{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DYNE7DXYNDTVBAEOMBOICQQ4JR","short_pith_number":"pith:DYNE7DXY","schema_version":"1.0","canonical_sha256":"1e1a4f8ef868e750808e605c81421c4c79ed721b15ab4eeac1068b342964abeb","source":{"kind":"arxiv","id":"2012.15000","version":1},"attestation_state":"computed","paper":{"title":"DeepSphere: a graph-based spherical CNN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fr\\'ed\\'erick Gusset, Martino Milani, Micha\\\"el Defferrard, Nathana\\\"el Perraudin","submitted_at":"2020-12-30T01:35:27Z","abstract_excerpt":"Designing a convolution for a spherical neural network requires a delicate tradeoff between efficiency and rotation equivariance. DeepSphere, a method based on a graph representation of the sampled sphere, strikes a controllable balance between these two desiderata. This contribution is twofold. First, we study both theoretically and empirically how equivariance is affected by the underlying graph with respect to the number of vertices and neighbors. Second, we evaluate DeepSphere on relevant problems. Experiments show state-of-the-art performance and demonstrates the efficiency and flexibilit"},"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":"2012.15000","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-30T01:35:27Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"e999c8a132248f3457b63135ec55604ec69cc922047b97cb7a5d4833f966aba9","abstract_canon_sha256":"87d24381efe507f425169f27435820c90225054fecad6424bd54c309f3a6a6f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:03:03.509986Z","signature_b64":"hveblHw4EgQrbZmjCxeYKGdPiZyrMqKH/kfRx+GNN5Pj5u6nNXPYRBFp8SBvFPQf764eqyPNPzAbk+dlTjklCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e1a4f8ef868e750808e605c81421c4c79ed721b15ab4eeac1068b342964abeb","last_reissued_at":"2026-07-05T02:03:03.509478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:03:03.509478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepSphere: a graph-based spherical CNN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fr\\'ed\\'erick Gusset, Martino Milani, Micha\\\"el Defferrard, Nathana\\\"el Perraudin","submitted_at":"2020-12-30T01:35:27Z","abstract_excerpt":"Designing a convolution for a spherical neural network requires a delicate tradeoff between efficiency and rotation equivariance. DeepSphere, a method based on a graph representation of the sampled sphere, strikes a controllable balance between these two desiderata. This contribution is twofold. First, we study both theoretically and empirically how equivariance is affected by the underlying graph with respect to the number of vertices and neighbors. Second, we evaluate DeepSphere on relevant problems. Experiments show state-of-the-art performance and demonstrates the efficiency and flexibilit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15000","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.15000/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2012.15000","created_at":"2026-07-05T02:03:03.509541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.15000v1","created_at":"2026-07-05T02:03:03.509541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15000","created_at":"2026-07-05T02:03:03.509541+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYNE7DXYNDTV","created_at":"2026-07-05T02:03:03.509541+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYNE7DXYNDTVBAEO","created_at":"2026-07-05T02:03:03.509541+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYNE7DXY","created_at":"2026-07-05T02:03:03.509541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27745","citing_title":"Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11309","citing_title":"Dark Energy Survey Year 3 results: optimized $w$CDM simulation-based inference with weak lensing map-level hybrid statistics","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00139","citing_title":"Deep Learning for CMB Foreground Removal and Beam Deconvolution: A U-Net GAN Approach","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYNE7DXYNDTVBAEOMBOICQQ4JR","json":"https://pith.science/pith/DYNE7DXYNDTVBAEOMBOICQQ4JR.json","graph_json":"https://pith.science/api/pith-number/DYNE7DXYNDTVBAEOMBOICQQ4JR/graph.json","events_json":"https://pith.science/api/pith-number/DYNE7DXYNDTVBAEOMBOICQQ4JR/events.json","paper":"https://pith.science/paper/DYNE7DXY"},"agent_actions":{"view_html":"https://pith.science/pith/DYNE7DXYNDTVBAEOMBOICQQ4JR","download_json":"https://pith.science/pith/DYNE7DXYNDTVBAEOMBOICQQ4JR.json","view_paper":"https://pith.science/paper/DYNE7DXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.15000&json=true","fetch_graph":"https://pith.science/api/pith-number/DYNE7DXYNDTVBAEOMBOICQQ4JR/graph.json","fetch_events":"https://pith.science/api/pith-number/DYNE7DXYNDTVBAEOMBOICQQ4JR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYNE7DXYNDTVBAEOMBOICQQ4JR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYNE7DXYNDTVBAEOMBOICQQ4JR/action/storage_attestation","attest_author":"https://pith.science/pith/DYNE7DXYNDTVBAEOMBOICQQ4JR/action/author_attestation","sign_citation":"https://pith.science/pith/DYNE7DXYNDTVBAEOMBOICQQ4JR/action/citation_signature","submit_replication":"https://pith.science/pith/DYNE7DXYNDTVBAEOMBOICQQ4JR/action/replication_record"}},"created_at":"2026-07-05T02:03:03.509541+00:00","updated_at":"2026-07-05T02:03:03.509541+00:00"}