{"as_of":"2026-08-13T15:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7137d788b7b70944157b102146419b69a7d90a14d05155cb908de035be2bbad2","coverage":[{"denominator":69,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":69,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T15:19:48.397805Z","state":"measured"},{"denominator":69,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":69,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2411.14345/citation-record","integrity":"/paper/2411.14345/integrity","json":"/paper/2411.14345/citation-record.json","paper":"/paper/2411.14345"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T15:19:51.739281Z","title":"DECORE: deep compression with reinforce- ment learning","venue":null,"work_id":"ce3c6207-d1cc-444a-9a39-2ecc982c6656","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.624767Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:deafa3f544bbe51466ae37543400305224f37d1bea9159ec77ce0b3aa3339449","observation_id":"16722dfa-157a-48c2-9bb5-33fd7c9f2655","resolution":{"observed_at":"2026-08-12T15:19:51.745688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.707436Z","title":null,"venue":null,"work_id":"7e14ddfd-b73d-491c-9f2c-6a75ec814606","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.636388Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:43313432c1ddfcc2dbe1145bc00f75df9d6e5a01aca7f9a6eff27029e5803716","observation_id":"a536cc2c-2738-4346-ba2c-591c84049cc6","resolution":{"observed_at":"2026-08-12T15:19:51.714608Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.680425Z","title":"Bartoldson, Ari S","venue":null,"work_id":"4d7d678f-b93f-42dd-97ec-d3b63de8a66c","year":2020},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.645410Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:7cd45eaa2203c40a716104834757791301402bbb2c0ec4ca1e55f71911d57369","observation_id":"043c473e-a6fc-44bd-9c41-f66d0e6aba3a","resolution":{"observed_at":"2026-08-12T15:19:51.690370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.640927Z","title":"Shallowing deep networks: Layer-wise pruning based on feature representa- tions","venue":null,"work_id":"b57e72a0-4c7f-4d7a-b9ae-4b5e5519dab5","year":2019},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.651473Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:1dd607643ba6648b138ecc86c455b784b6823d5ebf88c36991eceb7910bb055b","observation_id":"96578257-0bc1-4ea0-9614-56d6f25be0a5","resolution":{"observed_at":"2026-08-12T15:19:51.648032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.605990Z","title":"Dynamical channel pruning by conditional accuracy change for deep neural networks","venue":null,"work_id":"a2c3ba0e-f3ec-4dba-bae0-143672ba3de3","year":2021},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.655778Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:5e933843f85eec80ed38657da2b78123d6040def2448efec3df6b61166c5fb0d","observation_id":"ca5500ac-9806-4b8e-b5ec-619348f564df","resolution":{"observed_at":"2026-08-12T15:19:51.618238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.573780Z","title":"A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommen- dations","venue":null,"work_id":"567ccbea-e3b1-4f84-86e7-604453dc97b5","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.662004Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:ad0a825d3c1fd38cbfe0c051f46ea0b4fd15176f6fd945d0cccf8df11dc99c52","observation_id":"7de62fb0-48dc-498e-a49b-309ba11da3a6","resolution":{"observed_at":"2026-08-12T15:19:51.580304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.537063Z","title":"The efficiency mis- nomer","venue":null,"work_id":"22d4383c-5095-4c9e-89fc-f07b5b1edb77","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.674658Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:10f112ba933589f6210894baa51a5c49b8728a49fb6544c479c8a85505a33c92","observation_id":"c40ecd32-f28c-4f01-a379-629f81695d4c","resolution":{"observed_at":"2026-08-12T15:19:51.543722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.503687Z","title":"Attention is not all you need: pure attention loses rank doubly exponentially with depth","venue":null,"work_id":"257d2259-d334-4266-ad3b-9a40aa27c64e","year":2021},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.683395Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:9ce0e527a7f976b21b7ff06c1fae9b2335b5f4940155d7f4a76c57131390bdad","observation_id":"28905082-d5a4-420a-b59c-4e71358080d8","resolution":{"observed_at":"2026-08-12T15:19:51.516217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.471388Z","title":"Layer