{"as_of":"2026-08-10T03:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:61fa8d29f1f7c209f8fe908a459015851633c0c17fb23ad74a49a5347e2edd55","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":"2026-08-08T20:49:36.313625Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.04975/citation-record","integrity":"/paper/2502.04975/integrity","json":"/paper/2502.04975/citation-record.json","paper":"/paper/2502.04975"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.08134","last_updated":"2021-03-19T10:43:12Z","snapshot_observed_at":"2026-07-06T10:34:02.819928Z","submitted_at":"2021-01-20T13:59:52Z","title":"Zero-Cost Proxies for Lightweight NAS","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.08134","snapshot_observed_at":"2026-08-08T20:49:36.169720Z","title":"Zero-cost proxies for lightweight NAS","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.169720Z"},"links":{"cited_paper":"/paper/2101.08134","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:7891b7526846d72c3ce698006115d0e0600154a682478c64176a38f87979928d","observation_id":"ebb9ae70-4b75-4d24-bf49-fdd0fd4255e8","resolution":{"observed_at":"2026-08-08T20:49:36.169720Z","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":"2026-08-08T20:49:36.701223Z","title":"Learning to ran k using gradient descent","venue":null,"work_id":"0e538b71-fa16-450c-9aea-cff3492ca0a9","year":2005},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.173679Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:5e812fa6f732a3596ca7c5b3975f065292f91f744f4ac304b2a6fea9a8c8ac12","observation_id":"a70283de-144a-4802-a8f1-202287a5e6bb","resolution":{"observed_at":"2026-08-08T20:49:36.704492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00332","last_updated":"2019-02-23T01:36:47Z","snapshot_observed_at":"2026-07-06T07:18:27.408498Z","submitted_at":"2018-12-02T05:29:53Z","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00332","snapshot_observed_at":"2026-08-08T20:49:36.176438Z","title":"Proxylessnas: Direct neural architecture search on target task and hardware","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.176438Z"},"links":{"cited_paper":"/paper/1812.00332","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:36bb398a695bd8b4734baef2749fa5845fa97f5046b53dfda69b20894ec4c061","observation_id":"94efbe89-42ff-404c-8c96-1b68dd627766","resolution":{"observed_at":"2026-08-08T20:49:36.176438Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.09791","last_updated":"2020-04-29T20:49:05Z","snapshot_observed_at":"2026-08-10T01:26:42.567690Z","submitted_at":"2019-08-26T16:46:23Z","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.09791","snapshot_observed_at":"2026-08-08T20:49:36.179681Z","title":"Once-for-all: Train one network and specialize it for efficient deployment","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.179681Z"},"links":{"cited_paper":"/paper/1908.09791","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:dcad4d92a6826da8b09a8fc49abc662343de83a6fc0017eb62f1939b97a5d3ed","observation_id":"e8dd7067-09a8-4604-91fe-5591af87f3cf","resolution":{"observed_at":"2026-08-08T20:49:36.179681Z","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":"2026-08-08T20:49:36.693090Z","title":"BN-NAS: Neural architecture search with batch normalization","venue":null,"work_id":"a5e6a188-468e-48c6-b81b-651053910791","year":2021},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.182764Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:b252c3a25fb6dd4285cea8539337f77bea560cb9721d6b34ca69245eef9b36e2","observation_id":"2267fce6-8023-4b71-bd84-c326363b89a3","resolution":{"observed_at":"2026-08-08T20:49:36.696585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.11535","last_updated":"2021-03-16T00:59:19Z","snapshot_observed_at":"2026-08-09T09:07:52.948334Z","submitted_at":"2021-02-23T07:50:44Z","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.11535","snapshot_observed_at":"2026-08-08T20:49:36.186440Z","title":"Neural ar- chitecture search on imagenet in four gpu hours: A theoretic ally inspired