{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PFAMHAVDQRXE4AV3YVI56U5FRG","short_pith_number":"pith:PFAMHAVD","canonical_record":{"source":{"id":"1708.00185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-01T07:14:36Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"0ce52fec8a3ecf985de46145380ce8276d0b587e414138a74402f617e0a2e03e","abstract_canon_sha256":"db97a9bceb18e0613e0b92e87bfdb68de4b488a590a241c8751f5958c7daa2e4"},"schema_version":"1.0"},"canonical_sha256":"7940c382a3846e4e02bbc551df53a5899a2ed487740fc6d219846ee03a97edf2","source":{"kind":"arxiv","id":"1708.00185","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00185","created_at":"2026-05-18T00:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00185v1","created_at":"2026-05-18T00:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00185","created_at":"2026-05-18T00:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"PFAMHAVDQRXE","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PFAMHAVDQRXE4AV3","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PFAMHAVD","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PFAMHAVDQRXE4AV3YVI56U5FRG","target":"record","payload":{"canonical_record":{"source":{"id":"1708.00185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-01T07:14:36Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"0ce52fec8a3ecf985de46145380ce8276d0b587e414138a74402f617e0a2e03e","abstract_canon_sha256":"db97a9bceb18e0613e0b92e87bfdb68de4b488a590a241c8751f5958c7daa2e4"},"schema_version":"1.0"},"canonical_sha256":"7940c382a3846e4e02bbc551df53a5899a2ed487740fc6d219846ee03a97edf2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:05.866071Z","signature_b64":"hfUzlG7oALDBVAtFAdmxA4oaBsNCG8mkhg+z+OA1e9wY0k/9X9coMCnr1G0LfyRTDEsrwBnuNxXZn4QPWhwnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7940c382a3846e4e02bbc551df53a5899a2ed487740fc6d219846ee03a97edf2","last_reissued_at":"2026-05-18T00:39:05.865443Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:05.865443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.00185","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":"2026-05-18T00:39:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"avmf7ESRghPfcE2JAP2NGy300tGzRDDOxTsObGOefc8qFvQQlxjKjSIwFvktGN62QHcl9MKFvyO+dALBDfDACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:34:14.572865Z"},"content_sha256":"8a104a9c43cec511fe47ad12afb215629469b999eebcb5d80c44bd76e2f47c9d","schema_version":"1.0","event_id":"sha256:8a104a9c43cec511fe47ad12afb215629469b999eebcb5d80c44bd76e2f47c9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PFAMHAVDQRXE4AV3YVI56U5FRG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tensorial Recurrent Neural Networks for Longitudinal Data Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Boyan Zhang, Junbin Gao, Mingyuan Bai","submitted_at":"2017-08-01T07:14:36Z","abstract_excerpt":"Traditional Recurrent Neural Networks assume vectorized data as inputs. However many data from modern science and technology come in certain structures such as tensorial time series data. To apply the recurrent neural networks for this type of data, a vectorisation process is necessary, while such a vectorisation leads to the loss of the precise information of the spatial or longitudinal dimensions. In addition, such a vectorized data is not an optimum solution for learning the representation of the longitudinal data. In this paper, we propose a new variant of tensorial neural networks which d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00185","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":"2026-05-18T00:39:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oj8BIloVGoRBxDWpYk8DQCPaR7hH5bAlwwO7wxvBcEG0xxWj4LMHaGlu0R8EyW8ZhkXK/8znlrQ1bd6cyoOfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:34:14.573213Z"},"content_sha256":"52e76a6696f619b9ac4413f60ce429392f53e8587cf407d246d318e568f7e0aa","schema_version":"1.0","event_id":"sha256:52e76a6696f619b9ac4413f60ce429392f53e8587cf407d246d318e568f7e0aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PFAMHAVDQRXE4AV3YVI56U5FRG/bundle.json","state_url":"https://pith.science