{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:BF7TNGCYU4AI3YOUFD35SNLVGK","short_pith_number":"pith:BF7TNGCY","schema_version":"1.0","canonical_sha256":"097f369858a7008de1d428f7d9357532b085bc7b1ca3102ca82a055eca18f353","source":{"kind":"arxiv","id":"1606.00819","version":2},"attestation_state":"computed","paper":{"title":"Matrix Factorization using Window Sampling and Negative Sampling for Improved Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Salle, Aline Villavicencio, Marco Idiart","submitted_at":"2016-06-02T19:35:46Z","abstract_excerpt":"In this paper, we propose LexVec, a new method for generating distributed word representations that uses low-rank, weighted factorization of the Positive Point-wise Mutual Information matrix via stochastic gradient descent, employing a weighting scheme that assigns heavier penalties for errors on frequent co-occurrences while still accounting for negative co-occurrence. Evaluation on word similarity and analogy tasks shows that LexVec matches and often outperforms state-of-the-art methods on many of these tasks."},"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":"1606.00819","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-02T19:35:46Z","cross_cats_sorted":[],"title_canon_sha256":"150f664c8d4685a78069834a71e8ec2531eed738b5e8430b11872710a96003ca","abstract_canon_sha256":"52154b0f1ed34a2f06165535a3b00efdd38377a8a223e2e9cfcc7813b2f7dfc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:45.040253Z","signature_b64":"g7fhBb3Jfl7VEWvAkPa2cdO2A6rctD1oy1nnlZ7o7MQKLT0icERA7E3z/zeet34F4x718l9vKgDP/JPh+kGgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"097f369858a7008de1d428f7d9357532b085bc7b1ca3102ca82a055eca18f353","last_reissued_at":"2026-05-18T01:12:45.039866Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:45.039866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matrix Factorization using Window Sampling and Negative Sampling for Improved Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Salle, Aline Villavicencio, Marco Idiart","submitted_at":"2016-06-02T19:35:46Z","abstract_excerpt":"In this paper, we propose LexVec, a new method for generating distributed word representations that uses low-rank, weighted factorization of the Positive Point-wise Mutual Information matrix via stochastic gradient descent, employing a weighting scheme that assigns heavier penalties for errors on frequent co-occurrences while still accounting for negative co-occurrence. Evaluation on word similarity and analogy tasks shows that LexVec matches and often outperforms state-of-the-art methods on many of these tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00819","kind":"arxiv","version":2},"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":"1606.00819","created_at":"2026-05-18T01:12:45.039921+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.00819v2","created_at":"2026-05-18T01:12:45.039921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00819","created_at":"2026-05-18T01:12:45.039921+00:00"},{"alias_kind":"pith_short_12","alias_value":"BF7TNGCYU4AI","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"BF7TNGCYU4AI3YOU","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"BF7TNGCY","created_at":"2026-05-18T12:30:07.202191+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/BF7TNGCYU4AI3YOUFD35SNLVGK","json":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK.json","graph_json":"https://pith.science/api/pith-number/BF7TNGCYU4AI3YOUFD35SNLVGK/graph.json","events_json":"https://pith.science/api/pith-number/BF7TNGCYU4AI3YOUFD35SNLVGK/events.json","paper":"https://pith.science/paper/BF7TNGCY"},"agent_actions":{"view_html":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK","download_json":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK.json","view_paper":"https://pith.science/paper/BF7TNGCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.00819&json=true","fetch_graph":"https://pith.science/api/pith-number/BF7TNGCYU4AI3YOUFD35SNLVGK/graph.json","fetch_events":"https://pith.science/api/pith-number/BF7TNGCYU4AI3YOUFD35SNLVGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/action/storage_attestation","attest_author":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/action/author_attestation","sign_citation":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/action/citation_signature","submit_replication":"https://pith.science/pith/BF7TNGCYU4AI3YOUFD35SNLVGK/action/replication_record"}},"created_at":"2026-05-18T01:12:45.039921+00:00","updated_at":"2026-05-18T01:12:45.039921+00:00"}