{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:7N2DOP35NNWQFLM4ROAYK5OMQJ","short_pith_number":"pith:7N2DOP35","schema_version":"1.0","canonical_sha256":"fb74373f7d6b6d02ad9c8b818575cc824ec626a1476ef88859ba8aae710d61fb","source":{"kind":"arxiv","id":"1602.02660","version":2},"attestation_state":"computed","paper":{"title":"Exploiting Cyclic Symmetry in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jeffrey De Fauw, Koray Kavukcuoglu, Sander Dieleman","submitted_at":"2016-02-08T17:37:16Z","abstract_excerpt":"Many classes of images exhibit rotational symmetry. Convolutional neural networks are sometimes trained using data augmentation to exploit this, but they are still required to learn the rotation equivariance properties from the data. Encoding these properties into the network architecture, as we are already used to doing for translation equivariance by using convolutional layers, could result in a more efficient use of the parameter budget by relieving the model from learning them. We introduce four operations which can be inserted into neural network models as layers, and which can be combine"},"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":"1602.02660","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-08T17:37:16Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"c76bb6acfd3b12d2b2ddf0b34f0464dac1b7915e36c25cd37bf266852cb6c33b","abstract_canon_sha256":"4970f3692f45149978ba2e4d12998a0e9dfc98dcb7c4d40c20d47ad374e6018e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:37.691055Z","signature_b64":"n/vNhygRCqZk90f47hbyx+DKayQD4mZYn4fFD/gmqgPUGjWBrSWb9IZ2aqu1br1f5pTAGtVjeBLztjL+uOb6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb74373f7d6b6d02ad9c8b818575cc824ec626a1476ef88859ba8aae710d61fb","last_reissued_at":"2026-05-18T01:13:37.690390Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:37.690390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Cyclic Symmetry in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jeffrey De Fauw, Koray Kavukcuoglu, Sander Dieleman","submitted_at":"2016-02-08T17:37:16Z","abstract_excerpt":"Many classes of images exhibit rotational symmetry. Convolutional neural networks are sometimes trained using data augmentation to exploit this, but they are still required to learn the rotation equivariance properties from the data. Encoding these properties into the network architecture, as we are already used to doing for translation equivariance by using convolutional layers, could result in a more efficient use of the parameter budget by relieving the model from learning them. We introduce four operations which can be inserted into neural network models as layers, and which can be combine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02660","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1602.02660","created_at":"2026-05-18T01:13:37.690477+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.02660v2","created_at":"2026-05-18T01:13:37.690477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02660","created_at":"2026-05-18T01:13:37.690477+00:00"},{"alias_kind":"pith_short_12","alias_value":"7N2DOP35NNWQ","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"7N2DOP35NNWQFLM4","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"7N2DOP35","created_at":"2026-05-18T12:30:04.600751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7N2DOP35NNWQFLM4ROAYK5OMQJ","json":"https://pith.science/pith/7N2DOP35NNWQFLM4ROAYK5OMQJ.json","graph_json":"https://pith.science/api/pith-number/7N2DOP35NNWQFLM4ROAYK5OMQJ/graph.json","events_json":"https://pith.science/api/pith-number/7N2DOP35NNWQFLM4ROAYK5OMQJ/events.json","paper":"https://pith.science/paper/7N2DOP35"},"agent_actions":{"view_html":"https://pith.science/pith/7N2DOP35NNWQFLM4ROAYK5OMQJ","download_json":"https://pith.science/pith/7N2DOP35NNWQFLM4ROAYK5OMQJ.json","view_paper":"https://pith.science/paper/7N2DOP35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.02660&json=true","fetch_graph":"https://pith.science/api/pith-number/7N2DOP35NNWQFLM4ROAYK5OMQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7N2DOP35NNWQFLM4ROAYK5OMQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7N2DOP35NNWQFLM4ROAYK5OMQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7N2DOP35NNWQFLM4ROAYK5OMQJ/action/storage_attestation","attest_author":"https://pith.science/pith/7N2DOP35NNWQFLM4ROAYK5OMQJ/action/author_attestation","sign_citation":"https://pith.science/pith/7N2DOP35NNWQFLM4ROAYK5OMQJ/action/citation_signature","submit_replication":"https://pith.science/pith/7N2DOP35NNWQFLM4ROAYK5OMQJ/action/replication_record"}},"created_at":"2026-05-18T01:13:37.690477+00:00","updated_at":"2026-05-18T01:13:37.690477+00:00"}