{"as_of":"2026-08-19T19:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ed37e020872a25a7118a546a7e19e6984862a11dea215a8afca8544e05258931","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:22:58.262373Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2505.07411/citation-record","integrity":"/paper/2505.07411/integrity","json":"/paper/2505.07411/citation-record.json","paper":"/paper/2505.07411"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:22:58.787152Z","title":"DLAS: A Conceptual Model for Across-Stack Deep Learning Acceleration,","venue":null,"work_id":"0c96e761-ede5-4868-aa7b-30f2950e72e0","year":2025},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.105032Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:746ad79cf9195745caa6d6cf136244c558c80f054877703fdb12108c38347478","observation_id":"96766cd7-39e1-4b71-81b7-bcc56fb9415b","resolution":{"observed_at":"2026-08-15T22:22:58.792131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.771693Z","title":"Linearly Replaceable Filters for Deep Network Channel Pruning,","venue":null,"work_id":"e2f13980-7839-4ed3-a9ba-5632ef930a02","year":2021},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.110601Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:e36cef37a953e575c437273280a375f55c62c631954a8d839c66f6976c7dacb2","observation_id":"126df150-6f61-43d7-9a25-a1b0229b0e1f","resolution":{"observed_at":"2026-08-15T22:22:58.777153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.05791","last_updated":"2017-06-19T05:29:29Z","snapshot_observed_at":"2026-08-18T19:59:15.445331Z","submitted_at":"2017-06-19T05:29:29Z","title":"An Entropy-based Pruning Method for CNN Compression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.05791","snapshot_observed_at":"2026-08-15T22:22:58.115444Z","title":"An entropy-based pruning method for cnn compression,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.115444Z"},"links":{"cited_paper":"/paper/1706.05791","citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:d86479d033a1dacda8673d5618cfc9d50c9bd11a208ab455d298f9b51a2e2cfb","observation_id":"f22195c0-3d7f-4051-92b8-c1534fd67bbb","resolution":{"observed_at":"2026-08-15T22:22:58.115444Z","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":"2026-08-15T22:22:58.757990Z","title":"Thinet: A filter level pruning method for deep neural network compression,","venue":null,"work_id":"86ff933d-0e2e-49e3-bd8e-4e222a4f1c0d","year":2017},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.121195Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:5c66ba24f4c33dac2a9a1ec7e1e5acf73d94e3bf02769893018eb15aef7d7b15","observation_id":"89885d7d-138d-49d0-a3a0-8f0bbd5342a0","resolution":{"observed_at":"2026-08-15T22:22:58.762656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.744098Z","title":"Pruning filters for efficient convnets,","venue":null,"work_id":"64311cf0-5707-4f8d-a499-812dd2af7e96","year":2017},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.126096Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:bbc585759a9d1b0ec669b901041a5dec7f74e3fa193c8497fb0b1a8d99e519ed","observation_id":"709dc15d-2d4b-47bb-8082-badcd8a42dd4","resolution":{"observed_at":"2026-08-15T22:22:58.749175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.730984Z","title":"Automatic attention pruning: Improv- ing and automating model pruning using attentions,","venue":null,"work_id":"f4493608-a4f6-4e1f-84c3-2d0fe6002a30","year":2023},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.131167Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:1b8164ff549334e4458fa6a9e7de9adef69b51474c4636cf653dbfe9851e14fd","observation_id":"5164eed0-069d-49aa-96a4-317612e6a2ad","resolution":{"observed_at":"2026-08-15T22:22:58.735060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.135740Z","title":"Pruning convolutional neural networks for resource efficient inference,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.135740Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:5a208b494465f8665616a541655829280c6e429ca092c04779267e5748b32950","observation_id":"5be34f93-3d77-4770-8609-0659db216112","resolution":{"observed_at":"2026-08-15T22:22:58.135740Z","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":"2026-08-15T22:22:58.714257Z","title":"What is the State of Neural Network