{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2O7FU2EHNVSIJHZ3ZT3SXNBJYN","short_pith_number":"pith:2O7FU2EH","canonical_record":{"source":{"id":"1811.02656","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-31T11:22:54Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"eac4c7f181a6d3aadd66a68cd9ae0515b6cae8d8b247c7c259fc00ff5b70f256","abstract_canon_sha256":"a331ab3d849677c3a1ec7cf98c294c3d2fbdd4cf5858a02ad6e2310f30cd2518"},"schema_version":"1.0"},"canonical_sha256":"d3be5a68876d64849f3bccf72bb429c365ebd695853d7141f28d47e0b787cae7","source":{"kind":"arxiv","id":"1811.02656","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02656","created_at":"2026-05-18T00:01:21Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02656v1","created_at":"2026-05-18T00:01:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02656","created_at":"2026-05-18T00:01:21Z"},{"alias_kind":"pith_short_12","alias_value":"2O7FU2EHNVSI","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2O7FU2EHNVSIJHZ3","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2O7FU2EH","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2O7FU2EHNVSIJHZ3ZT3SXNBJYN","target":"record","payload":{"canonical_record":{"source":{"id":"1811.02656","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-31T11:22:54Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"eac4c7f181a6d3aadd66a68cd9ae0515b6cae8d8b247c7c259fc00ff5b70f256","abstract_canon_sha256":"a331ab3d849677c3a1ec7cf98c294c3d2fbdd4cf5858a02ad6e2310f30cd2518"},"schema_version":"1.0"},"canonical_sha256":"d3be5a68876d64849f3bccf72bb429c365ebd695853d7141f28d47e0b787cae7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:21.121052Z","signature_b64":"jJyOHK1WFFwR8QABwUAHeh6QuuNuRj2HpQABSco9a4V5OJJ0FPkvIDgY5C51yNKkzyNS6tcOCkf3gafsTllyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3be5a68876d64849f3bccf72bb429c365ebd695853d7141f28d47e0b787cae7","last_reissued_at":"2026-05-18T00:01:21.120608Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:21.120608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.02656","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mjlP2slVZoUYAK/pKvdtF7q7wbGmxjx+tg67OwRQLgV1Pp/CzbwRm1guxpxGi4iyEbFGI3sLtfK8zR8s4rhHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:46:21.671126Z"},"content_sha256":"12b18df050316e9378d0bcd841e8edd65708a3cc7895b2a40b16e36a2e5ec461","schema_version":"1.0","event_id":"sha256:12b18df050316e9378d0bcd841e8edd65708a3cc7895b2a40b16e36a2e5ec461"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2O7FU2EHNVSIJHZ3ZT3SXNBJYN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quaternion Convolutional Neural Networks for Heterogeneous Image Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Georges Linar\\`es, Mohamed Morchid, Titouan Parcollet","submitted_at":"2018-10-31T11:22:54Z","abstract_excerpt":"Convolutional neural networks (CNN) have recently achieved state-of-the-art results in various applications. In the case of image recognition, an ideal model has to learn independently of the training data, both local dependencies between the three components (R,G,B) of a pixel, and the global relations describing edges or shapes, making it efficient with small or heterogeneous datasets. Quaternion-valued convolutional neural networks (QCNN) solved this problematic by introducing multidimensional algebra to CNN. This paper proposes to explore the fundamental reason of the success of QCNN over "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02656","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":""},"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":"2026-05-18T00:01:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JjlMLNUZJsEZoa7PtndvdqHOol8JUN7KpFfLskzZ2Geaqw8tklde/EP1LwEI3AE3jz7rfR372jUkocHdyHf1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:46:21.671696Z"},"content_sha256":"45444a1448b4bd250aa1f694c5283c77bb59a881bf4d96a7db933bac5567a0e3","schema_version":"1.0","event_id":"sha256:45444a1448b4bd250aa1f694c5283c77bb59a881bf4d96a7db933bac5567a0e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2O7FU2EHNVSIJHZ3ZT3SXNBJYN/bundle.json","state_url":"https://pith.science/pith/2O7FU2EHNVSIJHZ3ZT3SXNBJYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2O7FU2EHNVSIJHZ3ZT3SXNBJYN/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":"2026-05-28T18:46:21Z","links":{"resolver":"https://pith.science/pith/2O7FU2EHNVSIJHZ3ZT3SXNBJYN","bundle":"https://pith.science/pith/2O7FU2EHNVSIJHZ3ZT3SXNBJYN/bundle.json","state":"https://pith.science/pith/2O7FU2EHNVSIJHZ3ZT3SXNBJYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2O7FU2EHNVSIJHZ3ZT3SXNBJYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2O7FU2EHNVSIJHZ3ZT3SXNBJYN","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":"a331ab3d849677c3a1ec7cf98c294c3d2fbdd4cf5858a02ad6e2310f30cd2518","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-31T11:22:54Z","title_canon_sha256":"eac4c7f181a6d3aadd66a68cd9ae0515b6cae8d8b247c7c259fc00ff5b70f256"},"schema_version":"1.0","source":{"id":"1811.02656","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02656","created_at":"2026-05-18T00:01:21Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02656v1","created_at":"2026-05-18T00:01:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02656","created_at":"2026-05-18T00:01:21Z"},{"alias_kind":"pith_short_12","alias_value":"2O7FU2EHNVSI","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2O7FU2EHNVSIJHZ3","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2O7FU2EH","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:45444a1448b4bd250aa1f694c5283c77bb59a881bf4d96a7db933bac5567a0e3","target":"graph","created_at":"2026-05-18T00:01:21Z","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"},"paper":{"abstract_excerpt":"Convolutional neural networks (CNN) have recently achieved state-of-the-art results in various applications. In the case of image recognition, an ideal model has to learn independently of the training data, both local dependencies between the three components (R,G,B) of a pixel, and the global relations describing edges or shapes, making it efficient with small or heterogeneous datasets. Quaternion-valued convolutional neural networks (QCNN) solved this problematic by introducing multidimensional algebra to CNN. This paper proposes to explore the fundamental reason of the success of QCNN over ","authors_text":"Georges Linar\\`es, Mohamed Morchid, Titouan Parcollet","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-31T11:22:54Z","title":"Quaternion Convolutional Neural Networks for Heterogeneous Image Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02656","kind":"arxiv","version":1},"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":"sha256:12b18df050316e9378d0bcd841e8edd65708a3cc7895b2a40b16e36a2e5ec461","target":"record","created_at":"2026-05-18T00:01:21Z","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":"a331ab3d849677c3a1ec7cf98c294c3d2fbdd4cf5858a02ad6e2310f30cd2518","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-31T11:22:54Z","title_canon_sha256":"eac4c7f181a6d3aadd66a68cd9ae0515b6cae8d8b247c7c259fc00ff5b70f256"},"schema_version":"1.0","source":{"id":"1811.02656","kind":"arxiv","version":1}},"canonical_sha256":"d3be5a68876d64849f3bccf72bb429c365ebd695853d7141f28d47e0b787cae7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3be5a68876d64849f3bccf72bb429c365ebd695853d7141f28d47e0b787cae7","first_computed_at":"2026-05-18T00:01:21.120608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:21.120608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jJyOHK1WFFwR8QABwUAHeh6QuuNuRj2HpQABSco9a4V5OJJ0FPkvIDgY5C51yNKkzyNS6tcOCkf3gafsTllyBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:21.121052Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.02656","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12b18df050316e9378d0bcd841e8edd65708a3cc7895b2a40b16e36a2e5ec461","sha256:45444a1448b4bd250aa1f694c5283c77bb59a881bf4d96a7db933bac5567a0e3"],"state_sha256":"8e820f05687362d4471105d91d2e81d9c49831f10f7e42336a97eaf0e2207e11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q/PgZe6ocozh3r1Dc+LA+r9H+xuWwjWHLstYGamM+A40iPwrKTNKCrBUc68A6/QFRcdjQD3yDTuponf5/B5WBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T18:46:21.674379Z","bundle_sha256":"e3712c2022b343caa6c31fd08ac6d4d0e4d038f0282e19e0607b1d1b4ac029e9"}}