{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VRN2AWJFCAGEFTLVYAKVSN7F37","short_pith_number":"pith:VRN2AWJF","schema_version":"1.0","canonical_sha256":"ac5ba05925100c42cd75c0155937e5dfcdbe853d5700949622830498847e9e14","source":{"kind":"arxiv","id":"2607.19305","version":1},"attestation_state":"computed","paper":{"title":"Riemannian Deep Learning:Modules, Networks, and Geometries","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","math.DG"],"primary_cat":"cs.LG","authors_text":"Chen Ziheng","submitted_at":"2026-07-21T17:17:35Z","abstract_excerpt":"Deep neural networks on manifold-valued representations have attracted growing interest, but many basic components remain tied to specific manifolds, rely on Euclidean approximations, or require costly and numerically fragile geometric operations. This thesis develops a unified framework for Riemannian deep learning from three complementary perspectives: reusable neural modules, manifold-specific network architectures, and the design of underlying geometries. It generalizes batch normalization from Euclidean spaces and individual manifolds to broad classes of Lie groups and gyrogroups, and ext"},"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":"2607.19305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T17:17:35Z","cross_cats_sorted":["cs.AI","math.DG"],"title_canon_sha256":"d401858e15ee816b28fe79675689ba8b668ed4b559c1339c92a49bba42c720c7","abstract_canon_sha256":"4e19eb50a157fca6a26c2c5f70b360c0878339f4a1599edfca2ae06e818e0590"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:24:35.585230Z","signature_b64":"qeAs904n8aicHVJ6gxK+06l+s2CQyHDII9WmphEDtlpazWU3ZTB1ffOs7Rf3o1HdcvIbX4r9xpDsl7tI+5B8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac5ba05925100c42cd75c0155937e5dfcdbe853d5700949622830498847e9e14","last_reissued_at":"2026-07-22T01:24:35.584388Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:24:35.584388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Riemannian Deep Learning:Modules, Networks, and Geometries","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","math.DG"],"primary_cat":"cs.LG","authors_text":"Chen Ziheng","submitted_at":"2026-07-21T17:17:35Z","abstract_excerpt":"Deep neural networks on manifold-valued representations have attracted growing interest, but many basic components remain tied to specific manifolds, rely on Euclidean approximations, or require costly and numerically fragile geometric operations. This thesis develops a unified framework for Riemannian deep learning from three complementary perspectives: reusable neural modules, manifold-specific network architectures, and the design of underlying geometries. It generalizes batch normalization from Euclidean spaces and individual manifolds to broad classes of Lie groups and gyrogroups, and ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19305","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/2607.19305/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":"2607.19305","created_at":"2026-07-22T01:24:35.584840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19305v1","created_at":"2026-07-22T01:24:35.584840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19305","created_at":"2026-07-22T01:24:35.584840+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRN2AWJFCAGE","created_at":"2026-07-22T01:24:35.584840+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRN2AWJFCAGEFTLV","created_at":"2026-07-22T01:24:35.584840+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRN2AWJF","created_at":"2026-07-22T01:24:35.584840+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/VRN2AWJFCAGEFTLVYAKVSN7F37","json":"https://pith.science/pith/VRN2AWJFCAGEFTLVYAKVSN7F37.json","graph_json":"https://pith.science/api/pith-number/VRN2AWJFCAGEFTLVYAKVSN7F37/graph.json","events_json":"https://pith.science/api/pith-number/VRN2AWJFCAGEFTLVYAKVSN7F37/events.json","paper":"https://pith.science/paper/VRN2AWJF"},"agent_actions":{"view_html":"https://pith.science/pith/VRN2AWJFCAGEFTLVYAKVSN7F37","download_json":"https://pith.science/pith/VRN2AWJFCAGEFTLVYAKVSN7F37.json","view_paper":"https://pith.science/paper/VRN2AWJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19305&json=true","fetch_graph":"https://pith.science/api/pith-number/VRN2AWJFCAGEFTLVYAKVSN7F37/graph.json","fetch_events":"https://pith.science/api/pith-number/VRN2AWJFCAGEFTLVYAKVSN7F37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRN2AWJFCAGEFTLVYAKVSN7F37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRN2AWJFCAGEFTLVYAKVSN7F37/action/storage_attestation","attest_author":"https://pith.science/pith/VRN2AWJFCAGEFTLVYAKVSN7F37/action/author_attestation","sign_citation":"https://pith.science/pith/VRN2AWJFCAGEFTLVYAKVSN7F37/action/citation_signature","submit_replication":"https://pith.science/pith/VRN2AWJFCAGEFTLVYAKVSN7F37/action/replication_record"}},"created_at":"2026-07-22T01:24:35.584840+00:00","updated_at":"2026-07-22T01:24:35.584840+00:00"}