Pruning?","venue":null,"work_id":"49bce960-a293-480c-92ee-39eb9c9374bc","year":2020},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.139728Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:733d7c4aa2b0a3690509fba8448b0e77b228e2e1f2dc749749146f80fb913e2c","observation_id":"2f8b06a0-1b55-4b81-acb3-d6e2822cae15","resolution":{"observed_at":"2026-08-15T22:22:58.717947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.702843Z","title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks,","venue":null,"work_id":"7d97bd3b-7bac-421d-ba59-f98f1e4fbbad","year":2021},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.144107Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:47ad2fefd634cc66dc0a86d882b988a583d11a578e3a38299316e3432ca2488f","observation_id":"d5315563-37cc-4208-8e65-687b8df97396","resolution":{"observed_at":"2026-08-15T22:22:58.707417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.147949Z","title":"Model compression and hardware acceleration for neural networks: A comprehensive survey,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.147949Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:143b452521d84e7e61fa8f5c6f72949f294e7f9256113bfeebd2b416434a0cdb","observation_id":"41e3454a-b24a-4e3e-8dc5-bb7a9a52022a","resolution":{"observed_at":"2026-08-15T22:22:58.147949Z","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":"2026-08-15T22:22:58.692430Z","title":"Soft filter pruning for accelerating deep convolutional neural networks,","venue":null,"work_id":"e599ff5a-f7b0-4148-bf35-e3666655d8f6","year":2018},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.151286Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:c78fbd846efbb39321d2eed33cc5a04655069f014fd4d49dc585c62e7510410d","observation_id":"1e5f22f9-e503-44d2-9684-2f50844b1389","resolution":{"observed_at":"2026-08-15T22:22:58.696259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.679417Z","title":"Filter Pruning via Similarity Clustering for Deep Convolutional Neural Networks,","venue":null,"work_id":"92c825b4-c2d1-46d8-9f7f-dec22fe39746","year":2022},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.155099Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:92471d115e8f5b31265beb1edbcf441510ee212b228f0e822f0f943bb0416fb5","observation_id":"06284ee6-2096-4598-850f-d1f28a1c69d8","resolution":{"observed_at":"2026-08-15T22:22:58.684423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.666241Z","title":"Are Sixteen Heads Really Better than One?","venue":null,"work_id":"054fed51-c6ec-408c-8610-a811fe4b2d25","year":2019},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.158835Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:d1323e6a9a3b5c2e4e8ecafd8fc93616354b1e9b2021b9426b4211967f452727","observation_id":"a32812fd-7d9b-4e94-8ba2-b2de2c2acff9","resolution":{"observed_at":"2026-08-15T22:22:58.671135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.652841Z","title":"Pruning Convolutional Neural Networks for Resource Efficient Inference,","venue":null,"work_id":"5931b891-a0d1-4996-b802-95da32693daf","year":2017},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.162525Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:e85ab905c7c7ec2e1bcf741b185a4138063dc83a5aacc495300a6cf75297fb9e","observation_id":"376d103a-cab4-435a-a512-684d1856a21c","resolution":{"observed_at":"2026-08-15T22:22:58.657662Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.642039Z","title":"ICE-pick: Iterative cost-efficient pruning for DNNs,","venue":null,"work_id":"e9cd039a-f171-4194-af87-3fe1b3617271","year":2023},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.166056Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:c26c62af8ce096904cfdda1e5d47c3969945b95a6a3f3d0b0fcd2259cbc1acc0","observation_id":"a7e93adb-16a2-4b51-a021-6a37b0b00e37","resolution":{"observed_at":"2026-08-15T22:22:58.645892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.628437Z","title":"Nfp: A no fine- tuning pruning approach for convolutional neural network compression,","venue":null,"work_id":"9be04c43-8dfa-4ecd-8572-3c9dea3f8087","year":2020},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.169501Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:c0f9fd968456e305f734323952b8407b742894de1f8103903c2fe09cb4b8df98","observation_id":"a47a325d-d910-4324-82cc-1650b7484d3b","resolution":{"observed_at":"2026-08-15T22:22:58.633633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.613821Z","title":"Pruning filters while training for efficiently optimizing deep learning networks,","venue":null,"work_id":"44cabca2-8650-40be-a4f1-312bc63652f2","year":2020},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.172652Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:e4424cac369c6795eda10061f5db0ffe51080d18cfa08fab9529820447e1b5d0","observation_id":"50f5675e-ca9e-4cf0-a4a3-4bf9eca7fed6","resolution":{"observed_at":"2026-08-15T22:22:58.619622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.598345Z","title":"FreezeOut: Accelerate Training by Progressively Freezing Layers,","venue":null,"work_id":"7cab2289-5038-4292-9d31-284068ff808a","year":2017},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.176319Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:a4e467e02f4beee5c0eb783fbfa4ffc7bd844c03789e7d3a1cec838fef668a52","observation_id":"e23f103f-f663-4859-b98d-7e1f6c071b07","resolution":{"observed_at":"2026-08-15T22:22:58.603673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.01386","last_updated":"2021-04-03T15:08:06Z","snapshot_observed_at":"2026-08-16T18:48:21.350371Z","submitted_at":"2021-02-02T08:35:02Z","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.01386","snapshot_observed_at":"2026-08-15T22:22:58.179834Z","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.179834Z"},"links":{"cited_paper":"/paper/2102.01386","citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:c1223355b8ebef99fdfaeaa2bc76885aadade881aed315ce653b89741773305a","observation_id":"011d898f-4d48-41a3-81c3-961a37d00674","resolution":{"observed_at":"2026-08-15T22:22:58.179834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.03090","last_updated":"2019-11-08T07:05:20Z","snapshot_observed_at":"2026-08-15T11:37:14.735128Z","submitted_at":"2019-11-08T07:05:20Z","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.03090","snapshot_observed_at":"2026-08-15T22:22:58.183712Z","title":"What would elsa do? freezing layers during transformer fine-tuning,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.183712Z"},"links":{"cited_paper":"/paper/1911.03090","citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:071ef1199157f319561ca436cff09aef3929a3024fa6c1f22bcc1eafaa6d617b","observation_id":"b90bb6cd-fe5a-47bd-9b84-0c05da99f771","resolution":{"observed_at":"2026-08-15T22:22:58.183712Z","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":"2026-08-15T22:22:58.582752Z","title":"Local Masking Meets Progressive Freezing: Crafting Efficient Vision Transformers for Self-Supervised Learning,","venue":null,"work_id":"5c578322-9811-4ef1-8b7b-ee349c1039f9","year":2024},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.187927Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:bb19f796f0f9daa8d2419c7c386b142d6a93e451048688eef36e15071fd1fa2b","observation_id":"ee443bbf-35e1-418b-8910-31d329d47fd7","resolution":{"observed_at":"2026-08-15T22:22:58.587642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.566238Z","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks,","venue":null,"work_id":"2154b1e5-96e2-456a-b223-852262445333","year":2019},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.191106Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:fa19f09e04e9766459952246f1a382e0a623e4d74304db9d50a7177e450ae686","observation_id":"5afbf0f0-c583-495a-9865-473b62309742","resolution":{"observed_at":"2026-08-15T22:22:58.572900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.550766Z","title":"Do we actually need dense over-parameterization? in-time over-parameterization in sparse training,","venue":null,"work_id":"9f8625c0-1530-42b1-968a-bb1cdb982c93","year":2021},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.194482Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:6d8582cf458c920625170326bcd71de1b8095ae3a323f4db5ac1971d49e864a2","observation_id":"261945ca-8eea-470b-98c7-2eda2dd974c0","resolution":{"observed_at":"2026-08-15T22:22:58.556480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.536465Z","title":"Towards explaining the regularization effect of initial large learning rate in training neural networks,","venue":null,"work_id":"45177760-a1eb-4a7e-9560-00361a4aad01","year":2019},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.197929Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:a5e031b6bf6144675cb826538be5707ca7c67eda2c4d4924f91405bd2e1f6b37","observation_id":"a5e18390-96b8-4400-8ebc-92dd520fec53","resolution":{"observed_at":"2026-08-15T22:22:58.541111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.525087Z","title":"On the Variance of the Adaptive Learning Rate and Beyond,","venue":null,"work_id":"14d61b41-d839-463c-b188-604eb0416603","year":2020},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.201542Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:a0a15f81fc02937ef5e2b2c19f2c2045b66d54060950aaa6eb8469378ff27020","observation_id":"0c33ed33-5a35-4259-992e-2781988e34ee","resolution":{"observed_at":"2026-08-15T22:22:58.529092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.204890Z","title":"Visualizing the loss landscape of neural