{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VHFYXMQUCHLS4JAQLKFDFQLY6K","short_pith_number":"pith:VHFYXMQU","schema_version":"1.0","canonical_sha256":"a9cb8bb21411d72e24105a8a32c178f2af8eb84829c0b49fca38ddc0399136b1","source":{"kind":"arxiv","id":"2506.07747","version":1},"attestation_state":"computed","paper":{"title":"E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Breuer","submitted_at":"2025-06-06T07:05:48Z","abstract_excerpt":"In this paper, we provide the first practical algorithms with provable guarantees for the problem of inferring the topics assigned to each document in an LDA topic model. This is the primary inference problem for many applications of topic models in social science, data exploration, and causal inference settings. We obtain this result by showing a novel non-gradient-based, combinatorial approach to estimating topic models. This yields algorithms that converge to near-optimal posterior probability in logarithmic parallel computation time (adaptivity) -- exponentially faster than any known LDA a"},"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":"2506.07747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T07:05:48Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"670f46d854cb401d216c673770beebce36d85b6342c977595dd3c3b197904864","abstract_canon_sha256":"82b035a63d892ce4c87f713e0d58305ce8467e0da0f4c9850e57d490907db9b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:32.620700Z","signature_b64":"1/D2huPv4PPKXtvlHAiPQTeK4PEdHFJD64nP+jVGkQcxofIZY7k+6t47by3Lo872leHLdPbJigtSbxI0WWx7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9cb8bb21411d72e24105a8a32c178f2af8eb84829c0b49fca38ddc0399136b1","last_reissued_at":"2026-07-05T11:18:32.620214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:32.620214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Breuer","submitted_at":"2025-06-06T07:05:48Z","abstract_excerpt":"In this paper, we provide the first practical algorithms with provable guarantees for the problem of inferring the topics assigned to each document in an LDA topic model. This is the primary inference problem for many applications of topic models in social science, data exploration, and causal inference settings. We obtain this result by showing a novel non-gradient-based, combinatorial approach to estimating topic models. This yields algorithms that converge to near-optimal posterior probability in logarithmic parallel computation time (adaptivity) -- exponentially faster than any known LDA a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07747","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.07747/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":"2506.07747","created_at":"2026-07-05T11:18:32.620271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07747v1","created_at":"2026-07-05T11:18:32.620271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07747","created_at":"2026-07-05T11:18:32.620271+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHFYXMQUCHLS","created_at":"2026-07-05T11:18:32.620271+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHFYXMQUCHLS4JAQ","created_at":"2026-07-05T11:18:32.620271+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHFYXMQU","created_at":"2026-07-05T11:18:32.620271+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/VHFYXMQUCHLS4JAQLKFDFQLY6K","json":"https://pith.science/pith/VHFYXMQUCHLS4JAQLKFDFQLY6K.json","graph_json":"https://pith.science/api/pith-number/VHFYXMQUCHLS4JAQLKFDFQLY6K/graph.json","events_json":"https://pith.science/api/pith-number/VHFYXMQUCHLS4JAQLKFDFQLY6K/events.json","paper":"https://pith.science/paper/VHFYXMQU"},"agent_actions":{"view_html":"https://pith.science/pith/VHFYXMQUCHLS4JAQLKFDFQLY6K","download_json":"https://pith.science/pith/VHFYXMQUCHLS4JAQLKFDFQLY6K.json","view_paper":"https://pith.science/paper/VHFYXMQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07747&json=true","fetch_graph":"https://pith.science/api/pith-number/VHFYXMQUCHLS4JAQLKFDFQLY6K/graph.json","fetch_events":"https://pith.science/api/pith-number/VHFYXMQUCHLS4JAQLKFDFQLY6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHFYXMQUCHLS4JAQLKFDFQLY6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHFYXMQUCHLS4JAQLKFDFQLY6K/action/storage_attestation","attest_author":"https://pith.science/pith/VHFYXMQUCHLS4JAQLKFDFQLY6K/action/author_attestation","sign_citation":"https://pith.science/pith/VHFYXMQUCHLS4JAQLKFDFQLY6K/action/citation_signature","submit_replication":"https://pith.science/pith/VHFYXMQUCHLS4JAQLKFDFQLY6K/action/replication_record"}},"created_at":"2026-07-05T11:18:32.620271+00:00","updated_at":"2026-07-05T11:18:32.620271+00:00"}