{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:E5N4WQK7FHGTUOVLLWSWVXUBZH","short_pith_number":"pith:E5N4WQK7","canonical_record":{"source":{"id":"2306.03372","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-06-06T03:21:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2950efd9ba3050420754add4b7934deed46f4e3238135ed28c057d2a03cee8e3","abstract_canon_sha256":"3f3a103327b090f4bf08a8ab8ec16f54b82d986fe0426ca28172df3a5b1675d1"},"schema_version":"1.0"},"canonical_sha256":"275bcb415f29cd3a3aab5da56ade81c9ebfd9c27de3fc96d2dc3c58d754d155d","source":{"kind":"arxiv","id":"2306.03372","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03372","created_at":"2026-07-05T09:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03372v3","created_at":"2026-07-05T09:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03372","created_at":"2026-07-05T09:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"E5N4WQK7FHGT","created_at":"2026-07-05T09:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"E5N4WQK7FHGTUOVL","created_at":"2026-07-05T09:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"E5N4WQK7","created_at":"2026-07-05T09:23:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:E5N4WQK7FHGTUOVLLWSWVXUBZH","target":"record","payload":{"canonical_record":{"source":{"id":"2306.03372","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-06-06T03:21:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2950efd9ba3050420754add4b7934deed46f4e3238135ed28c057d2a03cee8e3","abstract_canon_sha256":"3f3a103327b090f4bf08a8ab8ec16f54b82d986fe0426ca28172df3a5b1675d1"},"schema_version":"1.0"},"canonical_sha256":"275bcb415f29cd3a3aab5da56ade81c9ebfd9c27de3fc96d2dc3c58d754d155d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:43.782968Z","signature_b64":"mQZ4vYOG7Zm80bnwMd5Fgg4m//RaOe7cbfNC9cdf64UK/imaOgANLbYA3twbCoqYQBYYlVYJYhpkF7BpE0mWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"275bcb415f29cd3a3aab5da56ade81c9ebfd9c27de3fc96d2dc3c58d754d155d","last_reissued_at":"2026-07-05T09:23:43.782463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:43.782463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.03372","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":"2026-07-05T09:23:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TRgCJv453d9QEwCmB3nxwX/TaVEGYBGzrLyzoJvyvVLKU3VzEpb7L4R2zTlniigPCITsXNj3NWKfM5AWYh8iAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:33:55.608886Z"},"content_sha256":"f13312d8e5fdd8eff092dd31f9e06bed7c43b06599f52032aa10ba6a13f2b4ad","schema_version":"1.0","event_id":"sha256:f13312d8e5fdd8eff092dd31f9e06bed7c43b06599f52032aa10ba6a13f2b4ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:E5N4WQK7FHGTUOVLLWSWVXUBZH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Tensor Learning: Computational and Statistical Trade-offs, Adaptivity and Optimal Regret","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dong Xia, Jian-Feng Cai, Jingyang Li, Yang Chen","submitted_at":"2023-06-06T03:21:28Z","abstract_excerpt":"Large tensor learning algorithms are typically computationally expensive and require storing a vast amount of data. In this paper, we propose a unified online Riemannian gradient descent (oRGrad) algorithm for tensor learning, which is computationally efficient, consumes much less memory, and can handle sequentially arriving data while making timely predictions. The algorithm is applicable to both linear and generalized linear models. If the time horizon T is known, oRGrad achieves statistical optimality by choosing an appropriate fixed step size. We find that noisy tensor completion particula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03372","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/2306.03372/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":"2026-07-05T09:23:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aq1A5R7btwX61OJrWhDNrPSyKgfEIXOEzguW+x91sq3PpZHfTG5fOrXp/eojjGwZh5iKFzauieqQ3U4pOg0FDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:33:55.611644Z"},"content_sha256":"e2f29d55e4a820c5c8d7fecb612d18b4231631de44d6a2f7a1df9cacf143aa40","schema_version":"1.0","event_id":"sha256:e2f29d55e4a820c5c8d7fecb612d18b4231631de44d6a2f7a1df9cacf143aa40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E5N4WQK7FHGTUOVLLWSWVXUBZH/bundle.json","state_url":"https