking vision transformers for mobilenet size and speed","venue":null,"work_id":"09b28f36-338d-4945-ba35-993da5a9e55d","year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.734121Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:5982915311bf1852a035b0dd6f597049d80d77af68a443ab1ee10fdf38bd4ded","observation_id":"ac5f6278-a097-477d-b730-9fa5aa1cc5e9","resolution":{"observed_at":"2026-08-11T00:15:12.926986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.905937Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":"16992d52-4dbf-4554-9f60-cef816fb6b61","year":2014},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.739403Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:07885f78b003b513e336dba8ead6e0b5cb48b3543095cc132ba5decf362c083e","observation_id":"7cb63205-f611-4a48-8744-dd93b7860c8f","resolution":{"observed_at":"2026-08-11T00:15:12.911337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.03620","last_updated":"2023-03-03T19:04:38Z","snapshot_observed_at":"2026-08-13T15:08:33.831885Z","submitted_at":"2022-07-07T23:55:52Z","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.03620","snapshot_observed_at":"2026-08-11T00:15:11.743980Z","title":"More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.743980Z"},"links":{"cited_paper":"/paper/2207.03620","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:3e61ac55c3aff819a45f15f60a8d19fa985120ca40a24046564a9bc1d0adbae8","observation_id":"b4cea5ca-66af-49b7-b5ef-56c5224f9dec","resolution":{"observed_at":"2026-08-11T00:15:11.743980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.890098Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":"e007215f-c7bf-4b6f-bcd7-7525f8608d26","year":2021},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.748652Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:691bfa4df98fc18fa5dd8559ef3f5a26bb2066f6c7df6c153c19adc3075bfd77","observation_id":"28327d26-f317-4396-8978-81ceb42cd597","resolution":{"observed_at":"2026-08-11T00:15:12.895412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.753141Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.753141Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:ef8c8b0d786f8d1ebb2dbafb311b63eed17c9b14cdbb998496536f722994cb99","observation_id":"fc000e5e-2403-4994-a9af-01400598bc26","resolution":{"observed_at":"2026-08-11T00:15:11.753141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.865062Z","title":"Rewrite the stars","venue":null,"work_id":"655704bc-7c63-474b-adbd-f8b0b86fd00f","year":2024},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.757557Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:9834e84d4295f52dd84b1394d1ced471c53c40ec157c68f3a475495d07d8dbd2","observation_id":"7881e22a-dd2a-47bc-9ee4-b0235a60f72b","resolution":{"observed_at":"2026-08-11T00:15:12.869926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.849215Z","title":"Efficient modulation for vision net- works","venue":null,"work_id":"856441d1-cce3-456d-b8ff-5825c7bb5f9d","year":2024},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.762039Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:5cb1d1ccabec349b07c28e19d4020d513205cb5bfd6c90a66b129040a8a5f3bc","observation_id":"f2332033-a575-41eb-b708-c3c42deab501","resolution":{"observed_at":"2026-08-11T00:15:12.854296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.832733Z","title":"Edgenext: Efficiently amalgamated cnn-transformer architecture for mobile vision applications","venue":null,"work_id":"e255cc66-5177-42a3-9ff0-351faf8bdf7b","year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.766431Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:98836a452d1afe4381ddb7985d5341b3b112aa4c82baf00138863039d3c1f8af","observation_id":"be449b22-584b-47ea-895d-503599d6a42a","resolution":{"observed_at":"2026-08-11T00:15:12.837954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.02178","last_updated":"2022-03-04T17:17:31Z","snapshot_observed_at":"2026-07-06T11:54:38.041673Z","submitted_at":"2021-10-05T17:07:53Z","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.02178","snapshot_observed_at":"2026-08-11T00:15:11.771256Z","title":"Mobilevit: light- weight, general-purpose, and mobile-friendly vision