{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:Y7YA5VZYKEENS2HFZ7FEHUIJIJ","short_pith_number":"pith:Y7YA5VZY","schema_version":"1.0","canonical_sha256":"c7f00ed7385108d968e5cfca43d1094279fc890435351a7ebb0ed606a3d115e1","source":{"kind":"arxiv","id":"1706.04964","version":4},"attestation_state":"computed","paper":{"title":"Learning Deep ResNet Blocks Sequentially using Boosting Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furong Huang, John Langford, Jordan Ash, Robert Schapire","submitted_at":"2017-06-15T16:59:07Z","abstract_excerpt":"Deep neural networks are known to be difficult to train due to the instability of back-propagation. A deep \\emph{residual network} (ResNet) with identity loops remedies this by stabilizing gradient computations. We prove a boosting theory for the ResNet architecture. We construct $T$ weak module classifiers, each contains two of the $T$ layers, such that the combined strong learner is a ResNet. Therefore, we introduce an alternative Deep ResNet training algorithm, \\emph{BoostResNet}, which is particularly suitable in non-differentiable architectures. Our proposed algorithm merely requires a se"},"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":"1706.04964","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-15T16:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"2f8e42b08b28a704875dec0c77623a1ffa4aacca983eec23a083a69ab0747cb9","abstract_canon_sha256":"3813eb4877a50bde4c68b9eed2d3cfa690ebec786d937beb3fa9b46bc6c354ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:15.694407Z","signature_b64":"I1C7mnclxeZcfgbbCV/qFS/LLcODCAxsEYIw/CyCQ6/V6QmH4/aUPhJ+IlRw1WKywCig9yOt+FTmHRCsvupdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7f00ed7385108d968e5cfca43d1094279fc890435351a7ebb0ed606a3d115e1","last_reissued_at":"2026-05-18T00:13:15.693729Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:15.693729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Deep ResNet Blocks Sequentially using Boosting Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furong Huang, John Langford, Jordan Ash, Robert Schapire","submitted_at":"2017-06-15T16:59:07Z","abstract_excerpt":"Deep neural networks are known to be difficult to train due to the instability of back-propagation. A deep \\emph{residual network} (ResNet) with identity loops remedies this by stabilizing gradient computations. We prove a boosting theory for the ResNet architecture. We construct $T$ weak module classifiers, each contains two of the $T$ layers, such that the combined strong learner is a ResNet. Therefore, we introduce an alternative Deep ResNet training algorithm, \\emph{BoostResNet}, which is particularly suitable in non-differentiable architectures. Our proposed algorithm merely requires a se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04964","kind":"arxiv","version":4},"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":"1706.04964","created_at":"2026-05-18T00:13:15.693822+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.04964v4","created_at":"2026-05-18T00:13:15.693822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04964","created_at":"2026-05-18T00:13:15.693822+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7YA5VZYKEEN","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7YA5VZYKEENS2HF","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7YA5VZY","created_at":"2026-05-18T12:31:56.362134+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/Y7YA5VZYKEENS2HFZ7FEHUIJIJ","json":"https://pith.science/pith/Y7YA5VZYKEENS2HFZ7FEHUIJIJ.json","graph_json":"https://pith.science/api/pith-number/Y7YA5VZYKEENS2HFZ7FEHUIJIJ/graph.json","events_json":"https://pith.science/api/pith-number/Y7YA5VZYKEENS2HFZ7FEHUIJIJ/events.json","paper":"https://pith.science/paper/Y7YA5VZY"},"agent_actions":{"view_html":"https://pith.science/pith/Y7YA5VZYKEENS2HFZ7FEHUIJIJ","download_json":"https://pith.science/pith/Y7YA5VZYKEENS2HFZ7FEHUIJIJ.json","view_paper":"https://pith.science/paper/Y7YA5VZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.04964&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7YA5VZYKEENS2HFZ7FEHUIJIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7YA5VZYKEENS2HFZ7FEHUIJIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7YA5VZYKEENS2HFZ7FEHUIJIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7YA5VZYKEENS2HFZ7FEHUIJIJ/action/storage_attestation","attest_author":"https://pith.science/pith/Y7YA5VZYKEENS2HFZ7FEHUIJIJ/action/author_attestation","sign_citation":"https://pith.science/pith/Y7YA5VZYKEENS2HFZ7FEHUIJIJ/action/citation_signature","submit_replication":"https://pith.science/pith/Y7YA5VZYKEENS2HFZ7FEHUIJIJ/action/replication_record"}},"created_at":"2026-05-18T00:13:15.693822+00:00","updated_at":"2026-05-18T00:13:15.693822+00:00"}