{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:N4KTRMMVDDERTP4LNSAFZ42N47","short_pith_number":"pith:N4KTRMMV","schema_version":"1.0","canonical_sha256":"6f1538b19518c919bf8b6c805cf34de7fcf42c908f3087604cd2d913c9453bc4","source":{"kind":"arxiv","id":"1803.08494","version":3},"attestation_state":"computed","paper":{"title":"Group Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kaiming He, Yuxin Wu","submitted_at":"2018-03-22T17:57:16Z","abstract_excerpt":"Batch Normalization (BN) is a milestone technique in the development of deep learning, enabling various networks to train. However, normalizing along the batch dimension introduces problems --- BN's error increases rapidly when the batch size becomes smaller, caused by inaccurate batch statistics estimation. This limits BN's usage for training larger models and transferring features to computer vision tasks including detection, segmentation, and video, which require small batches constrained by memory consumption. In this paper, we present Group Normalization (GN) as a simple alternative to BN"},"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":"1803.08494","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-22T17:57:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e9595cfb3a9b4f1fe4c48482b0fc3d2094c6ff6263f596acf81e285af9512b30","abstract_canon_sha256":"f36efc54117217caf43ef4db28255d66eb0a4c59a75cfa6763a673227df425ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:37.082481Z","signature_b64":"gpfXY4SGLxA10BaTUNDdnX/f1uFwnDya/Fq90tuwcs8KOrr/21CBp+/lrCfHzu20ehl296Z4SHorra+EXWvQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f1538b19518c919bf8b6c805cf34de7fcf42c908f3087604cd2d913c9453bc4","last_reissued_at":"2026-05-18T00:13:37.081900Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:37.081900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kaiming He, Yuxin Wu","submitted_at":"2018-03-22T17:57:16Z","abstract_excerpt":"Batch Normalization (BN) is a milestone technique in the development of deep learning, enabling various networks to train. However, normalizing along the batch dimension introduces problems --- BN's error increases rapidly when the batch size becomes smaller, caused by inaccurate batch statistics estimation. This limits BN's usage for training larger models and transferring features to computer vision tasks including detection, segmentation, and video, which require small batches constrained by memory consumption. In this paper, we present Group Normalization (GN) as a simple alternative to BN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.08494","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":"1803.08494","created_at":"2026-05-18T00:13:37.081996+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.08494v3","created_at":"2026-05-18T00:13:37.081996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.08494","created_at":"2026-05-18T00:13:37.081996+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4KTRMMVDDER","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4KTRMMVDDERTP4L","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4KTRMMV","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1907.04041","citing_title":"BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2404.05892","citing_title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13973","citing_title":"Determining star formation histories and age-metallicity relations with convolutional neural networks","ref_index":91,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10886","citing_title":"LoKA: Low-precision Kernel Applications for Recommendation Models At Scale","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10886","citing_title":"LoKA: Low-precision Kernel Applications for Recommendation Models At Scale","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07437","citing_title":"ASTRAFier: A Novel and Scalable Transformer-based Stellar Variability Classifier","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06475","citing_title":"AE-ViT: Stable Long-Horizon Parametric Partial Differential Equations Modeling","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13820","citing_title":"Stable Long-Horizon Neural ODE Reduced-Order Models via Learned Feedback for Biological Growth and Remodeling","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24913","citing_title":"Generative diffusion models for spatiotemporal influenza forecasting","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23799","citing_title":"VitaminP: cross-modal learning enables whole-cell segmentation from routine histology","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4KTRMMVDDERTP4LNSAFZ42N47","json":"https://pith.science/pith/N4KTRMMVDDERTP4LNSAFZ42N47.json","graph_json":"https://pith.science/api/pith-number/N4KTRMMVDDERTP4LNSAFZ42N47/graph.json","events_json":"https://pith.science/api/pith-number/N4KTRMMVDDERTP4LNSAFZ42N47/events.json","paper":"https://pith.science/paper/N4KTRMMV"},"agent_actions":{"view_html":"https://pith.science/pith/N4KTRMMVDDERTP4LNSAFZ42N47","download_json":"https://pith.science/pith/N4KTRMMVDDERTP4LNSAFZ42N47.json","view_paper":"https://pith.science/paper/N4KTRMMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.08494&json=true","fetch_graph":"https://pith.science/api/pith-number/N4KTRMMVDDERTP4LNSAFZ42N47/graph.json","fetch_events":"https://pith.science/api/pith-number/N4KTRMMVDDERTP4LNSAFZ42N47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4KTRMMVDDERTP4LNSAFZ42N47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4KTRMMVDDERTP4LNSAFZ42N47/action/storage_attestation","attest_author":"https://pith.science/pith/N4KTRMMVDDERTP4LNSAFZ42N47/action/author_attestation","sign_citation":"https://pith.science/pith/N4KTRMMVDDERTP4LNSAFZ42N47/action/citation_signature","submit_replication":"https://pith.science/pith/N4KTRMMVDDERTP4LNSAFZ42N47/action/replication_record"}},"created_at":"2026-05-18T00:13:37.081996+00:00","updated_at":"2026-05-18T00:13:37.081996+00:00"}