trans- former","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.771256Z"},"links":{"cited_paper":"/paper/2110.02178","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:08b53bd874d61c09ac4680c17db2275fe52e6de7f67ccd30aa8f67302fc37ff7","observation_id":"a64226ba-44b6-4776-8491-bb13c88af82f","resolution":{"observed_at":"2026-08-11T00:15:11.771256Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.02680","last_updated":"2022-06-06T15:31:35Z","snapshot_observed_at":"2026-08-13T15:29:23.546543Z","submitted_at":"2022-06-06T15:31:35Z","title":"Separable Self-attention for Mobile Vision Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.02680","snapshot_observed_at":"2026-08-11T00:15:11.776002Z","title":"Separable self- attention for mobile vision transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.776002Z"},"links":{"cited_paper":"/paper/2206.02680","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:1f9d5bb808791e6138adee1486a48128452fa40cb7694c5c194393228771dbd0","observation_id":"8d7d4c3d-022c-4020-a784-e360d785b23e","resolution":{"observed_at":"2026-08-11T00:15:11.776002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.817322Z","title":"Mo- bilevig: Graph-based sparse attention for mobile vision ap- plications","venue":null,"work_id":"3d266c33-27da-4119-85b3-baf02a11b2b4","year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.780668Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:269e05bd0c239329490015b7614f19780be52bd015e944da59c6d105bd46e468","observation_id":"c4a78063-fd0c-4d6c-8b50-89b8e48cd470","resolution":{"observed_at":"2026-08-11T00:15:12.822374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.785487Z","title":"Edgevits: Competing light-weight cnns on mobile devices with vision transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.785487Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:d349110b2472a28a2be3b20ac13346376ce70a16add4c9c73251993dc73c8043","observation_id":"2c27b4c7-8872-4b9f-ae38-6d4f32d67122","resolution":{"observed_at":"2026-08-11T00:15:11.785487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.789550Z","title":"Large kernel matters–improve semantic segmen- tation by global convolutional network","venue":null,"work_id":"5cb06643-387a-4f02-83bc-64a5be923a36","year":2017},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.790125Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:541d3146fe2bf8de1daf55009d8082159226652bec24b7cb4be50b4c7a391017","observation_id":"6a9900b4-dbd4-49a8-bedc-34d37cba32da","resolution":{"observed_at":"2026-08-11T00:15:12.794355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.773806Z","title":"Designing network design spaces","venue":null,"work_id":"4a287567-5ffc-48f7-8dec-2a5ef18da5c8","year":2020},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.794389Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:d4e83c8ec3b37d7f6dabb6634a5d4056acb2586c5ddd3ad0c19e6f837d5bdded","observation_id":"25fe3df9-affe-443c-8d08-d75d97eb5ae1","resolution":{"observed_at":"2026-08-11T00:15:12.778865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.758080Z","title":"Global filter networks for image classification","venue":null,"work_id":"39a5fd79-f8ed-4075-975b-1ab8afa92cff","year":2021},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.798890Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:e53e56c404fd84e04d6ff5c383bb3563f1268c41a424acb8aaa61832ad450ab9","observation_id":"c7d80500-5e3e-4893-81c0-9a76347f235e","resolution":{"observed_at":"2026-08-11T00:15:12.763090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.742755Z","title":"Hornet: Efficient high-order spatial interactions with recursive gated convolutions","venue":null,"work_id":"2f426230-f91c-40e8-a5b8-2a01e3924dc7","year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.803290Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:22112ab08a941db18a388d0dcfe3479e9dd844d73d7238843219ba39f5c301fe","observation_id":"4d067c96-3c56-4311-b704-ebd68fb68f58","resolution":{"observed_at":"2026-08-11T00:15:12.747962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.726510Z","title":"You only look once: Unified, real-time object de- tection","venue":null,"work_id":"a17095f3-a3dd-4145-9b3f-81956791c30f","year":2016},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.808000Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:0534dab2e95103806d59e9916b03a584d68a6a51f19c18ecbdf884273575179f","observation_id":"0476806e-6cc0-4199-a69d-801af68c21e4","resolution":{"observed_at":"2026-08-11T00:15:12.731351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.812751Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.812751Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:76d357659c06b56fa32c8a8f7e95a161b28801f683aa8f12ec767e792c519cb0","observation_id":"a76b06ce-6f4b-4bb5-b7fc-adbd38c7904f","resolution":{"observed_at":"2026-08-11T00:15:11.812751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.701324Z","title":"Schuster