{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HYXGAFRIO2OJCXMIYRC4SO5CJG","short_pith_number":"pith:HYXGAFRI","schema_version":"1.0","canonical_sha256":"3e2e601628769c915d88c445c93ba24999c134a429d36cf6a3e41c54098b3b0e","source":{"kind":"arxiv","id":"1703.09916","version":1},"attestation_state":"computed","paper":{"title":"Towards thinner convolutional neural networks through Gradually Global Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Zhu, Qi Guo, Yipeng Liu, Zhengtao Wang, Zhiqiang Xia","submitted_at":"2017-03-29T07:31:46Z","abstract_excerpt":"Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices. Among many pruning granularities, neuron level pruning will remove redundant neurons and filters in the model and result in thinner networks. In this paper, we propose a gradually global pruning scheme for neuron level pruning. In each pruning step, a small percent of neurons were selected and dropped across all layers in the model. We also propose a simple method to eliminate the biases in evaluating the importance of neurons to make th"},"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":"1703.09916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-29T07:31:46Z","cross_cats_sorted":[],"title_canon_sha256":"e777cd48a71e43e42e3ade0ef9dd239a03bc72c5cef89658c59dc2b59a7e5de2","abstract_canon_sha256":"de19ddd1690a082c5153e5b7106e282d024b87b6f6bcef3d1b826ed35430f94f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:39.017166Z","signature_b64":"We5RHlPT5UqFC01GEq6u47oO1A55tub7It9rBqSv5/hCaqnyxxt+bzS72MbkhPZbwJg6aRyj38L5mUAWI8NKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e2e601628769c915d88c445c93ba24999c134a429d36cf6a3e41c54098b3b0e","last_reissued_at":"2026-05-18T00:47:39.016606Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:39.016606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards thinner convolutional neural networks through Gradually Global Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Zhu, Qi Guo, Yipeng Liu, Zhengtao Wang, Zhiqiang Xia","submitted_at":"2017-03-29T07:31:46Z","abstract_excerpt":"Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices. Among many pruning granularities, neuron level pruning will remove redundant neurons and filters in the model and result in thinner networks. In this paper, we propose a gradually global pruning scheme for neuron level pruning. In each pruning step, a small percent of neurons were selected and dropped across all layers in the model. We also propose a simple method to eliminate the biases in evaluating the importance of neurons to make th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.09916","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":""},"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":"1703.09916","created_at":"2026-05-18T00:47:39.016691+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.09916v1","created_at":"2026-05-18T00:47:39.016691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.09916","created_at":"2026-05-18T00:47:39.016691+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYXGAFRIO2OJ","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYXGAFRIO2OJCXMI","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYXGAFRI","created_at":"2026-05-18T12:31:21.493067+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/HYXGAFRIO2OJCXMIYRC4SO5CJG","json":"https://pith.science/pith/HYXGAFRIO2OJCXMIYRC4SO5CJG.json","graph_json":"https://pith.science/api/pith-number/HYXGAFRIO2OJCXMIYRC4SO5CJG/graph.json","events_json":"https://pith.science/api/pith-number/HYXGAFRIO2OJCXMIYRC4SO5CJG/events.json","paper":"https://pith.science/paper/HYXGAFRI"},"agent_actions":{"view_html":"https://pith.science/pith/HYXGAFRIO2OJCXMIYRC4SO5CJG","download_json":"https://pith.science/pith/HYXGAFRIO2OJCXMIYRC4SO5CJG.json","view_paper":"https://pith.science/paper/HYXGAFRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.09916&json=true","fetch_graph":"https://pith.science/api/pith-number/HYXGAFRIO2OJCXMIYRC4SO5CJG/graph.json","fetch_events":"https://pith.science/api/pith-number/HYXGAFRIO2OJCXMIYRC4SO5CJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYXGAFRIO2OJCXMIYRC4SO5CJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYXGAFRIO2OJCXMIYRC4SO5CJG/action/storage_attestation","attest_author":"https://pith.science/pith/HYXGAFRIO2OJCXMIYRC4SO5CJG/action/author_attestation","sign_citation":"https://pith.science/pith/HYXGAFRIO2OJCXMIYRC4SO5CJG/action/citation_signature","submit_replication":"https://pith.science/pith/HYXGAFRIO2OJCXMIYRC4SO5CJG/action/replication_record"}},"created_at":"2026-05-18T00:47:39.016691+00:00","updated_at":"2026-05-18T00:47:39.016691+00:00"}