{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5ENQSICG6LNLNFBAPVJYVAPJVT","short_pith_number":"pith:5ENQSICG","canonical_record":{"source":{"id":"1806.04418","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T09:49:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48df7f55e00d64db6b33cb2ee434f5c518d988423595677bbb9ed0ecd7cd17bc","abstract_canon_sha256":"6b27b6de6d4260bff8a548b31537eb2d20685bf9e4fec9150b42e51c40c0b42f"},"schema_version":"1.0"},"canonical_sha256":"e91b092046f2dab694207d538a81e9accd85e41602f5ec4f46363a973b42a684","source":{"kind":"arxiv","id":"1806.04418","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04418","created_at":"2026-05-17T23:56:53Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04418v3","created_at":"2026-05-17T23:56:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04418","created_at":"2026-05-17T23:56:53Z"},{"alias_kind":"pith_short_12","alias_value":"5ENQSICG6LNL","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5ENQSICG6LNLNFBA","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5ENQSICG","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5ENQSICG6LNLNFBAPVJYVAPJVT","target":"record","payload":{"canonical_record":{"source":{"id":"1806.04418","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T09:49:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48df7f55e00d64db6b33cb2ee434f5c518d988423595677bbb9ed0ecd7cd17bc","abstract_canon_sha256":"6b27b6de6d4260bff8a548b31537eb2d20685bf9e4fec9150b42e51c40c0b42f"},"schema_version":"1.0"},"canonical_sha256":"e91b092046f2dab694207d538a81e9accd85e41602f5ec4f46363a973b42a684","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:53.289760Z","signature_b64":"Fgm/c1SRMd1c9Fq9mQNUC1xInZRgCpb7w21Jvix9hJ9kuuRfmIh7Oz3qKi3DcCazeu4IGLG0MiWHilONbSx3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e91b092046f2dab694207d538a81e9accd85e41602f5ec4f46363a973b42a684","last_reissued_at":"2026-05-17T23:56:53.289399Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:53.289399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.04418","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":"2026-05-17T23:56:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lA0IQMdg42IKrFhPC+HKVOe95w745htAW+d0hFKEpaostd9zY491t5z/3AVfpImELS6jGrkNInbHhOkGHO8ZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T18:47:28.762156Z"},"content_sha256":"c2f71a344e4abda3bd4188691413ae470bb4bfc05c7609d6a1a472fb2d43a19d","schema_version":"1.0","event_id":"sha256:c2f71a344e4abda3bd4188691413ae470bb4bfc05c7609d6a1a472fb2d43a19d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5ENQSICG6LNLNFBAPVJYVAPJVT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quaternion Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chiheb Trabelsi, Georges Linar\\`es, Mirco Ravanelli, Mohamed Morchid, Renato De Mori, Titouan Parcollet, Yoshua Bengio","submitted_at":"2018-06-12T09:49:40Z","abstract_excerpt":"Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or images recognition, involve multi-dimensional input features that are characterized by strong internal dependencies between the dimensions of the input vector. We propose a novel quaternion recurrent neural network (QRNN), alongside with a quaternion long-short term memory neural network (QLSTM), that take into account both the external relations and these in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04418","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":""},"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":"2026-05-17T23:56:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v75kBtWR7O9kq2VyUIJw77waAIvhTFStwirRdYzHuayRAiooTkv4HornHYEr9+fnu8T7/6CecJ5fsoIn/2ysCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T18:47:28.762530Z"},"content_sha256":"290ceb69ec90544626242b5b8c9b247f327088c88f8266d43d53e29141f9d378","schema_version":"1.0","event_id":"sha256:290ceb69ec90544626242b5b8c9b247f327088c88f8266d43d53e29141f9d378"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ENQSICG6LNLNFBAPVJYVAPJVT/bundle.json","state_url":"https://pith.science/pith/5ENQSICG6LNLNFBAPVJYVAPJVT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ENQSICG6LNLNFBAPVJYVAPJVT/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":"2026-05-21T18:47:28Z","links":{"resolver":"https://pith.science/pith/5ENQSICG6LNLNFBAPVJYVAPJVT","bundle":"https://pith.science/pith/5ENQSICG6LNLNFBAPVJYVAPJVT/bundle.json","state":"https://pith.science/pith/5ENQSICG6LNLNFBAPVJYVAPJVT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ENQSICG6LNLNFBAPVJYVAPJVT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5ENQSICG6LNLNFBAPVJYVAPJVT","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":"6b27b6de6d4260bff8a548b31537eb2d20685bf9e4fec9150b42e51c40c0b42f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T09:49:40Z","title_canon_sha256":"48df7f55e00d64db6b33cb2ee434f5c518d988423595677bbb9ed0ecd7cd17bc"},"schema_version":"1.0","source":{"id":"1806.04418","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04418","created_at":"2026-05-17T23:56:53Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04418v3","created_at":"2026-05-17T23:56:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04418","created_at":"2026-05-17T23:56:53Z"},{"alias_kind":"pith_short_12","alias_value":"5ENQSICG6LNL","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5ENQSICG6LNLNFBA","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5ENQSICG","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:290ceb69ec90544626242b5b8c9b247f327088c88f8266d43d53e29141f9d378","target":"graph","created_at":"2026-05-17T23:56:53Z","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":"Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or images recognition, involve multi-dimensional input features that are characterized by strong internal dependencies between the dimensions of the input vector. We propose a novel quaternion recurrent neural network (QRNN), alongside with a quaternion long-short term memory neural network (QLSTM), that take into account both the external relations and these in","authors_text":"Chiheb Trabelsi, Georges Linar\\`es, Mirco Ravanelli, Mohamed Morchid, Renato De Mori, Titouan Parcollet, Yoshua Bengio","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T09:49:40Z","title":"Quaternion Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04418","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:c2f71a344e4abda3bd4188691413ae470bb4bfc05c7609d6a1a472fb2d43a19d","target":"record","created_at":"2026-05-17T23:56:53Z","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":"6b27b6de6d4260bff8a548b31537eb2d20685bf9e4fec9150b42e51c40c0b42f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T09:49:40Z","title_canon_sha256":"48df7f55e00d64db6b33cb2ee434f5c518d988423595677bbb9ed0ecd7cd17bc"},"schema_version":"1.0","source":{"id":"1806.04418","kind":"arxiv","version":3}},"canonical_sha256":"e91b092046f2dab694207d538a81e9accd85e41602f5ec4f46363a973b42a684","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e91b092046f2dab694207d538a81e9accd85e41602f5ec4f46363a973b42a684","first_computed_at":"2026-05-17T23:56:53.289399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:53.289399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fgm/c1SRMd1c9Fq9mQNUC1xInZRgCpb7w21Jvix9hJ9kuuRfmIh7Oz3qKi3DcCazeu4IGLG0MiWHilONbSx3BA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:53.289760Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.04418","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2f71a344e4abda3bd4188691413ae470bb4bfc05c7609d6a1a472fb2d43a19d","sha256:290ceb69ec90544626242b5b8c9b247f327088c88f8266d43d53e29141f9d378"],"state_sha256":"a6cd11652d29fbba54f8cc0f031b39ff5f2c119c4ce7ee1f3ff11234ed7c553e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1adCPzPN8AqNmc8p5DPFhxpQyxkpucpRlovUeFIM/Nik5BoCA5u+gvTy7Jtc3k7ZzLYf1S6fpro4w4taNXvCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T18:47:28.764630Z","bundle_sha256":"bc7bbb73f4b3eca0a83c2656f70339d8a39a7fc8767ffe192824f973f852d880"}}