{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5JVJ7FONYFQXURRQHISH2ZRJRM","short_pith_number":"pith:5JVJ7FON","schema_version":"1.0","canonical_sha256":"ea6a9f95cdc1617a46303a247d66298b1a536c3836167193cf30b8f79d9fe8e6","source":{"kind":"arxiv","id":"1807.05726","version":3},"attestation_state":"computed","paper":{"title":"BRIEF: Backward Reduction of CNNs with Information Flow Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chun-Nan Chou, Edward Y. Chang, Yu-Hsun Lin","submitted_at":"2018-07-16T08:32:54Z","abstract_excerpt":"This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective. This algorithm can remove substantial non-zero weighting parameters (redundant neural channels) of a network by considering its dynamic behavior, which traditional model-compaction techniques cannot achieve. With the aid of our proposed algorithm, we achieve significant model reduction on ResNet-34 in the ImageNet scale (32.3% reduction), which is 3X better than the previous result (10.8%). Even for highly optimized models such as SqueezeNet and MobileNet, we"},"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":"1807.05726","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T08:32:54Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2ea773c0a4fd3227ac7bf8599d37251dea420e12f20faa7d24a849c48e9ca6ee","abstract_canon_sha256":"8189c6986674c034368982c8f838f47e1bc29f508d9ab1e1b8caa637467589bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:48.757897Z","signature_b64":"3eUN/4DeLt77SHXzEyy+oVNqMAgXi8EOkvO7NaNNiHgMKAYa5qXumC9yKc2PuOS426EGntQNcNV0uEqXaEQpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea6a9f95cdc1617a46303a247d66298b1a536c3836167193cf30b8f79d9fe8e6","last_reissued_at":"2026-05-18T00:01:48.757239Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:48.757239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BRIEF: Backward Reduction of CNNs with Information Flow Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chun-Nan Chou, Edward Y. Chang, Yu-Hsun Lin","submitted_at":"2018-07-16T08:32:54Z","abstract_excerpt":"This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective. This algorithm can remove substantial non-zero weighting parameters (redundant neural channels) of a network by considering its dynamic behavior, which traditional model-compaction techniques cannot achieve. With the aid of our proposed algorithm, we achieve significant model reduction on ResNet-34 in the ImageNet scale (32.3% reduction), which is 3X better than the previous result (10.8%). Even for highly optimized models such as SqueezeNet and MobileNet, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05726","kind":"arxiv","version":3},"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":"1807.05726","created_at":"2026-05-18T00:01:48.757327+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.05726v3","created_at":"2026-05-18T00:01:48.757327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05726","created_at":"2026-05-18T00:01:48.757327+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JVJ7FONYFQX","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JVJ7FONYFQXURRQ","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JVJ7FON","created_at":"2026-05-18T12:32:08.215937+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/5JVJ7FONYFQXURRQHISH2ZRJRM","json":"https://pith.science/pith/5JVJ7FONYFQXURRQHISH2ZRJRM.json","graph_json":"https://pith.science/api/pith-number/5JVJ7FONYFQXURRQHISH2ZRJRM/graph.json","events_json":"https://pith.science/api/pith-number/5JVJ7FONYFQXURRQHISH2ZRJRM/events.json","paper":"https://pith.science/paper/5JVJ7FON"},"agent_actions":{"view_html":"https://pith.science/pith/5JVJ7FONYFQXURRQHISH2ZRJRM","download_json":"https://pith.science/pith/5JVJ7FONYFQXURRQHISH2ZRJRM.json","view_paper":"https://pith.science/paper/5JVJ7FON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.05726&json=true","fetch_graph":"https://pith.science/api/pith-number/5JVJ7FONYFQXURRQHISH2ZRJRM/graph.json","fetch_events":"https://pith.science/api/pith-number/5JVJ7FONYFQXURRQHISH2ZRJRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JVJ7FONYFQXURRQHISH2ZRJRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JVJ7FONYFQXURRQHISH2ZRJRM/action/storage_attestation","attest_author":"https://pith.science/pith/5JVJ7FONYFQXURRQHISH2ZRJRM/action/author_attestation","sign_citation":"https://pith.science/pith/5JVJ7FONYFQXURRQHISH2ZRJRM/action/citation_signature","submit_replication":"https://pith.science/pith/5JVJ7FONYFQXURRQHISH2ZRJRM/action/replication_record"}},"created_at":"2026-05-18T00:01:48.757327+00:00","updated_at":"2026-05-18T00:01:48.757327+00:00"}