{"as_of":"2026-08-10T19:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:93107090aa10b5b6576f136e0a6e616e8bf5b8934a757322680b2a9776048bb6","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T05:22:08.069048Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2607.11473/citation-record","integrity":"/paper/2607.11473/integrity","json":"/paper/2607.11473/citation-record.json","paper":"/paper/2607.11473"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T05:22:08.069048Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:702771fa29bb94f62ebc60e74174ea663c4bf2f0f87e7a45a5454c2fffae0db3","observation_id":"a23f8e62-705f-4b44-9c35-5997505a65e0","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Bringing ai to edge: From deep learning’s perspective,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:bdffa65f6f9ea025e32b2a5eae006c270dd5b0e8af7bbf2d41e8888b13929c3d","observation_id":"b25a01f8-7048-46f5-a460-14886f42a0ef","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Edge computing: Vision and challenges,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:baac9e124dc9e248b17347a25d62a9aaebf82db363e468960c825e294bd7d27c","observation_id":"dab41dd6-6f33-478a-8329-dec1c0d6a7a2","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Edlab: A benchmark for edge deep learning accelerators,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:b7cc83aa22c899c1d94dd240f834aef1f6f567390def4eb113b3aec5e6c273e2","observation_id":"916f639a-8e13-4e74-a7af-3245053a6607","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Data-driven sparse structure selection for deep neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:bbfc58fd23c402c6745af0b35cfabd0bc0f343155c3ede8fce37719e0139bca8","observation_id":"82d4f435-1a0b-4bdc-a49f-9ee0ca110098","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Learning versatile filters for efficient convolutional neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:8d521f99218bb5df2136ce822f55a7eb6989ac4481f2c9be4c7d56fdc95f3c00","observation_id":"b9113238-c5d7-4550-9d58-5b3cd5cf02d4","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Importance estimation for neural network pruning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:4cd13d05e07489b0b36f6302b5122b91313f08efe05120d854c5d4c199d48aaa","observation_id":"2b4f4110-84a5-43fb-b4d0-3fd9baa67d57","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Hrank: Filter pruning using high-rank feature map,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:5cab460425b901acb7623f59cb9b683aa56d4fff04cc741ab78eae21462186c9","observation_id":"a54d7ef4-1841-4d7c-b544-4d614b80351b","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Towards optimal structured cnn pruning via generative adversarial learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:5770b751749a79e30b2adc500b331383701291fb7becbd499a21b1d85bb9e2fd","observation_id":"3810c658-d70f-46f3-8fd5-f3c18a4127b7","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Decore: Deep compression with reinforcement learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:3f2c151d1bd1264d6d8cf5ba6bfeabddba36a2fefd68f06216312df8bf6a4709","observation_id":"d42b1917-8800-4eff-bd5e-109708ffd2ba","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Hessian-aware pruning and optimal neural implant,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:cf60c41090c6f5d670def1f7716f0ee3fdc1b09b6f4da737d3d18b56bdadf33d","observation_id":"b5a625d1-f7c1-4d28-b54b-7d8d7f2c6abf","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Dnr: A tunable robust pruning framework through dynamic network rewiring of dnns,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:d29329bb3cda33f60ce240472942539f221055eb885ecc47177cf82da6165fb1","observation_id":"df67139f-0873-4ce3-a4d4-380175930c1a","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Acceleration-aware fine-grained channel pruning for deep neural networks via residual gating,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:a85a0ba59730eb8f2122ca6dec80e5d9f5849a2794a3d5c4239453119a2aaa6b","observation_id":"dd33cb00-a449-4ffd-a734-8bf80778c97d","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.10178","last_updated":"2019-12-21T02:11:47Z","snapshot_observed_at":"2026-07-06T08:46:12.464068Z","submitted_at":"2019-12-21T02:11:47Z","title":"DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.10178","snapshot_observed_at":"2026-07-14T05:22:08.069048Z","title":"Dbp: Discrimination based block-level pruning for deep model acceleration,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"cited_paper":"/paper/1912.10178","citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:81d0d24916ed122f34e97515f34a7d5f544b9dd7ea893ff160e0f079ddcad945","observation_id":"aba39510-1b66-435e-9a26-55c81407a3ce","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Learning structured sparsity in deep neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:b10d1370f42d298c73dd89e97d7069354c65d23260b4d10d01f33db6e0f518d6","observation_id":"a1e36696-5277-4a80-a03b-a94a6d2fca37","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Dy- namic resolution network,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:4f6701088c2a892d9328a84bae9d49bb7ce883f944ecd91fe7db0bdc6d8ca2cf","observation_id":"5e3feb34-f2f9-4d1c-b8fb-36e1e7a183a9","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Resolu- tion adaptive networks for efficient inference,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:4d1d14b1cc1b07f915a3b121dd6900c877f36d99ab578ddc0f42f1af94b9bb8a","observation_id":"cf402a19-850b-4731-9e6f-f86f051dd8ec","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Smart scissor: Coupling spatial redundancy reduction and cnn compression for embedded hardware,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:ba59b38199f7f37ecce4ea2835b1af8e4356d7338e51aa9ebcb4fdbbccffa418","observation_id":"a8caecb7-689f-43fe-a8a6-7574e3178196","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Provable filter pruning for efficient neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:a3c5234dd5c7fe7be98a06794b8e380996a7f11451667d5c4032929bd9089d58","observation_id":"c3927ffe-79ea-4fc2-a246-8acfe8b12707","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:f5802b55704792e75b79a42906fc193077231bbea71d1afda0464cfba03c5d52","observation_id":"2452379f-fd8a-4da7-a618-707d9f0dd51a","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Zerobn: Learning compact neural networks for latency-critical edge systems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:51c85a8127d596c5c221a3e6aee18829921b282515c48a1f5afa0156846df4d4","observation_id":"d685d51a-64c4-43a3-8ef7-faa6e66755d2","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Centripetal sgd for pruning very deep convolutional networks with complicated structure,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:fa99412bd980cd0bcec80d46bd905a1482079921cbdf9f21fc29cf7dfcc9fbe0","observation_id":"3f87de50-1d72-4f25-ba7b-c03ccc50c4f9","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"SGDR: Stochastic gradient descent with warm restarts,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:60082bff17443da802232d45efbcb2d952a8b539781f658129525bf04f6d29d7","observation_id":"1833ded4-472b-45a9-817f-1f78c0da4763","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","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":"2026-07-14T05:22:08.069048Z","title":"Grad-cam: Visual explanations from deep networks via gradient- based localization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-14T05:22:08.069048Z"},"links":{"citing_paper":"/paper/2607.11473"},"observation_digest":"sha256:8d334793b8bbaab70d6b340a42a7ad46d0ed575815573d6f2ff19cf642954a30","observation_id":"6ee1d770-f4c6-4afe-98f4-641ca582de3c","resolution":{"observed_at":"2026-07-14T05:22:08.069048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.11473","last_updated":"2026-07-13T12:27:33Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-02T05:47:53.579143Z","submitted_at":"2026-07-13T12:27:33Z","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":24},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2607.11473."}