{"as_of":"2026-08-09T14:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4de6cb444856574e8793105e3b4baf7dd049dcc0f4aa38b7f75e3280f8a49977","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:00:46.888693Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2506.20152/citation-record","integrity":"/paper/2506.20152/integrity","json":"/paper/2506.20152/citation-record.json","paper":"/paper/2506.20152"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-06T23:00:46.646985Z","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.646985Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:3587af534ffd70f6a08180e879bf39edf9c714e813eb4a0f0a20bf00f06b884c","observation_id":"8c80bc32-8ed6-42e7-b65c-6117236b9e4a","resolution":{"observed_at":"2026-08-06T23:00:46.646985Z","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":"2026-08-06T23:00:46.653363Z","title":"Learning both weights and connections for efficient neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.653363Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:6e06a6a431122e0e7f6302925276587744cb402b013fb68ee8c4820c819e095c","observation_id":"6a50b399-4a23-4ca1-8947-ecb2468ef4fe","resolution":{"observed_at":"2026-08-06T23:00:46.653363Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.03635","last_updated":"2019-03-04T15:51:11Z","snapshot_observed_at":"2026-08-05T23:54:27.386622Z","submitted_at":"2018-03-09T18:51:28Z","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.03635","snapshot_observed_at":"2026-08-06T23:00:46.658414Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.658414Z"},"links":{"cited_paper":"/paper/1803.03635","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:0ca9ccaa1a8c6b99322f270d0f2b51d2056a9875cfde4427d5891a76e5ff971d","observation_id":"e0fed8ae-afe4-4800-83d0-b1fbd64a5d3d","resolution":{"observed_at":"2026-08-06T23:00:46.658414Z","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":"2026-08-06T23:00:47.786761Z","title":"Global sparse momentum sgd for pruning very deep neural networks,","venue":null,"work_id":"c5a3c397-d5bf-4828-9d75-d3245b777e96","year":2019},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.664188Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:cc75b22e5cb80509c4ac10bc2bc09bfedea263e96880df4fed64c39721363f33","observation_id":"072a5c20-24df-4a51-bd5e-7b4d6f35667c","resolution":{"observed_at":"2026-08-06T23:00:47.792426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1808.06866","last_updated":"2018-08-21T12:22:38Z","snapshot_observed_at":"2026-07-06T06:56:39.566826Z","submitted_at":"2018-08-21T12:22:38Z","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.06866","snapshot_observed_at":"2026-08-06T23:00:46.669524Z","title":"Soft filter pruning for accelerating deep convolutional neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.669524Z"},"links":{"cited_paper":"/paper/1808.06866","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:e15a1a5c11042db776cf3cdb3fcaf48616778bced6f0fc09ab7cc6c2f27d9cec","observation_id":"99a7f68d-6783-4555-b17d-4b90287a939b","resolution":{"observed_at":"2026-08-06T23:00:46.669524Z","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":"2026-08-06T23:00:47.770010Z","title":"Learning filter pruning criteria for deep convolutional neural networks acceleration,","venue":null,"work_id":"4fe175f1-9130-430e-8565-72f38741006e","year":2020},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.674933Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:57ad3c3019ed63cf0f157ea248b09ad387fb3999b47670ccd8e7dfebef2c7e68","observation_id":"d513e7c7-73f8-4f96-acaf-ae5542a217d1","resolution":{"observed_at":"2026-08-06T23:00:47.775656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.753272Z","title":"Filter pruning via geometric me- dian for deep convolutional neural networks acceleration,","venue":null,"work_id":"6e88a8f1-3158-4a7f-8294-ddc39c4a911f","year":2019},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.680219Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:32ed3c711a087f33b8d99c277e98af7461b77bc1b69d4d10b30c171f7664dc4d","observation_id":"236cc7b9-84eb-4f3a-afc0-88a618ab92b6","resolution":{"observed_at":"2026-08-06T23:00:47.758686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.735855Z","title":"Filter pruning by switching to neighboring cnns with good attributes,","venue":null,"work_id":"ae1b4fee-c4b6-4e6c-aecf-fc71fc0c802f","year":2022},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.684742Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:e9cf3d8f6c8aea0e52082b66ae9444bc2c7241037a9898c09bacf8e5aee24f26","observation_id":"454298ce-3ab2-47a2-9dd2-8951b3905009","resolution":{"observed_at":"2026-08-06T23:00:47.741283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.720114Z","title":"Post