{"as_of":"2026-08-17T18:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a75e34e549669130fad426d27349871891d9d4bb0200db8c990ad3202c9db5fe","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T00:48:56.610102Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T15:49:04.044217Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-15T15:49:04.335099Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"cited_work":{"arxiv_id":"2502.08474","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.08474","snapshot_observed_at":"2026-08-15T15:49:04.335099Z","title":"Training-Free Restoration of Pruned Neural Networks","venue":"cs.LG","work_id":"0721a2de-04bc-4696-acbf-1ad3f91460d7","year":2025},"citing_paper":{"arxiv_id":"2509.25136","last_updated":"2026-07-02T17:21:41Z","snapshot_observed_at":"2026-08-15T15:41:01.928321Z","submitted_at":"2025-09-29T17:50:29Z","title":"BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T15:49:04.044217Z"},"links":{"cited_paper":"/paper/2502.08474","citing_paper":"/paper/2509.25136"},"observation_digest":"sha256:6543c3aace51f80455fd28c208352cce36c9344a900fd704012364ef316d7f3c","observation_id":"98671b65-f957-43ba-b178-98070c9b4e6b","resolution":{"observed_at":"2026-08-15T15:49:04.339398Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.08474/citation-record","integrity":"/paper/2502.08474/integrity","json":"/paper/2502.08474/citation-record.json","paper":"/paper/2502.08474"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:48:57.112208Z","title":"Coreset-based neural network compression,","venue":null,"work_id":"21b4deb4-4b5b-4502-8daf-adfff77fbd0a","year":2018},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.457817Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:35cc78e4045089a6c4bbf6b707e89378faf9b33e0ad4d0cdc1c4382ac8daa709","observation_id":"8b49a0b1-b54d-4299-962a-98c4c0f75169","resolution":{"observed_at":"2026-08-09T00:48:57.115218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.104320Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks,","venue":null,"work_id":"6acb836a-ff92-4366-9676-248fdc1d331e","year":2019},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.461749Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:874a82fa638ec626df61488eb0c634be7600bef073f392efe5acc2d98c8c5aa1","observation_id":"6adc9d03-1708-4411-bb19-edd404419d41","resolution":{"observed_at":"2026-08-09T00:48:57.107276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.095633Z","title":"Learning both weights and connections for efficient neural network,","venue":null,"work_id":"2c5724d9-4ac5-4f78-9ac5-14e08f4c1ff9","year":2015},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.465131Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:b26cf7e62880c30e93bbb82caeb919aa0ed61bf7eddfa9185b7c927aa8f8c59c","observation_id":"484129c1-81b8-415e-b2db-4f2169ee31fd","resolution":{"observed_at":"2026-08-09T00:48:57.098673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.087678Z","title":"Snip: single-shot network pruning based on connection sensitivity,","venue":null,"work_id":"cd9c4337-dcca-4345-afd1-74d313e0253c","year":2019},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.468710Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:11408e185c9bcf23259f214ba2858c00130c69b60665aabbf2b7132489fa9f1e","observation_id":"1cefb46e-db18-4a87-b60e-408b34a43bb8","resolution":{"observed_at":"2026-08-09T00:48:57.090585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.079633Z","title":"Pruning neural networks without any data by iteratively conserving synaptic flow,","venue":null,"work_id":"1b495634-b73b-4558-8d52-e1bc8c60193a","year":2020},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.471732Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:fc739c76f97ed0a56206d9cfd11025714a55818b934a00bce7ea33fe0295059d","observation_id":"1832a356-bd6b-452b-84a7-8c58ec6f132a","resolution":{"observed_at":"2026-08-09T00:48:57.082678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.071299Z","title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon,","venue":null,"work_id":"91a8e6e3-5f5a-48c3-876b-34e22ff72fda","year":2017},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.474908Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:8b8534266ebbace2c19922401a9c282720a5a7709e2df2cf316f367d0e2fb7be","observation_id":"63c952c7-bed6-40ff-ad24-517331b834c7","resolution":{"observed_at":"2026-08-09T00:48:57.074300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:48:56.478166Z","title":"Extremely sparse