{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QZJJHNE37HDNHKD33PVEGJF5ZN","short_pith_number":"pith:QZJJHNE3","schema_version":"1.0","canonical_sha256":"865293b49bf9c6d3a87bdbea4324bdcb666adc596a581995c0289978b4202f2d","source":{"kind":"arxiv","id":"1511.05392","version":3},"attestation_state":"computed","paper":{"title":"Learning the Dimensionality of Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Nalisnick, Sachin Ravi","submitted_at":"2015-11-17T13:28:55Z","abstract_excerpt":"We describe a method for learning word embeddings with data-dependent dimensionality. Our Stochastic Dimensionality Skip-Gram (SD-SG) and Stochastic Dimensionality Continuous Bag-of-Words (SD-CBOW) are nonparametric analogs of Mikolov et al.'s (2013) well-known 'word2vec' models. Vector dimensionality is made dynamic by employing techniques used by Cote & Larochelle (2016) to define an RBM with an infinite number of hidden units. We show qualitatively and quantitatively that SD-SG and SD-CBOW are competitive with their fixed-dimension counterparts while providing a distribution over embedding "},"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":"1511.05392","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-11-17T13:28:55Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"56b452d96b5e4ff1fb2e35684d7dd8ae09d862faaef6f6369e73d3b30a3706fc","abstract_canon_sha256":"44e53c719ab1076f424a243fc6bf0c7cac484d1070dbf32cc01aa294d5ffa4ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:25.210490Z","signature_b64":"Yg0p9Tcy6ypSjzqIQnsPSuS552QcPY4/tdqg/H4bqX1JTxyl/njVCn9GAZ2klQRU7bgpe4wKZ39iJBJhLV7tCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"865293b49bf9c6d3a87bdbea4324bdcb666adc596a581995c0289978b4202f2d","last_reissued_at":"2026-05-18T00:46:25.209842Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:25.209842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning the Dimensionality of Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Nalisnick, Sachin Ravi","submitted_at":"2015-11-17T13:28:55Z","abstract_excerpt":"We describe a method for learning word embeddings with data-dependent dimensionality. Our Stochastic Dimensionality Skip-Gram (SD-SG) and Stochastic Dimensionality Continuous Bag-of-Words (SD-CBOW) are nonparametric analogs of Mikolov et al.'s (2013) well-known 'word2vec' models. Vector dimensionality is made dynamic by employing techniques used by Cote & Larochelle (2016) to define an RBM with an infinite number of hidden units. We show qualitatively and quantitatively that SD-SG and SD-CBOW are competitive with their fixed-dimension counterparts while providing a distribution over embedding "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05392","kind":"arxiv","version":3},"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":"1511.05392","created_at":"2026-05-18T00:46:25.209949+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.05392v3","created_at":"2026-05-18T00:46:25.209949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05392","created_at":"2026-05-18T00:46:25.209949+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZJJHNE37HDN","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZJJHNE37HDNHKD3","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZJJHNE3","created_at":"2026-05-18T12:29:39.896362+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/QZJJHNE37HDNHKD33PVEGJF5ZN","json":"https://pith.science/pith/QZJJHNE37HDNHKD33PVEGJF5ZN.json","graph_json":"https://pith.science/api/pith-number/QZJJHNE37HDNHKD33PVEGJF5ZN/graph.json","events_json":"https://pith.science/api/pith-number/QZJJHNE37HDNHKD33PVEGJF5ZN/events.json","paper":"https://pith.science/paper/QZJJHNE3"},"agent_actions":{"view_html":"https://pith.science/pith/QZJJHNE37HDNHKD33PVEGJF5ZN","download_json":"https://pith.science/pith/QZJJHNE37HDNHKD33PVEGJF5ZN.json","view_paper":"https://pith.science/paper/QZJJHNE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.05392&json=true","fetch_graph":"https://pith.science/api/pith-number/QZJJHNE37HDNHKD33PVEGJF5ZN/graph.json","fetch_events":"https://pith.science/api/pith-number/QZJJHNE37HDNHKD33PVEGJF5ZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZJJHNE37HDNHKD33PVEGJF5ZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZJJHNE37HDNHKD33PVEGJF5ZN/action/storage_attestation","attest_author":"https://pith.science/pith/QZJJHNE37HDNHKD33PVEGJF5ZN/action/author_attestation","sign_citation":"https://pith.science/pith/QZJJHNE37HDNHKD33PVEGJF5ZN/action/citation_signature","submit_replication":"https://pith.science/pith/QZJJHNE37HDNHKD33PVEGJF5ZN/action/replication_record"}},"created_at":"2026-05-18T00:46:25.209949+00:00","updated_at":"2026-05-18T00:46:25.209949+00:00"}