{"as_of":"2026-08-09T10:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6fb7164e7f3bc07c5f09e6e86b67275e12fab6275603f895743e1f9be25631e6","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:45:29.376262Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"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/2506.04513/citation-record","integrity":"/paper/2506.04513/integrity","json":"/paper/2506.04513/citation-record.json","paper":"/paper/2506.04513"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:45:29.829027Z","title":"Meta-learning adaptable foundation models,","venue":null,"work_id":"dfdfa122-8293-4062-8edb-f008abd3f3e4","year":2025},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.232652Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:f71bcd7ec289e5e69074accec1a12886ee06cace66385418c4785cdd720bda98","observation_id":"c8c11ee5-cb2f-4b4b-a849-61d5912ad6cc","resolution":{"observed_at":"2026-08-07T10:45:29.832296Z","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":"2026-08-07T10:45:29.819647Z","title":"The llama 3 herd of models,","venue":null,"work_id":"a52a9468-bdaa-4f2a-bdd7-a70dd2031156","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.237204Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:a34b1a5c1ed774be4695bfca3c7baa59aaca1aaa36e0c781f208ef38cbaa40e7","observation_id":"863c5a3f-7e2c-469a-8ce8-9f69d23b8318","resolution":{"observed_at":"2026-08-07T10:45:29.823244Z","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":"2026-08-07T10:45:29.809772Z","title":"LLMCarbon: Modeling the end-to-end carbon footprint of large language models,","venue":null,"work_id":"7dd92acf-e482-4e36-b530-021e482d4144","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.240793Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:01206c2a302f962e6b21ab34f3a1f6de0c89bbae163758c4a88db60a09dbd993","observation_id":"2d4f0f6f-f685-4431-8294-ecb7dd581c18","resolution":{"observed_at":"2026-08-07T10:45:29.813557Z","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":"2026-08-07T10:45:29.800514Z","title":"A survey on deep neural net- work pruning: Taxonomy, comparison, analysis, and recommendations,","venue":null,"work_id":"8371de40-687d-4745-a543-4632832e5f14","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.244463Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:8d79927fdba348ef072cddebffb5ed42e8fba471779448b16c6dd60d1c83c1a1","observation_id":"5e6c4fdb-72b3-4081-a16b-e112178df18f","resolution":{"observed_at":"2026-08-07T10:45:29.803795Z","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":"2026-08-07T10:45:29.791117Z","title":"Structured pruning for deep convolutional neural networks: A survey,","venue":null,"work_id":"259a469a-053e-40cd-b47a-17ed2670b3c2","year":2023},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.247982Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:cf7bd26b429c5724ea9fd2d2dd591d6e9f6a4472a89c375875e38d4830f8bdae","observation_id":"05294e40-18d1-40bd-93ff-5ff0c9373c2a","resolution":{"observed_at":"2026-08-07T10:45:29.794701Z","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":"2026-08-07T10:45:29.781966Z","title":"Effective layer pruning through similarity metric perspective,","venue":null,"work_id":"78498465-3245-426b-87c3-b67ab7e5da05","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.251523Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:6048268cf5f7aaa7069671f4e5ad1869bb145fe083e17f111c16d0b9b7ea7098","observation_id":"5eff8eab-3d1b-4ea9-8bec-416063b91b3b","resolution":{"observed_at":"2026-08-07T10:45:29.785337Z","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":"2026-08-07T10:45:29.772363Z","title":"Layermerge: Neural network depth compression through layer pruning and merging,","venue":null,"work_id":"7c597bc4-ccfd-4398-bea0-09e5e88db549","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.255409Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:47a5dd66eecb39202d9ce9774269025472bc8549fbd9ed10ad9512898669bd75","observation_id":"11c69f83-3f4b-4de7-9a0f-3c3fe622a218","resolution":{"observed_at":"2026-08-07T10:45:29.775855Z","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":"2026-08-07T10:45:29.763187Z","title":"What makes a good prune? maximal unstructured pruning for maximal cosine similarity,","venue":null,"work_id":"66ce0503-693b-4bc9-b71e-ce378f945731","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.258502Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:b620ade7ab75433a6becf7bbbadd0858ad79241c03cd1e536728c349644a47f1","observation_id":"7eff0f70-3131-4964-a969-608d835e3137","resolution":{"observed_at":"2026-08-07T10:45:29.766511Z","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":"2026-08-07T10:45:29.754034Z","title":"Similarity of neural network representations