perspective","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.186440Z"},"links":{"cited_paper":"/paper/2102.11535","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:eaf1e5124e168c11ac02f2b5cc18e7e1d72713cc3d02ae6629ab97a7b07d5089","observation_id":"0976022a-d781-4691-8141-85a7009094b6","resolution":{"observed_at":"2026-08-08T20:49:36.186440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.08819","last_updated":"2017-08-23T16:06:20Z","snapshot_observed_at":"2026-07-06T05:52:59.445968Z","submitted_at":"2017-07-27T11:22:22Z","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.08819","snapshot_observed_at":"2026-08-08T20:49:36.190230Z","title":"A downsampled variant of imagenet as an alternative to the cif ar datasets","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.190230Z"},"links":{"cited_paper":"/paper/1707.08819","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:09f5d96da759c9e8f7458e744d6771f6919a4a80c1660dd2b9e8e401d156cfa6","observation_id":"193b3b82-21c6-4d23-b2b9-a13c5a236892","resolution":{"observed_at":"2026-08-08T20:49:36.190230Z","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":"2026-08-08T20:49:36.685159Z","title":"Mathematical methods of statistics","venue":null,"work_id":"426ed4bc-b5af-4a3a-addd-9ec36f930df4","year":1999},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.193779Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:b435260cf93f578a4c3480b520c3a39cdef794811ad03304d6573e19c762c51b","observation_id":"12a0b931-0a34-4a81-a36c-80d6ff73b4de","resolution":{"observed_at":"2026-08-08T20:49:36.688284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.676668Z","title":"Imagenet: A large-scale hierarchical image datab ase","venue":null,"work_id":"6232a6f9-d803-4301-baac-76eb498635e9","year":2009},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.196451Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:c84843244d38dcbed49a3d12157e9dbeb4f019c94a565c031c667f08d8ac541e","observation_id":"06ef0042-8d11-4cfa-8077-ebeff8838065","resolution":{"observed_at":"2026-08-08T20:49:36.680210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.00326","last_updated":"2020-01-15T12:38:55Z","snapshot_observed_at":"2026-08-08T12:15:50.581786Z","submitted_at":"2020-01-02T05:28:26Z","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.00326","snapshot_observed_at":"2026-08-08T20:49:36.199029Z","title":"Nas-bench-201: Extending the scope of reproducible neural architecture search","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.199029Z"},"links":{"cited_paper":"/paper/2001.00326","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:0fc50c420cb3b339da9a014b9848db0cbe1cb06407ca3d267b6d255a4ca069d6","observation_id":"5c8abed3-4699-4915-8bb3-9d3b5e805d55","resolution":{"observed_at":"2026-08-08T20:49:36.199029Z","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":"2026-08-08T20:49:36.668637Z","title":"Exploratory data analysis using Fisher information","venue":null,"work_id":"971f4f62-71f5-4a48-a9a3-7b7f80c5a331","year":2010},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.202264Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:b9c93b8fbe8b4b30b9ffa56a6aa1889cdd37d2d65e21759dfe93c5c6d83082d4","observation_id":"dd9bf209-bc4b-4e56-86aa-364894db94b4","resolution":{"observed_at":"2026-08-08T20:49:36.672062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.660556Z","title":"Complexity of linear reg ions in deep networks","venue":null,"work_id":"22ea074c-b592-44a9-be49-8c76a2cf3182","year":2019},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.205833Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:e008ed050e3f9b17fb91074fb14d6c695e85f2280b82058bceac858b1aca0361","observation_id":"6b0326dd-bbf5-4dda-8eed-d3026d912da6","resolution":{"observed_at":"2026-08-08T20:49:36.663966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.651991Z","title":"Ne ural tan- gent kernel: Convergence and generalization in neural netw orks","venue":null,"work_id":"8a79111a-65fe-4a1c-9a88-e033282df0d3","year":2018},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.208285Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:ed822df7f50b61b9857d73611e0416f6b2c968247b230f50daf81b4fe0d2b35c","observation_id":"73f77dcb-4723-4f42-a78b-84a47d0b03a0","resolution":{"observed_at":"2026-08-08T20:49:36.655693Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16551","last_updated":"2024-08-13T09:42:34Z","snapshot_observed_at":"2026-07-06T18:05:29.805179Z","submitted_at":"2024-04-25T12:07:41Z","title":"Surprisingly