{"as_of":"2026-08-20T10:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5421a3cd27dffbdcbfb6e3257cd563ec622dcfe0e11fe453484287e9fd57324e","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-25T10:02:28.469463Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T12:44:45.384791Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T14:55:28.623318Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02129","snapshot_observed_at":"2026-08-11T12:44:45.384791Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.13902","last_updated":"2025-01-10T09:55:54Z","snapshot_observed_at":"2026-08-17T20:26:32.950293Z","submitted_at":"2024-12-18T14:42:43Z","title":"Threshold Neuron: A Brain-inspired Artificial Neuron for Efficient On-device Inference","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T12:44:45.384791Z"},"links":{"cited_paper":"/paper/1907.02129","citing_paper":"/paper/2412.13902"},"observation_digest":"sha256:8c8a1e5104e6b916df0638712e99466c52fbfc0d098b4e3805d5048befcf5874","observation_id":"32c92b7f-ae0b-4811-9435-9ba2e3ee45b7","resolution":{"observed_at":"2026-08-11T12:44:45.384791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"cited_work":{"arxiv_id":"1907.02129","doi":null,"metadata_source":"pith","pith_arxiv_id":"1907.02129","snapshot_observed_at":"2026-08-06T14:55:28.623318Z","title":"The Indirect Convolution Algorithm","venue":"cs.CV","work_id":"613c5572-c8e9-4d22-83c6-097b87a189b1","year":2019},"citing_paper":{"arxiv_id":"2507.17301","last_updated":"2025-07-23T08:06:13Z","snapshot_observed_at":"2026-08-14T16:06:40.563359Z","submitted_at":"2025-07-23T08:06:13Z","title":"Efficient Column-Wise N:M Pruning on RISC-V CPU","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T14:55:28.362383Z"},"links":{"cited_paper":"/paper/1907.02129","citing_paper":"/paper/2507.17301"},"observation_digest":"sha256:56a24b5164eec92cc0ed07deb871341431512dfedc01fd90194621f2384f3478","observation_id":"488de650-a313-423d-a2ad-53c71e553fe3","resolution":{"observed_at":"2026-08-06T14:55:28.626810Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02129","snapshot_observed_at":"2026-08-01T00:06:38.994626Z","title":null,"venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2607.23227","last_updated":"2026-07-25T14:24:55Z","snapshot_observed_at":"2026-08-19T02:00:15.675635Z","submitted_at":"2026-07-25T14:24:55Z","title":"INT8 Quantization Makes ARM Edge Inference Dispatch-Invariant","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-01T00:06:38.994626Z"},"links":{"cited_paper":"/paper/1907.02129","citing_paper":"/paper/2607.23227"},"observation_digest":"sha256:a6efe01b5dd68c8815e34be6e16bf958112fff93e2bf7ed5077379a0271f54e3","observation_id":"38873f0f-7c40-40fa-81a4-9e74dd62c822","resolution":{"observed_at":"2026-08-01T00:06:38.994626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1907.02129/citation-record","integrity":"/paper/1907.02129/integrity","json":"/paper/1907.02129/citation-record.json","paper":"/paper/1907.02129"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tensorflow: A system for large-scale machine learning","venue":null,"work_id":"93515583-3fea-4e28-a344-bcd67160813f","year":2016},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:c88971f0c1dabb34a42313a41b01e551cdb8afeca5b8a9a3b5a729c86c6c2e5e","observation_id":"019e28a5-c62a-4912-9fd3-1f49b4da0f3b","resolution":{"observed_at":"2026-05-25T10:05:37.707256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1709.03395","last_updated":"2017-09-08T06:32:33Z","snapshot_observed_at":"2026-08-19T13:51:11.237464Z","submitted_at":"2017-09-08T06:32:33Z","title":"Low-memory GEMM-based convolution algorithms for deep neural networks","version":1},"cited_work":{"arxiv_id":"1709.03395","doi":null,"metadata_source":"pith","pith_arxiv_id":"1709.03395","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Low-memory