{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:JYC3SFKZV2IVZX5TBJX66DO7YO","short_pith_number":"pith:JYC3SFKZ","schema_version":"1.0","canonical_sha256":"4e05b91559ae915cdfb30a6fef0ddfc3a39cb24ba451590889fd2543626f004c","source":{"kind":"arxiv","id":"1206.6425","version":1},"attestation_state":"computed","paper":{"title":"Sparse Stochastic Inference for Latent Dirichlet allocation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Blei (Princeton University), David Mimno (Princeton University), Matt Hoffman (Columbia University)","submitted_at":"2012-06-27T19:59:59Z","abstract_excerpt":"We present a hybrid algorithm for Bayesian topic models that combines the efficiency of sparse Gibbs sampling with the scalability of online stochastic inference. We used our algorithm to analyze a corpus of 1.2 million books (33 billion words) with thousands of topics. Our approach reduces the bias of variational inference and generalizes to many Bayesian hidden-variable models."},"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":"1206.6425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"92124395fbb6688c9a5fac8ed0dbd26211d118202d2ffa57011bb6b7b18ceac6","abstract_canon_sha256":"b5a4531f1bdfbdd1cd5fe69b7266404560b2f1cda301c119cdce912c1fac182b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:14.238196Z","signature_b64":"rYoPaz5/gTcD8DEImdUUUCDYcWmV1FYxBVLaPdpqMuf++Q/B1qaoLw5hSMp1cz/E11+FC16khq7v0Avv1YF6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e05b91559ae915cdfb30a6fef0ddfc3a39cb24ba451590889fd2543626f004c","last_reissued_at":"2026-05-18T03:52:14.237629Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:14.237629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Stochastic Inference for Latent Dirichlet allocation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Blei (Princeton University), David Mimno (Princeton University), Matt Hoffman (Columbia University)","submitted_at":"2012-06-27T19:59:59Z","abstract_excerpt":"We present a hybrid algorithm for Bayesian topic models that combines the efficiency of sparse Gibbs sampling with the scalability of online stochastic inference. We used our algorithm to analyze a corpus of 1.2 million books (33 billion words) with thousands of topics. Our approach reduces the bias of variational inference and generalizes to many Bayesian hidden-variable models."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.6425","kind":"arxiv","version":1},"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":"1206.6425","created_at":"2026-05-18T03:52:14.237713+00:00"},{"alias_kind":"arxiv_version","alias_value":"1206.6425v1","created_at":"2026-05-18T03:52:14.237713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6425","created_at":"2026-05-18T03:52:14.237713+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYC3SFKZV2IV","created_at":"2026-05-18T12:27:11.947152+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYC3SFKZV2IVZX5T","created_at":"2026-05-18T12:27:11.947152+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYC3SFKZ","created_at":"2026-05-18T12:27:11.947152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.06600","citing_title":"High dimensional statistical inference: theoretical development to data analytics","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JYC3SFKZV2IVZX5TBJX66DO7YO","json":"https://pith.science/pith/JYC3SFKZV2IVZX5TBJX66DO7YO.json","graph_json":"https://pith.science/api/pith-number/JYC3SFKZV2IVZX5TBJX66DO7YO/graph.json","events_json":"https://pith.science/api/pith-number/JYC3SFKZV2IVZX5TBJX66DO7YO/events.json","paper":"https://pith.science/paper/JYC3SFKZ"},"agent_actions":{"view_html":"https://pith.science/pith/JYC3SFKZV2IVZX5TBJX66DO7YO","download_json":"https://pith.science/pith/JYC3SFKZV2IVZX5TBJX66DO7YO.json","view_paper":"https://pith.science/paper/JYC3SFKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1206.6425&json=true","fetch_graph":"https://pith.science/api/pith-number/JYC3SFKZV2IVZX5TBJX66DO7YO/graph.json","fetch_events":"https://pith.science/api/pith-number/JYC3SFKZV2IVZX5TBJX66DO7YO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYC3SFKZV2IVZX5TBJX66DO7YO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYC3SFKZV2IVZX5TBJX66DO7YO/action/storage_attestation","attest_author":"https://pith.science/pith/JYC3SFKZV2IVZX5TBJX66DO7YO/action/author_attestation","sign_citation":"https://pith.science/pith/JYC3SFKZV2IVZX5TBJX66DO7YO/action/citation_signature","submit_replication":"https://pith.science/pith/JYC3SFKZV2IVZX5TBJX66DO7YO/action/replication_record"}},"created_at":"2026-05-18T03:52:14.237713+00:00","updated_at":"2026-05-18T03:52:14.237713+00:00"}