{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RHPS5K6Q2T3H4JIURFHNRBDL5Q","short_pith_number":"pith:RHPS5K6Q","schema_version":"1.0","canonical_sha256":"89df2eabd0d4f67e2514894ed8846bec27b370ffe06e4c05681cfe920c837f1b","source":{"kind":"arxiv","id":"2412.14695","version":2},"attestation_state":"computed","paper":{"title":"Lorentzian Residual Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Menglin Yang, Neil He, Rex Ying","submitted_at":"2024-12-19T09:56:01Z","abstract_excerpt":"Hyperbolic neural networks have emerged as a powerful tool for modeling hierarchical data structures prevalent in real-world datasets. Notably, residual connections, which facilitate the direct flow of information across layers, have been instrumental in the success of deep neural networks. However, current methods for constructing hyperbolic residual networks suffer from limitations such as increased model complexity, numerical instability, and errors due to multiple mappings to and from the tangent space. To address these limitations, we introduce LResNet, a novel Lorentzian residual neural "},"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":"2412.14695","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T09:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"f968fc7dc9fa5058b00e73caa48112482e9cd946fe198128fc14cd34ac4da433","abstract_canon_sha256":"6557abc872767da6f67df927549c02d60e5636e14295a549b919bc66ac5e5dbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:57.421654Z","signature_b64":"pVsTvDEYkdZRSB9MFKzT6ymyJeH7MDOBGjENlqutc43ILhPKVx2Ai7ZR/ImlUwSH0ushdB/d17TcpZvgFPoFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89df2eabd0d4f67e2514894ed8846bec27b370ffe06e4c05681cfe920c837f1b","last_reissued_at":"2026-07-05T09:59:57.421256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:57.421256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lorentzian Residual Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Menglin Yang, Neil He, Rex Ying","submitted_at":"2024-12-19T09:56:01Z","abstract_excerpt":"Hyperbolic neural networks have emerged as a powerful tool for modeling hierarchical data structures prevalent in real-world datasets. Notably, residual connections, which facilitate the direct flow of information across layers, have been instrumental in the success of deep neural networks. However, current methods for constructing hyperbolic residual networks suffer from limitations such as increased model complexity, numerical instability, and errors due to multiple mappings to and from the tangent space. To address these limitations, we introduce LResNet, a novel Lorentzian residual neural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14695","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.14695/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":"2412.14695","created_at":"2026-07-05T09:59:57.421312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14695v2","created_at":"2026-07-05T09:59:57.421312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14695","created_at":"2026-07-05T09:59:57.421312+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHPS5K6Q2T3H","created_at":"2026-07-05T09:59:57.421312+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHPS5K6Q2T3H4JIU","created_at":"2026-07-05T09:59:57.421312+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHPS5K6Q","created_at":"2026-07-05T09:59:57.421312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17402","citing_title":"HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHPS5K6Q2T3H4JIURFHNRBDL5Q","json":"https://pith.science/pith/RHPS5K6Q2T3H4JIURFHNRBDL5Q.json","graph_json":"https://pith.science/api/pith-number/RHPS5K6Q2T3H4JIURFHNRBDL5Q/graph.json","events_json":"https://pith.science/api/pith-number/RHPS5K6Q2T3H4JIURFHNRBDL5Q/events.json","paper":"https://pith.science/paper/RHPS5K6Q"},"agent_actions":{"view_html":"https://pith.science/pith/RHPS5K6Q2T3H4JIURFHNRBDL5Q","download_json":"https://pith.science/pith/RHPS5K6Q2T3H4JIURFHNRBDL5Q.json","view_paper":"https://pith.science/paper/RHPS5K6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14695&json=true","fetch_graph":"https://pith.science/api/pith-number/RHPS5K6Q2T3H4JIURFHNRBDL5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/RHPS5K6Q2T3H4JIURFHNRBDL5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHPS5K6Q2T3H4JIURFHNRBDL5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHPS5K6Q2T3H4JIURFHNRBDL5Q/action/storage_attestation","attest_author":"https://pith.science/pith/RHPS5K6Q2T3H4JIURFHNRBDL5Q/action/author_attestation","sign_citation":"https://pith.science/pith/RHPS5K6Q2T3H4JIURFHNRBDL5Q/action/citation_signature","submit_replication":"https://pith.science/pith/RHPS5K6Q2T3H4JIURFHNRBDL5Q/action/replication_record"}},"created_at":"2026-07-05T09:59:57.421312+00:00","updated_at":"2026-07-05T09:59:57.421312+00:00"}