{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DC3PYGHD6PIUO3ETXCZAYC2NC4","short_pith_number":"pith:DC3PYGHD","schema_version":"1.0","canonical_sha256":"18b6fc18e3f3d1476c93b8b20c0b4d171a126db424240c96db40d235c746bd5e","source":{"kind":"arxiv","id":"1711.03946","version":2},"attestation_state":"computed","paper":{"title":"Bayesian Paragraph Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Erik B. Sudderth, Geng Ji, Robert Bamler, Stephan Mandt","submitted_at":"2017-11-10T18:09:15Z","abstract_excerpt":"Word2vec (Mikolov et al., 2013) has proven to be successful in natural language processing by capturing the semantic relationships between different words. Built on top of single-word embeddings, paragraph vectors (Le and Mikolov, 2014) find fixed-length representations for pieces of text with arbitrary lengths, such as documents, paragraphs, and sentences. In this work, we propose a novel interpretation for neural-network-based paragraph vectors by developing an unsupervised generative model whose maximum likelihood solution corresponds to traditional paragraph vectors. This probabilistic for"},"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":"1711.03946","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-10T18:09:15Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"51e2477ef9c61000131de4a6ad50e54f480fbc22d7bfbcbd328aaef8d8d944c5","abstract_canon_sha256":"d8313bc426a70949541afef5260d60fbfe215541da6f015c2e39c1fa961f0e66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:29.444875Z","signature_b64":"JQb9ctar1NCoKOk0eGurzqgQ12F/8Z5n6HH68kGeIsf9+sLx9P8gh2KVnxukSKD0AhNFim/XMAgt15QuSKGXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18b6fc18e3f3d1476c93b8b20c0b4d171a126db424240c96db40d235c746bd5e","last_reissued_at":"2026-05-18T00:28:29.444242Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:29.444242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Paragraph Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Erik B. Sudderth, Geng Ji, Robert Bamler, Stephan Mandt","submitted_at":"2017-11-10T18:09:15Z","abstract_excerpt":"Word2vec (Mikolov et al., 2013) has proven to be successful in natural language processing by capturing the semantic relationships between different words. Built on top of single-word embeddings, paragraph vectors (Le and Mikolov, 2014) find fixed-length representations for pieces of text with arbitrary lengths, such as documents, paragraphs, and sentences. In this work, we propose a novel interpretation for neural-network-based paragraph vectors by developing an unsupervised generative model whose maximum likelihood solution corresponds to traditional paragraph vectors. This probabilistic for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.03946","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":""},"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":"1711.03946","created_at":"2026-05-18T00:28:29.444380+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.03946v2","created_at":"2026-05-18T00:28:29.444380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.03946","created_at":"2026-05-18T00:28:29.444380+00:00"},{"alias_kind":"pith_short_12","alias_value":"DC3PYGHD6PIU","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DC3PYGHD6PIUO3ET","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DC3PYGHD","created_at":"2026-05-18T12:31:10.602751+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/DC3PYGHD6PIUO3ETXCZAYC2NC4","json":"https://pith.science/pith/DC3PYGHD6PIUO3ETXCZAYC2NC4.json","graph_json":"https://pith.science/api/pith-number/DC3PYGHD6PIUO3ETXCZAYC2NC4/graph.json","events_json":"https://pith.science/api/pith-number/DC3PYGHD6PIUO3ETXCZAYC2NC4/events.json","paper":"https://pith.science/paper/DC3PYGHD"},"agent_actions":{"view_html":"https://pith.science/pith/DC3PYGHD6PIUO3ETXCZAYC2NC4","download_json":"https://pith.science/pith/DC3PYGHD6PIUO3ETXCZAYC2NC4.json","view_paper":"https://pith.science/paper/DC3PYGHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.03946&json=true","fetch_graph":"https://pith.science/api/pith-number/DC3PYGHD6PIUO3ETXCZAYC2NC4/graph.json","fetch_events":"https://pith.science/api/pith-number/DC3PYGHD6PIUO3ETXCZAYC2NC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DC3PYGHD6PIUO3ETXCZAYC2NC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DC3PYGHD6PIUO3ETXCZAYC2NC4/action/storage_attestation","attest_author":"https://pith.science/pith/DC3PYGHD6PIUO3ETXCZAYC2NC4/action/author_attestation","sign_citation":"https://pith.science/pith/DC3PYGHD6PIUO3ETXCZAYC2NC4/action/citation_signature","submit_replication":"https://pith.science/pith/DC3PYGHD6PIUO3ETXCZAYC2NC4/action/replication_record"}},"created_at":"2026-05-18T00:28:29.444380+00:00","updated_at":"2026-05-18T00:28:29.444380+00:00"}