GEMM-based convolution algorithms for deep neural networks","venue":"cs.CV","work_id":"4a2f4adb-517a-4409-b49e-f0c8ec657d68","year":2017},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"cited_paper":"/paper/1709.03395","citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:71b6a07888aa2cbef10107f28a717a70787109e2701276e8d7ccd2f7aee487af","observation_id":"7a2c56eb-8194-4ea3-bdec-28dbfa2225f1","resolution":{"observed_at":"2026-05-25T10:05:36.950130Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"High per- formance convolutional neural networks for document pro- cessing","venue":null,"work_id":"92c8eb05-b0cc-493b-beb6-115f5c12e297","year":2006},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:981a33c30088fa9c7b05fdeaf20f69f51b15e7a386a44f9aa13e55a9b6d1f255","observation_id":"259de2c0-2068-4f4d-94f3-0aa08b6cf8eb","resolution":{"observed_at":"2026-05-25T10:05:37.714980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","venue":null,"work_id":"57e215dd-7a18-46a1-9238-e0dc72de4acb","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:845c9c80f05cf5fffd2584090a294423f453a16571d8054c674c64f1b8f0c9fd","observation_id":"567e16c1-98ba-4db0-a51e-af398aaa49c7","resolution":{"observed_at":"2026-05-25T10:05:37.719145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"{TVM}: An automated end-to-end optimizing compiler for deep learning","venue":null,"work_id":"82249e98-178a-4d40-86bc-e8f8358cad30","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:65a03ef2344ba17283f30612de0b3fd8ea4a09d5c58e8f34c68f838557ed018a","observation_id":"d218b9ff-056b-4b9b-ae9f-e118d7821ad2","resolution":{"observed_at":"2026-05-25T10:05:37.722880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1410.0759","last_updated":"2014-12-18T01:13:16Z","snapshot_observed_at":"2026-08-14T23:17:07.466378Z","submitted_at":"2014-10-03T06:16:43Z","title":"cuDNN: Efficient Primitives for Deep Learning","version":3},"cited_work":{"arxiv_id":"1410.0759","doi":"10.48550/arxiv.1410.0759","metadata_source":"pith","pith_arxiv_id":"1410.0759","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"cuDNN: Efficient Primitives for Deep Learning","venue":"cs.NE","work_id":"51f5e810-4624-486a-94dd-e2565c587ad0","year":2014},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"cited_paper":"/paper/1410.0759","citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:77afa83d95cb67b0348dffe6e2ebcb25891f3c7f249387d8e6e72a20b987a188","observation_id":"43334afb-5117-4838-84c2-ea2050ace2e2","resolution":{"observed_at":"2026-05-25T10:05:36.955808Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mec: memory-efficient con- volution for deep neural network","venue":null,"work_id":"e8d303e5-5d76-4665-ba40-4d06b5216667","year":2017},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:a914008ae71501630c8c08afeeba2ac9012ff731b14be1d520ed0d8691e83db3","observation_id":"720dfd14-b7be-4906-9c6a-542ba1120cae","resolution":{"observed_at":"2026-05-25T10:05:37.696087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Xception: Deep learning with depthwise separable convolutions","venue":null,"work_id":"c1d34432-6ce4-4798-9560-976093aad7b8","year":2017},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:8d01bc0a51364930a613b2726a2d41a587fb127a9708aebf8b5931648c6dd8dd","observation_id":"4cb4399a-56dd-494a-b3f7-79b7a1759456","resolution":{"observed_at":"2026-05-25T10:05:37.711266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Language modeling with gated convolutional net- works","venue":null,"work_id":"b029bce7-2282-4d3d-ba68-380ad98e8d37","year":2017},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:e7a3f843c11b3b810f3f293a0ed3b4399b1441c3f35f88a2924e75f1b020e52d","observation_id":"242d9a4e-daa8-4878-8fdf-e74f1e57f091","resolution":{"observed_at":"2026-05-25T10:05:37.730144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"QNNPACK: open source library for optimized mobile deep learn- ing","venue":null,"work_id":"14415f55-6555-4049-ad95-34294e534d11","year":2019},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:8d4d6072451fa5a9545e4354a042b7e0e1569cd1cd0d95d2d66f26a28b2874ff","observation_id":"633b5489-78c9-4c06-8288-0ff5d2d014e1","resolution":{"observed_at":"2026-05-25T10:05:37.726591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anatomy of high-performance deep learning con- volutions on simd architectures","venue":null,"work_id":"3ce9c35c-2f6d-43f2-b025-eead2597f2b5","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:ac94cd87a315db781ac854eeb75f7460f440ddf70f8ce4cd1fef0ca847ba3655","observation_id":"7fe8d467-35e8-433c-9aff-eb9225ff424a","resolution":{"observed_at":"2026-05-25T10:05:37.699680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anatomy of high- performance matrix multiplication","venue":null,"work_id":"ae4e096d-0f1c-4db2-9008-243c4b978a22","year":2008},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:1fe90b21d946b23dfb584de439abafd767940a520f2da195454532143fa7feb2","observation_id":"29871af8-36f0-452d-bd70-68ca1cd5f4af","resolution":{"observed_at":"2026-05-25T10:05:37.703624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mask r-cnn","venue":null,"work_id":"27c7e174-0c84-4d99-89c7-bbc4980f51cd","year":2017},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:11853fd13434a1f01a75b1e019bd0c5c2e8c4fc96dd9e462052fd980a4598df2","observation_id":"f60e1c61-34f8-4814-a255-8715e182ef63","resolution":{"observed_at":"2026-05-25T10:05:37.747432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"0e3764d3-713b-4c00-842d-00cf7487f164","year":2016},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:df822da68734d5f4f9ed9ff76d8141438ec3e0b9ed84a1af5a6a1c2f7f7ece8a","observation_id":"4d0f66a6-121a-47fd-beed-f8400bb31573","resolution":{"observed_at":"2026-05-25T10:05:37.773948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"LIBXSMM: accelerating small matrix multi- plications by runtime code generation","venue":null,"work_id":"240cbaaa-77a7-4bd4-a04d-9df827bbcef9","year":2016},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:c6efac54b0e9f2659f7e91b7a3192d9dacf4947306ca9d5304a8396e2eb5bc30","observation_id":"268b315c-1a19-40ef-9d04-d7d9cbd8cb82","resolution":{"observed_at":"2026-05-25T10:05:37.783769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Squeeze-and-excitation net- works","venue":null,"work_id":"7d678ffe-9814-46db-ad44-ed5c0884653b","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:a3901247d5ae7a0ada099138106766e80aefc92331917ace89a9c9e6f2ef96dd","observation_id":"6d922052-234b-480a-bef8-238ec591c1ea","resolution":{"observed_at":"2026-05-25T10:05:37.740424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.07360","last_updated":"2016-11-04T21:26:08Z","snapshot_observed_at":"2026-08-14T22:09:04.541956Z","submitted_at":"2016-02-24T00:09:45Z","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","version":4},"cited_work":{"arxiv_id":"1602.07360","doi":"10.48550/arxiv.1602.07360","metadata_source":"pith","pith_arxiv_id":"1602.07360","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","venue":"cs.CV","work_id":"755e91c7-dab5-418e-9316-bda99a153fed","year":2016},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"cited_paper":"/paper/1602.07360","citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:7c98039d3fca2d55c7ff7c65b3e0b6a27b44b6ca31468ade53a5e4f577d113ab","observation_id":"cb5e581f-25b6-46ff-8b38-3e3671f24e9c","resolution":{"observed_at":"2026-05-25T10:05:36.944385Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Caffe: Convolutional architecture for fast feature