{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:W2DEKMNW6BUHZJDEIB3OUD4UCC","short_pith_number":"pith:W2DEKMNW","schema_version":"1.0","canonical_sha256":"b6864531b6f0687ca4644076ea0f9410b933bf42001086c8ce168e008b927d63","source":{"kind":"arxiv","id":"1310.4546","version":1},"attestation_state":"computed","paper":{"title":"Distributed Representations of Words and Phrases and their Compositionality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Greg Corrado, Ilya Sutskever, Jeffrey Dean, Kai Chen, Tomas Mikolov","submitted_at":"2013-10-16T23:28:53Z","abstract_excerpt":"The recently introduced continuous Skip-gram model is an efficient method for learning high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships. In this paper we present several extensions that improve both the quality of the vectors and the training speed. By subsampling of the frequent words we obtain significant speedup and also learn more regular word representations. We also describe a simple alternative to the hierarchical softmax called negative sampling. An inherent limitation of word representations is their indif"},"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":"1310.4546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-10-16T23:28:53Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ab41f5bb6a50af5ed6b2de5b71ceb23ce1502d482c786756f2cd0a7a8f4e24e4","abstract_canon_sha256":"08bef1944f845244c5069673effb546b4fd2cdf9c9f2233ab295a02596f27585"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:13.812231Z","signature_b64":"/JdcAIPvgC4pt/nU4O/kol2/CVNTUY1B/G5U/JkqYtWj4F27MyMlKbik/EeoMlmTxN7FK4KfZqC2cYyR+x6gCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6864531b6f0687ca4644076ea0f9410b933bf42001086c8ce168e008b927d63","last_reissued_at":"2026-05-18T03:10:13.811642Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:13.811642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Representations of Words and Phrases and their Compositionality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Greg Corrado, Ilya Sutskever, Jeffrey Dean, Kai Chen, Tomas Mikolov","submitted_at":"2013-10-16T23:28:53Z","abstract_excerpt":"The recently introduced continuous Skip-gram model is an efficient method for learning high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships. In this paper we present several extensions that improve both the quality of the vectors and the training speed. By subsampling of the frequent words we obtain significant speedup and also learn more regular word representations. We also describe a simple alternative to the hierarchical softmax called negative sampling. An inherent limitation of word representations is their indif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1310.4546","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":"1310.4546","created_at":"2026-05-18T03:10:13.811754+00:00"},{"alias_kind":"arxiv_version","alias_value":"1310.4546v1","created_at":"2026-05-18T03:10:13.811754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1310.4546","created_at":"2026-05-18T03:10:13.811754+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2DEKMNW6BUH","created_at":"2026-05-18T12:28:04.890932+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2DEKMNW6BUHZJDE","created_at":"2026-05-18T12:28:04.890932+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2DEKMNW","created_at":"2026-05-18T12:28:04.890932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":12,"sample":[{"citing_arxiv_id":"1907.07225","citing_title":"DeepTrax: Embedding Graphs of Financial Transactions","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2108.00480","citing_title":"Realised Volatility Forecasting: Machine Learning via Financial Word Embedding","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2502.08875","citing_title":"Utilizing Pre-trained and Large Language Models for 10-K Items Segmentation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2504.02343","citing_title":"Toward General and Robust LLM-enhanced Text-attributed Graph Learning","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17187","citing_title":"PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media","ref_index":255,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18410","citing_title":"From Node2Vec to GPT-based GraphRAG: scientific impact prediction across graph and language models","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2510.12837","citing_title":"Semantic knowledge guides innovation and drives cultural evolution","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"2104.08821","citing_title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28816","citing_title":"ASTRA: Mapping Art-Technology Institutions via Conceptual Axes, Text Embeddings, and Unsupervised Clustering","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12813","citing_title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12809","citing_title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","ref_index":244,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02926","citing_title":"A Multi-head-based architecture for effective morphological tagging in Russian with open dictionary","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2404.08471","citing_title":"Revisiting Feature Prediction for Learning Visual Representations from Video","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24374","citing_title":"MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08846","citing_title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"1909.08053","citing_title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14907","citing_title":"Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2DEKMNW6BUHZJDEIB3OUD4UCC","json":"https://pith.science/pith/W2DEKMNW6BUHZJDEIB3OUD4UCC.json","graph_json":"https://pith.science/api/pith-number/W2DEKMNW6BUHZJDEIB3OUD4UCC/graph.json","events_json":"https://pith.science/api/pith-number/W2DEKMNW6BUHZJDEIB3OUD4UCC/events.json","paper":"https://pith.science/paper/W2DEKMNW"},"agent_actions":{"view_html":"https://pith.science/pith/W2DEKMNW6BUHZJDEIB3OUD4UCC","download_json":"https://pith.science/pith/W2DEKMNW6BUHZJDEIB3OUD4UCC.json","view_paper":"https://pith.science/paper/W2DEKMNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1310.4546&json=true","fetch_graph":"https://pith.science/api/pith-number/W2DEKMNW6BUHZJDEIB3OUD4UCC/graph.json","fetch_events":"https://pith.science/api/pith-number/W2DEKMNW6BUHZJDEIB3OUD4UCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2DEKMNW6BUHZJDEIB3OUD4UCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2DEKMNW6BUHZJDEIB3OUD4UCC/action/storage_attestation","attest_author":"https://pith.science/pith/W2DEKMNW6BUHZJDEIB3OUD4UCC/action/author_attestation","sign_citation":"https://pith.science/pith/W2DEKMNW6BUHZJDEIB3OUD4UCC/action/citation_signature","submit_replication":"https://pith.science/pith/W2DEKMNW6BUHZJDEIB3OUD4UCC/action/replication_record"}},"created_at":"2026-05-18T03:10:13.811754+00:00","updated_at":"2026-05-18T03:10:13.811754+00:00"}