{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZE5L37ENFVYJQKPRPJAXRKRLFG","short_pith_number":"pith:ZE5L37EN","schema_version":"1.0","canonical_sha256":"c93abdfc8d2d709829f17a4178aa2b29a20130ab21025e6b3fa3416d16fa7102","source":{"kind":"arxiv","id":"1603.09382","version":3},"attestation_state":"computed","paper":{"title":"Deep Networks with Stochastic Depth","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Daniel Sedra, Gao Huang, Kilian Weinberger, Yu Sun, Zhuang Liu","submitted_at":"2016-03-30T20:58:07Z","abstract_excerpt":"Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very deep networks comes with its own set of challenges. The gradients can vanish, the forward flow often diminishes, and the training time can be painfully slow. To address these problems, we propose stochastic depth, a training procedure that enables the seemingly contradictory setup to train short networks and use deep networks at test time. We start with very de"},"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":"1603.09382","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-30T20:58:07Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"86b185e24caa0044e97d203e8621e2b7292795e8de58098d07694badccef18ff","abstract_canon_sha256":"565d7bd5d398d0a62e73be37affc33bf3297b3b052ebe519c5b0b44427b11549"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:16.509081Z","signature_b64":"K2aXQgbnvi1dkOBBe9diSx7G/WWbGwNNVFI6Gu/DzmzAKzciQuxOxoehRFo4U+WDbpUFd2YA90F9azKtwms+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c93abdfc8d2d709829f17a4178aa2b29a20130ab21025e6b3fa3416d16fa7102","last_reissued_at":"2026-05-18T01:10:16.508479Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:16.508479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Networks with Stochastic Depth","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Daniel Sedra, Gao Huang, Kilian Weinberger, Yu Sun, Zhuang Liu","submitted_at":"2016-03-30T20:58:07Z","abstract_excerpt":"Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very deep networks comes with its own set of challenges. The gradients can vanish, the forward flow often diminishes, and the training time can be painfully slow. To address these problems, we propose stochastic depth, a training procedure that enables the seemingly contradictory setup to train short networks and use deep networks at test time. We start with very de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.09382","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":"1603.09382","created_at":"2026-05-18T01:10:16.508566+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.09382v3","created_at":"2026-05-18T01:10:16.508566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.09382","created_at":"2026-05-18T01:10:16.508566+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZE5L37ENFVYJ","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZE5L37ENFVYJQKPR","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZE5L37EN","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.29983","citing_title":"Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2212.08989","citing_title":"Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics","ref_index":130,"is_internal_anchor":true},{"citing_arxiv_id":"2010.01412","citing_title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2601.17636","citing_title":"HealDA: Highlighting the importance of initial errors in end-to-end AI weather forecasts","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2205.06175","citing_title":"A Generalist Agent","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"1605.07146","citing_title":"Wide Residual Networks","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08300","citing_title":"mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11890","citing_title":"Subcritical Signal Propagation at Initialization in Normalization-Free Transformers","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06678","citing_title":"A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG","json":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG.json","graph_json":"https://pith.science/api/pith-number/ZE5L37ENFVYJQKPRPJAXRKRLFG/graph.json","events_json":"https://pith.science/api/pith-number/ZE5L37ENFVYJQKPRPJAXRKRLFG/events.json","paper":"https://pith.science/paper/ZE5L37EN"},"agent_actions":{"view_html":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG","download_json":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG.json","view_paper":"https://pith.science/paper/ZE5L37EN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.09382&json=true","fetch_graph":"https://pith.science/api/pith-number/ZE5L37ENFVYJQKPRPJAXRKRLFG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZE5L37ENFVYJQKPRPJAXRKRLFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/action/storage_attestation","attest_author":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/action/author_attestation","sign_citation":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/action/citation_signature","submit_replication":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/action/replication_record"}},"created_at":"2026-05-18T01:10:16.508566+00:00","updated_at":"2026-05-18T01:10:16.508566+00:00"}