{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MOQXX623YES4DO6WIRV2CULAUP","short_pith_number":"pith:MOQXX623","schema_version":"1.0","canonical_sha256":"63a17bfb5bc125c1bbd6446ba15160a3fc3b1475af9e4eee73f758ed4e454c82","source":{"kind":"arxiv","id":"2007.02491","version":2},"attestation_state":"computed","paper":{"title":"EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bailin Li, Bowen Wu, Guangrun Wang, Jiang Su, Liang Lin","submitted_at":"2020-07-06T01:32:31Z","abstract_excerpt":"Finding out the computational redundant part of a trained Deep Neural Network (DNN) is the key question that pruning algorithms target on. Many algorithms try to predict model performance of the pruned sub-nets by introducing various evaluation methods. But they are either inaccurate or very complicated for general application. In this work, we present a pruning method called EagleEye, in which a simple yet efficient evaluation component based on adaptive batch normalization is applied to unveil a strong correlation between different pruned DNN structures and their final settled accuracy. This"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.02491","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-06T01:32:31Z","cross_cats_sorted":[],"title_canon_sha256":"7114fc1b95d62530bb0ce8f4a42bbd04866d017c2f9b8350153867b64fdee237","abstract_canon_sha256":"b3611e33b58c15310cfd23bbf08f628d302c54dbd3c8f1af2349aa5fd2b35201"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:24:53.300142Z","signature_b64":"+abhOgIqfEqIN/HSZV2lCKVaXRLZ4nARiFoeMjUt7OTzno9x7cF4DMDKXrfkUsi2le850sjkIY0Xknf9AjhkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63a17bfb5bc125c1bbd6446ba15160a3fc3b1475af9e4eee73f758ed4e454c82","last_reissued_at":"2026-07-05T01:24:53.299595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:24:53.299595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bailin Li, Bowen Wu, Guangrun Wang, Jiang Su, Liang Lin","submitted_at":"2020-07-06T01:32:31Z","abstract_excerpt":"Finding out the computational redundant part of a trained Deep Neural Network (DNN) is the key question that pruning algorithms target on. Many algorithms try to predict model performance of the pruned sub-nets by introducing various evaluation methods. But they are either inaccurate or very complicated for general application. In this work, we present a pruning method called EagleEye, in which a simple yet efficient evaluation component based on adaptive batch normalization is applied to unveil a strong correlation between different pruned DNN structures and their final settled accuracy. This"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02491","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.02491/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.02491","created_at":"2026-07-05T01:24:53.299689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.02491v2","created_at":"2026-07-05T01:24:53.299689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02491","created_at":"2026-07-05T01:24:53.299689+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOQXX623YES4","created_at":"2026-07-05T01:24:53.299689+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOQXX623YES4DO6W","created_at":"2026-07-05T01:24:53.299689+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOQXX623","created_at":"2026-07-05T01:24:53.299689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.10526","citing_title":"Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOQXX623YES4DO6WIRV2CULAUP","json":"https://pith.science/pith/MOQXX623YES4DO6WIRV2CULAUP.json","graph_json":"https://pith.science/api/pith-number/MOQXX623YES4DO6WIRV2CULAUP/graph.json","events_json":"https://pith.science/api/pith-number/MOQXX623YES4DO6WIRV2CULAUP/events.json","paper":"https://pith.science/paper/MOQXX623"},"agent_actions":{"view_html":"https://pith.science/pith/MOQXX623YES4DO6WIRV2CULAUP","download_json":"https://pith.science/pith/MOQXX623YES4DO6WIRV2CULAUP.json","view_paper":"https://pith.science/paper/MOQXX623","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.02491&json=true","fetch_graph":"https://pith.science/api/pith-number/MOQXX623YES4DO6WIRV2CULAUP/graph.json","fetch_events":"https://pith.science/api/pith-number/MOQXX623YES4DO6WIRV2CULAUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOQXX623YES4DO6WIRV2CULAUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOQXX623YES4DO6WIRV2CULAUP/action/storage_attestation","attest_author":"https://pith.science/pith/MOQXX623YES4DO6WIRV2CULAUP/action/author_attestation","sign_citation":"https://pith.science/pith/MOQXX623YES4DO6WIRV2CULAUP/action/citation_signature","submit_replication":"https://pith.science/pith/MOQXX623YES4DO6WIRV2CULAUP/action/replication_record"}},"created_at":"2026-07-05T01:24:53.299689+00:00","updated_at":"2026-07-05T01:24:53.299689+00:00"}