{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WEXB6OSI3AZ234ZVC2B6WDRQEO","short_pith_number":"pith:WEXB6OSI","schema_version":"1.0","canonical_sha256":"b12e1f3a48d833adf3351683eb0e3023ad25e9686edd4671783c247b9e655b19","source":{"kind":"arxiv","id":"2205.03602","version":1},"attestation_state":"computed","paper":{"title":"Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Honggang Qi, Xiaoyu Song, Zhaofeng Si","submitted_at":"2022-05-07T09:03:32Z","abstract_excerpt":"Convolutional neural networks are prevailing in deep learning tasks. However, they suffer from massive cost issues when working on mobile devices. Network pruning is an effective method of model compression to handle such problems. This paper presents a novel structured network pruning method with auxiliary gating structures which assigns importance marks to blocks in backbone network as a criterion when pruning. Block-wise pruning is then realized by proposed voting strategy, which is different from prevailing methods who prune a model in small granularity like channel-wise. We further develo"},"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":"2205.03602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-07T09:03:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"571b0616335b91e093709b2fcdc89915c890599b9516303997feb73e0141ea70","abstract_canon_sha256":"450eb131ac5e5a9efc63a26324778416fe3d77b138a9f2f30c6596e9622fc3ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:16.515022Z","signature_b64":"wxpNibLvSZNSiiE2L7JvotKFG1gctde/DDv0e3QUDCUywTSc1dWxEEqB89UHYP+DUXxfbTmfb8Eo8K1PTPHkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b12e1f3a48d833adf3351683eb0e3023ad25e9686edd4671783c247b9e655b19","last_reissued_at":"2026-07-05T04:21:16.514625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:16.514625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Honggang Qi, Xiaoyu Song, Zhaofeng Si","submitted_at":"2022-05-07T09:03:32Z","abstract_excerpt":"Convolutional neural networks are prevailing in deep learning tasks. However, they suffer from massive cost issues when working on mobile devices. Network pruning is an effective method of model compression to handle such problems. This paper presents a novel structured network pruning method with auxiliary gating structures which assigns importance marks to blocks in backbone network as a criterion when pruning. Block-wise pruning is then realized by proposed voting strategy, which is different from prevailing methods who prune a model in small granularity like channel-wise. We further develo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03602","kind":"arxiv","version":1},"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/2205.03602/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":"2205.03602","created_at":"2026-07-05T04:21:16.514688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03602v1","created_at":"2026-07-05T04:21:16.514688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03602","created_at":"2026-07-05T04:21:16.514688+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEXB6OSI3AZ2","created_at":"2026-07-05T04:21:16.514688+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEXB6OSI3AZ234ZV","created_at":"2026-07-05T04:21:16.514688+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEXB6OSI","created_at":"2026-07-05T04:21:16.514688+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/WEXB6OSI3AZ234ZVC2B6WDRQEO","json":"https://pith.science/pith/WEXB6OSI3AZ234ZVC2B6WDRQEO.json","graph_json":"https://pith.science/api/pith-number/WEXB6OSI3AZ234ZVC2B6WDRQEO/graph.json","events_json":"https://pith.science/api/pith-number/WEXB6OSI3AZ234ZVC2B6WDRQEO/events.json","paper":"https://pith.science/paper/WEXB6OSI"},"agent_actions":{"view_html":"https://pith.science/pith/WEXB6OSI3AZ234ZVC2B6WDRQEO","download_json":"https://pith.science/pith/WEXB6OSI3AZ234ZVC2B6WDRQEO.json","view_paper":"https://pith.science/paper/WEXB6OSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03602&json=true","fetch_graph":"https://pith.science/api/pith-number/WEXB6OSI3AZ234ZVC2B6WDRQEO/graph.json","fetch_events":"https://pith.science/api/pith-number/WEXB6OSI3AZ234ZVC2B6WDRQEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEXB6OSI3AZ234ZVC2B6WDRQEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEXB6OSI3AZ234ZVC2B6WDRQEO/action/storage_attestation","attest_author":"https://pith.science/pith/WEXB6OSI3AZ234ZVC2B6WDRQEO/action/author_attestation","sign_citation":"https://pith.science/pith/WEXB6OSI3AZ234ZVC2B6WDRQEO/action/citation_signature","submit_replication":"https://pith.science/pith/WEXB6OSI3AZ234ZVC2B6WDRQEO/action/replication_record"}},"created_at":"2026-07-05T04:21:16.514688+00:00","updated_at":"2026-07-05T04:21:16.514688+00:00"}