{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:UR7ACT4KFKHQQNBD4EOJNWEQKT","short_pith_number":"pith:UR7ACT4K","schema_version":"1.0","canonical_sha256":"a47e014f8a2a8f083423e11c96d89054ed8776bc3d786beb1ddbb03e0fd2a740","source":{"kind":"arxiv","id":"1510.02675","version":2},"attestation_state":"computed","paper":{"title":"Controlled Experiments for Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adriaan M. J. Schakel, Benjamin J. Wilson","submitted_at":"2015-10-09T14:03:33Z","abstract_excerpt":"An experimental approach to studying the properties of word embeddings is proposed. Controlled experiments, achieved through modifications of the training corpus, permit the demonstration of direct relations between word properties and word vector direction and length. The approach is demonstrated using the word2vec CBOW model with experiments that independently vary word frequency and word co-occurrence noise. The experiments reveal that word vector length depends more or less linearly on both word frequency and the level of noise in the co-occurrence distribution of the word. The coefficient"},"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":"1510.02675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-10-09T14:03:33Z","cross_cats_sorted":[],"title_canon_sha256":"e617cb59bf398f66d428a253de1d0a63f3c2c6b57d774cf7166ca1942eb17c5d","abstract_canon_sha256":"de2a0740da56788a04e28c8a11319c237fd01794e9d1b6868be69e5d53989529"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:24.270838Z","signature_b64":"8zYx0jWYvRba9ZlAbhmza7GW/vBNYfF+teuGr4FbhfSw9FWjzfDDL1ffU9ldg1Uq5VGBED1AoFgao02Kdv7kCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a47e014f8a2a8f083423e11c96d89054ed8776bc3d786beb1ddbb03e0fd2a740","last_reissued_at":"2026-05-18T01:24:24.270152Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:24.270152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlled Experiments for Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adriaan M. J. Schakel, Benjamin J. Wilson","submitted_at":"2015-10-09T14:03:33Z","abstract_excerpt":"An experimental approach to studying the properties of word embeddings is proposed. Controlled experiments, achieved through modifications of the training corpus, permit the demonstration of direct relations between word properties and word vector direction and length. The approach is demonstrated using the word2vec CBOW model with experiments that independently vary word frequency and word co-occurrence noise. The experiments reveal that word vector length depends more or less linearly on both word frequency and the level of noise in the co-occurrence distribution of the word. The coefficient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.02675","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":"1510.02675","created_at":"2026-05-18T01:24:24.270253+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.02675v2","created_at":"2026-05-18T01:24:24.270253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.02675","created_at":"2026-05-18T01:24:24.270253+00:00"},{"alias_kind":"pith_short_12","alias_value":"UR7ACT4KFKHQ","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_16","alias_value":"UR7ACT4KFKHQQNBD","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_8","alias_value":"UR7ACT4K","created_at":"2026-05-18T12:29:44.643036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.27322","citing_title":"Semantic Gradients Interactions in SSD: A Case Study in Racial Identity and Hate Speech","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UR7ACT4KFKHQQNBD4EOJNWEQKT","json":"https://pith.science/pith/UR7ACT4KFKHQQNBD4EOJNWEQKT.json","graph_json":"https://pith.science/api/pith-number/UR7ACT4KFKHQQNBD4EOJNWEQKT/graph.json","events_json":"https://pith.science/api/pith-number/UR7ACT4KFKHQQNBD4EOJNWEQKT/events.json","paper":"https://pith.science/paper/UR7ACT4K"},"agent_actions":{"view_html":"https://pith.science/pith/UR7ACT4KFKHQQNBD4EOJNWEQKT","download_json":"https://pith.science/pith/UR7ACT4KFKHQQNBD4EOJNWEQKT.json","view_paper":"https://pith.science/paper/UR7ACT4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.02675&json=true","fetch_graph":"https://pith.science/api/pith-number/UR7ACT4KFKHQQNBD4EOJNWEQKT/graph.json","fetch_events":"https://pith.science/api/pith-number/UR7ACT4KFKHQQNBD4EOJNWEQKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UR7ACT4KFKHQQNBD4EOJNWEQKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UR7ACT4KFKHQQNBD4EOJNWEQKT/action/storage_attestation","attest_author":"https://pith.science/pith/UR7ACT4KFKHQQNBD4EOJNWEQKT/action/author_attestation","sign_citation":"https://pith.science/pith/UR7ACT4KFKHQQNBD4EOJNWEQKT/action/citation_signature","submit_replication":"https://pith.science/pith/UR7ACT4KFKHQQNBD4EOJNWEQKT/action/replication_record"}},"created_at":"2026-05-18T01:24:24.270253+00:00","updated_at":"2026-05-18T01:24:24.270253+00:00"}