{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MNZ336O3XZDFCE5G3VB44AGHTT","short_pith_number":"pith:MNZ336O3","schema_version":"1.0","canonical_sha256":"6373bdf9dbbe465113a6dd43ce00c79cea73ac1327c6aa4f4a6654451d8b832a","source":{"kind":"arxiv","id":"1602.07576","version":3},"attestation_state":"computed","paper":{"title":"Group Equivariant Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Max Welling, Taco S. Cohen","submitted_at":"2016-02-24T16:17:15Z","abstract_excerpt":"We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of layer that enjoys a substantially higher degree of weight sharing than regular convolution layers. G-convolutions increase the expressive capacity of the network without increasing the number of parameters. Group convolution layers are easy to use and can be implemented with negligible computational overhead for discrete groups generated by translations, reflections and "},"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":"1602.07576","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-24T16:17:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"12878ade5bd0fee362e652b3541fbfa9f35af0ea5e6b4d18d28fe4272cb9459a","abstract_canon_sha256":"94f1f147a1cfe9b4e42f1edde05d066f165280ded9fceba3c4e8cb15debf6004"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:59.598983Z","signature_b64":"MzCBq9sJ7GMauYLkokT82JiLwJSUiMqNINyuI+r2G7A9ZdKVrRw3f27SrCm7Sfmo9XGeliaLvn/M7kZRE0P5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6373bdf9dbbe465113a6dd43ce00c79cea73ac1327c6aa4f4a6654451d8b832a","last_reissued_at":"2026-05-18T01:12:59.598539Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:59.598539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group Equivariant Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Max Welling, Taco S. Cohen","submitted_at":"2016-02-24T16:17:15Z","abstract_excerpt":"We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of layer that enjoys a substantially higher degree of weight sharing than regular convolution layers. G-convolutions increase the expressive capacity of the network without increasing the number of parameters. Group convolution layers are easy to use and can be implemented with negligible computational overhead for discrete groups generated by translations, reflections and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.07576","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":"1602.07576","created_at":"2026-05-18T01:12:59.598589+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.07576v3","created_at":"2026-05-18T01:12:59.598589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.07576","created_at":"2026-05-18T01:12:59.598589+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNZ336O3XZDF","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNZ336O3XZDFCE5G","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNZ336O3","created_at":"2026-05-18T12:30:32.724797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.21483","citing_title":"Velocityformer: Broken-Symmetry-Matched Equivariant Graph Transformers for Cosmological Velocity Reconstruction","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16891","citing_title":"Tensor Channel Equivariant Graph Neural Networks for Molecular Polarizability Prediction","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2510.06508","citing_title":"Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi^4 field theory","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15073","citing_title":"Fast contracted Clebsch--Gordan tensor products for equivariant graph neural networks","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11199","citing_title":"Operator Spectroscopy of Trained Lattice Samplers","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03901","citing_title":"Graph Neural Networks in the Wilson Loop Representation of Abelian Lattice Gauge Theories","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14599","citing_title":"Disk-like galaxies at 4 < z < 7.7 : JWST/NIRCam morphologies revealed by denoising VAE-GCNN classification","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20797","citing_title":"Gauge-Equivariant Graph Neural Networks for Lattice Gauge Theories","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNZ336O3XZDFCE5G3VB44AGHTT","json":"https://pith.science/pith/MNZ336O3XZDFCE5G3VB44AGHTT.json","graph_json":"https://pith.science/api/pith-number/MNZ336O3XZDFCE5G3VB44AGHTT/graph.json","events_json":"https://pith.science/api/pith-number/MNZ336O3XZDFCE5G3VB44AGHTT/events.json","paper":"https://pith.science/paper/MNZ336O3"},"agent_actions":{"view_html":"https://pith.science/pith/MNZ336O3XZDFCE5G3VB44AGHTT","download_json":"https://pith.science/pith/MNZ336O3XZDFCE5G3VB44AGHTT.json","view_paper":"https://pith.science/paper/MNZ336O3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.07576&json=true","fetch_graph":"https://pith.science/api/pith-number/MNZ336O3XZDFCE5G3VB44AGHTT/graph.json","fetch_events":"https://pith.science/api/pith-number/MNZ336O3XZDFCE5G3VB44AGHTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNZ336O3XZDFCE5G3VB44AGHTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNZ336O3XZDFCE5G3VB44AGHTT/action/storage_attestation","attest_author":"https://pith.science/pith/MNZ336O3XZDFCE5G3VB44AGHTT/action/author_attestation","sign_citation":"https://pith.science/pith/MNZ336O3XZDFCE5G3VB44AGHTT/action/citation_signature","submit_replication":"https://pith.science/pith/MNZ336O3XZDFCE5G3VB44AGHTT/action/replication_record"}},"created_at":"2026-05-18T01:12:59.598589+00:00","updated_at":"2026-05-18T01:12:59.598589+00:00"}