and K.K","venue":null,"work_id":"842d63c7-e964-4fa7-8e88-15f45aa80f18","year":1997},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.817277Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:59fc137b9690f3bacccd3009b0f2020dcacc1fcb5ca9581c0df7c616999847f0","observation_id":"42344248-27a0-441b-afe5-b2c17bd13f5a","resolution":{"observed_at":"2026-08-11T00:15:12.706031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.685264Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","venue":null,"work_id":"5e4803f9-effb-4138-850d-138c8aea03cb","year":2017},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.821464Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:a047c74d29c154e7e230d1b72106c42fbb1d3ece9036ced0f27657d61ff8f708","observation_id":"e5112bca-b6af-4b39-82ff-0898b2fe241d","resolution":{"observed_at":"2026-08-11T00:15:12.690257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.669852Z","title":"Swiftformer: Efficient additive attention for transformer- based real-time mobile vision applications","venue":null,"work_id":"19e26f9b-cbe0-48dd-aa6c-b063bce467f7","year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.825763Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:b3cf8479192e719180402b06b35f90364c0ed797f6acf279d7b0de03d02c8afd","observation_id":"9cfee071-18bb-4d77-aca9-7e60f32ca734","resolution":{"observed_at":"2026-08-11T00:15:12.674786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-14T04:13:35.056640Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-11T00:15:11.830075Z","title":"Very deep convo- lutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.830075Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:33030d9c11847b8fe87dea626921c1ff562279fc2f471324ab051fb6962d367b","observation_id":"2f61033e-f9fd-49a0-9674-1bdf34b78f00","resolution":{"observed_at":"2026-08-11T00:15:11.830075Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.834814Z","title":"Going deeper with convolutions","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.834814Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:179e8a2dafbbac8c9956d1b83c725965e491f3c6037299cd04365ee50e51ea59","observation_id":"17c3f433-1db5-4bba-bffd-60b57d234fe0","resolution":{"observed_at":"2026-08-11T00:15:11.834814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.643978Z","title":"Rethinking the inception archi- tecture for computer vision","venue":null,"work_id":"b9076a84-47a5-42ef-afc1-18625a4e8dac","year":2016},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.839430Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:0c294ea9af2ba514ee48f60caee040a9b67d5a4947969f0cae4d780775d0bda0","observation_id":"b8ce0958-8202-4c4e-9654-149f4951c45b","resolution":{"observed_at":"2026-08-11T00:15:12.648876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.627460Z","title":"Inception-v4, inception-resnet and the impact of residual connections on learning","venue":null,"work_id":"5f4479ed-c90d-420d-bc2c-a6fa9354ab0f","year":2017},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.844053Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:72e5a2abce31e4de210708a9565272b1f1b82c642d3e8d7f0019c7df003ace11","observation_id":"6cd04796-16f9-434c-a22e-715d351be4ae","resolution":{"observed_at":"2026-08-11T00:15:12.633180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.848531Z","title":"Efficientnet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.848531Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:4b31dc9512bc6300157402b85218ccf171af76c5ec8dc0346f3091c3a2ceb348","observation_id":"47b30a16-f7b2-4eff-98d9-aa3ef3ae0402","resolution":{"observed_at":"2026-08-11T00:15:11.848531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.601381Z","title":"Mnas- net: Platform-aware neural architecture search for mobile","venue":null,"work_id":"dbdc4a4c-35ab-4205-9d7e-09b3f5f9d4ff","year":2019},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.853447Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:80a574335dea7476442ceb1fe51ca93b7882ed25f5b4db894162ebbb48866571","observation_id":"5df25abc-e910-4ff9-b3ec-c03fe9493019","resolution":{"observed_at":"2026-08-11T00:15:12.606396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-06T23:46:59.006674Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-11T00:15:11.858137Z","title":"Mlp-mixer: An all-mlp architecture for vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.858137Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:0f0f2154c0df0e2a6be8e152b2dc99bca17ec6d45028d0ce10f2723f84125758","observation_id":"03a491d0-fdb0-4e89-9e8f-aa29dff04439","resolution":{"observed_at":"2026-08-11T00:15:11.858137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.09792","last_updated":"2022-01-24T16:42:56Z","snapshot_observed_at":"2026-08-13T17:32:56.434179Z","submitted_at":"2022-01-24T16:42:56Z","title":"Patches Are All You Need?