{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:P2Y4C3ANAR4NEPTTU5KHTZQAVR","short_pith_number":"pith:P2Y4C3AN","schema_version":"1.0","canonical_sha256":"7eb1c16c0d0478d23e73a75479e600ac4d21de0f82379a2eada57d5c2ce722bb","source":{"kind":"arxiv","id":"1607.05368","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jey Han Lau, Timothy Baldwin","submitted_at":"2016-07-19T01:55:55Z","abstract_excerpt":"Recently, Le and Mikolov (2014) proposed doc2vec as an extension to word2vec (Mikolov et al., 2013a) to learn document-level embeddings. Despite promising results in the original paper, others have struggled to reproduce those results. This paper presents a rigorous empirical evaluation of doc2vec over two tasks. We compare doc2vec to two baselines and two state-of-the-art document embedding methodologies. We found that doc2vec performs robustly when using models trained on large external corpora, and can be further improved by using pre-trained word embeddings. We also provide recommendations"},"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":"1607.05368","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-19T01:55:55Z","cross_cats_sorted":[],"title_canon_sha256":"dc7e1a4e55ffb35c0a7f9c6e53e75b31c49de0602954ceddaef6104b9a0618da","abstract_canon_sha256":"22088a2269190b3c880a7ac60c890b3422a2729e707a0012432d3456fa6b3a73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:52.721011Z","signature_b64":"XDe9xuCnYXbIq82u1rolLKufqJl2ckKIEGSBPX+RWQ2nAqIoWnVg71i/Pv+hN4Gs64dq2WotPBxbgcQxxlKEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eb1c16c0d0478d23e73a75479e600ac4d21de0f82379a2eada57d5c2ce722bb","last_reissued_at":"2026-05-18T00:54:52.720519Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:52.720519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jey Han Lau, Timothy Baldwin","submitted_at":"2016-07-19T01:55:55Z","abstract_excerpt":"Recently, Le and Mikolov (2014) proposed doc2vec as an extension to word2vec (Mikolov et al., 2013a) to learn document-level embeddings. Despite promising results in the original paper, others have struggled to reproduce those results. This paper presents a rigorous empirical evaluation of doc2vec over two tasks. We compare doc2vec to two baselines and two state-of-the-art document embedding methodologies. We found that doc2vec performs robustly when using models trained on large external corpora, and can be further improved by using pre-trained word embeddings. We also provide recommendations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05368","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":"1607.05368","created_at":"2026-05-18T00:54:52.720589+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.05368v1","created_at":"2026-05-18T00:54:52.720589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05368","created_at":"2026-05-18T00:54:52.720589+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2Y4C3ANAR4N","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2Y4C3ANAR4NEPTT","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2Y4C3AN","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2506.06226","citing_title":"No Data? No Problem: Synthesizing Security Graphs for Better Intrusion Detection","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2512.12280","citing_title":"Optimising for the long game: methodological challenges in energy system optimisation pathways","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2Y4C3ANAR4NEPTTU5KHTZQAVR","json":"https://pith.science/pith/P2Y4C3ANAR4NEPTTU5KHTZQAVR.json","graph_json":"https://pith.science/api/pith-number/P2Y4C3ANAR4NEPTTU5KHTZQAVR/graph.json","events_json":"https://pith.science/api/pith-number/P2Y4C3ANAR4NEPTTU5KHTZQAVR/events.json","paper":"https://pith.science/paper/P2Y4C3AN"},"agent_actions":{"view_html":"https://pith.science/pith/P2Y4C3ANAR4NEPTTU5KHTZQAVR","download_json":"https://pith.science/pith/P2Y4C3ANAR4NEPTTU5KHTZQAVR.json","view_paper":"https://pith.science/paper/P2Y4C3AN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.05368&json=true","fetch_graph":"https://pith.science/api/pith-number/P2Y4C3ANAR4NEPTTU5KHTZQAVR/graph.json","fetch_events":"https://pith.science/api/pith-number/P2Y4C3ANAR4NEPTTU5KHTZQAVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2Y4C3ANAR4NEPTTU5KHTZQAVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2Y4C3ANAR4NEPTTU5KHTZQAVR/action/storage_attestation","attest_author":"https://pith.science/pith/P2Y4C3ANAR4NEPTTU5KHTZQAVR/action/author_attestation","sign_citation":"https://pith.science/pith/P2Y4C3ANAR4NEPTTU5KHTZQAVR/action/citation_signature","submit_replication":"https://pith.science/pith/P2Y4C3ANAR4NEPTTU5KHTZQAVR/action/replication_record"}},"created_at":"2026-05-18T00:54:52.720589+00:00","updated_at":"2026-05-18T00:54:52.720589+00:00"}