folding: Neu- ral network depth reduction using activation lin- earization","venue":null,"work_id":"d49af241-fc5c-476e-8fc7-86a30fb88622","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.690072Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:206ba60c4456f6b3e0eae2124ca46e320faa28c64b0bde54ae527c16e16af84b","observation_id":"23c8d423-d385-4f95-99da-10e857e87647","resolution":{"observed_at":"2026-08-12T15:19:51.480183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.414388Z","title":"Duong and et al","venue":null,"work_id":"68783ce4-82b9-453f-a5cb-d1bcadcb336e","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.708259Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:414f17290eba44f217824374220f739a2a34b171f0c5504ec1719899b593ad21","observation_id":"fef7097f-794d-41dc-b5c9-6d7cbb46f300","resolution":{"observed_at":"2026-08-12T15:19:51.424916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.378298Z","title":null,"venue":null,"work_id":"dbd35cc2-5f93-4d66-8a6a-8a62db0f22a2","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.716918Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:c8016c8f8ea88b79b57b943603cbd3597a8daee1bf0f147a0cae258631a66613","observation_id":"04b337db-223f-4e10-8fa0-7becf0e6da1a","resolution":{"observed_at":"2026-08-12T15:19:51.387767Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.342714Z","title":"Llmcarbon: Modeling the end-to-end carbon foot- print of large language models","venue":null,"work_id":"cb2ce6c4-39e3-43ca-a4eb-758cfcb17afa","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.730411Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:bc29a44d1fff4fd34d2952af30f319c365ae56b20629a51d46e48a40df983d3e","observation_id":"ffd3247c-6268-4e1b-8125-3a8a811d4a4c","resolution":{"observed_at":"2026-08-12T15:19:51.348886Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.309804Z","title":"Sparsegpt: Mas- sive language models can be accurately pruned in one-shot","venue":null,"work_id":"f271f00e-73c9-4248-9c53-3be78115169c","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.738367Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:6b428d2e23237d311a79e0a4b6dd8cd0884623507ef680133e1942606b25d351","observation_id":"5602010e-b283-4bf0-b4d5-abfaeac35e6c","resolution":{"observed_at":"2026-08-12T15:19:51.330044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.210022Z","title":"Depthshrinker: A new com- pression paradigm towards boosting real-hardware efficiency of compact neural networks","venue":null,"work_id":"987ee80a-fbf4-4ad2-ac3c-5ff2f539dd42","year":null},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.746367Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:b3cbb9f6ff747d47631be35b4669404f9f34541fa59350ebe4cd87ed2795f941","observation_id":"ab86bc0d-945a-4858-8eec-96df8b645a74","resolution":{"observed_at":"2026-08-12T15:19:51.225575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.166205Z","title":"Jointly training and pruning cnns via learnable agent guidance and alignment","venue":null,"work_id":"4c93e7ca-98cf-4fbd-957b-7a250a57bd5f","year":null},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.760655Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:4f4a33c45803094d76a9480bebc732ccdbb5ffde28dfeed31e9450caa921bce4","observation_id":"cd0d012f-2999-4f90-889f-665bd83f7c82","resolution":{"observed_at":"2026-08-12T15:19:51.182964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.143000Z","title":"Bilevelpruning: Unified dynamic and static channel pruning for convolutional neu- ral networks","venue":null,"work_id":"d9cb6c65-41dc-4809-83bd-38d8702b8bf1","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.778302Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:eb63daca41a0ed56b1de354ebb7fdf0ca4b08813349e7dcb9db8cb736d888504","observation_id":"02064ec8-3951-4861-be72-ce5c418a8c13","resolution":{"observed_at":"2026-08-12T15:19:51.150241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.103796Z","title":"Shortcut learning in deep neural networks","venue":null,"work_id":"91dd2b3f-55aa-4250-b0e6-ad4d23fa8b1a","year":2020},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.788669Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:6a8ed31f9d2244bb5a30726afe9fb00e345db34f073168976a93c171a51cdf9f","observation_id":"874ecc6d-f4f5-4cc9-a866-def5563a0ffa","resolution":{"observed_at":"2026-08-12T15:19:51.113853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.069818Z","title":"DAIS: automatic chan- nel pruning via differentiable annealing indicator search","venue":null,"work_id":"edefc42b-24c5-4948-8c9a-74e516d00aea","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.810404Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:bb83df1ea37f68b1741d04c6d1cf4a0799cb76c2dde9f93cbb2894c575fcb1f3","observation_id":"da38632d-6777-4c0a-a8e1-766e758a9c48","resolution":{"observed_at":"2026-08-12T15:19:51.080061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:51.022922Z","title":"Blending pruning criteria for convolutional neural networks","venue":null,"work_id":"b0a635c0-3de4-4e30-b7c4-6111575eb6bd","year":2021},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.830741Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:4bb61c46da350b76b985bddda9dd1328331ac460c274cdcbc058f27fde09eeb7","observation_id":"cb4558f3-7c73-4e57-9e42-1597aa21535e","resolution":{"observed_at":"2026-08-12T15:19:51.034235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.970731Z","title":"Structured pruning for deep convolutional neural networks: A survey","venue":null,"work_id":"65aac56b-e35f-463f-a3b0-b6868c7195ba","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.866832Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:700e51d4e56d66ea37a552f296e8b15bc1e83a3ef601b947e268e4f57cfd071f","observation_id":"a553edb6-95ae-48c4-b353-841036ad2527","resolution":{"observed_at":"2026-08-12T15:19:50.987365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.928032Z","title":"Dietterich","venue":null,"work_id":"efbffa7a-1226-4742-8d10-a6cbf00cea80","year":2019},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.875860Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:7a0c9b48cd82e83e8e04d081bb3c50894a10f7b8694ccff1cae16d5048a1fd49","observation_id":"13a46510-6c43-4eb1-b7d5-3757e6d0c3a7","resolution":{"observed_at":"2026-08-12T15:19:50.936397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.903410Z","title":"Pixmix: Dreamlike pic- tures comprehensively improve safety measures","venue":null,"work_id":"034706cc-99a0-48c4-826f-14430a6be8cf","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.888436Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:23c67e529f3f5a78b1c3c2c1256486880d806306261026c058d03958b8e4bfe6","observation_id":"98f9008a-ae75-4239-9fcb-bb7daae83279","resolution":{"observed_at":"2026-08-12T15:19:50.909270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.868731Z","title":"Hermann and et al","venue":null,"work_id":"b4574e31-99ac-4e7b-8036-228cc64afe14","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.902417Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:593a712bd64c90884c52ba70b8a62df789fd8e928f5a7ef4e7d754a2d180d7d7","observation_id":"bd5635b1-5b93-496a-a8b7-11380de47191","resolution":{"observed_at":"2026-08-12T15:19:50.877810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.837927Z","title":"Deep networks with stochas- tic depth","venue":null,"work_id":"623f2bfc-5fb4-4878-81fa-b73045d1f84a","year":2016},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.967946Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:961b4cec86d6d72cabc3ddf973b5422d83e6ac3d06f40963e53a7a58a298c934","observation_id":"cabbe051-a3a6-4ec2-ba6b-e32d7893ea58","resolution":{"observed_at":"2026-08-12T15:19:50.849850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.801226Z","title":"Rethinking the prun- ing criteria for convolutional neural network","venue":null,"work_id":"21aa83fe-4677-4088-ba84-72c9a5961756","year":2021},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.988511Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:f5cede03652b55f316fc832d8bb2ce5dfde82e8d7432318e5c660c1bb80a93c7","observation_id":"2ae870da-1d5e-4ca8-bd4c-1e9e493ddfff","resolution":{"observed_at":"2026-08-12T15:19:50.807722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.752314Z","title":"On the channel pruning using graph convolution network for convolutional neural network acceleration","venue":null,"work_id":"2023304b-1e7e-4634-8300-68a108cc21e5","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:47.997133Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:ea71f35466e2835d462d02c768fa83e359c4b0322d7706a6abe516fc20442ee1","observation_id":"d693a871-902f-468d-805a-f5c3e9660dea","resolution":{"observed_at":"2026-08-12T15:19:50.771503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.695741Z","title":"Discriminative