revisited,","venue":null,"work_id":"fd168b63-c65c-4226-8203-dd54cb8f03f6","year":2019},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.261825Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:5456c4eeab6207a25b505f0215aac6b3474ca474f63302eb3ff43b28943e01ab","observation_id":"008c1ede-4799-4454-a108-25c9c0c695c0","resolution":{"observed_at":"2026-08-07T10:45:29.757142Z","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":"2026-08-07T10:45:29.744422Z","title":"Compact language models via pruning and knowledge distillation,","venue":null,"work_id":"4a9fc52f-7b7c-485b-b864-57547e15fd77","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.264942Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:abd22919f1b78e14d59dde5f8c585c2ce218ca40870e5513afd8377e0b13383c","observation_id":"89f949bd-fe28-41c1-947a-9ac8fdaf1ba5","resolution":{"observed_at":"2026-08-07T10:45:29.748481Z","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":"2026-08-07T10:45:29.733730Z","title":"Structural pruning via latency-saliency knapsack,","venue":null,"work_id":"4e4ed83f-8805-47ae-9693-81d905009174","year":2022},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.268748Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:de143a868161705b7bdffd2fa6599494a225052ad5e03a6a3587bede4daa4087","observation_id":"5c34e9a5-bde4-42d3-beae-3edff3363865","resolution":{"observed_at":"2026-08-07T10:45:29.738169Z","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":"2026-08-07T10:45:29.723578Z","title":"Jointly training and pruning cnns via learnable agent guidance and alignment,","venue":null,"work_id":"cf10aa9d-dca2-4dbc-b203-7cdc3edfb994","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.272313Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:5f8950fabec6a4ad6224ac572b302c84e3151fb9bdedaedc07efe0bd72889720","observation_id":"e1f47548-97ec-4e45-91e3-a7d27220f547","resolution":{"observed_at":"2026-08-07T10:45:29.727854Z","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":"2026-08-07T10:45:29.713895Z","title":"Quantifying the carbon emissions of machine learning,","venue":null,"work_id":"0aa24458-9f1a-491c-aa5d-8fd2f2a3d0fa","year":2019},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.275533Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:dd495a329390d9d1c75a3cb71096068b5b521554851b7637d5781d3bf5bc0ac2","observation_id":"0c5e4dde-bbaf-449e-9b43-fb0f9f133eeb","resolution":{"observed_at":"2026-08-07T10:45:29.717527Z","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":"2026-08-07T10:45:29.703853Z","title":"Holistically evaluating the environmental impact of creating language models,","venue":null,"work_id":"fd757be4-99ed-4afa-a5b1-7c4a849e4b33","year":2025},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.278733Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:c2a1cac901f4507b5a626f01b6a6344179e8c7e204b4327d567d3148c0b1161f","observation_id":"9e123eca-151a-4bf0-a5d4-cec1fcc05289","resolution":{"observed_at":"2026-08-07T10:45:29.707098Z","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":"2026-08-07T10:45:29.694499Z","title":"Bilevelpruning: Unified dynamic and static channel pruning for convolutional neural networks,","venue":null,"work_id":"2830a597-27db-4aab-8212-d277ed13ca07","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.281877Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:2791f53e3d95533ab9183ae44c52dc28e3c6a468a372a0516ef54cd67b216dfe","observation_id":"2e2364da-3d81-4513-a82e-c67073360c92","resolution":{"observed_at":"2026-08-07T10:45:29.697826Z","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":"2026-08-07T10:45:29.684823Z","title":"Auto-train-once: Controller network guided automatic network pruning from scratch,","venue":null,"work_id":"fcfed6a2-14da-4cb4-8f7b-564b102efa58","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.284933Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:be1d8135b5f28c18e4582f32dbbd47e4255ef3545fb39f26238660b4cb4f6d9e","observation_id":"72878c8e-1ea9-47b8-9f23-567d657acb41","resolution":{"observed_at":"2026-08-07T10:45:29.688130Z","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":"2026-08-07T10:45:29.675546Z","title":"Laco: Large language model pruning via layer collapse,","venue":null,"work_id":"8fa47fe3-54af-4c14-a590-dc868b92c957","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.288432Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:24859a297cc528ff19bcd8113c77b1fd14eadbbcfbcd9ca590e905919dd621cc","observation_id":"cf7339bd-c4cb-482e-b0b5-82f70e3f3b8e","resolution":{"observed_at":"2026-08-07T10:45:29.678783Z","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":"2026-08-07T10:45:29.665283Z","title":"The unreasonable ineffectiveness of the deeper