networks via binary augmented pruning for fast image classification,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.478166Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:afbd27d2e3d21564a536cf463965f44f914122cdccf36ca56d9b2caf0eee2f32","observation_id":"5daf189a-7129-452b-ad93-9e84a9f8a877","resolution":{"observed_at":"2026-08-09T00:48:56.478166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:48:57.063366Z","title":"Filter pruning via geometric median for deep convolutional neural networks acceleration,","venue":null,"work_id":"64eb39df-b7aa-4231-9c2b-41310cd8aa9c","year":2019},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.480961Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:30e6701ede7a491b4f18d8c42f2181cf390b6e3d764c84a1e3251020c07f94a6","observation_id":"e9559110-267b-4f23-afd7-c84ae5cb78dc","resolution":{"observed_at":"2026-08-09T00:48:57.066298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.055420Z","title":"Channel pruning for accelerating very deep neural networks,","venue":null,"work_id":"895cb0fd-cded-4df2-9749-010566ce82f1","year":2017},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.484947Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:234fa45308a6b60ca562d73dc54af103d38133553a7ca86707bad88b384756e5","observation_id":"d707b6ca-cfb6-4e36-8a2e-9044ad774bd9","resolution":{"observed_at":"2026-08-09T00:48:57.058425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.047301Z","title":"Eagleeye: Fast sub-net evaluation for efficient neural network pruning,","venue":null,"work_id":"7be93308-1099-4767-8b4b-c45427a90d40","year":2020},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.487836Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:2855701392acad6b421d41a23bc2827431c793190ebad1f6065a3efd8a2927b8","observation_id":"132ce426-eced-432a-a305-ddc511a7da57","resolution":{"observed_at":"2026-08-09T00:48:57.050256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.039464Z","title":"Rethinking the value of network pruning,","venue":null,"work_id":"663ff82a-cd28-454d-a66b-75acee84fb9e","year":2019},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.490676Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:3dbb16a96910344fe2540c0f0d36a030d6f9dfc939f49e985a5e649aabd80506","observation_id":"8bfb7186-9f9c-485a-b074-cd2bff7f7d74","resolution":{"observed_at":"2026-08-09T00:48:57.042324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.031339Z","title":"Thinet: A filter level pruning method for deep neural network compression,","venue":null,"work_id":"778d9eb7-ecd9-48a3-a5c7-03ce82874871","year":2017},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.493724Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:bd592a0d9b7fc14c9f09aa0a72027fb2ba9e4193919da0c1fc926a9ac21ec5bb","observation_id":"22d7f81e-f2b4-427d-bac4-be55b2dffa31","resolution":{"observed_at":"2026-08-09T00:48:57.034461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.023227Z","title":"Discrimination-aware channel pruning for deep neural networks,","venue":null,"work_id":"799a3143-5c31-4f98-9529-8e939adaba47","year":2018},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.496548Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:7c7c5af0996e4b1c40f96d71fc52ed7519cbed24509924f3a424d41b727a36c5","observation_id":"c6a0d312-e6f0-49af-83e6-3ec39672accf","resolution":{"observed_at":"2026-08-09T00:48:57.026215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.015149Z","title":"Soft filter pruning for accelerating deep convolutional neural networks,","venue":null,"work_id":"2458050d-1240-49cb-90d5-4e92693b9066","year":2018},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.499392Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:7b0fb6d01827eaa5b95e258301392eba309826e42b4eede130bb4de71763e102","observation_id":"24a09424-a2a1-4419-bc4b-e54841fd3b93","resolution":{"observed_at":"2026-08-09T00:48:57.018096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:57.007021Z","title":"Accelerating convolutional networks via global & dynamic filter pruning,","venue":null,"work_id":"3f450fd6-8109-4c2f-9861-b0fb151db45c","year":2018},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.502122Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:46629b0bb3467b77c558aa75d9b52d8d1a8b0bd3e91de8312dcf0bc047b848d9","observation_id":"b5765af2-626f-4e09-8efb-fcd539f19f8a","resolution":{"observed_at":"2026-08-09T00:48:57.009888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.998856Z","title":"Neural network pruning