nets,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.204890Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:0d20bdc02f6d4b85f9bcf87ee5fed2724847e7dce0a702ee6955c3eb01919bc5","observation_id":"9f37eab4-8cf1-4d63-af2f-f81ff56abe2c","resolution":{"observed_at":"2026-08-15T22:22:58.204890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.08764","last_updated":"2021-10-17T08:58:08Z","snapshot_observed_at":"2026-08-16T21:03:25.331309Z","submitted_at":"2021-10-17T08:58:08Z","title":"S-Cyc: A Learning Rate Schedule for Iterative Pruning of ReLU-based Networks","version":1},"cited_work":{"arxiv_id":"2110.08764","doi":null,"metadata_source":"pith","pith_arxiv_id":"2110.08764","snapshot_observed_at":"2026-08-15T22:22:58.372563Z","title":"S-Cyc: A Learning Rate Schedule for Iterative Pruning of ReLU-based Networks","venue":"cs.LG","work_id":"4148e946-b37f-413c-bcf1-f05d9508f482","year":2021},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.208657Z"},"links":{"cited_paper":"/paper/2110.08764","citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:7cd657cfc049d3575eecacc7191318734bbfb2e4f0dac59903797aae86e12297","observation_id":"75856f42-f771-48c5-99f3-8f68be0a0ae8","resolution":{"observed_at":"2026-08-15T22:22:58.376687Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.505058Z","title":"Algorithms for hyper- parameter optimization,","venue":null,"work_id":"9d499ed6-3bdb-4cc1-b921-dbb1e64aca45","year":2011},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.212750Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:0bcf1d6e035a1ee4f8fff9d44e934cf7acd34e2a36c4ba9ace0cc69f84293952","observation_id":"43b13feb-bc5d-4d5b-bda4-b05ac0b37ded","resolution":{"observed_at":"2026-08-15T22:22:58.509863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.491459Z","title":"Optuna: A Next-generation Hyperparameter Optimization Framework,","venue":null,"work_id":"1a91d248-61be-4fd6-b079-a1c9711292ea","year":2019},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.217447Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:53a43e2bc5b80dc45eda2c7969b462068117cbbf2b785aab32b8f345f2dd9216","observation_id":"de7d5608-f18e-45ef-abf6-7113138e0742","resolution":{"observed_at":"2026-08-15T22:22:58.496209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.221126Z","title":"Learning Multiple Layers of Features from Tiny Im- ages,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.221126Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:77d14b77b3811b043929b5f3ca45e3f2b59d7a68ee9dc4ade760805ebcd67be5","observation_id":"7f70f34d-c0dc-4219-87ff-cc1edcc411e7","resolution":{"observed_at":"2026-08-15T22:22:58.221126Z","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":"2026-08-15T22:22:58.467029Z","title":"Tiny ImageNet Visual Recognition Challenge,","venue":null,"work_id":"59d6b2a8-0fba-4066-8c80-c5497dc54620","year":2015},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.224932Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:380b86140fed5fcf2ae98119a3cee01a581e5d086deea696bf2ea99abeccba2b","observation_id":"fad4d535-12cf-496b-b0d7-af2078fa4c9e","resolution":{"observed_at":"2026-08-15T22:22:58.473912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.228521Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.228521Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:9aa65ca50ca4e538c097deea7c6099372e563a21505b100aada9899d404719f3","observation_id":"cb15bd4c-adfc-44a1-9dae-3675cd0d6549","resolution":{"observed_at":"2026-08-15T22:22:58.228521Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-16T18:00:58.008096Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-15T22:22:58.232255Z","title":"Distilling the Knowledge in a Neural Network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.232255Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:4b8caf421a67e48b0015682f1b1a18a98f7a686caade4a590de39e97109722ba","observation_id":"e60ba28c-4787-4984-835f-cf129c276c3b","resolution":{"observed_at":"2026-08-15T22:22:58.232255Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.10460","last_updated":"2019-03-07T16:19:50Z","snapshot_observed_at":"2026-08-14T18:09:54.374755Z","submitted_at":"2018-10-24T15:45:36Z","title":"Distilling with Performance Enhanced Students","version":2},"cited_work":{"arxiv_id":"1810.10460","doi":null,"metadata_source":"pith","pith_arxiv_id":"1810.10460","snapshot_observed_at":"2026-08-15T22:22:58.342431Z","title":"Distilling with Performance Enhanced