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.09792","snapshot_observed_at":"2026-08-11T00:15:11.862905Z","title":"Patches are all you need? arXiv preprint arXiv:2201.09792, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.862905Z"},"links":{"cited_paper":"/paper/2201.09792","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:1c60050303af62b018bd5eaf2b4d9b5622fd276ab553bf0edef127c93ab4e393","observation_id":"9675a279-b9fc-45cc-a232-8650b41299ee","resolution":{"observed_at":"2026-08-11T00:15:11.862905Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.14189","last_updated":"2023-08-17T21:10:59Z","snapshot_observed_at":"2026-08-13T12:17:30.975465Z","submitted_at":"2023-03-24T17:58:32Z","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.14189","snapshot_observed_at":"2026-08-11T00:15:11.867792Z","title":"Fastvit: A fast hybrid vi- sion transformer using structural reparameterization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.867792Z"},"links":{"cited_paper":"/paper/2303.14189","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:56cc3e48398c5f2ef7ff73457dca53c61f6a82940845c889626403263a55e347","observation_id":"d19c5602-797d-4264-8f35-b8faf5f7a887","resolution":{"observed_at":"2026-08-11T00:15:11.867792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.585471Z","title":"Mobileone: An im- proved one millisecond mobile backbone","venue":null,"work_id":"2c60500d-e1f6-404d-b59e-4f11a62825d7","year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.872685Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:8ebc33b58ff63e3eacb070d5d20943f288c45bb959b38c66c4d7d33f0c4d674a","observation_id":"755afaf6-c7eb-41fe-ac5b-0646e06db64a","resolution":{"observed_at":"2026-08-11T00:15:12.590863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.877285Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.877285Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:213077cc42f72e2b9c92dcb09d36e2b54313c9da6642273c0619586db073e9b6","observation_id":"1fa697ed-e05a-422e-bc2b-569aea321fd0","resolution":{"observed_at":"2026-08-11T00:15:11.877285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.15159","last_updated":"2022-10-06T14:19:13Z","snapshot_observed_at":"2026-08-14T15:43:58.543322Z","submitted_at":"2022-09-30T01:04:10Z","title":"MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.15159","snapshot_observed_at":"2026-08-11T00:15:11.882090Z","title":"Mobilevitv3: Mobile-friendly vision transformer with simple and effec- tive fusion of local, global and input features","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.882090Z"},"links":{"cited_paper":"/paper/2209.15159","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:ef03b61a4a9ad96864ac6c445b8df2325a3ef9f8bec1ec79ebc69c9c935d0f04","observation_id":"9df00cef-8095-4934-ad78-3b27f3a4fdfe","resolution":{"observed_at":"2026-08-11T00:15:11.882090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09283","last_updated":"2024-03-14T08:28:13Z","snapshot_observed_at":"2026-08-13T18:35:45.971169Z","submitted_at":"2023-07-18T14:24:33Z","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09283","snapshot_observed_at":"2026-08-11T00:15:11.886964Z","title":"Repvit: Revisiting mobile cnn from vit perspective","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.886964Z"},"links":{"cited_paper":"/paper/2307.09283","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:fbe71165e95ad6da2ca6c5f0b557f7a0e5aad27921466d8fac6b12976e9cc60d","observation_id":"23762d59-4fb9-4707-ae6c-844b283a7a1e","resolution":{"observed_at":"2026-08-11T00:15:11.886964Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14458","last_updated":"2024-10-30T01:49:34Z","snapshot_observed_at":"2026-08-12T23:59:58.018406Z","submitted_at":"2024-05-23T11:44:29Z","title":"YOLOv10: Real-Time End-to-End