Strong Performance Prediction with Neural Graph Features","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16551","snapshot_observed_at":"2026-08-08T20:49:36.211272Z","title":"Surprisingly strong performance prediction with neural gr aph features","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.211272Z"},"links":{"cited_paper":"/paper/2404.16551","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:3cf6f047ba35c1aaad5b7ffbb1d72d9d91e166d28b0693636d7b75b3c9aeabc1","observation_id":"9cff16e4-cedf-4df6-99da-e9aae4ac0dc3","resolution":{"observed_at":"2026-08-08T20:49:36.211272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.05992","last_updated":"2020-09-27T08:31:59Z","snapshot_observed_at":"2026-08-09T22:53:30.724164Z","submitted_at":"2019-10-14T08:54:56Z","title":"Pathological spectra of the Fisher information metric and its variants in deep neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.05992","snapshot_observed_at":"2026-08-08T20:49:36.214208Z","title":"Path olog- ical spectra of the fisher information metric and its variant s in deep neural networks","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.214208Z"},"links":{"cited_paper":"/paper/1910.05992","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:0f4cc4eced810ff193eba7f181be272c52f4659e435940737c0a50c582b89985","observation_id":"5cf90128-7bed-4b9d-ad56-1b26f2875841","resolution":{"observed_at":"2026-08-08T20:49:36.214208Z","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":"2026-08-08T20:49:36.644403Z","title":"Univ ersal statistics of fisher information in deep neural networks: Me an field approach","venue":null,"work_id":"61ce854a-7690-4b24-a7b9-f64272db65ec","year":2019},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.217932Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:8d9f8e9eae63bd724c9487a1722e40564843f6622472ee85805be05d299ae726","observation_id":"eb894dd9-8c7e-4dda-a741-513e168fe2bb","resolution":{"observed_at":"2026-08-08T20:49:36.647268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.220508Z","title":"A new measure of rank correlation","venue":null,"work_id":null,"year":1938},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.220508Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:23d6eb7221acdbedaefcec0e2d5aca9714da7905f513b76725a67f8a07c0cd19","observation_id":"4641bc54-8bfa-42e3-83da-59ada5821877","resolution":{"observed_at":"2026-08-08T20:49:36.220508Z","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":"2026-08-08T20:49:36.223090Z","title":"Learning mult iple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.223090Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:4e0a5078fb7ab283364133d435adc02d3bbf93c77cd1b44da516ba6cc578bb8c","observation_id":"70be1125-85f8-42fd-acf9-5d8774e9d304","resolution":{"observed_at":"2026-08-08T20:49:36.223090Z","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":"2026-08-08T20:49:36.629446Z","title":"L imita- tions of the empirical fisher approximation for natural grad ient descent","venue":null,"work_id":"8bb978e8-7ed8-45cd-8cbb-5f962626f24e","year":2019},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.226235Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:e7286f681253c3ec5005d2f85c3039a7b757263d17a483b40bfa37b6530a4fbb","observation_id":"abbc63f0-b671-4651-a1b7-620366682181","resolution":{"observed_at":"2026-08-08T20:49:36.632234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.621794Z","title":"Masking adversarial damage: Finding adversarial saliency for robu st and sparse network","venue":null,"work_id":"bac6d414-b4fc-41d3-b771-601ca5e8794d","year":2022},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.229055Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:7fd9b44f1b4b971069acef756638e21f82cbfb7bab43381f6aad1a96caa0eefa","observation_id":"80b6ff2a-c215-4fa6-a0bc-6416d717ddfc","resolution":{"observed_at":"2026-08-08T20:49:36.624833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.614422Z","title":"AZ-NAS: Assembling zero- cost proxies for network architecture