{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:J235AHNAEXANJLTF2PIIUBFIS3","short_pith_number":"pith:J235AHNA","schema_version":"1.0","canonical_sha256":"4eb7d01da025c0d4ae65d3d08a04a896eab6b7826268b9dfbd2ca7232b0eda66","source":{"kind":"arxiv","id":"2011.04908","version":2},"attestation_state":"computed","paper":{"title":"Effective Model Compression via Stage-wise Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingtao Rong, Linlin Ou, Mingyang Zhang, Xinyi Yu","submitted_at":"2020-11-10T05:19:05Z","abstract_excerpt":"Automated Machine Learning(Auto-ML) pruning methods aim at searching a pruning strategy automatically to reduce the computational complexity of deep Convolutional Neural Networks(deep CNNs). However, some previous work found that the results of many Auto-ML pruning methods cannot even surpass the results of the uniformly pruning method. In this paper, the ineffectiveness of Auto-ML pruning which is caused by unfull and unfair training of the supernet is shown. A deep supernet suffers from unfull training because it contains too many candidates. To overcome the unfull training, a stage-wise pru"},"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":"2011.04908","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-10T05:19:05Z","cross_cats_sorted":[],"title_canon_sha256":"7c82455f38955e6b97985aa7d8fcd133add8d0dcbda8f03d53bd17c72b295af6","abstract_canon_sha256":"161336a65478a4764e5d0d080154356e68c3d9cbb54aef61535f33e3da79ba8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:30.411167Z","signature_b64":"x6ztS40NEDBTO4/Wt0qcbSoIFwtop4/4nMEZc+ABoE71N713AKSgHzLL2ab4BVT7vHuTi1JdkCG53xBbnO5SAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eb7d01da025c0d4ae65d3d08a04a896eab6b7826268b9dfbd2ca7232b0eda66","last_reissued_at":"2026-07-05T03:16:30.410724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:30.410724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Model Compression via Stage-wise Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingtao Rong, Linlin Ou, Mingyang Zhang, Xinyi Yu","submitted_at":"2020-11-10T05:19:05Z","abstract_excerpt":"Automated Machine Learning(Auto-ML) pruning methods aim at searching a pruning strategy automatically to reduce the computational complexity of deep Convolutional Neural Networks(deep CNNs). However, some previous work found that the results of many Auto-ML pruning methods cannot even surpass the results of the uniformly pruning method. In this paper, the ineffectiveness of Auto-ML pruning which is caused by unfull and unfair training of the supernet is shown. A deep supernet suffers from unfull training because it contains too many candidates. To overcome the unfull training, a stage-wise pru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04908","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/2011.04908/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":"2011.04908","created_at":"2026-07-05T03:16:30.410781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.04908v2","created_at":"2026-07-05T03:16:30.410781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04908","created_at":"2026-07-05T03:16:30.410781+00:00"},{"alias_kind":"pith_short_12","alias_value":"J235AHNAEXAN","created_at":"2026-07-05T03:16:30.410781+00:00"},{"alias_kind":"pith_short_16","alias_value":"J235AHNAEXANJLTF","created_at":"2026-07-05T03:16:30.410781+00:00"},{"alias_kind":"pith_short_8","alias_value":"J235AHNA","created_at":"2026-07-05T03:16:30.410781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J235AHNAEXANJLTF2PIIUBFIS3","json":"https://pith.science/pith/J235AHNAEXANJLTF2PIIUBFIS3.json","graph_json":"https://pith.science/api/pith-number/J235AHNAEXANJLTF2PIIUBFIS3/graph.json","events_json":"https://pith.science/api/pith-number/J235AHNAEXANJLTF2PIIUBFIS3/events.json","paper":"https://pith.science/paper/J235AHNA"},"agent_actions":{"view_html":"https://pith.science/pith/J235AHNAEXANJLTF2PIIUBFIS3","download_json":"https://pith.science/pith/J235AHNAEXANJLTF2PIIUBFIS3.json","view_paper":"https://pith.science/paper/J235AHNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.04908&json=true","fetch_graph":"https://pith.science/api/pith-number/J235AHNAEXANJLTF2PIIUBFIS3/graph.json","fetch_events":"https://pith.science/api/pith-number/J235AHNAEXANJLTF2PIIUBFIS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J235AHNAEXANJLTF2PIIUBFIS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J235AHNAEXANJLTF2PIIUBFIS3/action/storage_attestation","attest_author":"https://pith.science/pith/J235AHNAEXANJLTF2PIIUBFIS3/action/author_attestation","sign_citation":"https://pith.science/pith/J235AHNAEXANJLTF2PIIUBFIS3/action/citation_signature","submit_replication":"https://pith.science/pith/J235AHNAEXANJLTF2PIIUBFIS3/action/replication_record"}},"created_at":"2026-07-05T03:16:30.410781+00:00","updated_at":"2026-07-05T03:16:30.410781+00:00"}