{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OVQVXXGMPSYETRRG7SD4ZFUH25","short_pith_number":"pith:OVQVXXGM","canonical_record":{"source":{"id":"2303.15919","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T12:20:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6dc754b7ab2e10dc94aca931b061edd1024fbf01ae9c5c29a9ff3add6a0f9030","abstract_canon_sha256":"ad8d7151b2de3aa4be63590454d4e40cf8f0cdc652ba2ef45bf92fe4c545c24b"},"schema_version":"1.0"},"canonical_sha256":"75615bdccc7cb049c626fc87cc9687d7791ef494553e297279becd023ba2a66b","source":{"kind":"arxiv","id":"2303.15919","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15919","created_at":"2026-07-05T07:42:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15919v3","created_at":"2026-07-05T07:42:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15919","created_at":"2026-07-05T07:42:16Z"},{"alias_kind":"pith_short_12","alias_value":"OVQVXXGMPSYE","created_at":"2026-07-05T07:42:16Z"},{"alias_kind":"pith_short_16","alias_value":"OVQVXXGMPSYETRRG","created_at":"2026-07-05T07:42:16Z"},{"alias_kind":"pith_short_8","alias_value":"OVQVXXGM","created_at":"2026-07-05T07:42:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OVQVXXGMPSYETRRG7SD4ZFUH25","target":"record","payload":{"canonical_record":{"source":{"id":"2303.15919","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T12:20:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6dc754b7ab2e10dc94aca931b061edd1024fbf01ae9c5c29a9ff3add6a0f9030","abstract_canon_sha256":"ad8d7151b2de3aa4be63590454d4e40cf8f0cdc652ba2ef45bf92fe4c545c24b"},"schema_version":"1.0"},"canonical_sha256":"75615bdccc7cb049c626fc87cc9687d7791ef494553e297279becd023ba2a66b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:16.753006Z","signature_b64":"3MPliK1aLd4Qru8zgy6oaEZ2YKElw4MZ6OZtLmqovvV2rm/8SKkgCPRSNSbDNQ+TGa7nDioow7KnHnvijrewAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75615bdccc7cb049c626fc87cc9687d7791ef494553e297279becd023ba2a66b","last_reissued_at":"2026-07-05T07:42:16.752553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:16.752553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.15919","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:42:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXFoMWJjCYuA2A6s/JBtaL7E7xRb/4yczSdCjhVuFdINGBkExXsyeB7vG+YNbcBtW7BUssLOMS2EF3qA+3/KBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:15:25.152124Z"},"content_sha256":"081e095ad5d52093098d277ec8aedb6cf11540f5acd88db6517a0eb09aaa30f4","schema_version":"1.0","event_id":"sha256:081e095ad5d52093098d277ec8aedb6cf11540f5acd88db6517a0eb09aaa30f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OVQVXXGMPSYETRRG7SD4ZFUH25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fully Hyperbolic Convolutional Neural Networks for Computer Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ahmad Bdeir, Kristian Schwethelm, Niels Landwehr","submitted_at":"2023-03-28T12:20:52Z","abstract_excerpt":"Real-world visual data exhibit intrinsic hierarchical structures that can be represented effectively in hyperbolic spaces. Hyperbolic neural networks (HNNs) are a promising approach for learning feature representations in such spaces. However, current HNNs in computer vision rely on Euclidean backbones and only project features to the hyperbolic space in the task heads, limiting their ability to fully leverage the benefits of hyperbolic geometry. To address this, we present HCNN, a fully hyperbolic convolutional neural network (CNN) designed for computer vision tasks. Based on the Lorentz mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15919","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/2303.15919/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:42:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vIVioHDHW/5tZJbGqx+kDqSMdfdFMpXmj6jyIvw0HdFs3bjlZL00UpGVQdCQCsyMQcoF0mxr1p+kJKzsmzvjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:15:25.152646Z"},"content_sha256":"857214a231b3c9f94bc0ba6a0c2d5fb7c8ee8081aeaee9bab4a004487b78a2c2","schema_version":"1.0","event_id":"sha256:857214a231b3c9f94bc0ba6a0c2d5fb7c8ee8081aeaee9bab4a004487b78a2c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OVQVXXGMPSYETRRG7SD4ZFUH25/bundle.json","state_url":"https://pith.science/pith/OVQVXXGMPSYETRRG7SD4ZFUH25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OVQVXXGMPSYETRRG7SD4ZFUH25/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T04:15:25Z","links":{"resolver":"https://pith.science/pith/OVQVXXGMPSYETRRG7SD4ZFUH25","bundle":"https://pith.science/pith/OVQVXXGMPSYETRRG7SD4ZFUH25/bundle.json","state":"https://pith.science/pith/OVQVXXGMPSYETRRG7SD4ZFUH25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OVQVXXGMPSYETRRG7SD4ZFUH25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OVQVXXGMPSYETRRG7SD4ZFUH25","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ad8d7151b2de3aa4be63590454d4e40cf8f0cdc652ba2ef45bf92fe4c545c24b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T12:20:52Z","title_canon_sha256":"6dc754b7ab2e10dc94aca931b061edd1024fbf01ae9c5c29a9ff3add6a0f9030"},"schema_version":"1.0","source":{"id":"2303.15919","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15919","created_at":"2026-07-05T07:42:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15919v3","created_at":"2026-07-05T07:42:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15919","created_at":"2026-07-05T07:42:16Z"},{"alias_kind":"pith_short_12","alias_value":"OVQVXXGMPSYE","created_at":"2026-07-05T07:42:16Z"},{"alias_kind":"pith_short_16","alias_value":"OVQVXXGMPSYETRRG","created_at":"2026-07-05T07:42:16Z"},{"alias_kind":"pith_short_8","alias_value":"OVQVXXGM","created_at":"2026-07-05T07:42:16Z"}],"graph_snapshots":[{"event_id":"sha256:857214a231b3c9f94bc0ba6a0c2d5fb7c8ee8081aeaee9bab4a004487b78a2c2","target":"graph","created_at":"2026-07-05T07:42:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.15919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world visual data exhibit intrinsic hierarchical structures that can be represented effectively in hyperbolic spaces. Hyperbolic neural networks (HNNs) are a promising approach for learning feature representations in such spaces. However, current HNNs in computer vision rely on Euclidean backbones and only project features to the hyperbolic space in the task heads, limiting their ability to fully leverage the benefits of hyperbolic geometry. To address this, we present HCNN, a fully hyperbolic convolutional neural network (CNN) designed for computer vision tasks. Based on the Lorentz mode","authors_text":"Ahmad Bdeir, Kristian Schwethelm, Niels Landwehr","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T12:20:52Z","title":"Fully Hyperbolic Convolutional Neural Networks for Computer Vision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15919","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:081e095ad5d52093098d277ec8aedb6cf11540f5acd88db6517a0eb09aaa30f4","target":"record","created_at":"2026-07-05T07:42:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ad8d7151b2de3aa4be63590454d4e40cf8f0cdc652ba2ef45bf92fe4c545c24b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T12:20:52Z","title_canon_sha256":"6dc754b7ab2e10dc94aca931b061edd1024fbf01ae9c5c29a9ff3add6a0f9030"},"schema_version":"1.0","source":{"id":"2303.15919","kind":"arxiv","version":3}},"canonical_sha256":"75615bdccc7cb049c626fc87cc9687d7791ef494553e297279becd023ba2a66b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75615bdccc7cb049c626fc87cc9687d7791ef494553e297279becd023ba2a66b","first_computed_at":"2026-07-05T07:42:16.752553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:16.752553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3MPliK1aLd4Qru8zgy6oaEZ2YKElw4MZ6OZtLmqovvV2rm/8SKkgCPRSNSbDNQ+TGa7nDioow7KnHnvijrewAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:16.753006Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.15919","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:081e095ad5d52093098d277ec8aedb6cf11540f5acd88db6517a0eb09aaa30f4","sha256:857214a231b3c9f94bc0ba6a0c2d5fb7c8ee8081aeaee9bab4a004487b78a2c2"],"state_sha256":"96f700dc0bb2e71f186e21a655d7c9d99476aa92a021e6f4bfdca5252c09fff1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FzOWrp7xh8Qu8LbETXCBYF4QzYreZriv5c37933oUDjQ+ngI7P90reh0HAWMyBpf74NcOdHd/u/I0QVJH/whCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:15:25.157869Z","bundle_sha256":"756ecb03f5305760a57ebf1a81789031ff707b2566c27f32bce4e7cab97c04ed"}}