{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GLKKOHHCIPJRSRCAOOQ2UU3QSU","short_pith_number":"pith:GLKKOHHC","schema_version":"1.0","canonical_sha256":"32d4a71ce243d319444073a1aa5370951ab4941a0488c082861186ffe81e62cb","source":{"kind":"arxiv","id":"1909.06397","version":3},"attestation_state":"computed","paper":{"title":"Horizontal Flows and Manifold Stochastics in Geometric Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Bronstein, Stefan Sommer","submitted_at":"2019-09-13T18:27:02Z","abstract_excerpt":"We introduce two constructions in geometric deep learning for 1) transporting orientation-dependent convolutional filters over a manifold in a continuous way and thereby defining a convolution operator that naturally incorporates the rotational effect of holonomy; and 2) allowing efficient evaluation of manifold convolution layers by sampling manifold valued random variables that center around a weighted diffusion mean. Both methods are inspired by stochastics on manifolds and geometric statistics, and provide examples of how stochastic methods -- here horizontal frame bundle flows and non-lin"},"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":"1909.06397","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-13T18:27:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fbc2720625ff91976c07412ba7a1dd8ab17a3cf116123e77778c3e685418bfb0","abstract_canon_sha256":"f256f3f5ea6d844dc79103f3cfa6c8f2fc06b88976669eb694329bce8c3e5a15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:47.162201Z","signature_b64":"MWq3cdOZ6F7mJFeax1+Q3jO1C6mR9mgJxQdVpYoRfpMDsHpPF8gwD+sw76RdYfc9Uf+jjoDoDtTqgDHV0hJKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32d4a71ce243d319444073a1aa5370951ab4941a0488c082861186ffe81e62cb","last_reissued_at":"2026-07-05T02:44:47.161785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:47.161785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Horizontal Flows and Manifold Stochastics in Geometric Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Bronstein, Stefan Sommer","submitted_at":"2019-09-13T18:27:02Z","abstract_excerpt":"We introduce two constructions in geometric deep learning for 1) transporting orientation-dependent convolutional filters over a manifold in a continuous way and thereby defining a convolution operator that naturally incorporates the rotational effect of holonomy; and 2) allowing efficient evaluation of manifold convolution layers by sampling manifold valued random variables that center around a weighted diffusion mean. Both methods are inspired by stochastics on manifolds and geometric statistics, and provide examples of how stochastic methods -- here horizontal frame bundle flows and non-lin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06397","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.06397/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":"1909.06397","created_at":"2026-07-05T02:44:47.161849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.06397v3","created_at":"2026-07-05T02:44:47.161849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06397","created_at":"2026-07-05T02:44:47.161849+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLKKOHHCIPJR","created_at":"2026-07-05T02:44:47.161849+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLKKOHHCIPJRSRCA","created_at":"2026-07-05T02:44:47.161849+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLKKOHHC","created_at":"2026-07-05T02:44:47.161849+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/GLKKOHHCIPJRSRCAOOQ2UU3QSU","json":"https://pith.science/pith/GLKKOHHCIPJRSRCAOOQ2UU3QSU.json","graph_json":"https://pith.science/api/pith-number/GLKKOHHCIPJRSRCAOOQ2UU3QSU/graph.json","events_json":"https://pith.science/api/pith-number/GLKKOHHCIPJRSRCAOOQ2UU3QSU/events.json","paper":"https://pith.science/paper/GLKKOHHC"},"agent_actions":{"view_html":"https://pith.science/pith/GLKKOHHCIPJRSRCAOOQ2UU3QSU","download_json":"https://pith.science/pith/GLKKOHHCIPJRSRCAOOQ2UU3QSU.json","view_paper":"https://pith.science/paper/GLKKOHHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.06397&json=true","fetch_graph":"https://pith.science/api/pith-number/GLKKOHHCIPJRSRCAOOQ2UU3QSU/graph.json","fetch_events":"https://pith.science/api/pith-number/GLKKOHHCIPJRSRCAOOQ2UU3QSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLKKOHHCIPJRSRCAOOQ2UU3QSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLKKOHHCIPJRSRCAOOQ2UU3QSU/action/storage_attestation","attest_author":"https://pith.science/pith/GLKKOHHCIPJRSRCAOOQ2UU3QSU/action/author_attestation","sign_citation":"https://pith.science/pith/GLKKOHHCIPJRSRCAOOQ2UU3QSU/action/citation_signature","submit_replication":"https://pith.science/pith/GLKKOHHCIPJRSRCAOOQ2UU3QSU/action/replication_record"}},"created_at":"2026-07-05T02:44:47.161849+00:00","updated_at":"2026-07-05T02:44:47.161849+00:00"}