embedding","venue":null,"work_id":"e8210618-a030-439e-8405-8cef7b2bc423","year":2014},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:01b4596927b25ce883891ab30a82a5d493c222a1102b9adfd16fc8675c5a06fb","observation_id":"33f087cd-08af-420f-b7a4-816baac765fd","resolution":{"observed_at":"2026-05-25T10:05:37.790768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03284","last_updated":"2018-07-09T17:40:09Z","snapshot_observed_at":"2026-08-18T02:40:46.331293Z","submitted_at":"2018-07-09T17:40:09Z","title":"Pooling Pyramid Network for Object Detection","version":1},"cited_work":{"arxiv_id":"1807.03284","doi":null,"metadata_source":"pith","pith_arxiv_id":"1807.03284","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pooling Pyramid Network for Object Detection","venue":"cs.CV","work_id":"bd161a01-fbf3-4da1-8127-f65b3213f872","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"cited_paper":"/paper/1807.03284","citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:1aecf62c12383e8589d3c8fb05f9c7d44501d21dc1ebf89eeade5c8db85124e7","observation_id":"b90131df-3977-4050-922b-c20b62a45c70","resolution":{"observed_at":"2026-05-25T10:05:36.932245Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.02446","last_updated":"2019-04-10T18:09:43Z","snapshot_observed_at":"2026-08-19T05:59:36.899693Z","submitted_at":"2019-01-08T18:55:31Z","title":"Panoptic Feature Pyramid Networks","version":2},"cited_work":{"arxiv_id":"1901.02446","doi":"10.48550/arxiv.1901.02446","metadata_source":"pith","pith_arxiv_id":"1901.02446","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"Panoptic Feature Pyramid Networks","venue":"cs.CV","work_id":"4bc5a076-27b4-49a3-b2de-8a5cfe854c6e","year":2019},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"cited_paper":"/paper/1901.02446","citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:4ada84c5b5606c86ca223631ba196b95471931889d8982bdfe10df7c62d738cb","observation_id":"56f18808-c08f-4b24-9622-0d104b9213d6","resolution":{"observed_at":"2026-05-25T10:05:36.926520Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fast algorithms for convo- lutional neural networks","venue":null,"work_id":"3e5f4e50-bb30-4a39-9192-15a45e3f123a","year":2016},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:5cd2ed22b3f487d196427ac23bb45bb8f38a5a6117c8e929ffb81a184305c78b","observation_id":"173d820d-6b88-4893-b961-6854c5abb1b5","resolution":{"observed_at":"2026-05-25T10:05:37.743770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Focal loss for dense object detection","venue":null,"work_id":"ad66e91a-dcc2-42a9-9949-b86a0f133c30","year":2017},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:ade3837cfdf1212d7d73ab05338e687c9c77f2a962d7f9868bcbdbf85034a139","observation_id":"e28b38ca-dd9f-43ed-b99a-ca4ef59090e3","resolution":{"observed_at":"2026-05-25T10:05:37.780371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Shufflenet v2: Practical guidelines for efficient CNN archi- tecture design","venue":null,"work_id":"1d73ca06-cb73-4317-a0c5-1177cf46d8ae","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:2b06bd231fa4666719053b91d533bed445550db1a032cc02fac1295719f73f60","observation_id":"02384c4d-4bca-4170-a578-ee89daa9faa7","resolution":{"observed_at":"2026-05-25T10:05:37.737042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Automatic differentiation in PyTorch","venue":null,"work_id":"b03486cf-81d4-4164-8489-eb8e63df08e0","year":2017},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:4a14f4300f01a232c0d1dab9f7e39b834c9b3792eb767e4dd689bb9eaf80a250","observation_id":"b326dfba-7a6f-4223-9f8f-541dcfd5f3f6","resolution":{"observed_at":"2026-05-25T10:05:37.755675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.02767","last_updated":"2018-04-08T22:27:57Z","snapshot_observed_at":"2026-08-15T16:54:48.034047Z","submitted_at":"2018-04-08T22:27:57Z","title":"YOLOv3: An Incremental