{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:P7DQL47ODL3BRJPVEMBH4HURKE","short_pith_number":"pith:P7DQL47O","schema_version":"1.0","canonical_sha256":"7fc705f3ee1af618a5f523027e1e91513b7d48142c3617a6ce95ffe2c5c9785c","source":{"kind":"arxiv","id":"1210.7559","version":4},"attestation_state":"computed","paper":{"title":"Tensor decompositions for learning latent variable models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Daniel Hsu, Matus Telgarsky, Rong Ge, Sham M. Kakade","submitted_at":"2012-10-29T04:38:41Z","abstract_excerpt":"This work considers a computationally and statistically efficient parameter estimation method for a wide class of latent variable models---including Gaussian mixture models, hidden Markov models, and latent Dirichlet allocation---which exploits a certain tensor structure in their low-order observable moments (typically, of second- and third-order). Specifically, parameter estimation is reduced to the problem of extracting a certain (orthogonal) decomposition of a symmetric tensor derived from the moments; this decomposition can be viewed as a natural generalization of the singular value decomp"},"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":"1210.7559","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-10-29T04:38:41Z","cross_cats_sorted":["math.NA","stat.ML"],"title_canon_sha256":"1645c1783b4a4086fbfd4c489cf22923f605a4fd3a9f40dfc037c6e7f5610c8c","abstract_canon_sha256":"16a55c9f28996dca6093a95a96cc5a751c36319144fb22f34f5788ca08638c6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:37:43.077392Z","signature_b64":"/apczLY+nS1RMVgr2al8P4X8I07fAX8DdZIrVYROUXe1JEfMfxZmmz3cn3TW9Y9TTsPxnkqk9Hxs+kWcqLl0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fc705f3ee1af618a5f523027e1e91513b7d48142c3617a6ce95ffe2c5c9785c","last_reissued_at":"2026-05-18T02:37:43.077001Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:37:43.077001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tensor decompositions for learning latent variable models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Daniel Hsu, Matus Telgarsky, Rong Ge, Sham M. Kakade","submitted_at":"2012-10-29T04:38:41Z","abstract_excerpt":"This work considers a computationally and statistically efficient parameter estimation method for a wide class of latent variable models---including Gaussian mixture models, hidden Markov models, and latent Dirichlet allocation---which exploits a certain tensor structure in their low-order observable moments (typically, of second- and third-order). Specifically, parameter estimation is reduced to the problem of extracting a certain (orthogonal) decomposition of a symmetric tensor derived from the moments; this decomposition can be viewed as a natural generalization of the singular value decomp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1210.7559","kind":"arxiv","version":4},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1210.7559","created_at":"2026-05-18T02:37:43.077056+00:00"},{"alias_kind":"arxiv_version","alias_value":"1210.7559v4","created_at":"2026-05-18T02:37:43.077056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1210.7559","created_at":"2026-05-18T02:37:43.077056+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7DQL47ODL3B","created_at":"2026-05-18T12:27:18.751474+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7DQL47ODL3BRJPV","created_at":"2026-05-18T12:27:18.751474+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7DQL47O","created_at":"2026-05-18T12:27:18.751474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.01066","citing_title":"Language Models as Knowledge Bases?","ref_index":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7DQL47ODL3BRJPVEMBH4HURKE","json":"https://pith.science/pith/P7DQL47ODL3BRJPVEMBH4HURKE.json","graph_json":"https://pith.science/api/pith-number/P7DQL47ODL3BRJPVEMBH4HURKE/graph.json","events_json":"https://pith.science/api/pith-number/P7DQL47ODL3BRJPVEMBH4HURKE/events.json","paper":"https://pith.science/paper/P7DQL47O"},"agent_actions":{"view_html":"https://pith.science/pith/P7DQL47ODL3BRJPVEMBH4HURKE","download_json":"https://pith.science/pith/P7DQL47ODL3BRJPVEMBH4HURKE.json","view_paper":"https://pith.science/paper/P7DQL47O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1210.7559&json=true","fetch_graph":"https://pith.science/api/pith-number/P7DQL47ODL3BRJPVEMBH4HURKE/graph.json","fetch_events":"https://pith.science/api/pith-number/P7DQL47ODL3BRJPVEMBH4HURKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7DQL47ODL3BRJPVEMBH4HURKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7DQL47ODL3BRJPVEMBH4HURKE/action/storage_attestation","attest_author":"https://pith.science/pith/P7DQL47ODL3BRJPVEMBH4HURKE/action/author_attestation","sign_citation":"https://pith.science/pith/P7DQL47ODL3BRJPVEMBH4HURKE/action/citation_signature","submit_replication":"https://pith.science/pith/P7DQL47ODL3BRJPVEMBH4HURKE/action/replication_record"}},"created_at":"2026-05-18T02:37:43.077056+00:00","updated_at":"2026-05-18T02:37:43.077056+00:00"}