Object Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14458","snapshot_observed_at":"2026-08-11T00:15:11.891896Z","title":"Yolov10: Real-time end- to-end object detection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.891896Z"},"links":{"cited_paper":"/paper/2405.14458","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:bb4b9c08763f230cf6b9ac37df81f284b5f90335ebb2e0b378cc981396c21518","observation_id":"8a513cde-00b2-4c47-b4a2-631ae80900bf","resolution":{"observed_at":"2026-08-11T00:15:11.891896Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.561018Z","title":"Lsnet: See large, focus small, 2025","venue":null,"work_id":"2f055bac-3f12-4fb0-98d7-da323c16d66a","year":2025},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.897207Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:56393bd1d22304f64ad5dc7e73743051275852a741475c1ef56a7e3be97330dc","observation_id":"76e7dad2-ef35-4bf5-a054-f24714832b4e","resolution":{"observed_at":"2026-08-11T00:15:12.565605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.544783Z","title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","venue":null,"work_id":"6a75183e-9f72-4352-9462-ed2c4e0ca7a7","year":2021},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.902559Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:ec336bb4daa268e684d8de297e6b731b97043d103f2ba63e75670551e52e752d","observation_id":"51e9cb59-e9f2-45c9-8e66-d80de41c57ff","resolution":{"observed_at":"2026-08-11T00:15:12.550142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.528575Z","title":"Early convolutions help trans- formers see better","venue":null,"work_id":"9851193b-2f76-4d7d-97a9-df1b537e59fb","year":2021},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.907162Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:bde664537601aaf99ff146d55ad891e4e3cf02d411f01f7f9406b7c0d2d1468a","observation_id":"5e99c2e0-84fb-4c81-b476-45a8312c7aa0","resolution":{"observed_at":"2026-08-11T00:15:12.533500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.513609Z","title":"Metaformer is actually what you need for vision","venue":null,"work_id":"f18778b0-3ffb-4a65-b443-1c80d0f70ec9","year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.912303Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:20860b2583cb72354f7299f6867f1b8ae7be6225cc8380a05c0836106c8ccdb0","observation_id":"ab14644c-78b5-4cbc-a1a3-4fc9b2e41aa6","resolution":{"observed_at":"2026-08-11T00:15:12.518336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.16900","last_updated":"2025-04-05T22:33:58Z","snapshot_observed_at":"2026-08-13T12:13:51.068891Z","submitted_at":"2023-03-29T17:59:58Z","title":"InceptionNeXt: When Inception Meets ConvNeXt","version":3},"cited_work":{"arxiv_id":"2303.16900","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.16900","snapshot_observed_at":"2026-08-11T00:15:12.027833Z","title":"InceptionNeXt: When Inception Meets ConvNeXt","venue":"cs.CV","work_id":"41fde4cf-1b9e-4cfb-8265-6d1ecab39da7","year":2023},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.917585Z"},"links":{"cited_paper":"/paper/2303.16900","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:41b4b6417b3be845433f2c903700cf1ecb0047c4483d1317be03634a1a0fe3e9","observation_id":"dfbc776a-2522-4928-bc5e-497c293dffe7","resolution":{"observed_at":"2026-08-11T00:15:12.033104Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16456","last_updated":"2024-03-27T04:14:59Z","snapshot_observed_at":"2026-08-13T04:32:53.899650Z","submitted_at":"2024-01-29T09:12:23Z","title":"SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design","version":2},"cited_work":{"arxiv_id":"2401.16456","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.16456","snapshot_observed_at":"2026-08-11T00:15:12.001416Z","title":"SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design","venue":"cs.CV","work_id":"fda57776-5070-433e-8559-9029aeaf3673","year":2024},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.923213Z"},"links":{"cited_paper":"/paper/2401.16456","citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:00d1b2dddf6ae54afdd9069531e3256bb701802f6d7cd3ab5ca59a9cdac779e9","observation_id":"77e0cecc-fa2f-4033-8daf-ec13db1e4716","resolution":{"observed_at":"2026-08-11T00:15:12.009456Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.498667Z","title":"Parc-net: Po- sition aware circular convolution with merits from convnets and