layers,","venue":null,"work_id":"89dfcedb-5e82-4c3a-a112-7508ce30e43e","year":2025},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.291504Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:99aa6b79aa46a14ac53c94cd273345a071c48bf815b13d5a007db89f3ca92534","observation_id":"8d9b8c2f-d88e-416a-825c-01402c55a0fc","resolution":{"observed_at":"2026-08-07T10:45:29.669199Z","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":"2026-08-07T10:45:29.654524Z","title":"Shortened LLaMA: A simple depth pruning for large language models,","venue":null,"work_id":"93c60881-23b7-4c2e-a8c5-1a4027b315e1","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.294569Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:14cad114307b16356f6efe76c21f2f052a68ad20ebf3ac6f15270895eb9efcb1","observation_id":"0057769d-de8a-4c57-9ef6-0b49d12273fd","resolution":{"observed_at":"2026-08-07T10:45:29.658140Z","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":"2026-08-07T10:45:29.643659Z","title":"Revisiting random channel pruning for neural network compression,","venue":null,"work_id":"e8fec036-1206-405a-bb2a-058ca0a3f548","year":2022},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.297571Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:c1fbd4573747dfe57e8180f1197944aa5f9d40555d83c8560cbb96ca674e78a9","observation_id":"fa2fa2ab-e9e4-4006-9139-4e0c2d1c593b","resolution":{"observed_at":"2026-08-07T10:45:29.647343Z","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":"2026-08-07T10:45:29.633857Z","title":"Measuring statistical dependence with hilbert-schmidt norms,","venue":null,"work_id":"4a2e42df-ecfa-42aa-9dbe-c4f2063f3bda","year":2005},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.302200Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:91117ddfb61250a193fa44be8f04e1fae7470a812bfb9b4429a62d18095ad843","observation_id":"d836676d-5c7d-4382-ac04-418365aad719","resolution":{"observed_at":"2026-08-07T10:45:29.637428Z","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":"2026-08-07T10:45:29.623216Z","title":"When layers play the lottery, all tickets win at initialization,","venue":null,"work_id":"a12c9b4f-31d1-4282-a13c-96b7c4d74c73","year":2023},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.305707Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:e7af49e25531772bc612d7679a4060cd97483e6ab814f5806d9bb7f51007426e","observation_id":"5bd9397d-96ba-47b8-ae53-9b6047a19d23","resolution":{"observed_at":"2026-08-07T10:45:29.626683Z","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":"2026-08-07T10:45:29.613451Z","title":"Neural network pruning with residual-connections and limited-data,","venue":null,"work_id":"9b735c04-83ee-4484-b56b-949de1ce49c6","year":2020},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.308807Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:719c55d989de88a47ef37c309f1f836708222a8a9cee41dc0427c26c37b67993","observation_id":"9f66c185-db54-4dfb-9775-e5d7afebbcc1","resolution":{"observed_at":"2026-08-07T10:45:29.616993Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:45:29.311855Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.311855Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:a343e30904e77737d188a2f75c8814aa06ce39715037c9542804eece1701547b","observation_id":"1ba053f7-1bf2-43e1-9e96-3e3ce7775a9f","resolution":{"observed_at":"2026-08-07T10:45:29.311855Z","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":"2026-08-07T10:45:29.597178Z","title":"A simple and effective pruning approach for large language models,","venue":null,"work_id":"a3545122-f622-4963-8b6e-f615d3f423df","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.315225Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:32991f15a821c449aeafb059e077b22f2468b457ce7e9dd69a27826e14084c34","observation_id":"2f17f4f5-3e72-4b8f-9784-1406f7a98a1b","resolution":{"observed_at":"2026-08-07T10:45:29.600422Z","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":"2026-08-07T10:45:29.587785Z","title":"Shallowing deep networks: Layer-wise pruning based on feature representations,","venue":null,"work_id":"894a8dd1-7c22-4749-a864-81c6ba99060a","year":2019},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.318494Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:c7d35e9aa9ecf589a60fc1aeb2ae7ebf331ddedb184be6f28da0a490821a403c","observation_id":"3e22393d-3443-4d80-b804-c734d6ded89b","resolution":{"observed_at":"2026-08-07T10:45:29.591512Z","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":"2026-08-07T10:45:29.578846Z","title":"Evolutionary shallowing deep neural networks at block levels,","venue":null,"work_id":"f588e25a-14fe-471b-a031-8dbdd1477d80","year":2022},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.321959Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:291878acf9e35a8bfcf5b6f31166323b22da35ff70cdc218668c99a0619ecd6c","observation_id":"c342afe3-db8f-41d1-9d0f-2ec18340e894","resolution":{"observed_at":"2026-08-07T10:45:29.582095Z","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":"2026-08-07T10:45:29.569636Z","title":"DECORE: deep compression with reinforcement learning,","venue":null,"work_id":"d73a6047-d701-42b5-ac21-89553f351186","year":2022},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.325210Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:593b0dc0f01a50085e6e09ed3e4720934fc86e006f0035e49c9e9d679c17c030","observation_id":"5273fe54-af5f-493a-b9a8-7508b4ce1414","resolution":{"observed_at":"2026-08-07T10:45:29.572870Z","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":"2026-08-07T10:45:29.559544Z","title":"SOKS: automatic searching of the optimal kernel shapes for stripe-wise network pruning,","venue":null,"work_id":"9fbdb0e7-9ffb-437f-a84a-762e5ad08c51","year":2023},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.328717Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:4aed671c4403cf8a100c4f2e5b07af2c2290fc0f8130cc054ad01742aaa9ee75","observation_id":"ce55b556-4e44-4a62-91ef-5e7f79a102dd","resolution":{"observed_at":"2026-08-07T10:45:29.562929Z","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":"2026-08-07T10:45:29.550304Z","title":"Revisit kernel pruning with lottery regulated grouped convolutions,","venue":null,"work_id":"ab988ca4-74da-4882-9cf5-256879b45aa1","year":2022},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.331658Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:43f2cfe5a907849493c70793e4ebe3818150b6244f9f42ffe456c3ae8ac7928a","observation_id":"f7b43201-a00c-4c31-94b7-c928cf9741b6","resolution":{"observed_at":"2026-08-07T10:45:29.553650Z","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":"2026-08-07T10:45:29.539853Z","title":"On the channel pruning using graph convolution network for convolutional neural network acceleration,","venue":null,"work_id":"3e6d71ba-e3e2-4103-81b3-b606b78882be","year":2022},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.334639Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:c85b87b000e129e22bbee09d7174ef23a6b405af560132dfe0f03eddfff0dc82","observation_id":"3141c9f6-134c-471a-a498-248847781cfe","resolution":{"observed_at":"2026-08-07T10:45:29.544256Z","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":"2026-08-07T10:45:29.529385Z","title":"Pruning neural networks via coresets and convex geometry: Towards no assumptions,","venue":null,"work_id":"a63ddc93-272b-441a-8c55-1cd9fea3d382","year":2022},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.337684Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:09270adf613e5d5800b0c62150e464f27cfc82d8561eccb96eb513a38896deb7","observation_id":"d303e2c8-6bf1-45f5-b960-95a7c0c6b37f","resolution":{"observed_at":"2026-08-07T10:45:29.533621Z","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":"2026-08-07T10:45:29.515468Z","title":"Topology-aware network pruning using multi-stage graph embedding and reinforcement learning,","venue":null,"work_id":"7c14e7ca-ab48-41fe-bb74-b1495cdd9cc2","year":2022},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.340631Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:e338930e079156c8affc9b854ead44155baed16f7f9d1623d464046d3dcd3818","observation_id":"475fcf2e-892d-496b-9138-7062db909e8a","resolution":{"observed_at":"2026-08-07T10:45:29.519123Z","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":"2026-08-07T10:45:29.505418Z","title":"Carrying out CNN channel pruning in a white box,","venue":null,"work_id":"aac4c4f3-26f0-45b8-ba76-96181c720dd9","year":2023},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.344346Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:bda2d04d806cf804bc63ea6dbd48bee77cbb06035e39a33a5425a7749fc18d20","observation_id":"ba81b484-5306-4b03-a2c5-8fffefe28401","resolution":{"observed_at":"2026-08-07T10:45:29.509305Z","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":"2026-08-07T10:45:29.495919Z","title":"Pruning networks with cross-layer ranking & k-reciprocal nearest filters,","venue":null,"work_id":"9df5f1bf-3f3a-4e9a-bc56-ffff10696395","year":2023},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.347470Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:2b84842adfd5bcf8bea9f96730f7ae55707bd6cee6317ac269a174fcb202292b","observation_id":"762796b8-161a-41fa-a266-5cc6b066574b","resolution":{"observed_at":"2026-08-07T10:45:29.499324Z","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":"2026-08-07T10:45:29.486484Z","title":"DAIS: automatic channel pruning via differentiable annealing indicator search,","venue":null,"work_id":"904fb036-1bdc-452f-ad32-21203b916c46","year":2023},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.350483Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:da74c30aaa6d727c6b62cd06a9914900bb2e63040ebd1fd2bfaa2f731e40b06e","observation_id":"32fc9cf2-9c02-4c93-aa75-2d4ca292cec8","resolution":{"observed_at":"2026-08-07T10:45:29.489881Z","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":"2026-08-07T10:45:29.475257Z","title":"SOSP: efficiently capturing global correlations by second- order structured pruning,","venue":null,"work_id":"2e476a65-9a98-4a5d-92f3-8e8763b47c13","year":2022},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.353997Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:89836607b56499e4ff45dcc182331ceaa6bbb79971440b1a97fdeba11ce560bf","observation_id":"aef684ab-449f-4949-b041-9c04a02b077b","resolution":{"observed_at":"2026-08-07T10:45:29.479246Z","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":"2026-08-07T10:45:29.464468Z","title":"Generalized shape metrics on neural representations,","venue":null,"work_id":"77459dbc-0f68-4f18-977d-aff1bef3543a","year":2021},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.357135Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:f1ce93c7de6db14ec39216053eaf894b52d848daa6d7f9cfffd180f33fe0a64a","observation_id":"d3050307-8ffe-4cfa-ad0e-3db00f5ba3e3","resolution":{"observed_at":"2026-08-07T10:45:29.468712Z","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":"2026-08-07T10:45:29.453676Z","title":"Representational dissimilarity metric spaces for stochastic neural networks,","venue":null,"work_id":"ecad0523-a200-4ace-a85e-71da43ecae72","year":2023},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.360029Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:0b4f17f589927076066dcc02db6958c568d95cb3725d6cc9d5084a63331a8365","observation_id":"92eec26f-95dd-4307-aec9-b397a37224ba","resolution":{"observed_at":"2026-08-07T10:45:29.457475Z","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":"2026-08-07T10:45:29.442853Z","title":"Adversarial attack robust dataset pruning,","venue":null,"work_id":"7df1e9a6-8f7c-4de9-8aa6-80d8befc7078","year":2025},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.363058Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:0ed7459bdf300b438f7e090cfce79355b34e5dd809624f0404fb5b69aa4516b3","observation_id":"f2d4915a-4de9-46bf-82bb-3ed112a07e15","resolution":{"observed_at":"2026-08-07T10:45:29.446379Z","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":"2026-08-07T10:45:29.433360Z","title":"Adaptive sharpness-aware pruning for robust sparse networks,","venue":null,"work_id":"b921a1ca-c5a2-47a2-8c19-da96e216d57e","year":2024},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.366185Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:a45ca327c1c98f01edd6a0ebb015b0fd8ac66fdfc293d85e175a8c6f8579a229","observation_id":"0b26e3dc-a0a7-4300-9a50-b9cde4b6f2fb","resolution":{"observed_at":"2026-08-07T10:45:29.436675Z","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":"2026-08-07T10:45:29.423310Z","title":"Benchmarking neural network robustness to common corruptions and perturbations,","venue":null,"work_id":"d54f830a-3ac6-4c5c-90eb-39cdabb18166","year":2019},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.370158Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:584b8a27be045b37b4312bbf6d517155fcae60bb9845d7ae0b56f3049edde3aa","observation_id":"ceee8315-4859-408e-8bc5-febe6fa0b489","resolution":{"observed_at":"2026-08-07T10:45:29.426760Z","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":"2026-08-07T10:45:29.413296Z","title":"Harder or different? a closer look at distribution shift in dataset reproduction,","venue":null,"work_id":"771df628-6592-4c8b-a5d9-88c62f241248","year":2020},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.373319Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:763b62e8e315515866373321dc7906992bb3496bca72721aa214df6a64faff31","observation_id":"996a6c11-8487-419f-a2a1-437d062648c5","resolution":{"observed_at":"2026-08-07T10:45:29.416811Z","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":"2026-08-07T10:45:29.400752Z","title":"Human activity recognition based on smartphone and wearable sensors using multiscale dcnn ensemble,","venue":null,"work_id":"0c00537a-3387-4f93-8213-caef4e19509d","year":2021},"citing_paper":{"arxiv_id":"2506.04513","last_updated":"2025-06-04T23:34:28Z","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:29.376262Z"},"links":{"citing_paper":"/paper/2506.04513"},"observation_digest":"sha256:1f1f29b672cc6e5935787b7bfa60e5b550b766d0eda3626aa32e5654ef2f64a0","observation_id":"87f4f246-eb6f-4cff-9c17-a7f29f5be030","resolution":{"observed_at":"2026-08-07T10:45:29.406141Z","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":"2506.04513","last_updated":"2025-06-04T23:34:28Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T00:49:43.913797Z","submitted_at":"2025-06-04T23:34:28Z","title":"Pruning Everything, Everywhere, All at Once"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":0,"verified_fuzzy":43},"total_outbound_references":44},"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 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2506.04513."}