{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:S24CVI25UBKIOFTOSMWC36XZ7S","short_pith_number":"pith:S24CVI25","schema_version":"1.0","canonical_sha256":"96b82aa35da05487166e932c2dfaf9fca086bc9fdf58232758cc8560e1be326d","source":{"kind":"arxiv","id":"1508.01011","version":1},"attestation_state":"computed","paper":{"title":"Learning from LDA using Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.NE"],"primary_cat":"cs.LG","authors_text":"Dong Wang, Dongxu Zhang, Rong Liu, Tianyi Luo","submitted_at":"2015-08-05T09:22:25Z","abstract_excerpt":"Latent Dirichlet Allocation (LDA) is a three-level hierarchical Bayesian model for topic inference. In spite of its great success, inferring the latent topic distribution with LDA is time-consuming. Motivated by the transfer learning approach proposed by~\\newcite{hinton2015distilling}, we present a novel method that uses LDA to supervise the training of a deep neural network (DNN), so that the DNN can approximate the costly LDA inference with less computation. Our experiments on a document classification task show that a simple DNN can learn the LDA behavior pretty well, while the inference is"},"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":"1508.01011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-08-05T09:22:25Z","cross_cats_sorted":["cs.CL","cs.IR","cs.NE"],"title_canon_sha256":"2beb7b8c512d90a90eef2a604a7171faceb3a58f25cf7b1f9f23cce63dc7b980","abstract_canon_sha256":"45f8b26d724e8a9fa072ca41e75f2068cf1e431e360692f34eab8eddd4b8d833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:44.266805Z","signature_b64":"UlSFeR+f3FVjVfZSWwOpblzpxFnknqFV3NnPh+/l4G7cQGW8WcVcWpWld9TVFgxlYSbYRCkddDgo6T0hzxSUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96b82aa35da05487166e932c2dfaf9fca086bc9fdf58232758cc8560e1be326d","last_reissued_at":"2026-05-18T01:35:44.266429Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:44.266429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from LDA using Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.NE"],"primary_cat":"cs.LG","authors_text":"Dong Wang, Dongxu Zhang, Rong Liu, Tianyi Luo","submitted_at":"2015-08-05T09:22:25Z","abstract_excerpt":"Latent Dirichlet Allocation (LDA) is a three-level hierarchical Bayesian model for topic inference. In spite of its great success, inferring the latent topic distribution with LDA is time-consuming. Motivated by the transfer learning approach proposed by~\\newcite{hinton2015distilling}, we present a novel method that uses LDA to supervise the training of a deep neural network (DNN), so that the DNN can approximate the costly LDA inference with less computation. Our experiments on a document classification task show that a simple DNN can learn the LDA behavior pretty well, while the inference is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.01011","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":"1508.01011","created_at":"2026-05-18T01:35:44.266484+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.01011v1","created_at":"2026-05-18T01:35:44.266484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.01011","created_at":"2026-05-18T01:35:44.266484+00:00"},{"alias_kind":"pith_short_12","alias_value":"S24CVI25UBKI","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"S24CVI25UBKIOFTO","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"S24CVI25","created_at":"2026-05-18T12:29:39.896362+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/S24CVI25UBKIOFTOSMWC36XZ7S","json":"https://pith.science/pith/S24CVI25UBKIOFTOSMWC36XZ7S.json","graph_json":"https://pith.science/api/pith-number/S24CVI25UBKIOFTOSMWC36XZ7S/graph.json","events_json":"https://pith.science/api/pith-number/S24CVI25UBKIOFTOSMWC36XZ7S/events.json","paper":"https://pith.science/paper/S24CVI25"},"agent_actions":{"view_html":"https://pith.science/pith/S24CVI25UBKIOFTOSMWC36XZ7S","download_json":"https://pith.science/pith/S24CVI25UBKIOFTOSMWC36XZ7S.json","view_paper":"https://pith.science/paper/S24CVI25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.01011&json=true","fetch_graph":"https://pith.science/api/pith-number/S24CVI25UBKIOFTOSMWC36XZ7S/graph.json","fetch_events":"https://pith.science/api/pith-number/S24CVI25UBKIOFTOSMWC36XZ7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S24CVI25UBKIOFTOSMWC36XZ7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S24CVI25UBKIOFTOSMWC36XZ7S/action/storage_attestation","attest_author":"https://pith.science/pith/S24CVI25UBKIOFTOSMWC36XZ7S/action/author_attestation","sign_citation":"https://pith.science/pith/S24CVI25UBKIOFTOSMWC36XZ7S/action/citation_signature","submit_replication":"https://pith.science/pith/S24CVI25UBKIOFTOSMWC36XZ7S/action/replication_record"}},"created_at":"2026-05-18T01:35:44.266484+00:00","updated_at":"2026-05-18T01:35:44.266484+00:00"}