{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:J7CQZBTIBL4E2NSUUORYIDQQOI","short_pith_number":"pith:J7CQZBTI","schema_version":"1.0","canonical_sha256":"4fc50c86680af84d3654a3a3840e10722ced9d4aedb5b888eec4a025269431db","source":{"kind":"arxiv","id":"1612.08498","version":1},"attestation_state":"computed","paper":{"title":"Steerable CNNs","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":"2016-12-27T04:38:28Z","abstract_excerpt":"It has long been recognized that the invariance and equivariance properties of a representation are critically important for success in many vision tasks. In this paper we present Steerable Convolutional Neural Networks, an efficient and flexible class of equivariant convolutional networks. We show that steerable CNNs achieve state of the art results on the CIFAR image classification benchmark. The mathematical theory of steerable representations reveals a type system in which any steerable representation is a composition of elementary feature types, each one associated with a particular kind "},"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":"1612.08498","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-27T04:38:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"848ab3ef1c51e5f0fe924eaef420c6c5c62352c5a67bdc1624b1678c440a7ed5","abstract_canon_sha256":"06b0344a7508e6b8c017b5ed71f29e944a85d5ecb6bcb31c17dd4a84dbb92fa6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:06.995112Z","signature_b64":"5q/RSYh88UtQcUvKIzZeaWU4Bhys0HslIAeUF5LnDpxOWVWrmDorQhbgmWITVgp4X85ANLKM5ADtdhYMwOLQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fc50c86680af84d3654a3a3840e10722ced9d4aedb5b888eec4a025269431db","last_reissued_at":"2026-05-17T23:48:06.994404Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:06.994404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Steerable CNNs","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":"2016-12-27T04:38:28Z","abstract_excerpt":"It has long been recognized that the invariance and equivariance properties of a representation are critically important for success in many vision tasks. In this paper we present Steerable Convolutional Neural Networks, an efficient and flexible class of equivariant convolutional networks. We show that steerable CNNs achieve state of the art results on the CIFAR image classification benchmark. The mathematical theory of steerable representations reveals a type system in which any steerable representation is a composition of elementary feature types, each one associated with a particular kind "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08498","kind":"arxiv","version":1},"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":"1612.08498","created_at":"2026-05-17T23:48:06.994518+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.08498v1","created_at":"2026-05-17T23:48:06.994518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08498","created_at":"2026-05-17T23:48:06.994518+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7CQZBTIBL4E","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7CQZBTIBL4E2NSU","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7CQZBTI","created_at":"2026-05-18T12:30:22.444734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2506.08244","citing_title":"Algebraic Priors for Approximately Equivariant Networks","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2507.18847","citing_title":"Equivariant Volumetric Grasping","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2509.24886","citing_title":"Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09138","citing_title":"Rotation Equivariant Mamba for Vision Tasks","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03901","citing_title":"Graph Neural Networks in the Wilson Loop Representation of Abelian Lattice Gauge Theories","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08034","citing_title":"Rotation Equivariant Convolutions in Deformable Registration of Brain MRI","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17371","citing_title":"Leveraging Kernel Symmetry for Joint Compression and Error Mitigation in Edge Model Transfer","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7CQZBTIBL4E2NSUUORYIDQQOI","json":"https://pith.science/pith/J7CQZBTIBL4E2NSUUORYIDQQOI.json","graph_json":"https://pith.science/api/pith-number/J7CQZBTIBL4E2NSUUORYIDQQOI/graph.json","events_json":"https://pith.science/api/pith-number/J7CQZBTIBL4E2NSUUORYIDQQOI/events.json","paper":"https://pith.science/paper/J7CQZBTI"},"agent_actions":{"view_html":"https://pith.science/pith/J7CQZBTIBL4E2NSUUORYIDQQOI","download_json":"https://pith.science/pith/J7CQZBTIBL4E2NSUUORYIDQQOI.json","view_paper":"https://pith.science/paper/J7CQZBTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.08498&json=true","fetch_graph":"https://pith.science/api/pith-number/J7CQZBTIBL4E2NSUUORYIDQQOI/graph.json","fetch_events":"https://pith.science/api/pith-number/J7CQZBTIBL4E2NSUUORYIDQQOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7CQZBTIBL4E2NSUUORYIDQQOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7CQZBTIBL4E2NSUUORYIDQQOI/action/storage_attestation","attest_author":"https://pith.science/pith/J7CQZBTIBL4E2NSUUORYIDQQOI/action/author_attestation","sign_citation":"https://pith.science/pith/J7CQZBTIBL4E2NSUUORYIDQQOI/action/citation_signature","submit_replication":"https://pith.science/pith/J7CQZBTIBL4E2NSUUORYIDQQOI/action/replication_record"}},"created_at":"2026-05-17T23:48:06.994518+00:00","updated_at":"2026-05-17T23:48:06.994518+00:00"}