with residual-connections and limited-data,","venue":null,"work_id":"854712b6-3e0a-4684-8b6d-40cd58da7be9","year":2020},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.504995Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:92f6ea012b9d830a4446575d6ca5d6bd64b4ded06f55de8efdfe93e07b0004fe","observation_id":"daa923a2-4bcf-4aa1-accb-eb100c6636c2","resolution":{"observed_at":"2026-08-09T00:48:57.001865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.982692Z","title":"Importance estimation for neural network pruning,","venue":null,"work_id":"d307d68b-e19d-48a7-8e18-02d8b188e89e","year":2019},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.510677Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:e7e6db94a3a5a05992f1e832615c8eb406d2f0956f31f7517d25bf105110b915","observation_id":"59b3426a-35aa-4a15-8428-8dca6b0c7b83","resolution":{"observed_at":"2026-08-09T00:48:56.985645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.974588Z","title":"NISP: pruning networks using neuron importance score propagation,","venue":null,"work_id":"7bccd3b4-2847-47ae-8a06-0207475e9b84","year":2018},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.513604Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:751614630ba0212da9602e4e39248abd9913dbc8894398aa7f1e0c080b6debff","observation_id":"4417fa6b-5dd3-4e78-a6b6-61a63ee05651","resolution":{"observed_at":"2026-08-09T00:48:56.977560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.966312Z","title":"Exploring the limits of weakly supervised pretraining,","venue":null,"work_id":"6df2d355-efac-47ad-b002-4c80be6c226c","year":2018},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.516509Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:9bf88fbb9380b04ba40638c21c2bcb2d3d602fb24b79d1563ff3c5f4bcc0b475","observation_id":"cdcb569d-f4bb-49bb-9b5a-02b66623b02a","resolution":{"observed_at":"2026-08-09T00:48:56.969467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.958037Z","title":"Reborn filters: Pruning convolutional neural networks with limited data,","venue":null,"work_id":"6e370462-a1e2-4a11-a7de-f8207bd68083","year":2020},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.519347Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:1a8af2b8dc355469d06211c9adff57a75cf0ee9e7ffd3e236a0cac20946076e8","observation_id":"a554605c-6ce8-4029-9ee4-d1d97144c683","resolution":{"observed_at":"2026-08-09T00:48:56.961160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.949800Z","title":"Neuron merging: Compensating for pruned neurons,","venue":null,"work_id":"526bd8bf-2228-47aa-b61c-885cde6e0cb7","year":2020},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.522321Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:6b541a3eabc9ed36fd8ed6bb6a6360a79746d3a20c06ec372ccc0e03f77021ae","observation_id":"2e8facaa-a5d8-4ce5-ac8d-92bb8a9c4f69","resolution":{"observed_at":"2026-08-09T00:48:56.952832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.941254Z","title":"Data-free parameter pruning for deep neural networks,","venue":null,"work_id":"2f544b4f-cdd3-4775-b9fd-1cbb5cdb8bf3","year":2015},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.525393Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:ab4736a428990fe38d80bdf151b7b6e487449ceda289facdc930048b56e42d4e","observation_id":"8b10310d-0707-47d4-a919-dfcea48307f4","resolution":{"observed_at":"2026-08-09T00:48:56.944349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.933036Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"24de1c5a-a687-4437-9173-7618d4733877","year":2016},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.528350Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:08d0c39c21e8d153710c85d1583afdaace1e73834ff5e1174b1d7268cbe027e9","observation_id":"e0d5883e-3cdc-4d3f-926c-fd3eb0ec2764","resolution":{"observed_at":"2026-08-09T00:48:56.936119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.923949Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":"8950c2de-d814-423a-ba35-ab5d51586576","year":2009},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.531339Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:a4f2d56474de08cced2594177555236018b7a970a48e16272ba1b2b9e37ce6b9","observation_id":"a1d9a190-d19e-45f1-ac3a-a237df7a2aee","resolution":{"observed_at":"2026-08-09T00:48:56.927236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.915544Z","title":"Adaptive filter pruning via sensitivity