training 4-bit quantization of con- volutional networks for rapid-deployment,","venue":null,"work_id":"a5ee939a-a7f8-4c24-bc9b-96e7263d8b79","year":2019},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.694252Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:ccd48ae2fc385a2a8bc6ced272961d636e92c71785e025d2e88b7f5ebf857644","observation_id":"94f13891-e80d-4e60-b2e4-1d20416f90d5","resolution":{"observed_at":"2026-08-06T23:00:47.725269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.705263Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference,","venue":null,"work_id":"aaa317b4-352c-45d9-a7a0-c34f55f2ad35","year":2018},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.698905Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:02730661c832f0976538fadbbd8069c37f9f53b28db53fe40618806aa4c86731","observation_id":"7e9ff812-6dea-4aa3-bfd3-ffedc5e3945c","resolution":{"observed_at":"2026-08-06T23:00:47.710094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.05668","last_updated":"2018-02-15T17:18:49Z","snapshot_observed_at":"2026-07-06T06:23:42.900306Z","submitted_at":"2018-02-15T17:18:49Z","title":"Model compression via distillation and quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.05668","snapshot_observed_at":"2026-08-06T23:00:46.703614Z","title":"Model compression via distillation and quantization,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.703614Z"},"links":{"cited_paper":"/paper/1802.05668","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:f318185b164efeb935399c2d2f123b33949c2338e37e6be0860eefebd4da21bd","observation_id":"d4285451-bf15-42c1-917d-d55264cf5b55","resolution":{"observed_at":"2026-08-06T23:00:46.703614Z","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":"2026-08-06T23:00:47.690348Z","title":"Refine myself by teaching myself: Feature refinement via self-knowledge distillation,","venue":null,"work_id":"a3d4dc90-9901-4c5e-842e-3e07cd1a0cd7","year":2021},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.708607Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:d3a5658c80537807f5c46d1d22e383bd4e31759074b017c5e3ef9315c1c7a738","observation_id":"352f36a6-1183-404a-b9a7-b36681d1fa87","resolution":{"observed_at":"2026-08-06T23:00:47.694962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.672300Z","title":"Learning low-rank deep neural networks via singular vector orthogonality regularization and singular value sparsification,","venue":null,"work_id":"f7f979cb-36d7-4fe0-9cff-d946a000ec6c","year":2020},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.713473Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:b2e6596ef698e2c0f350e65e70ad62e18220e326233684ccf57d46f3b1a5bbce","observation_id":"28271015-a834-45ab-984b-5ac1c2409d7e","resolution":{"observed_at":"2026-08-06T23:00:47.678831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.653037Z","title":"Towards efficient tensor decomposition- based dnn model compression with optimization framework,","venue":null,"work_id":"53495247-a829-451b-8437-d433b15cc4fa","year":2021},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.718528Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:9c9b4e84155d13e2a04ace762149b932bc2d1c62c6ffa7dbae8481087ede0d05","observation_id":"c65debca-951e-47d0-9c27-34ce7163c3c5","resolution":{"observed_at":"2026-08-06T23:00:47.659648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03916","last_updated":"2023-02-07T07:33:25Z","snapshot_observed_at":"2026-08-09T13:18:52.627719Z","submitted_at":"2022-04-08T08:29:52Z","title":"A Survey of Supernet Optimization and its Applications: Spatial and Temporal Optimization for Neural Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03916","snapshot_observed_at":"2026-08-06T23:00:46.722928Z","title":"Supernet in neural architecture search: A taxonomic survey,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.722928Z"},"links":{"cited_paper":"/paper/2204.03916","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:149994b9e0ab15b5518600282331a85586a4aea354627320c94dfad164f4308a","observation_id":"547132fc-21f3-402a-ba52-ae67b0cb261f","resolution":{"observed_at":"2026-08-06T23:00:46.722928Z","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":"2026-08-06T23:00:47.637226Z","title":"Model compression and hardware acceleration for neural networks: A