{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CH6QMPS4XYBV4G4HFQZPGWAQQE","short_pith_number":"pith:CH6QMPS4","schema_version":"1.0","canonical_sha256":"11fd063e5cbe035e1b872c32f358108100532d608d6b0b40b28e071ebd536467","source":{"kind":"arxiv","id":"1908.02620","version":1},"attestation_state":"computed","paper":{"title":"Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingbing Ni, Chenglong Zhao, Haoran Deng, Jian Zhang, Yunxiang Zhang","submitted_at":"2019-08-06T12:44:30Z","abstract_excerpt":"To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and accelerate deep CNNs via channel pruning. Precisely, we argue that channels revealing similar feature information have functional overlap and that most channels within each such similarity group can be removed without compromising model's representational power. After deriving an effective metric for evaluating channel similarity through probabilistic modeling,"},"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":"1908.02620","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-06T12:44:30Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"1a304f6bf2e99c431b8df2547806353a2116d31b3857a67809a43624080c2147","abstract_canon_sha256":"5226648090bbc09efae0b788213be2ae6d63328c67815e1d825caa8769e14b0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:10.824028Z","signature_b64":"LHh0H7uYf0cVU6HrrO1DYT328UTaE/aFyzq2iTVVrcs3JYm/UHsreY2Ahipjzz3ndhTI6pd7KdYbmewioghVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11fd063e5cbe035e1b872c32f358108100532d608d6b0b40b28e071ebd536467","last_reissued_at":"2026-07-04T23:52:10.823564Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:10.823564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingbing Ni, Chenglong Zhao, Haoran Deng, Jian Zhang, Yunxiang Zhang","submitted_at":"2019-08-06T12:44:30Z","abstract_excerpt":"To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and accelerate deep CNNs via channel pruning. Precisely, we argue that channels revealing similar feature information have functional overlap and that most channels within each such similarity group can be removed without compromising model's representational power. After deriving an effective metric for evaluating channel similarity through probabilistic modeling,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02620","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/1908.02620/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":"1908.02620","created_at":"2026-07-04T23:52:10.823621+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.02620v1","created_at":"2026-07-04T23:52:10.823621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02620","created_at":"2026-07-04T23:52:10.823621+00:00"},{"alias_kind":"pith_short_12","alias_value":"CH6QMPS4XYBV","created_at":"2026-07-04T23:52:10.823621+00:00"},{"alias_kind":"pith_short_16","alias_value":"CH6QMPS4XYBV4G4H","created_at":"2026-07-04T23:52:10.823621+00:00"},{"alias_kind":"pith_short_8","alias_value":"CH6QMPS4","created_at":"2026-07-04T23:52:10.823621+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/CH6QMPS4XYBV4G4HFQZPGWAQQE","json":"https://pith.science/pith/CH6QMPS4XYBV4G4HFQZPGWAQQE.json","graph_json":"https://pith.science/api/pith-number/CH6QMPS4XYBV4G4HFQZPGWAQQE/graph.json","events_json":"https://pith.science/api/pith-number/CH6QMPS4XYBV4G4HFQZPGWAQQE/events.json","paper":"https://pith.science/paper/CH6QMPS4"},"agent_actions":{"view_html":"https://pith.science/pith/CH6QMPS4XYBV4G4HFQZPGWAQQE","download_json":"https://pith.science/pith/CH6QMPS4XYBV4G4HFQZPGWAQQE.json","view_paper":"https://pith.science/paper/CH6QMPS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.02620&json=true","fetch_graph":"https://pith.science/api/pith-number/CH6QMPS4XYBV4G4HFQZPGWAQQE/graph.json","fetch_events":"https://pith.science/api/pith-number/CH6QMPS4XYBV4G4HFQZPGWAQQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CH6QMPS4XYBV4G4HFQZPGWAQQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CH6QMPS4XYBV4G4HFQZPGWAQQE/action/storage_attestation","attest_author":"https://pith.science/pith/CH6QMPS4XYBV4G4HFQZPGWAQQE/action/author_attestation","sign_citation":"https://pith.science/pith/CH6QMPS4XYBV4G4HFQZPGWAQQE/action/citation_signature","submit_replication":"https://pith.science/pith/CH6QMPS4XYBV4G4HFQZPGWAQQE/action/replication_record"}},"created_at":"2026-07-04T23:52:10.823621+00:00","updated_at":"2026-07-04T23:52:10.823621+00:00"}