transformer","venue":null,"work_id":"ada62aee-9c8b-4de5-9561-3579e3c25693","year":2022},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.928142Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:7bffb4132bdd8cf845132d7011ac34d741d32cec0447b3c82733f31d7df19b12","observation_id":"457d03ea-290a-4acb-9832-218f0fb9074c","resolution":{"observed_at":"2026-08-11T00:15:12.503594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.483872Z","title":"Repnext: A fast multi-scale cnn using structural reparameterization, 2024","venue":null,"work_id":"1ba4c58a-3d61-4396-b13d-4b10879d0a55","year":2024},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.932857Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:faa1f2ffc9bd3715873500ac73e6431cefaacc9a5d4accc392ea472b81d8da9b","observation_id":"dfe53f0b-ed49-438f-b8f6-7995d8efdb59","resolution":{"observed_at":"2026-08-11T00:15:12.488574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.469066Z","title":"Torr, and Li Zhang","venue":null,"work_id":"8f7ac978-eecc-4fd1-97e9-691bb3a70372","year":2021},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.938666Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:fbc15851cb93a0a23cfd3b53479436a7e6364cfbbb9734e3fa1cc95eba64fbc2","observation_id":"1da1cfa2-efad-4d76-8b2c-52f307630258","resolution":{"observed_at":"2026-08-11T00:15:12.473694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:11.943886Z","title":"Scene parsing through ade20k dataset","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.943886Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:f92dde674c2d567d161b29ed80cdf93373a04c8e54355af76cbc358a4e84cf68","observation_id":"c1208d0d-5c1e-45c5-a36a-604ee3b83e4a","resolution":{"observed_at":"2026-08-11T00:15:11.943886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.427592Z","title":"this approach treats the sequence of downsampled feature maps from each decomposition level as the input to a recurrent model","venue":null,"work_id":"0bb9ffbe-d78e-4808-9e32-200f9d2f73bf","year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.953291Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:8a945aa34d83046cb625e0abed7c998c7313298496393dfda66efd57e9f8c366","observation_id":"e9b2eac1-f3eb-4ce4-b4cd-70c1edf5de31","resolution":{"observed_at":"2026-08-11T00:15:12.432987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.412942Z","title":"T”, “S”, “B","venue":null,"work_id":"532b32d7-3640-40bb-80e7-45ba83f19cb5","year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.958189Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:69c019b6a7c27366712f8a5c0b324f35d3c96ea34e5b5abad38827e0c5be7e63","observation_id":"8c516be3-e840-4ef9-a30d-1068e89a4f69","resolution":{"observed_at":"2026-08-11T00:15:12.417612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.397049Z","title":"M” and “A","venue":null,"work_id":"88251b3e-e6b8-45a5-964a-88f9d13dabce","year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.963083Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:dc5f33a59e278ed2aeb6cfcc3c6d36c7230c5a1bd3f1d7b4cbb2ca0262b91536","observation_id":"e915fa30-5397-4f1f-abb6-781d8c8a1232","resolution":{"observed_at":"2026-08-11T00:15:12.402130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:15:12.443289Z","title":"h = None for i, o in reversed(zip(fs[1:], fs[:-1])): h = self.a(h) + self.b(i) if h else self.b(i) h = interpolate(h, size=o.shape[2:]) return self.c(h) + self.d(x)","venue":null,"work_id":"498004f8-e4db-45f8-8ec6-18ff1f9f76ef","year":null},"citing_paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations","version":3},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-11T00:15:11.948631Z"},"links":{"citing_paper":"/paper/2412.19628"},"observation_digest":"sha256:48587716a2b402cf71f23f4d90991cdef5104732e67795dde4547076f447b8c4","observation_id":"3a00d546-6149-41cb-a8fb-efb68bc57456","resolution":{"observed_at":"2026-08-11T00:15:12.449235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.19628","last_updated":"2025-07-30T12:28:59Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T05:13:52.391851Z","submitted_at":"2024-12-27T13:13:52Z","title":"RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations"},"reference_resolution":{"displayed":91,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":42,"verified_exact":5,"verified_fuzzy":44},"total_outbound_references":91},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 91 of 91 outbound references and 0 inbound Pith citation observations for arXiv:2412.19628."}