comprehensive survey,","venue":null,"work_id":"425928cc-701e-46c9-932d-9c98c974b75d","year":2020},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.732544Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:76f01cb915d883ec8dab6e41de21e4f8596dd60f1da966ddf6cb7cd67f21a0c6","observation_id":"ec9c9e1c-a843-43f9-b405-6fb2aa370c77","resolution":{"observed_at":"2026-08-06T23:00:47.642543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.619920Z","title":"A survey on efficient convolutional neural networks and hardware acceleration,","venue":null,"work_id":"f37b64e4-5b9c-4549-b8e2-af86244daf0b","year":2022},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.737564Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:4317887023e11115e105cc7b53dba71f7bc576fa403b5cb7dc96680f3ad983b3","observation_id":"63dc786a-77f8-464d-8f71-cb27e39e8755","resolution":{"observed_at":"2026-08-06T23:00:47.625363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.08710","last_updated":"2017-03-10T17:57:56Z","snapshot_observed_at":"2026-08-09T05:37:48.140401Z","submitted_at":"2016-08-31T02:29:59Z","title":"Pruning Filters for Efficient ConvNets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.08710","snapshot_observed_at":"2026-08-06T23:00:46.743246Z","title":"Pruning filters for efficient convnets,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.743246Z"},"links":{"cited_paper":"/paper/1608.08710","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:88b97b2cdd98803f9bd72d97023864addabca32a05ba3adb79806d60c29181c4","observation_id":"c91111d1-1a7d-4665-aa9f-bf439e651d5b","resolution":{"observed_at":"2026-08-06T23:00:46.743246Z","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":"2026-08-06T23:00:47.601642Z","title":"Thinet: A filter level pruning method for deep neu- ral network compression,","venue":null,"work_id":"06efaa29-ba89-4b50-9e80-cd257dde4f94","year":2017},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.748106Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:93eaf7e4f72c5cfb666310f1d822710fe37c1755d46a4d9295a6d55f2536f3f4","observation_id":"2bbb818d-f76c-444c-aab8-f3380b8b754a","resolution":{"observed_at":"2026-08-06T23:00:47.606110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.586844Z","title":"Nisp: Pruning networks using neuron importance score prop- agation,","venue":null,"work_id":"1bf1d132-9eb8-4ea7-a2d9-65b5f2f132d1","year":2018},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.752441Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:12bf03daa4eec43a6c88fef080bce4f3a52afdbe685f8d2d27dbe42f692325f6","observation_id":"4635f5ed-fc6a-4ac6-a398-5184fb1306e8","resolution":{"observed_at":"2026-08-06T23:00:47.592028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.572060Z","title":"Automated filter pruning based on high- dimensional bayesian optimization,","venue":null,"work_id":"24828fe0-801e-4e28-9767-6569492dc617","year":2022},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.757401Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:1b4b88079b491f31473a8dac824ae081a950ab05413e1bae14c24536adb63f5a","observation_id":"028c291b-b0db-4e73-82a6-a620720d21e8","resolution":{"observed_at":"2026-08-06T23:00:47.576740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.556286Z","title":"Adaptive cnn filter pruning using global importance metric,","venue":null,"work_id":"7b9554bb-18af-4dcd-a0ea-05f2faa54c1c","year":2022},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.761676Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:e563da548cb61aa80f28c862cd7d7c090a3edd9ac386911a852638564df3d3aa","observation_id":"75393631-0ad4-4b44-8c2b-2641a4804984","resolution":{"observed_at":"2026-08-06T23:00:47.561627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.538218Z","title":"Filter pruning without damaging networks capacity,","venue":null,"work_id":"a53da599-3494-4a5e-bf8b-f8256340c852","year":2020},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.766685Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:318afe1d7556a61493dcd260107f28af5a4bd1d8acd9f6df95abe151e93dc846","observation_id":"f9f8a5ef-bcc9-4ae0-83bb-09b5a4b525ac","resolution":{"observed_at":"2026-08-06T23:00:47.544325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.522150Z","title":"Magnitude and similarity based variable rate fil- ter pruning for efficient convolution neural