{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:D3DD3LDKIP3O57ZH2BTNEWH3PB","short_pith_number":"pith:D3DD3LDK","schema_version":"1.0","canonical_sha256":"1ec63dac6a43f6eeff27d066d258fb786475a5bc5414210f739a82724a527ea3","source":{"kind":"arxiv","id":"2110.03975","version":3},"attestation_state":"computed","paper":{"title":"Tensor train completion: local recovery guarantees via Riemannian optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Nikolai Zamarashkin, Stanislav Budzinskiy","submitted_at":"2021-10-08T08:49:35Z","abstract_excerpt":"In this work, we estimate the number of randomly selected elements of a tensor that with high probability guarantees local convergence of Riemannian gradient descent for tensor train completion. We derive a new bound for the orthogonal projections onto the tangent spaces based on the harmonic mean of the unfoldings' singular values and introduce a notion of core coherence for tensor trains. We also extend the results to tensor train completion with auxiliary subspace information and obtain the corresponding local convergence guarantees."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.03975","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2021-10-08T08:49:35Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"a77ff7decac3ea61e419fe1c42c9bbbc403fa10b75fcffe40689501a67bdc7ac","abstract_canon_sha256":"04aeef61ca21b272bc38e617d8e34d3d14279364381051887c18f76862faebec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:48.415378Z","signature_b64":"aaL3jWtSuKydaRt/nsZObkNAmze8sADBqcYys4SR0alX6mVALJGGKx9N1cbimpv8xr9jCHJKKmqV1D2QwV40Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ec63dac6a43f6eeff27d066d258fb786475a5bc5414210f739a82724a527ea3","last_reissued_at":"2026-07-05T10:45:48.414876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:48.414876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tensor train completion: local recovery guarantees via Riemannian optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Nikolai Zamarashkin, Stanislav Budzinskiy","submitted_at":"2021-10-08T08:49:35Z","abstract_excerpt":"In this work, we estimate the number of randomly selected elements of a tensor that with high probability guarantees local convergence of Riemannian gradient descent for tensor train completion. We derive a new bound for the orthogonal projections onto the tangent spaces based on the harmonic mean of the unfoldings' singular values and introduce a notion of core coherence for tensor trains. We also extend the results to tensor train completion with auxiliary subspace information and obtain the corresponding local convergence guarantees."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03975","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/2110.03975/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.03975","created_at":"2026-07-05T10:45:48.414935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03975v3","created_at":"2026-07-05T10:45:48.414935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03975","created_at":"2026-07-05T10:45:48.414935+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3DD3LDKIP3O","created_at":"2026-07-05T10:45:48.414935+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3DD3LDKIP3O57ZH","created_at":"2026-07-05T10:45:48.414935+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3DD3LDK","created_at":"2026-07-05T10:45:48.414935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16032","citing_title":"A Scalable Factorization Approach for High-Order Structured Tensor Recovery","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3DD3LDKIP3O57ZH2BTNEWH3PB","json":"https://pith.science/pith/D3DD3LDKIP3O57ZH2BTNEWH3PB.json","graph_json":"https://pith.science/api/pith-number/D3DD3LDKIP3O57ZH2BTNEWH3PB/graph.json","events_json":"https://pith.science/api/pith-number/D3DD3LDKIP3O57ZH2BTNEWH3PB/events.json","paper":"https://pith.science/paper/D3DD3LDK"},"agent_actions":{"view_html":"https://pith.science/pith/D3DD3LDKIP3O57ZH2BTNEWH3PB","download_json":"https://pith.science/pith/D3DD3LDKIP3O57ZH2BTNEWH3PB.json","view_paper":"https://pith.science/paper/D3DD3LDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03975&json=true","fetch_graph":"https://pith.science/api/pith-number/D3DD3LDKIP3O57ZH2BTNEWH3PB/graph.json","fetch_events":"https://pith.science/api/pith-number/D3DD3LDKIP3O57ZH2BTNEWH3PB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3DD3LDKIP3O57ZH2BTNEWH3PB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3DD3LDKIP3O57ZH2BTNEWH3PB/action/storage_attestation","attest_author":"https://pith.science/pith/D3DD3LDKIP3O57ZH2BTNEWH3PB/action/author_attestation","sign_citation":"https://pith.science/pith/D3DD3LDKIP3O57ZH2BTNEWH3PB/action/citation_signature","submit_replication":"https://pith.science/pith/D3DD3LDKIP3O57ZH2BTNEWH3PB/action/replication_record"}},"created_at":"2026-07-05T10:45:48.414935+00:00","updated_at":"2026-07-05T10:45:48.414935+00:00"}