{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ZE5L37ENFVYJQKPRPJAXRKRLFG","short_pith_number":"pith:ZE5L37EN","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"},"canonical_sha256":"c93abdfc8d2d709829f17a4178aa2b29a20130ab21025e6b3fa3416d16fa7102","source":{"kind":"arxiv","id":"1603.09382","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.09382","created_at":"2026-05-18T01:10:16Z"},{"alias_kind":"arxiv_version","alias_value":"1603.09382v3","created_at":"2026-05-18T01:10:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.09382","created_at":"2026-05-18T01:10:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZE5L37ENFVYJ","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZE5L37ENFVYJQKPR","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZE5L37EN","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ZE5L37ENFVYJQKPRPJAXRKRLFG","target":"record","payload":{"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"},"canonical_sha256":"c93abdfc8d2d709829f17a4178aa2b29a20130ab21025e6b3fa3416d16fa7102","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"},"source_kind":"arxiv","source_id":"1603.09382","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:10:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YknPrRIU3UlqBr8Q4a1dQoDbpMylwiPqaR//cdVkAbpvR9cS1+MnM5G3vathPq3f9gJb5oB6vi++UE2sy8YIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T06:52:36.176467Z"},"content_sha256":"4aadfe16b59861649f2a88fee1eb5dab9cfe0dac6dba4a25c594c01b6277bf95","schema_version":"1.0","event_id":"sha256:4aadfe16b59861649f2a88fee1eb5dab9cfe0dac6dba4a25c594c01b6277bf95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ZE5L37ENFVYJQKPRPJAXRKRLFG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:10:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLKPiwyKH2vRIraFxpipRwRedwinf9y5L22n0aoH3eHqaPlvmcHkiJcaDNJ4sygE9yvXOqQgkOWiqlulTwsIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T06:52:36.176814Z"},"content_sha256":"9a92e88a9c443c5a49e2bade09f7793a8519fe0b486ba6cd41a3867c91ec8990","schema_version":"1.0","event_id":"sha256:9a92e88a9c443c5a49e2bade09f7793a8519fe0b486ba6cd41a3867c91ec8990"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/bundle.json","state_url":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-22T06:52:36Z","links":{"resolver":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG","bundle":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/bundle.json","state":"https://pith.science/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZE5L37ENFVYJQKPRPJAXRKRLFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ZE5L37ENFVYJQKPRPJAXRKRLFG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"565d7bd5d398d0a62e73be37affc33bf3297b3b052ebe519c5b0b44427b11549","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-30T20:58:07Z","title_canon_sha256":"86b185e24caa0044e97d203e8621e2b7292795e8de58098d07694badccef18ff"},"schema_version":"1.0","source":{"id":"1603.09382","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.09382","created_at":"2026-05-18T01:10:16Z"},{"alias_kind":"arxiv_version","alias_value":"1603.09382v3","created_at":"2026-05-18T01:10:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.09382","created_at":"2026-05-18T01:10:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZE5L37ENFVYJ","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZE5L37ENFVYJQKPR","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZE5L37EN","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:9a92e88a9c443c5a49e2bade09f7793a8519fe0b486ba6cd41a3867c91ec8990","target":"graph","created_at":"2026-05-18T01:10:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Daniel Sedra, Gao Huang, Kilian Weinberger, Yu Sun, Zhuang Liu","cross_cats":["cs.CV","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-30T20:58:07Z","title":"Deep Networks with Stochastic Depth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.09382","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4aadfe16b59861649f2a88fee1eb5dab9cfe0dac6dba4a25c594c01b6277bf95","target":"record","created_at":"2026-05-18T01:10:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"565d7bd5d398d0a62e73be37affc33bf3297b3b052ebe519c5b0b44427b11549","cross_cats_sorted":["cs.CV","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-03-30T20:58:07Z","title_canon_sha256":"86b185e24caa0044e97d203e8621e2b7292795e8de58098d07694badccef18ff"},"schema_version":"1.0","source":{"id":"1603.09382","kind":"arxiv","version":3}},"canonical_sha256":"c93abdfc8d2d709829f17a4178aa2b29a20130ab21025e6b3fa3416d16fa7102","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c93abdfc8d2d709829f17a4178aa2b29a20130ab21025e6b3fa3416d16fa7102","first_computed_at":"2026-05-18T01:10:16.508479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:10:16.508479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K2aXQgbnvi1dkOBBe9diSx7G/WWbGwNNVFI6Gu/DzmzAKzciQuxOxoehRFo4U+WDbpUFd2YA90F9azKtwms+CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:10:16.509081Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.09382","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aadfe16b59861649f2a88fee1eb5dab9cfe0dac6dba4a25c594c01b6277bf95","sha256:9a92e88a9c443c5a49e2bade09f7793a8519fe0b486ba6cd41a3867c91ec8990"],"state_sha256":"c112183494ae1bae3bcaf4daa490fa0e0cdb49530e885dfe603f58c9f14516e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LyyXEhRPz17woKxbCvF1gEYje6ZadB2NLrk4b0vMz6e06hWt1jPxfXSjtE5SkxHPc5TWXPrviV3emiTNaLllDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T06:52:36.178896Z","bundle_sha256":"46d0e0c7cdc43851a2d69d9adf125b08469895ec88961361e8161a594e374f5b"}}