{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ABYXKLFJNEFMJPT3NF7FQ6WPZ7","short_pith_number":"pith:ABYXKLFJ","schema_version":"1.0","canonical_sha256":"0071752ca9690ac4be7b697e587acfcff38ea3b19207fca22f0a2cb4be3753da","source":{"kind":"arxiv","id":"1610.02915","version":4},"attestation_state":"computed","paper":{"title":"Deep Pyramidal Residual Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongyoon Han, Jiwhan Kim, Junmo Kim","submitted_at":"2016-10-10T13:47:13Z","abstract_excerpt":"Deep convolutional neural networks (DCNNs) have shown remarkable performance in image classification tasks in recent years. Generally, deep neural network architectures are stacks consisting of a large number of convolutional layers, and they perform downsampling along the spatial dimension via pooling to reduce memory usage. Concurrently, the feature map dimension (i.e., the number of channels) is sharply increased at downsampling locations, which is essential to ensure effective performance because it increases the diversity of high-level attributes. This also applies to residual networks an"},"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":"1610.02915","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-10-10T13:47:13Z","cross_cats_sorted":[],"title_canon_sha256":"41ca16957e74ce41d25231659db0a113867bfaa4ee300203feedb5ca00438587","abstract_canon_sha256":"60b090b3409d50bb4d0811f3a23746becaf7f0fc3b2e542a27ad042a4f3241d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:55.542183Z","signature_b64":"2oux+Fi1P59Roy0neCyCVklp9A4C5ccEjf4jf8kyS+4o1JZm6x5s4ilTrB43dUOiKZDSwNLjsX3N/IlJFOPIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0071752ca9690ac4be7b697e587acfcff38ea3b19207fca22f0a2cb4be3753da","last_reissued_at":"2026-05-18T00:35:55.541732Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:55.541732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Pyramidal Residual Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongyoon Han, Jiwhan Kim, Junmo Kim","submitted_at":"2016-10-10T13:47:13Z","abstract_excerpt":"Deep convolutional neural networks (DCNNs) have shown remarkable performance in image classification tasks in recent years. Generally, deep neural network architectures are stacks consisting of a large number of convolutional layers, and they perform downsampling along the spatial dimension via pooling to reduce memory usage. Concurrently, the feature map dimension (i.e., the number of channels) is sharply increased at downsampling locations, which is essential to ensure effective performance because it increases the diversity of high-level attributes. This also applies to residual networks an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.02915","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":"1610.02915","created_at":"2026-05-18T00:35:55.541799+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.02915v4","created_at":"2026-05-18T00:35:55.541799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.02915","created_at":"2026-05-18T00:35:55.541799+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABYXKLFJNEFM","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABYXKLFJNEFMJPT3","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABYXKLFJ","created_at":"2026-05-18T12:30:07.202191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2010.01412","citing_title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1608.03983","citing_title":"SGDR: Stochastic Gradient Descent with Warm Restarts","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABYXKLFJNEFMJPT3NF7FQ6WPZ7","json":"https://pith.science/pith/ABYXKLFJNEFMJPT3NF7FQ6WPZ7.json","graph_json":"https://pith.science/api/pith-number/ABYXKLFJNEFMJPT3NF7FQ6WPZ7/graph.json","events_json":"https://pith.science/api/pith-number/ABYXKLFJNEFMJPT3NF7FQ6WPZ7/events.json","paper":"https://pith.science/paper/ABYXKLFJ"},"agent_actions":{"view_html":"https://pith.science/pith/ABYXKLFJNEFMJPT3NF7FQ6WPZ7","download_json":"https://pith.science/pith/ABYXKLFJNEFMJPT3NF7FQ6WPZ7.json","view_paper":"https://pith.science/paper/ABYXKLFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.02915&json=true","fetch_graph":"https://pith.science/api/pith-number/ABYXKLFJNEFMJPT3NF7FQ6WPZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/ABYXKLFJNEFMJPT3NF7FQ6WPZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABYXKLFJNEFMJPT3NF7FQ6WPZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABYXKLFJNEFMJPT3NF7FQ6WPZ7/action/storage_attestation","attest_author":"https://pith.science/pith/ABYXKLFJNEFMJPT3NF7FQ6WPZ7/action/author_attestation","sign_citation":"https://pith.science/pith/ABYXKLFJNEFMJPT3NF7FQ6WPZ7/action/citation_signature","submit_replication":"https://pith.science/pith/ABYXKLFJNEFMJPT3NF7FQ6WPZ7/action/replication_record"}},"created_at":"2026-05-18T00:35:55.541799+00:00","updated_at":"2026-05-18T00:35:55.541799+00:00"}