search","venue":null,"work_id":"55e427ff-d4ba-4f7a-acb2-fca70514511c","year":2024},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.231665Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:005740c9e77301b807790e066b7c8731210c95d91b8cd072b2c20be417d0f5c7","observation_id":"00f505d9-bf71-4624-8eae-76ceddd960af","resolution":{"observed_at":"2026-08-08T20:49:36.617234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.606978Z","title":"Wide neural networks of any depth evolve as linear models under gradient descent","venue":null,"work_id":"98c2e85e-6924-4f97-836a-7d263f8ccc28","year":2019},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.234673Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:64247b57274dca112e48057070f30c1465cbcfbe792fa5a8fe91376385253293","observation_id":"d3fa12cf-7839-4190-b842-73e9979eb68a","resolution":{"observed_at":"2026-08-08T20:49:36.609672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.02340","last_updated":"2019-02-23T07:45:29Z","snapshot_observed_at":"2026-07-06T07:06:10.289386Z","submitted_at":"2018-10-04T17:39:58Z","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.02340","snapshot_observed_at":"2026-08-08T20:49:36.237228Z","title":"Snip: Single-shot network pruning based on connection sens i- tivity","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.237228Z"},"links":{"cited_paper":"/paper/1810.02340","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:15ce6501228807338164c148eb1d8554c953f8778682819ad493d9171e65f3a0","observation_id":"e030d473-3f5e-411d-b825-85db097c863c","resolution":{"observed_at":"2026-08-08T20:49:36.237228Z","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":"2026-08-08T20:49:36.599826Z","title":"Linear algebra with applications","venue":null,"work_id":"5c2b48e1-44f8-4812-a043-1b0ee969612f","year":2006},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.239956Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:7f2456e781289006382c0e2e55626c7cfd5b0320c15b943b8225e65048f5e5d3","observation_id":"1e42ce6e-bcc5-4937-b8f9-98fe5ac9abda","resolution":{"observed_at":"2026-08-08T20:49:36.602452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.592216Z","title":"ZiCo: Zero-shot NAS via inverse coefficient of variation on gradients","venue":null,"work_id":"94112582-9a53-4395-bcfb-1dc7f77ea083","year":2023},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.242657Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:a560726ccd7cce2cdf1c98f389a14d616865714d2d081394fdc62cfc2ca1f367","observation_id":"3a4cdba0-8283-4f48-ba3d-cb4e2eb26d7b","resolution":{"observed_at":"2026-08-08T20:49:36.595062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.585094Z","title":"Zen-nas: A zero-shot nas for high-performance image recognition","venue":null,"work_id":"24a0bf36-8f30-433f-93b7-65699ea39ad4","year":2021},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.245048Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:fe34de67fc3669fabfcc84b2156c515338ab955762964b8a2aa8ff71b324083f","observation_id":"769f42ac-5894-4de7-a82e-180ef3209916","resolution":{"observed_at":"2026-08-08T20:49:36.587818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.09055","last_updated":"2019-04-23T06:29:32Z","snapshot_observed_at":"2026-08-09T13:23:20.015254Z","submitted_at":"2018-06-24T00:06:13Z","title":"DARTS: Differentiable Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.09055","snapshot_observed_at":"2026-08-08T20:49:36.247541Z","title":"DARTS: Differentiable architecture search","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.247541Z"},"links":{"cited_paper":"/paper/1806.09055","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:4bd95f1ec72aa625d2f64fec843164ac79a5451e3a5aa3f42442efe58619a9d1","observation_id":"f9ba9db3-a52e-4f80-834f-cc536d708114","resolution":{"observed_at":"2026-08-08T20:49:36.247541Z","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":"2026-08-08T20:49:36.577293Z","title":"A tutorial on fisher information","venue":null,"work_id":"5cac835c-b8d0-49e5-9acc-3aefb28271e6","year":2017},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.250928Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:6a2421c6d372bc48d7e07741754422e8e2f60ee3d99d62d5b828e5202dc18874","observation_id":"993340fc-1ee5-43fc-957c-a5f4064d6607","resolution":{"observed_at":"2026-08-08T20:49:36.580727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.569522Z","title":"New