/pith/PFAMHAVDQRXE4AV3YVI56U5FRG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PFAMHAVDQRXE4AV3YVI56U5FRG/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":"2026-05-30T18:34:14Z","links":{"resolver":"https://pith.science/pith/PFAMHAVDQRXE4AV3YVI56U5FRG","bundle":"https://pith.science/pith/PFAMHAVDQRXE4AV3YVI56U5FRG/bundle.json","state":"https://pith.science/pith/PFAMHAVDQRXE4AV3YVI56U5FRG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PFAMHAVDQRXE4AV3YVI56U5FRG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PFAMHAVDQRXE4AV3YVI56U5FRG","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":"db97a9bceb18e0613e0b92e87bfdb68de4b488a590a241c8751f5958c7daa2e4","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-01T07:14:36Z","title_canon_sha256":"0ce52fec8a3ecf985de46145380ce8276d0b587e414138a74402f617e0a2e03e"},"schema_version":"1.0","source":{"id":"1708.00185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00185","created_at":"2026-05-18T00:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00185v1","created_at":"2026-05-18T00:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00185","created_at":"2026-05-18T00:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"PFAMHAVDQRXE","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PFAMHAVDQRXE4AV3","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PFAMHAVD","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:52e76a6696f619b9ac4413f60ce429392f53e8587cf407d246d318e568f7e0aa","target":"graph","created_at":"2026-05-18T00:39:05Z","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":"Traditional Recurrent Neural Networks assume vectorized data as inputs. However many data from modern science and technology come in certain structures such as tensorial time series data. To apply the recurrent neural networks for this type of data, a vectorisation process is necessary, while such a vectorisation leads to the loss of the precise information of the spatial or longitudinal dimensions. In addition, such a vectorized data is not an optimum solution for learning the representation of the longitudinal data. In this paper, we propose a new variant of tensorial neural networks which d","authors_text":"Boyan Zhang, Junbin Gao, Mingyuan Bai","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-01T07:14:36Z","title":"Tensorial Recurrent Neural Networks for Longitudinal Data Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00185","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":"sha256:8a104a9c43cec511fe47ad12afb215629469b999eebcb5d80c44bd76e2f47c9d","target":"record","created_at":"2026-05-18T00:39:05Z","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":"db97a9bceb18e0613e0b92e87bfdb68de4b488a590a241c8751f5958c7daa2e4","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-01T07:14:36Z","title_canon_sha256":"0ce52fec8a3ecf985de46145380ce8276d0b587e414138a74402f617e0a2e03e"},"schema_version":"1.0","source":{"id":"1708.00185","kind":"arxiv","version":1}},"canonical_sha256":"7940c382a3846e4e02bbc551df53a5899a2ed487740fc6d219846ee03a97edf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7940c382a3846e4e02bbc551df53a5899a2ed487740fc6d219846ee03a97edf2","first_computed_at":"2026-05-18T00:39:05.865443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:05.865443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hfUzlG7oALDBVAtFAdmxA4oaBsNCG8mkhg+z+OA1e9wY0k/9X9coMCnr1G0LfyRTDEsrwBnuNxXZn4QPWhwnAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:05.866071Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.00185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a104a9c43cec511fe47ad12afb215629469b999eebcb5d80c44bd76e2f47c9d","sha256:52e76a6696f619b9ac4413f60ce429392f53e8587cf407d246d318e568f7e0aa"],"state_sha256":"1ca312edd8a35e6bf2045b0fdaed4246e9ce6c40fe6f12c299f25937b1964f14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wb7/wOJzy0e/ZWxlV5n16jrPwmPdib3vpMUmHbzF7kJllXfsNBgfmGl2N4E9ln0vlARgS0f0STNoS7id+C6iAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T18:34:14.575680Z","bundle_sha256":"7d1382500b1bc56b0e1d105d2a64e7e13b5abbed23296c9fbd0049719a562513"}}