{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:G5SJVGFYUM37FI36EJ2ZA7ICQM","short_pith_number":"pith:G5SJVGFY","canonical_record":{"source":{"id":"1702.03275","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-10T18:27:17Z","cross_cats_sorted":[],"title_canon_sha256":"073ce9988c0f8f4510ff71b894d4a1a88c04e11917c07b99874912c84e727d40","abstract_canon_sha256":"31e2f876e3cc62b5c2e9d719a5ffd5f862c29a42a901b3a8fc6f2f2d5985349a"},"schema_version":"1.0"},"canonical_sha256":"37649a98b8a337f2a37e2275907d0283360267bb746f0122e60366bbd9c5c622","source":{"kind":"arxiv","id":"1702.03275","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.03275","created_at":"2026-05-18T00:47:36Z"},{"alias_kind":"arxiv_version","alias_value":"1702.03275v2","created_at":"2026-05-18T00:47:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03275","created_at":"2026-05-18T00:47:36Z"},{"alias_kind":"pith_short_12","alias_value":"G5SJVGFYUM37","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"G5SJVGFYUM37FI36","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"G5SJVGFY","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:G5SJVGFYUM37FI36EJ2ZA7ICQM","target":"record","payload":{"canonical_record":{"source":{"id":"1702.03275","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-10T18:27:17Z","cross_cats_sorted":[],"title_canon_sha256":"073ce9988c0f8f4510ff71b894d4a1a88c04e11917c07b99874912c84e727d40","abstract_canon_sha256":"31e2f876e3cc62b5c2e9d719a5ffd5f862c29a42a901b3a8fc6f2f2d5985349a"},"schema_version":"1.0"},"canonical_sha256":"37649a98b8a337f2a37e2275907d0283360267bb746f0122e60366bbd9c5c622","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:36.870305Z","signature_b64":"IJKguc12S+6uQGhRCTGym3MscNf6tBVtn81A1jGq9fl/vvcQR7wsuRgCo806sBhAk3lD6tZX8L3yncJr2D8JBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37649a98b8a337f2a37e2275907d0283360267bb746f0122e60366bbd9c5c622","last_reissued_at":"2026-05-18T00:47:36.869800Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:36.869800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.03275","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uQiTk99pJfk/D2v/qkjyIhtVxIMvGkzqhRUPtscNtYZ5DIGrT7RGun0/Lb0Mw/IGjQYJs3DNOujjXMpwtJowAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:20:56.883341Z"},"content_sha256":"3101c114f8e0129e1438d9c2d7a217bf57f5fc93895aedb0d4a61690dc5d22d7","schema_version":"1.0","event_id":"sha256:3101c114f8e0129e1438d9c2d7a217bf57f5fc93895aedb0d4a61690dc5d22d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:G5SJVGFYUM37FI36EJ2ZA7ICQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sergey Ioffe","submitted_at":"2017-02-10T18:27:17Z","abstract_excerpt":"Batch Normalization is quite effective at accelerating and improving the training of deep models. However, its effectiveness diminishes when the training minibatches are small, or do not consist of independent samples. We hypothesize that this is due to the dependence of model layer inputs on all the examples in the minibatch, and different activations being produced between training and inference. We propose Batch Renormalization, a simple and effective extension to ensure that the training and inference models generate the same outputs that depend on individual examples rather than the entir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03275","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HYuHCzZYHO0K69kTFHnyfvZZzJPIgqB5xp9SskuG8ytFsbzuH9k+hFujRhzUOrx7qVZWEKZQFC6yE6dzF0kJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:20:56.884022Z"},"content_sha256":"d7dbb042c153e261a62c3a0eba92b54582842173aa51604e12a4ec74585c550a","schema_version":"1.0","event_id":"sha256:d7dbb042c153e261a62c3a0eba92b54582842173aa51604e12a4ec74585c550a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5SJVGFYUM37FI36EJ2ZA7ICQM/bundle.json","state_url":"https://pith.science/pith/G5SJVGFYUM37FI36EJ2ZA7ICQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5SJVGFYUM37FI36EJ2ZA7ICQM/