Improvement","version":1},"cited_work":{"arxiv_id":"1804.02767","doi":"10.48550/arxiv.1804.02767","metadata_source":"pith","pith_arxiv_id":"1804.02767","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"YOLOv3: An Incremental Improvement","venue":"cs.CV","work_id":"d737b3cc-9bd1-43d6-8310-c91e64b510f7","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"cited_paper":"/paper/1804.02767","citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:2197f26ca0b17494d6f4229f70150dca4fe39f5340a86a8f38f1f4788a9455f5","observation_id":"f28965b4-5ee8-4ee9-a44b-9d5f3a59c8ac","resolution":{"observed_at":"2026-05-25T10:05:36.900994Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-07-12T23:51:10.097273+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T23:51:10.097273+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":"b264bead-f2eb-4ac8-bc6e-dbe6ef8b64cb","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:48fec719a6f4fe04e8cb74cf3820eb9ea177f91bc330f293206d0963b039d550","observation_id":"b0be89a2-3f64-44de-9c13-84ebd69372a0","resolution":{"observed_at":"2026-05-25T10:05:37.787037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Wavenet: A generative model for raw audio","venue":null,"work_id":"50722b95-f792-44b8-8725-3d02a3792ffe","year":2016},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:188cc1b02431d16b8070482b881c859df4f40c50ed46381b0d859bac2a4dd95d","observation_id":"fcf0e441-32dc-4abc-a32b-ead0168c6c05","resolution":{"observed_at":"2026-05-25T10:05:37.794373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Blis: A frame- work for rapidly instantiating BLAS functionality","venue":null,"work_id":"b69c4b12-b6fa-47d0-a036-78f095df1ef9","year":2015},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:b492fa72167bba8192984054fb6b22cef5322ae38f4d6a226baaa3daa0a000ff","observation_id":"cda8d6b8-a01c-46ec-9e06-3c78032e9f21","resolution":{"observed_at":"2026-05-25T10:05:37.733527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.7580","last_updated":"2015-04-10T20:01:00Z","snapshot_observed_at":"2026-08-14T23:06:13.335368Z","submitted_at":"2014-12-24T01:31:36Z","title":"Fast Convolutional Nets With fbfft: A GPU Performance Evaluation","version":3},"cited_work":{"arxiv_id":"1412.7580","doi":null,"metadata_source":"pith","pith_arxiv_id":"1412.7580","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fast Convolutional Nets With fbfft: A GPU Performance Evaluation","venue":"cs.LG","work_id":"e38af448-ec52-46f5-ab0b-319101b6f10a","year":2014},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"cited_paper":"/paper/1412.7580","citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:65cb27d4cc416f3b64d78a3c70f49cefce2574b2f066f5f1de78262ba1f7909e","observation_id":"04e42665-d871-4bb0-ae70-be5653302f44","resolution":{"observed_at":"2026-05-25T10:05:36.907482Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Roofline: An insightful visual performance model for floating-point programs and multicore architectures","venue":null,"work_id":"ff2d48e5-9a58-4e12-9d0e-e5463d9f113f","year":2009},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:b01b05c00e5d17eea933ca67c41ef2b7f1edd14872b657e07661959d634be435","observation_id":"9562219f-aa1e-4b0d-9d8c-f314ffbc0f62","resolution":{"observed_at":"2026-05-25T10:05:37.750949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.03443","last_updated":"2019-05-24T05:47:40Z","snapshot_observed_at":"2026-08-17T11:26:18.594189Z","submitted_at":"2018-12-09T08:24:50Z","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","version":3},"cited_work":{"arxiv_id":"1812.03443","doi":null,"metadata_source":"pith","pith_arxiv_id":"1812.03443","snapshot_observed_at":"2026-06-29T00:22:51.672010Z","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","venue":"cs.CV","work_id":"601724aa-8608-49fa-a54f-7b75f64f8b77","