feedback,","venue":null,"work_id":"9e8854ed-86db-40a3-996c-bd1699b701c0","year":2024},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.534304Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:d90c964aef372ae6a6b874c061219289864069e613e5abce03b3d6297e97113e","observation_id":"61f9adee-f76f-4224-a193-28db74cb2eda","resolution":{"observed_at":"2026-08-09T00:48:56.918546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.907227Z","title":"Towards efficient model compression via learned global ranking,","venue":null,"work_id":"353b0c08-08a7-4ea5-bc34-d831bd1cdcbd","year":2020},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.537358Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:c9e26f833f6d29f2414971357d7600631ca1b7cd25445d984929d15e716cf1b3","observation_id":"b5f7a712-d909-4e03-bb11-f50ac9867c9e","resolution":{"observed_at":"2026-08-09T00:48:56.910321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.898639Z","title":"Hierarchical threshold pruning based on uniform response criterion,","venue":null,"work_id":"09f6a336-be81-420b-9b3c-b3feace15edd","year":2024},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.540512Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:f771c636037d86fb637d4edac01173281eb3234d4b4fa9f39158ecd6286cca5d","observation_id":"9e91d090-4350-42aa-b4bc-b68c29339dff","resolution":{"observed_at":"2026-08-09T00:48:56.901774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.890230Z","title":"CATRO: channel pruning via class-aware trace ratio optimization,","venue":null,"work_id":"b6f21f39-fcb1-45ae-afdc-17065f63c250","year":2024},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.543588Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:48a32d24c0bd7da1506b1f18e1b1bd777e38b88aa5bd25ff2d8e6a49ad832c91","observation_id":"008f5322-ee14-4e6d-a3b0-0b2c084502d9","resolution":{"observed_at":"2026-08-09T00:48:56.893247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.881784Z","title":"Data- independent neural pruning via coresets,","venue":null,"work_id":"c34ec337-e414-4b40-9e25-fdda5026a099","year":2020},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.546645Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:d4990bc1be8a8fb2ad41baa9259e0af5fe30c401122571a12469b7f3392f7394","observation_id":"973f4478-7973-4e41-bc41-de22b1072eb4","resolution":{"observed_at":"2026-08-09T00:48:56.884900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.873107Z","title":"Fast filter pruning via coarse-to-fine neural architecture search and contrastive knowledge transfer,","venue":null,"work_id":"e87b3dcb-114b-48ee-a7fd-c4f6ef70d6ad","year":2024},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.549569Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:cf11a2f3d169da440e926d9ec622cd38ed9f561e6036c8cb2539f977e2d5f2c3","observation_id":"467489ec-d9f4-407b-827d-7776757658e0","resolution":{"observed_at":"2026-08-09T00:48:56.876267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-16T18:00:58.008096Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-09T00:48:56.552755Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.552755Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:c611b448a52baa05630344eac9e80888c574e2224150b97fed6514a9baaaed8f","observation_id":"957a8609-eea1-47a9-a7fa-274a0a6e4211","resolution":{"observed_at":"2026-08-09T00:48:56.552755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:48:56.864286Z","title":"RED++ : Data-free pruning of deep neural networks via input splitting and output merging,","venue":null,"work_id":"8f866bbb-1977-4588-887c-9b4ac77adb6f","year":2023},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.556276Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:ce7011c481832c5a567929c2c73f1cbba202e26e5b2e9c3c039f3d2b264ac75a","observation_id":"ca15b9b4-10ed-4021-9265-4fc42b241548","resolution":{"observed_at":"2026-08-09T00:48:56.867573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.855362Z","title":"Knowledge extraction with no observable data,","venue":null,"work_id":"3d6a2ee0-2c3b-4fe2-a0b8-8e00b6f42f73","year":2019},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.559183Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:aff874cdee27a89b5d9eff964923b35fdb8f2a57bf54462971aa5f49878659ca","observation_id":"94f39705-59e6-410e-a472-812441d5b595","resolution":{"observed_at":"2026-08-09T00:48:56.858557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.846604Z","title":"Data-free learning of student