insights and perspectives on the nat ural gradient method","venue":null,"work_id":"77dec649-c331-4378-bba7-41925a14e877","year":2020},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.253494Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:fd56b25edc6b399b202916032a0237957697e6ead43d25e8a9a9ad56924e3229","observation_id":"8309f476-9be0-4717-b246-2c436d491839","resolution":{"observed_at":"2026-08-08T20:49:36.572840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.561737Z","title":"Nas-bench-asr: Reproducible neural architecture search for speech recognition","venue":null,"work_id":"3e1df39a-7279-49ed-83de-9de8b83ea50a","year":2021},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.255939Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:6c22f4f9e6a43ebff529ad70d0c0b96d67e71288595acd1350067009722c7581","observation_id":"d7aa474b-01e2-40fc-ab70-24a84c7b79d2","resolution":{"observed_at":"2026-08-08T20:49:36.564874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.554570Z","title":"Neural architecture search without training","venue":null,"work_id":"eb1eb671-6107-4e5c-a270-4f8ee1f64dac","year":2021},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.259221Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:760224c0e939144434dd1acff61a01c12cf75093c6b60fa16065ee09f0ce2323","observation_id":"85a42eba-1d91-49f6-ad76-058feee52685","resolution":{"observed_at":"2026-08-08T20:49:36.557274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.546357Z","title":"Distil ling optimal neural networks: Rapid search in diverse spaces","venue":null,"work_id":"9da3e406-dd7e-4ee5-826a-77286075c2ce","year":2021},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.261713Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:c34fc19fc7f25177514bb8a81a8b1c7650b465cb87109516af7b8b882d06ba25","observation_id":"edbba381-6130-438f-9740-0bc8ede38673","resolution":{"observed_at":"2026-08-08T20:49:36.549368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.536051Z","title":"Evaluating effi- cient performance estimators of neural architectures","venue":null,"work_id":"d971dd47-02eb-4614-8675-aa75069b1670","year":2021},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.264198Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:0b0169a859eae60bdda4c45bd6579c44e384f8452ce3f51446ed34257530fb75","observation_id":"b83cc35f-18a9-49bd-a716-7bbf5f2a41ce","resolution":{"observed_at":"2026-08-08T20:49:36.540113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.527378Z","title":"Fast finite width neural tangent kernel","venue":null,"work_id":"fb4f9c40-5d38-49b0-a9de-f7874db32b78","year":2022},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.267253Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:a7360e1358aa8933f42a10790f950eb692e2f9c61858f6ce596036197efacfa9","observation_id":"fb329c5a-76e3-4059-b35b-bbce159a279f","resolution":{"observed_at":"2026-08-08T20:49:36.530843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.517567Z","title":"Adaptive natural gradi ent method for learning of stochastic neural networks in mini-b atch mode","venue":null,"work_id":"9e57a0b7-fa49-4f6c-ae36-d336f953d14a","year":2019},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.269681Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:e823f7569b373ea43371bce5d7b616606f61f38a23a25d25fe62804c15a6f7a4","observation_id":"2b27cfc3-8831-4b22-9c57-a11eadb4e7c9","resolution":{"observed_at":"2026-08-08T20:49:36.521472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.509009Z","title":"The spectrum of th e fisher information matrix of a single-hidden-layer neural networ k","venue":null,"work_id":"b8e4c1a3-4bb0-408a-8a7e-d882845f0641","year":2018},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.272269Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:93f1d484000e060a5afd468cf1b795fd21a3ed10f1d664587a87f4a345f4d3d5","observation_id":"706df0b3-ffb4-4dc2-89bb-a2b3ee51adbf","resolution":{"observed_at":"2026-08-08T20:49:36.511971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.500761Z","title":"Information and the accuracy attai nable in the estimation of statistical