{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RXQ65Q3E7EUW2GT7RX7EORVHPA","short_pith_number":"pith:RXQ65Q3E","schema_version":"1.0","canonical_sha256":"8de1eec364f9296d1a7f8dfe4746a7782e03463f66a2458d98d2a80e411236b6","source":{"kind":"arxiv","id":"1603.04747","version":1},"attestation_state":"computed","paper":{"title":"Topic Modeling Using Distributed Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gagan Madan, Parag Jain, Ramandeep S Randhawa","submitted_at":"2016-03-15T16:21:58Z","abstract_excerpt":"We propose a new algorithm for topic modeling, Vec2Topic, that identifies the main topics in a corpus using semantic information captured via high-dimensional distributed word embeddings. Our technique is unsupervised and generates a list of topics ranked with respect to importance. We find that it works better than existing topic modeling techniques such as Latent Dirichlet Allocation for identifying key topics in user-generated content, such as emails, chats, etc., where topics are diffused across the corpus. We also find that Vec2Topic works equally well for non-user generated content, such"},"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":"1603.04747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-03-15T16:21:58Z","cross_cats_sorted":[],"title_canon_sha256":"04dd7f152ee2520123660869c80272db22ce91881020f831f47ee483836a5ade","abstract_canon_sha256":"1c51e120b6fb9532bea2ced4458a5c02a9384c086da401836cb6ca04f92516e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:04.056723Z","signature_b64":"UqGvrS5PL2tyquKXC0QTkO+BuMByFjSXV7d5f3G3dcymJiiQ+d/dV0uz6orGXeje4FN2mS5QDhXZlJ5VjmWbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8de1eec364f9296d1a7f8dfe4746a7782e03463f66a2458d98d2a80e411236b6","last_reissued_at":"2026-05-18T01:19:04.056127Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:04.056127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topic Modeling Using Distributed Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gagan Madan, Parag Jain, Ramandeep S Randhawa","submitted_at":"2016-03-15T16:21:58Z","abstract_excerpt":"We propose a new algorithm for topic modeling, Vec2Topic, that identifies the main topics in a corpus using semantic information captured via high-dimensional distributed word embeddings. Our technique is unsupervised and generates a list of topics ranked with respect to importance. We find that it works better than existing topic modeling techniques such as Latent Dirichlet Allocation for identifying key topics in user-generated content, such as emails, chats, etc., where topics are diffused across the corpus. We also find that Vec2Topic works equally well for non-user generated content, such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.04747","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":"1603.04747","created_at":"2026-05-18T01:19:04.056205+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.04747v1","created_at":"2026-05-18T01:19:04.056205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.04747","created_at":"2026-05-18T01:19:04.056205+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXQ65Q3E7EUW","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXQ65Q3E7EUW2GT7","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXQ65Q3E","created_at":"2026-05-18T12:30:41.710351+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/RXQ65Q3E7EUW2GT7RX7EORVHPA","json":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA.json","graph_json":"https://pith.science/api/pith-number/RXQ65Q3E7EUW2GT7RX7EORVHPA/graph.json","events_json":"https://pith.science/api/pith-number/RXQ65Q3E7EUW2GT7RX7EORVHPA/events.json","paper":"https://pith.science/paper/RXQ65Q3E"},"agent_actions":{"view_html":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA","download_json":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA.json","view_paper":"https://pith.science/paper/RXQ65Q3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.04747&json=true","fetch_graph":"https://pith.science/api/pith-number/RXQ65Q3E7EUW2GT7RX7EORVHPA/graph.json","fetch_events":"https://pith.science/api/pith-number/RXQ65Q3E7EUW2GT7RX7EORVHPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/action/storage_attestation","attest_author":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/action/author_attestation","sign_citation":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/action/citation_signature","submit_replication":"https://pith.science/pith/RXQ65Q3E7EUW2GT7RX7EORVHPA/action/replication_record"}},"created_at":"2026-05-18T01:19:04.056205+00:00","updated_at":"2026-05-18T01:19:04.056205+00:00"}