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"cited_paper":"/paper/1812.03443","citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:b9c89642cc44111a1afddf6886394668629af54c8e02d40d6a5dc03c8724b52d","observation_id":"44eb7141-f690-469c-a80e-7e456bac9807","resolution":{"observed_at":"2026-05-25T10:05:36.938204Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.10430","last_updated":"2019-02-22T23:46:38Z","snapshot_observed_at":"2026-08-15T16:08:35.191385Z","submitted_at":"2019-01-29T18:01:35Z","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","version":2},"cited_work":{"arxiv_id":"1901.10430","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.10430","snapshot_observed_at":"2026-07-01T23:16:24.435389Z","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","venue":"cs.CL","work_id":"618a5083-a095-491b-83ac-5f1f3b7a4ad2","year":2019},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"cited_paper":"/paper/1901.10430","citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:71bbabe7eb961465d74d726ec0bb6fe735ae79558dc02c1139065826b36ac971","observation_id":"fef84997-e60d-4444-ac4d-2b8a9805f53f","resolution":{"observed_at":"2026-05-25T10:05:36.920371Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"1072056f-227f-4d70-bcff-abbd2d58aa61","year":2019},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:fd5e1f7838c494d46f4bd0b7c5cf9b2c571161f3e11aefb9e48ed8607fa284a9","observation_id":"a223c854-413d-4642-a8f3-15aa44276905","resolution":{"observed_at":"2026-05-25T10:05:37.765550Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Aggregated residual transformations for deep neural networks","venue":null,"work_id":"ef2d4086-7b6a-43e9-a546-19447eb26127","year":2017},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:10651c36fc5f99a477d115c91941e184993f8bfb500b4629d37e22ef682b2c23","observation_id":"519ad447-dffc-40e2-9489-7adcfb8f2f42","resolution":{"observed_at":"2026-05-25T10:05:37.769726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.10170","last_updated":"2018-09-20T00:48:12Z","snapshot_observed_at":"2026-08-14T18:26:05.069370Z","submitted_at":"2018-09-20T00:48:12Z","title":"High Performance Zero-Memory Overhead Direct Convolutions","version":1},"cited_work":{"arxiv_id":"1809.10170","doi":null,"metadata_source":"pith","pith_arxiv_id":"1809.10170","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"High Performance Zero-Memory Overhead Direct Convolutions","venue":"cs.LG","work_id":"7f30d6d9-2ab7-4ad9-92c7-5f09a057c789","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"cited_paper":"/paper/1809.10170","citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:06ad2dcdb689395b6769a2c4414937a63637f32c7141ff07a5634825e83bf0ed","observation_id":"273dcbbe-33ec-42fb-871e-70105c817fb0","resolution":{"observed_at":"2026-05-25T10:05:36.914218Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning transferable architectures for scalable image recognition","venue":null,"work_id":"8fb19f53-97b7-4413-a6a1-fb10e21d1b1d","year":2018},"citing_paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-25T10:02:28.469463Z"},"links":{"citing_paper":"/paper/1907.02129"},"observation_digest":"sha256:250bab98537865820d3d4d6a7f2b9795de20eff9a1424d8f9cd835742afc058f","observation_id":"d74cef89-b098-4758-b23c-0c2882326439","resolution":{"observed_at":"2026-05-25T10:05:37.760086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1907.02129","last_updated":"2019-07-03T20:51:18Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T05:00:09.699223Z","submitted_at":"2019-07-03T20:51:18Z","title":"The Indirect Convolution Algorithm"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":10,"verified_fuzzy":25},"total_outbound_references":36},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 3 inbound Pith citation observations for arXiv:1907.02129."}