networks,","venue":null,"work_id":"86901cc2-2a34-4028-a42e-669a0e6189a2","year":2023},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.771094Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:63842311f9cded2c3e17b54a5320d617b5bfe2050d7c5f1033ebb7d67ae06176","observation_id":"7d473cba-2451-433e-9167-f929665621c2","resolution":{"observed_at":"2026-08-06T23:00:47.528254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.12900","last_updated":"2023-03-23T12:55:02Z","snapshot_observed_at":"2026-08-09T03:18:22.656883Z","submitted_at":"2023-01-30T14:02:33Z","title":"DepGraph: Towards Any Structural Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.12900","snapshot_observed_at":"2026-08-06T23:00:46.775620Z","title":"Depgraph: Towards any structural pruning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.775620Z"},"links":{"cited_paper":"/paper/2301.12900","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:b64d0bfdcdbbf823d091be157b3bc7b05df90320065107ff341ccd517dbb0464","observation_id":"d16864f3-016b-495e-8a85-3ff18266cf7d","resolution":{"observed_at":"2026-08-06T23:00:46.775620Z","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":"2026-08-06T23:00:47.506421Z","title":"On the channel pruning using graph convolution network for convolutional neural network acceleration,","venue":null,"work_id":"6a95c83c-86a1-4e90-8910-c6ae20249082","year":2022},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.780312Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:6c5da74fcbcaebff376a8d0f10760f8f33301eb155fabcdc11259045391419b0","observation_id":"0cc0c05f-149b-488e-bb9c-b950210464e3","resolution":{"observed_at":"2026-08-06T23:00:47.512097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.489682Z","title":"Optimiz- ing deep neural networks on intelligent edge accelerators via flexible-rate filter pruning,","venue":null,"work_id":"b9af31c1-fd72-434f-aa28-8e1ad04bda79","year":2022},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.784930Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:2f810e4d539e48e42a3ec776fd92288b9e7742d1f43c89541b063093456d1806","observation_id":"69ca1d06-1013-42cf-93a5-733766a270a9","resolution":{"observed_at":"2026-08-06T23:00:47.495551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.473165Z","title":"Falf convnets: Fatuous auxiliary loss based filter-pruning for efficient deep cnns,","venue":null,"work_id":"96f7c374-44ba-49c5-a69b-12e9cf7dc404","year":2020},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.789486Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:007626e638068b66003859da730a4b202849ab53f239a51e6b4283eb05a62cf5","observation_id":"be3ac4ec-754f-4aea-be84-246aff6ec170","resolution":{"observed_at":"2026-08-06T23:00:47.478928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.456302Z","title":"Performance-aware approxima- tion of global channel pruning for multitask cnns,","venue":null,"work_id":"d1aee9e7-567d-4bb1-aede-74657380f14c","year":2023},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.793822Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:93959a4a2d006e3e1c5ab9545029a83265a003fef0f46de6d7cff80f9685bc69","observation_id":"aec16b09-b4dc-468a-8877-01247d73d539","resolution":{"observed_at":"2026-08-06T23:00:47.460822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.441504Z","title":"Pruning neural networks at initialization: Why are we missing the mark?","venue":null,"work_id":"cf4b74bc-1f2c-4fc4-b440-ce91d0a32e78","year":2021},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.798538Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:c7a152a1c45872c7eba5c92f2654b52905af8460605967606cbdeef00492b570","observation_id":"56baddfb-791f-4d06-ad1d-26460b0bd29b","resolution":{"observed_at":"2026-08-06T23:00:47.446368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.426239Z","title":"Linear mode connectivity and the lottery ticket hypothesis,","venue":null,"work_id":"4a72f0c4-1b87-440b-83f9-87cc6f383d6c","year":2020},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.803618Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:a2231bce233c7613ff770fcbce0cdc2916cf7066b393000f4448b8484af6c80b","observation_id":"c5dcda04-8317-4750-b5b5-77b79560bef3","resolution":{"observed_at":"2026-08-06T23:00:47.430958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.411406Z","title":"Prune- train: fast neural network training by dynamic sparse model