{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FQYA45FFUY3BDCZD26PNQ6CLHT","short_pith_number":"pith:FQYA45FF","schema_version":"1.0","canonical_sha256":"2c300e74a5a636118b23d79ed8784b3ce497f649e84e489fe7c65fc055dd0672","source":{"kind":"arxiv","id":"1808.00921","version":2},"attestation_state":"computed","paper":{"title":"Algorithmic thresholds for tensor PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"math.PR","authors_text":"Aukosh Jagannath, Gerard Ben Arous, Reza Gheissari","submitted_at":"2018-08-02T17:12:21Z","abstract_excerpt":"We study the algorithmic thresholds for principal component analysis of Gaussian $k$-tensors with a planted rank-one spike, via Langevin dynamics and gradient descent. In order to efficiently recover the spike from natural initializations, the signal to noise ratio must diverge in the dimension. Our proof shows that the mechanism for the success/failure of recovery is the strength of the \"curvature\" of the spike on the maximum entropy region of the initial data. To demonstrate this, we study the dynamics on a generalized family of high-dimensional landscapes with planted signals, containing th"},"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":"1808.00921","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2018-08-02T17:12:21Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"c5c30e9ce85439803e7b63ef29570f375b7091c0f63047c301b83e08329218e3","abstract_canon_sha256":"d67c38077ab07806481bb119b2d775cce98f54cb9015a99471e3249bdc9eb16d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:42.734696Z","signature_b64":"Nykrb1tNd3Jk+Rlv4/m/rLkJPmZ9qYMn+geDqz+AQILRuxT96JM+e1ffes1l1FrwTw6kjUtjg8avDIe47Se8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c300e74a5a636118b23d79ed8784b3ce497f649e84e489fe7c65fc055dd0672","last_reissued_at":"2026-07-05T06:23:42.734296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:42.734296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Algorithmic thresholds for tensor PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"math.PR","authors_text":"Aukosh Jagannath, Gerard Ben Arous, Reza Gheissari","submitted_at":"2018-08-02T17:12:21Z","abstract_excerpt":"We study the algorithmic thresholds for principal component analysis of Gaussian $k$-tensors with a planted rank-one spike, via Langevin dynamics and gradient descent. In order to efficiently recover the spike from natural initializations, the signal to noise ratio must diverge in the dimension. Our proof shows that the mechanism for the success/failure of recovery is the strength of the \"curvature\" of the spike on the maximum entropy region of the initial data. To demonstrate this, we study the dynamics on a generalized family of high-dimensional landscapes with planted signals, containing th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00921","kind":"arxiv","version":2},"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/1808.00921/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":"1808.00921","created_at":"2026-07-05T06:23:42.734374+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.00921v2","created_at":"2026-07-05T06:23:42.734374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00921","created_at":"2026-07-05T06:23:42.734374+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQYA45FFUY3B","created_at":"2026-07-05T06:23:42.734374+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQYA45FFUY3BDCZD","created_at":"2026-07-05T06:23:42.734374+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQYA45FF","created_at":"2026-07-05T06:23:42.734374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.11636","citing_title":"Notes on Computational Hardness of Hypothesis Testing: Predictions using the Low-Degree Likelihood Ratio","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQYA45FFUY3BDCZD26PNQ6CLHT","json":"https://pith.science/pith/FQYA45FFUY3BDCZD26PNQ6CLHT.json","graph_json":"https://pith.science/api/pith-number/FQYA45FFUY3BDCZD26PNQ6CLHT/graph.json","events_json":"https://pith.science/api/pith-number/FQYA45FFUY3BDCZD26PNQ6CLHT/events.json","paper":"https://pith.science/paper/FQYA45FF"},"agent_actions":{"view_html":"https://pith.science/pith/FQYA45FFUY3BDCZD26PNQ6CLHT","download_json":"https://pith.science/pith/FQYA45FFUY3BDCZD26PNQ6CLHT.json","view_paper":"https://pith.science/paper/FQYA45FF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.00921&json=true","fetch_graph":"https://pith.science/api/pith-number/FQYA45FFUY3BDCZD26PNQ6CLHT/graph.json","fetch_events":"https://pith.science/api/pith-number/FQYA45FFUY3BDCZD26PNQ6CLHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQYA45FFUY3BDCZD26PNQ6CLHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQYA45FFUY3BDCZD26PNQ6CLHT/action/storage_attestation","attest_author":"https://pith.science/pith/FQYA45FFUY3BDCZD26PNQ6CLHT/action/author_attestation","sign_citation":"https://pith.science/pith/FQYA45FFUY3BDCZD26PNQ6CLHT/action/citation_signature","submit_replication":"https://pith.science/pith/FQYA45FFUY3BDCZD26PNQ6CLHT/action/replication_record"}},"created_at":"2026-07-05T06:23:42.734374+00:00","updated_at":"2026-07-05T06:23:42.734374+00:00"}