layer prun- ing for convolutional neural networks","venue":null,"work_id":"d86da891-3b3a-463e-ab01-f56352ac1b89","year":null},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.004428Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:4740a418032cdc20b0ac672c8b3f0b613db535d271b02e674b89863a0c95717d","observation_id":"75a6cf32-adb6-44e6-ace3-9fad9298c4c6","resolution":{"observed_at":"2026-08-12T15:19:50.721327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.613048Z","title":"When layers play the lottery, all tickets win at initialization","venue":null,"work_id":"9fa589c4-a94e-4a79-b532-0a20eead6e2c","year":null},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.010433Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:b45b2d66e5c288c68c10c0d929b77039e2574f1cb948279471eaa601bacaab3d","observation_id":"dc63e71d-6069-4d4d-84ee-0c88e3da45c5","resolution":{"observed_at":"2026-08-12T15:19:50.645891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.530624Z","title":"On the effect of pruning on adversarial robustness","venue":null,"work_id":"a1518ef5-af33-4124-a574-9c81c5429d7d","year":2021},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.026393Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:87a5d76ebb86adf701287557aa07f19911ba7e0ec9b5fb134b4f1d5627b15147","observation_id":"e19e9314-d9ae-4413-87bc-2355ba22b8b9","resolution":{"observed_at":"2026-08-12T15:19:50.553598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.487522Z","title":"Shortened llama: A simple depth pruning for large language models","venue":null,"work_id":"33847e1c-3303-4887-b1b1-cefc2587967a","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.030592Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:dcad048790ce530f1514c957be80ab4ad71134d002c45dbe356e41219e83a0f4","observation_id":"32f7046e-1abf-475f-ae26-0d215649287e","resolution":{"observed_at":"2026-08-12T15:19:50.495716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.440598Z","title":"Last layer re-training is suf- ficient for robustness to spurious correlations","venue":null,"work_id":"98fe29eb-f69d-44ec-ab60-e20bcfa879b3","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.056359Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:e6f39e2130fee14fd9f7c3b9b69b14eb470cdd91f951d9709d907378cb706f3b","observation_id":"f339beb7-531a-4a78-8c02-f447b2f74d12","resolution":{"observed_at":"2026-08-12T15:19:50.450193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.382388Z","title":"Ma- honey, Joseph Hassoun, Kurt Keutzer, and Amir Gholami","venue":null,"work_id":"996af24a-27ab-4029-8d67-09a21f3c4879","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.072677Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:29df83a9834c2679187292dac73ff57236d0c7d43a5b237d25e6678507558af8","observation_id":"135c5a6e-6931-4f03-90f0-b4182b2c27f7","resolution":{"observed_at":"2026-08-12T15:19:50.400471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.329638Z","title":"Quantifying the carbon emissions of machine learning","venue":null,"work_id":"f21f7d3d-d75b-4ca0-a0b7-b7861bb21b0b","year":null},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.101745Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:68026a2c35bc0332f880b80b153912208fa06f51bef3a66ae482747af6fe2dca","observation_id":"1bfc175f-8ef2-4fb0-ada2-5406dfa24193","resolution":{"observed_at":"2026-08-12T15:19:50.344273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.289272Z","title":"Can pruning improve certi- fied robustness of neural networks? TMLR, 2023","venue":null,"work_id":"ec2367f0-a22f-46c1-aad3-6a3d2bcb2391","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.108749Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:26b1557b2d9aad542858f4bba9d636dc3351fb1f6762aed55f0f235daabbe736","observation_id":"7302cb59-101b-48d6-bcd8-6f35f1661aa3","resolution":{"observed_at":"2026-08-12T15:19:50.298358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.174040Z","title":"Pruning networks with cross-layer ranking & k-reciprocal nearest filters","venue":null,"work_id":"0871a57c-c5a1-4a9f-895e-883cd0011858","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.113810Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:2a6eefecc6cf789d88d98b232ddec95c3c53d5b3a72825337c38efa70cad8371","observation_id":"02cc3fda-af25-4296-919d-f84f6035b7c4","resolution":{"observed_at":"2026-08-12T15:19:50.192674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.099245Z","title":"Hrank: Filter pruning using high-rank feature map","venue":null,"work_id":"e6a77b1c-85bb-4329-b5c8-b52ffa17e076","year":2020},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.119719Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:ac859ba118dc67be8a91313d0e69c83921aa3a90c1ebe640f3e8681007b56bbb","observation_id":"959e77d2-19ac-4daa-9ea2-196096e36575","resolution":{"observed_at":"2026-08-12T15:19:50.117108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:50.003656Z","title":"SOKS: automatic searching of the optimal kernel shapes for stripe-wise network pruning","venue":null,"work_id":"c2696830-cf6f-488a-b046-a8b4e8de02aa","year":null},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.127016Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:fb4a6e7fe5f55ba8e5fd8368cb9e71532f754116661f7f51b396fcf6f25b430c","observation_id":"d65036cd-ad46-4278-ae4e-728a9f97de8f","resolution":{"observed_at":"2026-08-12T15:19:50.025892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.915246Z","title":"UPDP: A unified progressive depth pruner for CNN and vision transformer","venue":null,"work_id":"2d9d151b-435f-4766-b125-a916c6772bff","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.133480Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:c3e3b989396d294f1a14384a53da67bfb3b52a6270d4d5c6e5979dfabf0df16e","observation_id":"5967d7d2-522e-4bd2-bb5d-30e976925d71","resolution":{"observed_at":"2026-08-12T15:19:49.928408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.865106Z","title":"Harder or different? a closer look at distribution shift in dataset repro- duction","venue":null,"work_id":"db03a308-d1be-4ece-81e2-904efbbe66a6","year":2020},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.157024Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:1354f873cbd663b0d2ae523d3902ffe332b0b8b2ff56774906b9956c43225450","observation_id":"4602dba2-46ee-4103-8610-7a7f5dfc9fb9","resolution":{"observed_at":"2026-08-12T15:19:49.876867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.829954Z","title":"LLM-pruner: On the structural pruning of large language models","venue":null,"work_id":"d8b0c7bb-f65e-4eda-a6c9-e73275aee3ec","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.173549Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:7923f44dfde075bb236c1f1352cab968be3f7e2466f55f4268fc4392d25c60d1","observation_id":"b3c4bf68-26b9-4907-a0b3-4a4908a37b20","resolution":{"observed_at":"2026-08-12T15:19:49.847799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.792738Z","title":"The tunnel effect: Building data representations in deep neural net- works","venue":null,"work_id":"bf99fff8-535b-41a7-b7ef-94dacc03f6eb","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.181039Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:0f156af5b3950ff74a3d26a415b3c002a8733b7d79176c61f053ae16d45f0c97","observation_id":"b23e50e7-6d68-4787-8ec5-f06b83ea9fb7","resolution":{"observed_at":"2026-08-12T15:19:49.806235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.726818Z","title":"What makes a good prune? maximal unstructured pruning for maximal cosine similarity","venue":null,"work_id":"9a86be4d-4019-4094-bfc1-0fed9933675a","year":null},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.187529Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:986ab5ea23ad2b2c3cd2324ad7c7f0d5c916fa22dc76dfc97c8fd92d10f4d314","observation_id":"6edfa13e-f131-4982-b208-f56d8af71595","resolution":{"observed_at":"2026-08-12T15:19:49.742754Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.672232Z","title":"Investigating calibration and corruption robust- ness of post-hoc pruned perception cnns: An im- age classification benchmark study","venue":null,"work_id":"a24e6808-c942-4fa5-b0a6-d7fdebddb3f7","year":null},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.196326Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:71abde42bc66ccadb136dad7780f230a9e7b4d953216085c8b4669a99420dfda","observation_id":"c03d2f4c-f6c8-4a7d-93f9-10c0ce6aad51","resolution":{"observed_at":"2026-08-12T15:19:49.687630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.638219Z","title":"SOSP: efficiently captur- ing global correlations by second-order structured