parameters","venue":null,"work_id":"e931e848-137d-4a66-ad1f-a642694574c6","year":1992},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.275452Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:8b2df8d3901372f6f036f147fffc75099e133e5b7dc77b7d606f6b3f2c7b0128","observation_id":"4f242cc4-7d25-4a24-a371-665b7ca81dbf","resolution":{"observed_at":"2026-08-08T20:49:36.503703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.493127Z","title":"Mobilenetv2: Inverted resi d- uals and linear bottlenecks","venue":null,"work_id":"7e720ebd-c52a-46af-ab36-5e41536a8561","year":2018},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.277969Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:f8820a4201cb280dcff927aefd88770042f9f325a9dcf5a31bb7086a7bbdbd83","observation_id":"8a805ff9-197e-4054-8f87-6562fa1aaa4d","resolution":{"observed_at":"2026-08-08T20:49:36.496017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.485546Z","title":"The proof and measurement of associa tion between two things","venue":null,"work_id":"1603f989-9e03-4dfa-af46-43c847e08b8e","year":1961},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.280453Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:32dc48801063051055dae1da6d7b35de8e12f1032aed3e25d68c3682d37c483d","observation_id":"d015df08-06b5-4ac3-990f-65bd4b9f3be2","resolution":{"observed_at":"2026-08-08T20:49:36.488210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.478311Z","title":"An exact cholesky deco m- position and the generalized inverse of the variance–covar iance matrix of the multinomial distribution, with applications","venue":null,"work_id":"a04bd24d-03a6-4af6-9732-3a98e2b4f406","year":1992},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.283677Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:dae050c0e9bee155c035ec82c485700fb6129c4887e9e65669f05401e4b6ffe4","observation_id":"3cf05dcb-c7f1-45e4-9c92-09ae9d3fd7ec","resolution":{"observed_at":"2026-08-08T20:49:36.481089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.471123Z","title":"Pruning neural networks without any data by itera- tively conserving synaptic flow","venue":null,"work_id":"699898be-713f-40a3-b75e-45212b1647c8","year":2020},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.286060Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:785278a52ab69274e594e36def0b853a84dbe627bd08dd6cab654a9efc9f2d8c","observation_id":"0241662b-4b23-4df6-bde0-7c481a990049","resolution":{"observed_at":"2026-08-08T20:49:36.473871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07376","last_updated":"2020-08-07T00:02:33Z","snapshot_observed_at":"2026-08-03T13:48:05.558970Z","submitted_at":"2020-02-18T05:14:47Z","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07376","snapshot_observed_at":"2026-08-08T20:49:36.288557Z","title":"Picking winning tickets before training by preserving gradient flow","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.288557Z"},"links":{"cited_paper":"/paper/2002.07376","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:122284599d05c4fa49b49fb42027b705c8f673fe405667f9861ad871a705a461","observation_id":"c860b926-b457-490b-8064-136cd630760d","resolution":{"observed_at":"2026-08-08T20:49:36.288557Z","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":"2026-08-08T20:49:36.463937Z","title":"A deeper look at zero-cost proxies for lightweight NAS","venue":null,"work_id":"edc140e6-cefb-484f-a6ec-d9a5a57465cb","year":2022},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.291720Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:f3a2eedaf076f4d6a8736844bae17931995771b1d8efbc1632da11b4e6c67db4","observation_id":"6e66af6a-c5ce-4093-9948-788081b5c448","resolution":{"observed_at":"2026-08-08T20:49:36.466716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.456562Z","title":"On the number of linear regions of convolutional neural networks","venue":null,"work_id":"dd9fe03b-43fb-42b7-bbb2-181d7642cab8","year":2020},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.294209Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:c7373ea62489c53439f720a514edc0e957b9c5fdd0b12242e1ef52f68424ae96","observation_id":"ccb1ba4c-e86b-4de1-af63-2b4f38723f74","resolution":{"observed_at":"2026-08-08T20:49:36.459463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.448930Z","title":"CARS: Continuous evolution for efficient neural architecture search","venue":null,"work_id":"947fb490-6307-460a-ac1b-3ac4f9d6a3a9","year":2020},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.296607Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:d11d2bea02c7e88e4b024ec29fd8921978d52aad33809e0c1f1cf364724de4af","observation_id":"4e58cc95-24aa-4a14-9c34-2f3f07575b9a","resolution":{"observed_at":"2026-08-08T20:49:36.451822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.441269Z","title":"Nas-bench-101: Towards repro- ducible neural architecture search","venue":null,"work_id":"d9eec987-93b1-4f1e-9569-c07f230d9c25","year":2019},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.299864Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:7a19bbf3923d3441ed90ea79a6103a92dba230d7581a1871bc92f575893c913a","observation_id":"3ccf8196-8e4d-4178-9e5e-53a02cec6214","resolution":{"observed_at":"2026-08-08T20:49:36.444075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.433825Z","title":"A theoretical analysis of ndcg ranking measure s","venue":null,"work_id":"eefdcccc-f9ca-436b-bacf-0dca243ad35d","year":2013},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.302409Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:5f4c3e4841970d60aeca17f83548a34473e54d1ee6df62a2ec2882a09d8f456d","observation_id":"51a6e3ec-73ab-4c8f-bd1a-2d0b5032b7d4","resolution":{"observed_at":"2026-08-08T20:49:36.436634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.426455Z","title":"Neural architecture search with random labels","venue":null,"work_id":"0825b325-ce7b-4f99-a68a-e65291eceed3","year":2021},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.304788Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:76ff6300641aacdf620dc0936d3091715189d46a13c3e70abf0d42a7b5a7eaaa","observation_id":"8253b640-e1f2-4d27-9fd2-98d0591ad8c4","resolution":{"observed_at":"2026-08-08T20:49:36.429260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.08616","last_updated":"2022-06-18T19:34:43Z","snapshot_observed_at":"2026-08-04T20:30:24.201248Z","submitted_at":"2021-10-16T17:03:10Z","title":"GradSign: Model Performance Inference with Theoretical Insights","version":2},"cited_work":{"arxiv_id":"2110.08616","doi":null,"metadata_source":"pith","pith_arxiv_id":"2110.08616","snapshot_observed_at":"2026-08-08T20:49:36.334084Z","title":"GradSign: Model Performance Inference with Theoretical Insights","venue":"cs.LG","work_id":"d338ffb4-4e60-43b0-b1b2-3e4c981102dc","year":2021},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.308035Z"},"links":{"cited_paper":"/paper/2110.08616","citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:d744620314a9a75f2fb7f80c0c4f14e743067b47eb74c9d64cb72f37e80aa139","observation_id":"cb73891c-862e-4ad3-85ef-ccface29297e","resolution":{"observed_at":"2026-08-08T20:49:36.338865Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.418719Z","title":"Learning transferable architectures for scalable imag e recognition","venue":null,"work_id":"54c179cf-664e-484c-8886-08802029d7f2","year":2018},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.310713Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:537cb84851460a74378719c3080f137cdb5469e7c07ccb7ae5af8f3dc00ebf60","observation_id":"666d1f11-cd67-4646-8b72-228071762b25","resolution":{"observed_at":"2026-08-08T20:49:36.421423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T20:49:36.410921Z","title":"Our VKDNW proxy has the lowest correlation, ie","venue":null,"work_id":"9eaa033c-75e6-4402-820b-a8317f6fe21d","year":null},"citing_paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-08T20:49:36.313625Z"},"links":{"citing_paper":"/paper/2502.04975"},"observation_digest":"sha256:10a18d073ac8911a8f50d9d8ec933eb10011e3f48de4893d1d946dd2d22470db","observation_id":"98728326-c304-4363-96e1-c444f8f99c1c","resolution":{"observed_at":"2026-08-08T20:49:36.413747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.04975","last_updated":"2025-02-07T14:48:28Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T09:08:44.434946Z","submitted_at":"2025-02-07T14:48:28Z","title":"Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":1,"verified_fuzzy":37},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2502.04975."}