{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:B3565FYBBM5DJVLPKSCNXLA57E","short_pith_number":"pith:B3565FYB","schema_version":"1.0","canonical_sha256":"0efbee97010b3a34d56f5484dbac1df92b638c9daf03cf580cc65f5258ae66cc","source":{"kind":"arxiv","id":"1710.11176","version":2},"attestation_state":"computed","paper":{"title":"CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Feng Luo, Hongxin Hu, Nishant Vishwamitra, Xiang Zhang","submitted_at":"2017-10-30T18:35:01Z","abstract_excerpt":"We introduce a new deep convolutional neural network, CrescendoNet, by stacking simple building blocks without residual connections. Each Crescendo block contains independent convolution paths with increased depths. The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks. In experiments, CrescendoNet with only 15 layers outperforms almost all networks without residual connections on benchmark datasets, CIFAR10, CIFAR100, and SVHN. Given sufficient amount of data as in SVHN dataset, CrescendoNet with 15 layers and 4.1M parameters can match the performanc"},"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":"1710.11176","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-30T18:35:01Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"34563ea4a1d3ba3bee17f65ba6a78051dd51a35e2c23fa2402a972fb2519f602","abstract_canon_sha256":"d8480f0c3f23bd9a9cdb2ad5c72b8871291c39f70224a6aa52ca63d6441407da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:43.412938Z","signature_b64":"16zL/UF2Phz/7dJB/jCdYNj+1L3t/qrgy0YjXSTVO35IitIryowqGsbSnavbrPzbStP4YBwS3gXDf9mm7U4hDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0efbee97010b3a34d56f5484dbac1df92b638c9daf03cf580cc65f5258ae66cc","last_reissued_at":"2026-05-18T00:26:43.412289Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:43.412289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Feng Luo, Hongxin Hu, Nishant Vishwamitra, Xiang Zhang","submitted_at":"2017-10-30T18:35:01Z","abstract_excerpt":"We introduce a new deep convolutional neural network, CrescendoNet, by stacking simple building blocks without residual connections. Each Crescendo block contains independent convolution paths with increased depths. The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks. In experiments, CrescendoNet with only 15 layers outperforms almost all networks without residual connections on benchmark datasets, CIFAR10, CIFAR100, and SVHN. Given sufficient amount of data as in SVHN dataset, CrescendoNet with 15 layers and 4.1M parameters can match the performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11176","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":""},"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":"1710.11176","created_at":"2026-05-18T00:26:43.412392+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.11176v2","created_at":"2026-05-18T00:26:43.412392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11176","created_at":"2026-05-18T00:26:43.412392+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3565FYBBM5D","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3565FYBBM5DJVLP","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3565FYB","created_at":"2026-05-18T12:31:08.081275+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/B3565FYBBM5DJVLPKSCNXLA57E","json":"https://pith.science/pith/B3565FYBBM5DJVLPKSCNXLA57E.json","graph_json":"https://pith.science/api/pith-number/B3565FYBBM5DJVLPKSCNXLA57E/graph.json","events_json":"https://pith.science/api/pith-number/B3565FYBBM5DJVLPKSCNXLA57E/events.json","paper":"https://pith.science/paper/B3565FYB"},"agent_actions":{"view_html":"https://pith.science/pith/B3565FYBBM5DJVLPKSCNXLA57E","download_json":"https://pith.science/pith/B3565FYBBM5DJVLPKSCNXLA57E.json","view_paper":"https://pith.science/paper/B3565FYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.11176&json=true","fetch_graph":"https://pith.science/api/pith-number/B3565FYBBM5DJVLPKSCNXLA57E/graph.json","fetch_events":"https://pith.science/api/pith-number/B3565FYBBM5DJVLPKSCNXLA57E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3565FYBBM5DJVLPKSCNXLA57E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3565FYBBM5DJVLPKSCNXLA57E/action/storage_attestation","attest_author":"https://pith.science/pith/B3565FYBBM5DJVLPKSCNXLA57E/action/author_attestation","sign_citation":"https://pith.science/pith/B3565FYBBM5DJVLPKSCNXLA57E/action/citation_signature","submit_replication":"https://pith.science/pith/B3565FYBBM5DJVLPKSCNXLA57E/action/replication_record"}},"created_at":"2026-05-18T00:26:43.412392+00:00","updated_at":"2026-05-18T00:26:43.412392+00:00"}