pruning","venue":null,"work_id":"9882fd9e-de29-4114-b306-672c2ed7bf43","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.204973Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:f26727f0b7f2ce13ade23bd13954219f6fd6fade09234b2f0dbec1059b00468c","observation_id":"525c9227-cd3d-404a-822c-2bb9a147d7e8","resolution":{"observed_at":"2026-08-12T15:19:49.643974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.602802Z","title":"An introduction to adversarially robust deep learning","venue":null,"work_id":"fc0b4f9a-ab7c-41bd-89f0-89bedbc13d3b","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.210223Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:3728361b6b5633f2dfd6bc13c24f57ff0a26c54b41e20c3b00a268fea94cfcbb","observation_id":"74362ce2-79db-4cda-b3f5-8f4893fe3834","resolution":{"observed_at":"2026-08-12T15:19:49.610555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.576673Z","title":null,"venue":null,"work_id":"cfe7a84b-dc76-49ac-a8dd-93740e9fb30e","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.222379Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:49ac370a85a33342c9dcfc98a4b0850429c78808f4452a8d051fbe2e7b147f79","observation_id":"07e833a5-7265-4182-93f9-ec4600b99f64","resolution":{"observed_at":"2026-08-12T15:19:49.584686Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17081","last_updated":"2024-11-04T18:39:10Z","snapshot_observed_at":"2026-08-12T23:57:14.030074Z","submitted_at":"2024-05-27T11:54:51Z","title":"Effective Layer Pruning Through Similarity Metric Perspective","version":2},"cited_work":{"arxiv_id":"2405.17081","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.17081","snapshot_observed_at":"2026-08-12T15:19:48.505741Z","title":"Effective Layer Pruning Through Similarity Metric Perspective","venue":"cs.LG","work_id":"13160c63-a89f-402d-89d5-d5bad588e43a","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.226478Z"},"links":{"cited_paper":"/paper/2405.17081","citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:90726d2517901e98a57ea70810220c60a2f9af32252a5890b50edb0669ecde80","observation_id":"36ce54fb-f7f7-4b12-a394-46ba5913b919","resolution":{"observed_at":"2026-08-12T15:19:48.528535Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.537196Z","title":"Smith, and Oren Etzioni","venue":null,"work_id":"3876eb3d-2df1-4c91-bace-ff31e15b9e7c","year":2020},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.236954Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:f41d02d93d281517e10f92e70eb46445d56298f398d31c918af126441369d78a","observation_id":"1157b4f0-bbbb-4d98-940d-2ca031405cd7","resolution":{"observed_at":"2026-08-12T15:19:49.549952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.508231Z","title":"Human activity recognition based on smartphone and wearable sensors using multiscale dcnn ensemble","venue":null,"work_id":"8f4c8a6f-ca75-46fd-a495-57cb8a3c40ec","year":2021},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.241764Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:042ef7c0dab577fd0120fd94662cbc70270bc2eab793a799094744492f415bb4","observation_id":"4a941a1e-51dc-4d23-9675-14979c41b9ad","resolution":{"observed_at":"2026-08-12T15:19:49.515319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.465189Z","title":"´Alvarez","venue":null,"work_id":"1e425aac-80ee-4f35-98c5-6b85e8382878","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.251037Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:88db7216d6f27a86c3d748d8443309638e56843d3ea9530dc1184f7789ced40e","observation_id":"6d74e088-802c-438f-aff2-adcc4065e6aa","resolution":{"observed_at":"2026-08-12T15:19:49.476889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.434683Z","title":"Energy and policy considerations for deep learning in NLP","venue":null,"work_id":"9b439e38-c760-4234-aebd-cd613c962931","year":2019},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.256220Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:95505f9295b0eea1b6a18b51eaca3a64ce26beb4dd1e57efaf68568f906ba475","observation_id":"d7bcf5f0-ade5-46fd-bd36-2d80c93cf731","resolution":{"observed_at":"2026-08-12T15:19:49.440781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.408630Z","title":"Zico