{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6SZ6E6NRT547Z6UTO7ZR33PFCC","short_pith_number":"pith:6SZ6E6NR","schema_version":"1.0","canonical_sha256":"f4b3e279b19f79fcfa9377f31dede510b3053b96c76fba2c11f616118beb27bb","source":{"kind":"arxiv","id":"2506.01893","version":2},"attestation_state":"computed","paper":{"title":"Variational Inference for Latent Variable Models in High Dimensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Bodhisattva Sen, Chenyang Zhong, Sumit Mukherjee","submitted_at":"2025-06-02T17:19:58Z","abstract_excerpt":"Variational inference (VI) is a popular method for approximating intractable posterior distributions in Bayesian inference and probabilistic machine learning. In this paper, we introduce a general framework for quantifying the statistical accuracy of mean-field variational inference (MFVI) for posterior approximation in Bayesian latent variable models with categorical local latent variables (and arbitrary global latent variables). Utilizing our general framework, we capture the exact regime where MFVI 'works' for the celebrated latent Dirichlet allocation model. Focusing on the mixed membershi"},"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":"2506.01893","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-06-02T17:19:58Z","cross_cats_sorted":["math.PR","stat.ML","stat.TH"],"title_canon_sha256":"ad7134f6dc8c0e4fe53d71dd17f668062ee696bb341f4fcd7317df0888827a6e","abstract_canon_sha256":"e99d12899c1a005c073bd78140910addea6f4c416dc841fc77dd88e576031916"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:29.872398Z","signature_b64":"uuHcCZvXdyRFMBFzWtRXWUD0ztnOvdAZkq4QDQNlq9uigQ7w3MZ9gODVAK0EFddD50HwR2OeKlPnNcVZWJzYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4b3e279b19f79fcfa9377f31dede510b3053b96c76fba2c11f616118beb27bb","last_reissued_at":"2026-07-05T11:38:29.871892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:29.871892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Inference for Latent Variable Models in High Dimensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Bodhisattva Sen, Chenyang Zhong, Sumit Mukherjee","submitted_at":"2025-06-02T17:19:58Z","abstract_excerpt":"Variational inference (VI) is a popular method for approximating intractable posterior distributions in Bayesian inference and probabilistic machine learning. In this paper, we introduce a general framework for quantifying the statistical accuracy of mean-field variational inference (MFVI) for posterior approximation in Bayesian latent variable models with categorical local latent variables (and arbitrary global latent variables). Utilizing our general framework, we capture the exact regime where MFVI 'works' for the celebrated latent Dirichlet allocation model. Focusing on the mixed membershi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01893","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/2506.01893/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":"2506.01893","created_at":"2026-07-05T11:38:29.871947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01893v2","created_at":"2026-07-05T11:38:29.871947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01893","created_at":"2026-07-05T11:38:29.871947+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SZ6E6NRT547","created_at":"2026-07-05T11:38:29.871947+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SZ6E6NRT547Z6UT","created_at":"2026-07-05T11:38:29.871947+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SZ6E6NR","created_at":"2026-07-05T11:38:29.871947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SZ6E6NRT547Z6UTO7ZR33PFCC","json":"https://pith.science/pith/6SZ6E6NRT547Z6UTO7ZR33PFCC.json","graph_json":"https://pith.science/api/pith-number/6SZ6E6NRT547Z6UTO7ZR33PFCC/graph.json","events_json":"https://pith.science/api/pith-number/6SZ6E6NRT547Z6UTO7ZR33PFCC/events.json","paper":"https://pith.science/paper/6SZ6E6NR"},"agent_actions":{"view_html":"https://pith.science/pith/6SZ6E6NRT547Z6UTO7ZR33PFCC","download_json":"https://pith.science/pith/6SZ6E6NRT547Z6UTO7ZR33PFCC.json","view_paper":"https://pith.science/paper/6SZ6E6NR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01893&json=true","fetch_graph":"https://pith.science/api/pith-number/6SZ6E6NRT547Z6UTO7ZR33PFCC/graph.json","fetch_events":"https://pith.science/api/pith-number/6SZ6E6NRT547Z6UTO7ZR33PFCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SZ6E6NRT547Z6UTO7ZR33PFCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SZ6E6NRT547Z6UTO7ZR33PFCC/action/storage_attestation","attest_author":"https://pith.science/pith/6SZ6E6NRT547Z6UTO7ZR33PFCC/action/author_attestation","sign_citation":"https://pith.science/pith/6SZ6E6NRT547Z6UTO7ZR33PFCC/action/citation_signature","submit_replication":"https://pith.science/pith/6SZ6E6NRT547Z6UTO7ZR33PFCC/action/replication_record"}},"created_at":"2026-07-05T11:38:29.871947+00:00","updated_at":"2026-07-05T11:38:29.871947+00:00"}