://pith.science/pith/E5N4WQK7FHGTUOVLLWSWVXUBZH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E5N4WQK7FHGTUOVLLWSWVXUBZH/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":"2026-08-05T12:33:55Z","links":{"resolver":"https://pith.science/pith/E5N4WQK7FHGTUOVLLWSWVXUBZH","bundle":"https://pith.science/pith/E5N4WQK7FHGTUOVLLWSWVXUBZH/bundle.json","state":"https://pith.science/pith/E5N4WQK7FHGTUOVLLWSWVXUBZH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E5N4WQK7FHGTUOVLLWSWVXUBZH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E5N4WQK7FHGTUOVLLWSWVXUBZH","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":"3f3a103327b090f4bf08a8ab8ec16f54b82d986fe0426ca28172df3a5b1675d1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-06-06T03:21:28Z","title_canon_sha256":"2950efd9ba3050420754add4b7934deed46f4e3238135ed28c057d2a03cee8e3"},"schema_version":"1.0","source":{"id":"2306.03372","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03372","created_at":"2026-07-05T09:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03372v3","created_at":"2026-07-05T09:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03372","created_at":"2026-07-05T09:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"E5N4WQK7FHGT","created_at":"2026-07-05T09:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"E5N4WQK7FHGTUOVL","created_at":"2026-07-05T09:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"E5N4WQK7","created_at":"2026-07-05T09:23:43Z"}],"graph_snapshots":[{"event_id":"sha256:e2f29d55e4a820c5c8d7fecb612d18b4231631de44d6a2f7a1df9cacf143aa40","target":"graph","created_at":"2026-07-05T09:23:43Z","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/2306.03372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large tensor learning algorithms are typically computationally expensive and require storing a vast amount of data. In this paper, we propose a unified online Riemannian gradient descent (oRGrad) algorithm for tensor learning, which is computationally efficient, consumes much less memory, and can handle sequentially arriving data while making timely predictions. The algorithm is applicable to both linear and generalized linear models. If the time horizon T is known, oRGrad achieves statistical optimality by choosing an appropriate fixed step size. We find that noisy tensor completion particula","authors_text":"Dong Xia, Jian-Feng Cai, Jingyang Li, Yang Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-06-06T03:21:28Z","title":"Online Tensor Learning: Computational and Statistical Trade-offs, Adaptivity and Optimal Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03372","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:f13312d8e5fdd8eff092dd31f9e06bed7c43b06599f52032aa10ba6a13f2b4ad","target":"record","created_at":"2026-07-05T09:23:43Z","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":"3f3a103327b090f4bf08a8ab8ec16f54b82d986fe0426ca28172df3a5b1675d1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-06-06T03:21:28Z","title_canon_sha256":"2950efd9ba3050420754add4b7934deed46f4e3238135ed28c057d2a03cee8e3"},"schema_version":"1.0","source":{"id":"2306.03372","kind":"arxiv","version":3}},"canonical_sha256":"275bcb415f29cd3a3aab5da56ade81c9ebfd9c27de3fc96d2dc3c58d754d155d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"275bcb415f29cd3a3aab5da56ade81c9ebfd9c27de3fc96d2dc3c58d754d155d","first_computed_at":"2026-07-05T09:23:43.782463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:43.782463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mQZ4vYOG7Zm80bnwMd5Fgg4m//RaOe7cbfNC9cdf64UK/imaOgANLbYA3twbCoqYQBYYlVYJYhpkF7BpE0mWDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:43.782968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.03372","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f13312d8e5fdd8eff092dd31f9e06bed7c43b06599f52032aa10ba6a13f2b4ad","sha256:e2f29d55e4a820c5c8d7fecb612d18b4231631de44d6a2f7a1df9cacf143aa40"],"state_sha256":"4226250ae5a810256c3d5152e00c61a8a85cd842a08789070c0e93f1f22dc19b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ziy97UELjQA3DZOjXPJXlK4SqEGqaRwhGGksgwZP9s9UwryZa1w7f+EvhhRxy4M2ZAr258lq5BhkEEMn4xRDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:33:55.624076Z","bundle_sha256":"e7c4baefdef1b231a9c63f6f32fe3821233b1b966b40e7dceb11bef877f3edab"}}