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":"2026-06-06T18:20:56Z","links":{"resolver":"https://pith.science/pith/G5SJVGFYUM37FI36EJ2ZA7ICQM","bundle":"https://pith.science/pith/G5SJVGFYUM37FI36EJ2ZA7ICQM/bundle.json","state":"https://pith.science/pith/G5SJVGFYUM37FI36EJ2ZA7ICQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5SJVGFYUM37FI36EJ2ZA7ICQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:G5SJVGFYUM37FI36EJ2ZA7ICQM","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":"31e2f876e3cc62b5c2e9d719a5ffd5f862c29a42a901b3a8fc6f2f2d5985349a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-10T18:27:17Z","title_canon_sha256":"073ce9988c0f8f4510ff71b894d4a1a88c04e11917c07b99874912c84e727d40"},"schema_version":"1.0","source":{"id":"1702.03275","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.03275","created_at":"2026-05-18T00:47:36Z"},{"alias_kind":"arxiv_version","alias_value":"1702.03275v2","created_at":"2026-05-18T00:47:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03275","created_at":"2026-05-18T00:47:36Z"},{"alias_kind":"pith_short_12","alias_value":"G5SJVGFYUM37","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"G5SJVGFYUM37FI36","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"G5SJVGFY","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:d7dbb042c153e261a62c3a0eba92b54582842173aa51604e12a4ec74585c550a","target":"graph","created_at":"2026-05-18T00:47:36Z","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":"Batch Normalization is quite effective at accelerating and improving the training of deep models. However, its effectiveness diminishes when the training minibatches are small, or do not consist of independent samples. We hypothesize that this is due to the dependence of model layer inputs on all the examples in the minibatch, and different activations being produced between training and inference. We propose Batch Renormalization, a simple and effective extension to ensure that the training and inference models generate the same outputs that depend on individual examples rather than the entir","authors_text":"Sergey Ioffe","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-10T18:27:17Z","title":"Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03275","kind":"arxiv","version":2},"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":"sha256:3101c114f8e0129e1438d9c2d7a217bf57f5fc93895aedb0d4a61690dc5d22d7","target":"record","created_at":"2026-05-18T00:47:36Z","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":"31e2f876e3cc62b5c2e9d719a5ffd5f862c29a42a901b3a8fc6f2f2d5985349a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-10T18:27:17Z","title_canon_sha256":"073ce9988c0f8f4510ff71b894d4a1a88c04e11917c07b99874912c84e727d40"},"schema_version":"1.0","source":{"id":"1702.03275","kind":"arxiv","version":2}},"canonical_sha256":"37649a98b8a337f2a37e2275907d0283360267bb746f0122e60366bbd9c5c622","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37649a98b8a337f2a37e2275907d0283360267bb746f0122e60366bbd9c5c622","first_computed_at":"2026-05-18T00:47:36.869800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:36.869800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IJKguc12S+6uQGhRCTGym3MscNf6tBVtn81A1jGq9fl/vvcQR7wsuRgCo806sBhAk3lD6tZX8L3yncJr2D8JBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:36.870305Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.03275","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3101c114f8e0129e1438d9c2d7a217bf57f5fc93895aedb0d4a61690dc5d22d7","sha256:d7dbb042c153e261a62c3a0eba92b54582842173aa51604e12a4ec74585c550a"],"state_sha256":"24f6ffba0a208be4494b1b60690b3f7b857c4686b762718f1f000d92060a0187"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JLmanelEusNNFjz2g1WWZRktNBzeMqEADtwtqjxaDzuvtWfZE0t93kAQ5inXtfKUR2D3ilQltukISUNgs/zjCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T18:20:56.887828Z","bundle_sha256":"8e3399ee62310122ff8e00e54b90c8c3a8f6d311db71a9650140a085dd7c3510"}}