{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:MV45KWEJMYK5EOI3VH7GGABCGX","short_pith_number":"pith:MV45KWEJ","schema_version":"1.0","canonical_sha256":"6579d558896615d2391ba9fe63002235dd7ff0424d5a0ec1d298e176e8c5e66a","source":{"kind":"arxiv","id":"1506.08422","version":1},"attestation_state":"computed","paper":{"title":"Topic2Vec: Learning Distributed Representations of Topics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Li-Qiang Niu, Xin-Yu Dai","submitted_at":"2015-06-28T16:17:40Z","abstract_excerpt":"Latent Dirichlet Allocation (LDA) mining thematic structure of documents plays an important role in nature language processing and machine learning areas. However, the probability distribution from LDA only describes the statistical relationship of occurrences in the corpus and usually in practice, probability is not the best choice for feature representations. Recently, embedding methods have been proposed to represent words and documents by learning essential concepts and representations, such as Word2Vec and Doc2Vec. The embedded representations have shown more effectiveness than LDA-style "},"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":"1506.08422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-06-28T16:17:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a696b563d761328a22bd1f7eab2af615db5e4e752fd0fb1b67a5bd41b7c8eff0","abstract_canon_sha256":"d405d4c781a6559389ae98e0c99791e152b478a5ae054086c188027748449309"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:37:45.357463Z","signature_b64":"Rl94F2cOnJEmtaJZzfnNl9UjsRXPpfGdjlpHLrY0HSASqi1vYTf3J8tSDNJQNaCxTnLQExJ2K5WiMF6+TtgACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6579d558896615d2391ba9fe63002235dd7ff0424d5a0ec1d298e176e8c5e66a","last_reissued_at":"2026-05-18T01:37:45.356909Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:37:45.356909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topic2Vec: Learning Distributed Representations of Topics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Li-Qiang Niu, Xin-Yu Dai","submitted_at":"2015-06-28T16:17:40Z","abstract_excerpt":"Latent Dirichlet Allocation (LDA) mining thematic structure of documents plays an important role in nature language processing and machine learning areas. However, the probability distribution from LDA only describes the statistical relationship of occurrences in the corpus and usually in practice, probability is not the best choice for feature representations. Recently, embedding methods have been proposed to represent words and documents by learning essential concepts and representations, such as Word2Vec and Doc2Vec. The embedded representations have shown more effectiveness than LDA-style "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.08422","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":"1506.08422","created_at":"2026-05-18T01:37:45.356995+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.08422v1","created_at":"2026-05-18T01:37:45.356995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.08422","created_at":"2026-05-18T01:37:45.356995+00:00"},{"alias_kind":"pith_short_12","alias_value":"MV45KWEJMYK5","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_16","alias_value":"MV45KWEJMYK5EOI3","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_8","alias_value":"MV45KWEJ","created_at":"2026-05-18T12:29:32.376354+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/MV45KWEJMYK5EOI3VH7GGABCGX","json":"https://pith.science/pith/MV45KWEJMYK5EOI3VH7GGABCGX.json","graph_json":"https://pith.science/api/pith-number/MV45KWEJMYK5EOI3VH7GGABCGX/graph.json","events_json":"https://pith.science/api/pith-number/MV45KWEJMYK5EOI3VH7GGABCGX/events.json","paper":"https://pith.science/paper/MV45KWEJ"},"agent_actions":{"view_html":"https://pith.science/pith/MV45KWEJMYK5EOI3VH7GGABCGX","download_json":"https://pith.science/pith/MV45KWEJMYK5EOI3VH7GGABCGX.json","view_paper":"https://pith.science/paper/MV45KWEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.08422&json=true","fetch_graph":"https://pith.science/api/pith-number/MV45KWEJMYK5EOI3VH7GGABCGX/graph.json","fetch_events":"https://pith.science/api/pith-number/MV45KWEJMYK5EOI3VH7GGABCGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MV45KWEJMYK5EOI3VH7GGABCGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MV45KWEJMYK5EOI3VH7GGABCGX/action/storage_attestation","attest_author":"https://pith.science/pith/MV45KWEJMYK5EOI3VH7GGABCGX/action/author_attestation","sign_citation":"https://pith.science/pith/MV45KWEJMYK5EOI3VH7GGABCGX/action/citation_signature","submit_replication":"https://pith.science/pith/MV45KWEJMYK5EOI3VH7GGABCGX/action/replication_record"}},"created_at":"2026-05-18T01:37:45.356995+00:00","updated_at":"2026-05-18T01:37:45.356995+00:00"}