networks,","venue":null,"work_id":"6317b7e0-d918-428c-b049-2067eb9ba780","year":2019},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.563116Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:ef28ab745ec5a2b559fa1380c5e9edd5b349b78e09d80e783b5b0ff2864d23ba","observation_id":"e3c8d235-81e0-4619-bb94-d291e4763c10","resolution":{"observed_at":"2026-08-09T00:48:56.849651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.837854Z","title":"Zero-shot knowledge transfer via adversar- ial belief matching,","venue":null,"work_id":"b81a3d49-db5e-48c8-8dd1-36a13acb4107","year":2019},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.565993Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:0de9ea16b3ea383df2c132ca0223dd047fd0089c88528cc3abdfabf6725145d9","observation_id":"7ca7a9b9-f1f1-4da9-8690-e8f229992892","resolution":{"observed_at":"2026-08-09T00:48:56.841110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.11006","last_updated":"2020-03-02T12:12:43Z","snapshot_observed_at":"2026-08-14T02:55:22.370407Z","submitted_at":"2019-12-23T18:08:33Z","title":"Data-Free Adversarial Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.11006","snapshot_observed_at":"2026-08-09T00:48:56.568884Z","title":"Data-free adversarial distillation,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.568884Z"},"links":{"cited_paper":"/paper/1912.11006","citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:e56ea75fe2d140799d679f8f87908ec9c3d7e5ffec7cb00a67a93b6df11fb819","observation_id":"39119898-6b0e-421d-8184-98c8b48b921d","resolution":{"observed_at":"2026-08-09T00:48:56.568884Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:48:56.829221Z","title":"Dreaming to distill: Data-free knowledge transfer via deepinversion,","venue":null,"work_id":"66730779-79a6-461c-bc71-08ad6bd8a56e","year":2020},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.572195Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:49cbcb0d2a719eab627fc9fc29d772a3f7ffaeb45552148d06abbd57ba2a5ec9","observation_id":"e2bab72c-d77a-4a6f-afbf-701cb89fdcd3","resolution":{"observed_at":"2026-08-09T00:48:56.832534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.820515Z","title":"Data-free network pruning for model compression,","venue":null,"work_id":"6925f8d4-edf2-4c86-afc8-b7aacd189aa3","year":2021},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.575030Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:79566901fd8568037d039d38099ec788cf12a62452b017d0965fd94fd0b1d837","observation_id":"5530b5fe-c0fe-481c-9e9a-14291dc6a632","resolution":{"observed_at":"2026-08-09T00:48:56.823662Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:48:56.577974Z","title":"Tensor decompositions and applications,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.577974Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:4183cd2f7fd8b62d0718d2a90549bbc06889aacffbd250e5ab8e94e6b12299ef","observation_id":"0861be33-c3ad-4750-b9ad-ac7bbd1c40e0","resolution":{"observed_at":"2026-08-09T00:48:56.577974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:48:56.580716Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.580716Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:b9cee1f49abf85f11f7d7f5af3f5facdf4e28589e427b435391ae787eb0d5c82","observation_id":"80fc9f9d-8f34-45b5-aa57-48d5dd535232","resolution":{"observed_at":"2026-08-09T00:48:56.580716Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:48:56.801201Z","title":"Pytorch: An imperative style, high- performance deep learning library,","venue":null,"work_id":"081d81b9-48ae-48cf-9a4f-905531b383a1","year":2019},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.583610Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:ec42ba2b27f81f5c76e5f5476db3d4052be5dbd962433a6d86c772d6ccf9e2a7","observation_id":"babc09ad-4ba3-406b-94c2-420f595c4777","resolution":{"observed_at":"2026-08-09T00:48:56.804529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.791179Z","title":"Pruning filters for efficient convnets,","venue":null,"work_id":"37a19c96-c9f8-4d83-83bc-2361611d6361","year":2017},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.586421Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:996d9470e706beadf6975f3ce8425b699674b039aac3b52b281173e703f51dfc","observation_id":"d8d2a0aa-cc8e-42c3-a969-fcc8f65838e4","resolution":{"observed_at":"2026-08-09T00:48:56.794607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:48:56.589348Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.589348Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:34b57c918c70b88712f25550567a821ae852b3e310f499cb5814014a7aada146","observation_id":"44900dd7-48a5-4572-9a3b-174530232107","resolution":{"observed_at":"2026-08-09T00:48:56.589348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:48:56.775634Z","title":"Very