Kolter","venue":null,"work_id":"4d3be1d4-5e34-4c05-b003-a8b806935348","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.261037Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:78e6439fae9bdf6e6da677a65cf269bf3d6186966c24d6d4278f49c7aa9da045","observation_id":"70fed6b3-b5f5-4a19-bb31-b59442072b13","resolution":{"observed_at":"2026-08-12T15:19:49.417197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.357702Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":"cc5618b0-6154-47e6-b9fb-2eae2cef2e33","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.272966Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:25ba08e8597e8833e70b156deff298ccb461589c632ea0757c9cf1239d003c57","observation_id":"f843c5d7-e009-46e4-b1c0-94039abc81a5","resolution":{"observed_at":"2026-08-12T15:19:49.383049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.322516Z","title":"Mobileone: An improved one millisecond mobile backbone","venue":null,"work_id":"9448597a-71d0-4a22-a544-496b515bdf2b","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.278251Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:d6c2b8cd215d3ca37ed1200e71e2fbc4553f0746a7a89d5f721d4728c178b4a4","observation_id":"8176dae5-7551-4eaa-9512-daa78e33ae73","resolution":{"observed_at":"2026-08-12T15:19:49.330869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.278394Z","title":"Wilber, and Serge J","venue":null,"work_id":"0e474200-eac0-416b-b0ac-43f265cdd802","year":2016},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.288073Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:3aaab4e12e1ba85471ad5e96feef493feb52d15e5af49e3a2d948bee26de18c2","observation_id":"e8c7bcd4-a935-46e8-8aea-be4e0b3b41ad","resolution":{"observed_at":"2026-08-12T15:19:49.289355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.216296Z","title":"Recent advances on neural network prun- ing at initialization","venue":null,"work_id":"007da684-2296-4e22-823b-28395f4671ef","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.293690Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:8402d9dfa4c5bcd3d7e0678052d7abb24011d954ae29f995a71802538c89fdbf","observation_id":"a4e0dec4-10ef-408e-8984-d167c120f99c","resolution":{"observed_at":"2026-08-12T15:19:49.231523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.177939Z","title":"Channel pruning via lookahead search guided reinforcement learn- ing","venue":null,"work_id":"ab6f0add-0972-4782-a9ec-ac8282f09292","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.300636Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:a10d70eff8a1e9261b7e6e752513692995e1513405b88bb9977315846fa0aff9","observation_id":"a5c54fef-98a2-4d43-9bf1-bcc7cf3e7c1e","resolution":{"observed_at":"2026-08-12T15:19:49.196991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.134411Z","title":"Generalized shape metrics on neural representations","venue":null,"work_id":"d16d67e9-d42a-452a-b2f4-de65a4fb5a4c","year":2021},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.312490Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:32ba1c86558e31f34ad7d33a44e998bc92a86028d1b9c5b056a961e8a6140936","observation_id":"a8e555e5-11d5-45bc-a4c2-c93b9c950b29","resolution":{"observed_at":"2026-08-12T15:19:49.145264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.098520Z","title":"Auto-train-once: Con- troller network guided automatic network pruning from scratch","venue":null,"work_id":"0f0d45ac-614f-413a-b002-84d1aae37886","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.319419Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:1a42c98d0fea80805a7c04ed62b9eef7ed31c5b5118bb91e88b1203f5f9a5477","observation_id":"0b7d8a51-1067-43cc-bd34-185f131403cc","resolution":{"observed_at":"2026-08-12T15:19:49.113094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.049020Z","title":"Sheared llama: Accelerating lan- guage model pre-training via structured pruning","venue":null,"work_id":"29020dbd-e60c-45ef-9334-d008999e3618","year":2024},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.325043Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:a3bc8eb30c77f8462c539bf8e540513f6fc8eed2f95527ecacafce7a128a74db","observation_id":"18721321-eabf-4905-8e81-caed88d75350","resolution":{"observed_at":"2026-08-12T15:19:49.067337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:49.014392Z","title":"Imagenet-OOD: Deciphering modern out-of-distribution detection algorithms","venue":null,"work_id":"99fb4eda-824a-4150-8d4b-2c373e7f885c","year":null},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.332250Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:dd97e369ba5ef164cc6e2c0097407a8361c2aaa9dfcfa66c377e1d98e22264c0","observation_id":"b067576d-ef5b-4310-bd91-ee2a1b7c3dbe","resolution":{"observed_at":"2026-08-12T15:19:49.023006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:48.973180Z","title":"Auto