reconfiguration,","venue":null,"work_id":"de809f89-827a-4299-b8a8-3d57870e08ca","year":2019},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.808245Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:28b35c3fc7f0aafe636cbb73b6b259b5cbd0a6aa3f615ab2be688f70b0f4c048","observation_id":"778795c9-89b8-4ced-b9bf-b92c86fa566c","resolution":{"observed_at":"2026-08-06T23:00:47.416290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2023.10474","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:00:47.155539Z","title":"Oyedotun, D","venue":null,"work_id":"4b697dc9-cdd3-4c44-8776-d604cff9c9ee","year":2023},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.812795Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:945f27f32a3485103bb8b5c5dee653003e71a70427db6aa0c3e5197ccd649bd4","observation_id":"550ffccc-47dc-47b3-b571-01075f003c0c","resolution":{"observed_at":"2026-08-06T23:00:47.164426Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.395577Z","title":"Only train once: A one-shot neural network training and pruning framework,","venue":null,"work_id":"bd28ea59-4d96-4856-9d61-f2dd54ac5cc3","year":2021},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.817614Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:350134a6cf85cf99f8c5ac674365f235d1f474d6b91180f6662fd884fff4fde7","observation_id":"20d3b737-d88e-4e62-8926-93fe6ec85dfb","resolution":{"observed_at":"2026-08-06T23:00:47.401028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06862","last_updated":"2023-06-23T05:41:26Z","snapshot_observed_at":"2026-07-06T15:02:25.281739Z","submitted_at":"2023-03-13T05:13:47Z","title":"OTOV2: Automatic, Generic, User-Friendly","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06862","snapshot_observed_at":"2026-08-06T23:00:46.822471Z","title":"Otov2: Automatic, generic, user-friendly,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.822471Z"},"links":{"cited_paper":"/paper/2303.06862","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:f89a0ad94ecf43388f9ddca4cbe5c7e42ae96ddad54a152f855bf0d6d92d2d5c","observation_id":"542ce889-bc8d-4e4d-8b42-2cbbf8fc493f","resolution":{"observed_at":"2026-08-06T23:00:46.822471Z","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":"2026-08-06T23:00:47.379013Z","title":"When to prune? a policy towards early structural pruning,","venue":null,"work_id":"a7536727-30bb-4596-9cff-8fdcf1142fd5","year":2022},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.828028Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:dfca78fa99eca5cdf7bb98e548d17472d02303776dcb7297e70d0da02f3d0ec9","observation_id":"6396bf7b-8f5b-488e-93bd-147466d342bb","resolution":{"observed_at":"2026-08-06T23:00:47.384326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.363260Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":"80f00154-eb60-47aa-bb19-6d118dabe697","year":2009},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.832972Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:ac553e86ac71c5d315c98083a57e67656cba78649bd66bc4e81aec6d66312e4e","observation_id":"51980705-0830-4838-8260-bf68e1d58217","resolution":{"observed_at":"2026-08-06T23:00:47.368043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.346899Z","title":"Imagenet large scale visual recog- nition challenge,","venue":null,"work_id":"b6d57e5e-4047-4ec6-a5ec-df16793ba13b","year":2015},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.837780Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:7a2d5405cd6c28e6658c951460a66ee647c79424deedc67800d4ce0f02649f21","observation_id":"2d6ab385-947a-4a8b-b990-41d015804645","resolution":{"observed_at":"2026-08-06T23:00:47.352270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.331202Z","title":"Deep residual learning for image recog- nition,","venue":null,"work_id":"18a7201e-fd54-44d9-8eaf-179d8115544d","year":2016},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.843699Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:5552bc33c48ca3084c7e3b17cb6870a6ad6a281f49b8bbedf80ed4f9dbc2a24a","observation_id":"292c5da1-332d-46bf-811a-0e4292538487","resolution":{"observed_at":"2026-08-06T23:00:47.336088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-07-06T03:53:32.549552Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-06T23:00:46.849802Z","title":"Very deep convolutional networks for large- scale image recognition,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.849802Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:f93c7f20fe3a338d483e9371401fd1c950347d5d3d2e1fbc2ab2a164603b5fe5","observation_id":"db96e12c-b3c2-43ad-8a4f-f00d527bdf55","resolution":{"observed_at":"2026-08-06T23:00:46.849802Z","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":"2026-08-06T23:00:47.314918Z","title":"Identity mappings in deep residual