{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:O6CFPRUAGQHOCXZEIWCS7JG36E","short_pith_number":"pith:O6CFPRUA","schema_version":"1.0","canonical_sha256":"778457c680340ee15f2445852fa4dbf12de287cc42ee02d1e504a36cf8cf1770","source":{"kind":"arxiv","id":"1409.3970","version":3},"attestation_state":"computed","paper":{"title":"A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Hugo Larochelle, Yin Zheng, Yu-Jin Zhang","submitted_at":"2014-09-13T17:17:05Z","abstract_excerpt":"Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to deal with multimodal data, such as in image annotation tasks. Another popular approach to model the multimodal data is through deep neural networks, such as the deep Boltzmann machine (DBM). Recently, a new type of topic model called the Document Neural Autoregressive Distribution Estimator (DocNADE) was proposed and demonstrated state-of-the-art performance for text document modeling. In this work, we show how to successfully apply and extend this model to multimodal data, such as simultaneous image cl"},"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":"1409.3970","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-09-13T17:17:05Z","cross_cats_sorted":["cs.IR","cs.LG","cs.NE"],"title_canon_sha256":"05c49c70817379932cd91be8ba329439d42c0a88386fcfcdf9fba4c181d471d4","abstract_canon_sha256":"efe75bef8752d6eacb4bc952dd5288d30e38f90bb2f7eb84b3b4f03716234b0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:33.736911Z","signature_b64":"TWUZm53z7WInkDE7brNG5THSoMaHRTL+cXcpnDPvOvz7PqKzU0Hom7nZt/OaePYh0PwohgVuCyzfS48LuyXYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"778457c680340ee15f2445852fa4dbf12de287cc42ee02d1e504a36cf8cf1770","last_reissued_at":"2026-05-18T01:23:33.736173Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:33.736173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Hugo Larochelle, Yin Zheng, Yu-Jin Zhang","submitted_at":"2014-09-13T17:17:05Z","abstract_excerpt":"Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to deal with multimodal data, such as in image annotation tasks. Another popular approach to model the multimodal data is through deep neural networks, such as the deep Boltzmann machine (DBM). Recently, a new type of topic model called the Document Neural Autoregressive Distribution Estimator (DocNADE) was proposed and demonstrated state-of-the-art performance for text document modeling. In this work, we show how to successfully apply and extend this model to multimodal data, such as simultaneous image cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.3970","kind":"arxiv","version":3},"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":"1409.3970","created_at":"2026-05-18T01:23:33.736296+00:00"},{"alias_kind":"arxiv_version","alias_value":"1409.3970v3","created_at":"2026-05-18T01:23:33.736296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.3970","created_at":"2026-05-18T01:23:33.736296+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6CFPRUAGQHO","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6CFPRUAGQHOCXZE","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6CFPRUA","created_at":"2026-05-18T12:28:41.024544+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/O6CFPRUAGQHOCXZEIWCS7JG36E","json":"https://pith.science/pith/O6CFPRUAGQHOCXZEIWCS7JG36E.json","graph_json":"https://pith.science/api/pith-number/O6CFPRUAGQHOCXZEIWCS7JG36E/graph.json","events_json":"https://pith.science/api/pith-number/O6CFPRUAGQHOCXZEIWCS7JG36E/events.json","paper":"https://pith.science/paper/O6CFPRUA"},"agent_actions":{"view_html":"https://pith.science/pith/O6CFPRUAGQHOCXZEIWCS7JG36E","download_json":"https://pith.science/pith/O6CFPRUAGQHOCXZEIWCS7JG36E.json","view_paper":"https://pith.science/paper/O6CFPRUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1409.3970&json=true","fetch_graph":"https://pith.science/api/pith-number/O6CFPRUAGQHOCXZEIWCS7JG36E/graph.json","fetch_events":"https://pith.science/api/pith-number/O6CFPRUAGQHOCXZEIWCS7JG36E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6CFPRUAGQHOCXZEIWCS7JG36E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6CFPRUAGQHOCXZEIWCS7JG36E/action/storage_attestation","attest_author":"https://pith.science/pith/O6CFPRUAGQHOCXZEIWCS7JG36E/action/author_attestation","sign_citation":"https://pith.science/pith/O6CFPRUAGQHOCXZEIWCS7JG36E/action/citation_signature","submit_replication":"https://pith.science/pith/O6CFPRUAGQHOCXZEIWCS7JG36E/action/replication_record"}},"created_at":"2026-05-18T01:23:33.736296+00:00","updated_at":"2026-05-18T01:23:33.736296+00:00"}