deep convolutional networks for large-scale image recognition,","venue":null,"work_id":"1d287c09-7be8-40c4-926b-6981a411760d","year":2015},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.592169Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:4033a31c9875999c2cb5bfdcf04c9144f73dda3e1129baea9f075471269c91d4","observation_id":"352d8ebb-926a-4223-8d04-815411aa1439","resolution":{"observed_at":"2026-08-09T00:48:56.779064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.765494Z","title":"Microsoft COCO: common objects in context,","venue":null,"work_id":"1a9ca9aa-f039-4c2e-80dd-cb724cff5047","year":2014},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.595027Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:23a8a9ab2cfc6703e26648a7d51e3169b30bfb95a24b6714396ff2c874ca6966","observation_id":"272b2488-9a92-40a2-a526-164057dd924e","resolution":{"observed_at":"2026-08-09T00:48:56.768918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.755401Z","title":"SSD: single shot multibox detector,","venue":null,"work_id":"89e182d8-c577-417b-87d7-7c408292699e","year":2016},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.597917Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:957693e52ae33c0ac4d678dfa2e9fbd72f671ad7eadf614e3d0ee0e11fd8b3a4","observation_id":"04ef270f-3043-475a-b59f-b5908ebbec3c","resolution":{"observed_at":"2026-08-09T00:48:56.758803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.745910Z","title":"If there is only batch normalization between a feature map and its activation map, A(ℓ) = N (Z(ℓ))","venue":null,"work_id":"c8eaf210-b092-4a43-a54d-fd666b963a71","year":null},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.600833Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:96a1a92426188188fd38e1b84a4d94484de73a015553f33871a22f66fa87ab68","observation_id":"403610ce-de4d-4952-8961-f7a9fe3f9f2e","resolution":{"observed_at":"2026-08-09T00:48:56.749132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.735418Z","title":"If there are both batch normalization and a ReLU function between a feature map and its activation map, A(ℓ) = F (N (Z(ℓ)))","venue":null,"work_id":"1c2c498c-0389-4325-ada5-312f9bdf1778","year":null},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.604010Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:1a15f42c3ecdb5ac59b5b8c6278ffc3799a470e459fe0ee7352260b8a583780c","observation_id":"2245b02c-661e-4ddb-87de-30698162a6e1","resolution":{"observed_at":"2026-08-09T00:48:56.739477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.726852Z","title":null,"venue":null,"work_id":"779c120c-c369-41fd-859f-c6486da0f814","year":null},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.607042Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:b6f991a0f7be6f0c805ce6354d3dbb9adcb25af91693449f4bf22fbda0a0395b","observation_id":"d7197475-7c77-4892-b753-8a7cf505b712","resolution":{"observed_at":"2026-08-09T00:48:56.729826Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.716778Z","title":"Our loss function is as follows","venue":null,"work_id":"5dc3a51c-6176-481d-8473-e8b4cf2e4ba2","year":null},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.610102Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:7e9700b5011845c65db5f5d3766b4d8a4f0e605a128fa4fde5c1a2c01f997f76","observation_id":"3541fac9-c354-4e6d-9bcd-51c1118bbfa6","resolution":{"observed_at":"2026-08-09T00:48:56.720761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T00:48:56.990884Z","title":"1455–1464","venue":null,"work_id":"99659e81-cb0d-4e21-a795-abd5174ab1ec","year":2020},"citing_paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-09T00:48:56.507795Z"},"links":{"citing_paper":"/paper/2502.08474"},"observation_digest":"sha256:beef1f36095d7e0b591defd26c02a9722fca92e8502552ad7a917b36114b03ce","observation_id":"a3503521-8333-4875-a0de-4e32dd4e4fc3","resolution":{"observed_at":"2026-08-09T00:48:56.993682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.08474","last_updated":"2025-02-06T05:30:48Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T09:14:01.344108Z","submitted_at":"2025-02-06T05:30:48Z","title":"Training-Free Restoration of Pruned Neural Networks"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":0,"verified_fuzzy":44},"total_outbound_references":51},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 1 inbound Pith citation observation for arXiv:2502.08474."}