{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LFQEZOR6FCL3SY3QW32JRPHSB3","short_pith_number":"pith:LFQEZOR6","schema_version":"1.0","canonical_sha256":"59604cba3e2897b96370b6f498bcf20eec36f8bd21ac39ed66e96bba959f401e","source":{"kind":"arxiv","id":"1904.03858","version":3},"attestation_state":"computed","paper":{"title":"The Kikuchi Hierarchy and Tensor PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Ahmed El Alaoui, Alexander S. Wein, Cristopher Moore","submitted_at":"2019-04-08T06:26:35Z","abstract_excerpt":"For the tensor PCA (principal component analysis) problem, we propose a new hierarchy of increasingly powerful algorithms with increasing runtime. Our hierarchy is analogous to the sum-of-squares (SOS) hierarchy but is instead inspired by statistical physics and related algorithms such as belief propagation and AMP (approximate message passing). Our level-$\\ell$ algorithm can be thought of as a linearized message-passing algorithm that keeps track of $\\ell$-wise dependencies among the hidden variables. Specifically, our algorithms are spectral methods based on the Kikuchi Hessian, which genera"},"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":"1904.03858","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2019-04-08T06:26:35Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"1ede8f06d5313813bbf1a4ee6c6ee6c696733daba2a0eecd7c925a4b9b5ba41c","abstract_canon_sha256":"acba4fffce1ca1cf2fe990592af1c3fa52630034367a4061cd3780aa32c09e25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:11.586395Z","signature_b64":"lJgGLcNFDDbuCav0kt6jl2I8qDMHpybMWncdn4jYGuNRTen32DAKmsutxFZaqX46CVZa4PJSFrHFawhFWOB7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59604cba3e2897b96370b6f498bcf20eec36f8bd21ac39ed66e96bba959f401e","last_reissued_at":"2026-07-05T11:56:11.585783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:11.585783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Kikuchi Hierarchy and Tensor PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Ahmed El Alaoui, Alexander S. Wein, Cristopher Moore","submitted_at":"2019-04-08T06:26:35Z","abstract_excerpt":"For the tensor PCA (principal component analysis) problem, we propose a new hierarchy of increasingly powerful algorithms with increasing runtime. Our hierarchy is analogous to the sum-of-squares (SOS) hierarchy but is instead inspired by statistical physics and related algorithms such as belief propagation and AMP (approximate message passing). Our level-$\\ell$ algorithm can be thought of as a linearized message-passing algorithm that keeps track of $\\ell$-wise dependencies among the hidden variables. Specifically, our algorithms are spectral methods based on the Kikuchi Hessian, which genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03858","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/1904.03858/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":"1904.03858","created_at":"2026-07-05T11:56:11.585859+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03858v3","created_at":"2026-07-05T11:56:11.585859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03858","created_at":"2026-07-05T11:56:11.585859+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFQEZOR6FCL3","created_at":"2026-07-05T11:56:11.585859+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFQEZOR6FCL3SY3Q","created_at":"2026-07-05T11:56:11.585859+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFQEZOR6","created_at":"2026-07-05T11:56:11.585859+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":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFQEZOR6FCL3SY3QW32JRPHSB3","json":"https://pith.science/pith/LFQEZOR6FCL3SY3QW32JRPHSB3.json","graph_json":"https://pith.science/api/pith-number/LFQEZOR6FCL3SY3QW32JRPHSB3/graph.json","events_json":"https://pith.science/api/pith-number/LFQEZOR6FCL3SY3QW32JRPHSB3/events.json","paper":"https://pith.science/paper/LFQEZOR6"},"agent_actions":{"view_html":"https://pith.science/pith/LFQEZOR6FCL3SY3QW32JRPHSB3","download_json":"https://pith.science/pith/LFQEZOR6FCL3SY3QW32JRPHSB3.json","view_paper":"https://pith.science/paper/LFQEZOR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03858&json=true","fetch_graph":"https://pith.science/api/pith-number/LFQEZOR6FCL3SY3QW32JRPHSB3/graph.json","fetch_events":"https://pith.science/api/pith-number/LFQEZOR6FCL3SY3QW32JRPHSB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFQEZOR6FCL3SY3QW32JRPHSB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFQEZOR6FCL3SY3QW32JRPHSB3/action/storage_attestation","attest_author":"https://pith.science/pith/LFQEZOR6FCL3SY3QW32JRPHSB3/action/author_attestation","sign_citation":"https://pith.science/pith/LFQEZOR6FCL3SY3QW32JRPHSB3/action/citation_signature","submit_replication":"https://pith.science/pith/LFQEZOR6FCL3SY3QW32JRPHSB3/action/replication_record"}},"created_at":"2026-07-05T11:56:11.585859+00:00","updated_at":"2026-07-05T11:56:11.585859+00:00"}