graph encoder-decoder for neural network pruning","venue":null,"work_id":"db98c285-d84f-4677-b575-715e4d4f9231","year":2021},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.344685Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:64a6093c1c431859688ea8f92e4445c88d9d868ec12f86fb0e00aedc0f2c8b1d","observation_id":"eeddb151-ddd2-4604-a2de-401e67facabb","resolution":{"observed_at":"2026-08-12T15:19:48.988525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:48.914543Z","title":"Topology-aware network pruning using multi- stage graph embedding and reinforcement learn- ing","venue":null,"work_id":"5b3159d1-4b79-4855-b555-ff35a146e6c3","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.351450Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:b806299d455946c22dd21851c44f2b828a99b04cb6dc651dfc79bf3a37829108","observation_id":"30268781-cf54-4343-8e45-b5f1ece07eef","resolution":{"observed_at":"2026-08-12T15:19:48.938646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:48.863341Z","title":"Are all layers created equal? JMLR, 2022","venue":null,"work_id":"29875170-f211-4f97-9ff4-b8392ebdec77","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.358004Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:28abe851dfd87f7e91252852fe39389ba50c595d04839bd77951400b36416bac","observation_id":"1418fe26-b6d9-4efe-a105-5a5264fbf1ee","resolution":{"observed_at":"2026-08-12T15:19:48.871372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:48.823470Z","title":"Layer pruning for obtaining shallower resnets","venue":null,"work_id":"4f7f7eac-7b05-44f2-899e-22440dcfcc9e","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.365332Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:3033a8c3f8e7bde9b09660be3a58261fda897931028876f10e162bb569c10768","observation_id":"65a9045f-a5c1-412b-8121-f2ff475352a6","resolution":{"observed_at":"2026-08-12T15:19:48.829317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:48.757507Z","title":"Carrying out CNN channel prun- ing in a white box","venue":null,"work_id":"70d88c2e-d1f4-46fb-9281-3b41773d5e8c","year":2023},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.375733Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:f42d5ead2a2cf2c43257bd1783c85ac06f624d2d9348f96ee1312feb02c08605","observation_id":"fe34db74-df5f-449d-a086-2fe9910087d3","resolution":{"observed_at":"2026-08-12T15:19:48.764539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:48.711256Z","title":"Revisit kernel pruning with lottery regulated grouped convolutions","venue":null,"work_id":"967b03a3-98ec-400f-bff3-dab0a2e65715","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.384011Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:07c53671fe760a41742980b51dfdf6d3f2036598410b99cd9b8cf5527d4d767e","observation_id":"076573ce-6440-4536-aae0-b2a87d484c67","resolution":{"observed_at":"2026-08-12T15:19:48.724580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:48.634864Z","title":"Learning N: M fine-grained structured sparse neural networks from scratch","venue":null,"work_id":"d94af087-9cf1-40f5-983d-80aa42ba3d07","year":null},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.389415Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:5b5a9bcd2f629c90954b6e28415ab677922264b5f78842cde24145b3b6e209cd","observation_id":"93ded09e-ff23-4bee-bfd3-342700372892","resolution":{"observed_at":"2026-08-12T15:19:48.653228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T15:19:48.598779Z","title":"Yen, and Zhang Yi","venue":null,"work_id":"e553c8be-bfa8-43b4-bda0-ba3792a7a8be","year":2022},"citing_paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T15:19:48.397805Z"},"links":{"citing_paper":"/paper/2411.14345"},"observation_digest":"sha256:bf6cad3f7e1bc36254d46bb92a0d16d0a029eb39e214d3e24dcf474d6363250e","observation_id":"2f36c62c-e22c-4662-8683-d19f76e3484a","resolution":{"observed_at":"2026-08-12T15:19:48.607941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.14345","last_updated":"2024-11-21T17:41:27Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T15:14:30.385320Z","submitted_at":"2024-11-21T17:41:27Z","title":"Layer Pruning with Consensus: A Triple-Win Solution"},"reference_resolution":{"displayed":69,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":3,"verified_exact":0,"verified_fuzzy":65},"total_outbound_references":69},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 0 inbound Pith citation observations for arXiv:2411.14345."}