net- works,","venue":null,"work_id":"5f9d0459-9c8e-4715-9182-388990412c77","year":2016},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.854638Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:f266bdc6b061c3a927fef751ecbdcd391b094ab5b4493a1cef4373e0392203e2","observation_id":"cc461bc9-7fe8-4749-bc13-1354b763dab0","resolution":{"observed_at":"2026-08-06T23:00:47.320278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07146","last_updated":"2017-06-14T06:06:48Z","snapshot_observed_at":"2026-08-08T14:57:17.868613Z","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":"2026-08-06T23:00:46.859472Z","title":"Wide residual networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.859472Z"},"links":{"cited_paper":"/paper/1605.07146","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:76b6de1e1189e7762c1eef4c4309664790e4610e0c4aaefa6c524b9d59577829","observation_id":"ebbd47a5-c5a4-428a-b932-3037ddef9b90","resolution":{"observed_at":"2026-08-06T23:00:46.859472Z","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":"2026-08-06T23:00:47.298134Z","title":"Automatic differentiation in pytorch,","venue":null,"work_id":"442e26ab-97d6-4698-961b-b4339298764f","year":2017},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.864613Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:3465a7adf18da2fd06bb09824b873d005e143b0cb8314cc61953b40c35291eb6","observation_id":"8b6f6ded-d55c-40ce-ba88-8250d8ca40ff","resolution":{"observed_at":"2026-08-06T23:00:47.303132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.280156Z","title":"Hrank: Filter pruning using high-rank feature map,","venue":null,"work_id":"d61e67ce-be11-4a83-8a59-a35ee05d0c8a","year":2020},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.869452Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:0006728ae70613671704110bb3e2ba69846221f44aaae93acce02b69c20101e8","observation_id":"a6014b34-8911-43d3-ad96-0c910fda7cec","resolution":{"observed_at":"2026-08-06T23:00:47.285870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.261510Z","title":"Network pruning via performance maximization,","venue":null,"work_id":"09222055-5958-4d30-a935-ddd76ba6908c","year":2021},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.874426Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:a2e49a373c76fce81e1b756e923ecffa852d93df0e7568cdfd2cadbdd7973e14","observation_id":"5e5ed434-2b59-4c42-82bf-75bb343cd340","resolution":{"observed_at":"2026-08-06T23:00:47.267660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.05270","last_updated":"2019-03-05T05:58:11Z","snapshot_observed_at":"2026-07-06T07:07:34.689643Z","submitted_at":"2018-10-11T22:15:28Z","title":"Rethinking the Value of Network Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.05270","snapshot_observed_at":"2026-08-06T23:00:46.878982Z","title":"Rethinking the value of network pruning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.878982Z"},"links":{"cited_paper":"/paper/1810.05270","citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:5698758deda051eb5e0b3fdf7c77d76d4b0d440038a2db6accbfa4cb0aa80c45","observation_id":"41169b26-ed1d-47eb-96d6-31b101872ed1","resolution":{"observed_at":"2026-08-06T23:00:46.878982Z","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":"2026-08-06T23:00:47.245325Z","title":"Fusion-catalyzed pruning for optimizing deep learning on intelligent edge devices,","venue":null,"work_id":"fb5840bc-3939-47ad-b341-ec9322670ca1","year":2020},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.883712Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:c58fcd7b21eb43e47e46a9fcb1040f69b74358f5047095015778e91da96d63ef","observation_id":"e96936a1-a586-427a-866f-f942426d087b","resolution":{"observed_at":"2026-08-06T23:00:47.250555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:00:47.227867Z","title":"Leveraging filter correlations for deep model compression,","venue":null,"work_id":"71cd3be9-a5ff-425c-8e8e-1ffaef2b9f77","year":2020},"citing_paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T23:00:46.888693Z"},"links":{"citing_paper":"/paper/2506.20152"},"observation_digest":"sha256:b84fecbf2af220188c8a006352981fec7a32feb39ed3048fd70be9c5244192ab","observation_id":"3d5c01b3-db4b-402b-bb5e-8a9d2bc1d6d6","resolution":{"observed_at":"2026-08-06T23:00:47.234042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.20152","last_updated":"2025-06-25T06:18:46Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T10:45:06.267936Z","submitted_at":"2025-06-25T06:18:46Z","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":35},"total_outbound_references":48},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2506.20152."}