Students","venue":"stat.ML","work_id":"4bbe8547-cc82-432c-9ee2-7cc5a96eaa21","year":2018},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.236322Z"},"links":{"cited_paper":"/paper/1810.10460","citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:ceeadcc74586de0d62ca6b633dd2a92489927b6e2012edcc987927de5b53d092","observation_id":"b2d8fed3-72f7-47ff-bcaf-a2107b1da6eb","resolution":{"observed_at":"2026-08-15T22:22:58.348726Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.443954Z","title":"Deep Residual Learning for Image Recognition,","venue":null,"work_id":"fe56c4a4-3b37-479d-a350-0c43abaf13e7","year":2016},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.240187Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:8d468acf8fcfa790d0149c992ba80d758c0b737be0f848a6b2a31089f399175d","observation_id":"dda6e8c2-206c-4130-8305-1cd294b0f38a","resolution":{"observed_at":"2026-08-15T22:22:58.449310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T22:22:58.428432Z","title":"Densely connected convolutional networks,","venue":null,"work_id":"507618fb-0c53-4ba4-9d72-bd755c14865a","year":2017},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.243967Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:824ac5eb981ba481b5700b88b2577f366bdde76abc3ee7f8228f11d1259adabb","observation_id":"f37db7dd-f984-4f9f-a7bd-05ee12ec61ee","resolution":{"observed_at":"2026-08-15T22:22:58.433871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07146","last_updated":"2017-06-14T06:06:48Z","snapshot_observed_at":"2026-08-16T07:54:28.918946Z","submitted_at":"2016-05-23T19:27:13Z","title":"Wide Residual Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07146","snapshot_observed_at":"2026-08-15T22:22:58.247752Z","title":"Wide Residual Networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.247752Z"},"links":{"cited_paper":"/paper/1605.07146","citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:b46e778685f6eb2d9063cae32116a3f2daf014f70035cdd087c0c359454de48e","observation_id":"8163fc16-3ab5-46af-8b47-7abbf4155583","resolution":{"observed_at":"2026-08-15T22:22:58.247752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.04747","last_updated":"2017-06-15T13:21:04Z","snapshot_observed_at":"2026-08-15T03:49:17.013617Z","submitted_at":"2016-09-15T17:32:34Z","title":"An overview of gradient descent optimization algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.04747","snapshot_observed_at":"2026-08-15T22:22:58.251409Z","title":"An Overview of Gradient Descent Optimization Algorithms,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.251409Z"},"links":{"cited_paper":"/paper/1609.04747","citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:4f4b1e835190f3505ed39aa5455422a64c705abd6a885ab3de2cf08ea68f0db0","observation_id":"1797b787-1d8c-4a1a-9bd2-445656cc49d0","resolution":{"observed_at":"2026-08-15T22:22:58.251409Z","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":"2026-08-15T22:22:58.255065Z","title":"Pytorch: An imperative style, high-performance deep learning library,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.255065Z"},"links":{"citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:a5fbeeb741eae0a23161106c2810e9523f9fdf6513ba375258a2979d8f991048","observation_id":"3792ca1e-9e3a-4dc2-991a-1bef4a6fd47b","resolution":{"observed_at":"2026-08-15T22:22:58.255065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-15T22:22:58.258538Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.258538Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:0ee0b8db2025951e2d69a8bea31592061980ee65a632c54b726386375f98f9d2","observation_id":"48333c4c-c0b5-46df-93e8-d3a10eabb326","resolution":{"observed_at":"2026-08-15T22:22:58.258538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10420","last_updated":"2023-12-23T12:53:02Z","snapshot_observed_at":"2026-08-18T19:55:31.392155Z","submitted_at":"2023-03-18T14:02:04Z","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.10420","snapshot_observed_at":"2026-08-15T22:22:58.262373Z","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T22:22:58.262373Z"},"links":{"cited_paper":"/paper/2303.10420","citing_paper":"/paper/2505.07411"},"observation_digest":"sha256:44b8f4f1a4f5189775a8eebbfb3535046e1d614dbaf6d29289371ac88c96e92a","observation_id":"e3c5d2d6-3b27-46a8-8b05-2850d781e743","resolution":{"observed_at":"2026-08-15T22:22:58.262373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.07411","last_updated":"2025-06-15T08:13:14Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T03:48:20.487192Z","submitted_at":"2025-05-12T10:07:23Z","title":"ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":2,"verified_fuzzy":25},"total_outbound_references":41},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2505.07411."}