{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IVCXN2JM2A6V4MD2Z5ER3KPOMO","short_pith_number":"pith:IVCXN2JM","schema_version":"1.0","canonical_sha256":"454576e92cd03d5e307acf491da9ee63976a5c88f81b88893bfcedf8b86351c6","source":{"kind":"arxiv","id":"1712.09405","version":1},"attestation_state":"computed","paper":{"title":"Advances in Pre-Training Distributed Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armand Joulin, Christian Puhrsch, Edouard Grave, Piotr Bojanowski, Tomas Mikolov","submitted_at":"2017-12-26T21:00:04Z","abstract_excerpt":"Many Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl. In this paper, we show how to train high-quality word vector representations by using a combination of known tricks that are however rarely used together. The main result of our work is the new set of publicly available pre-trained models that outperform the current state of the art by a large margin on a number of 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":"1712.09405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-26T21:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"071efe1dedb149703f684174e2d7152a14724420f69c6f565b66cc73eda9f05a","abstract_canon_sha256":"944c094bc874ee9899349be68632e8228e6b39d71ac9e5fe6d9eb59bd11a2f22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:08.535366Z","signature_b64":"G7HBrTjsSQuJjWbuzDqsNRndMTJ55nPzazrZYnQuxMS4Hlv6HC7selbd+0eM+igvKNQ9aFOS+QWI6hV5mraLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"454576e92cd03d5e307acf491da9ee63976a5c88f81b88893bfcedf8b86351c6","last_reissued_at":"2026-05-18T00:27:08.534682Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:08.534682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advances in Pre-Training Distributed Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armand Joulin, Christian Puhrsch, Edouard Grave, Piotr Bojanowski, Tomas Mikolov","submitted_at":"2017-12-26T21:00:04Z","abstract_excerpt":"Many Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl. In this paper, we show how to train high-quality word vector representations by using a combination of known tricks that are however rarely used together. The main result of our work is the new set of publicly available pre-trained models that outperform the current state of the art by a large margin on a number of tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09405","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":"1712.09405","created_at":"2026-05-18T00:27:08.534795+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09405v1","created_at":"2026-05-18T00:27:08.534795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09405","created_at":"2026-05-18T00:27:08.534795+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVCXN2JM2A6V","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVCXN2JM2A6V4MD2","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVCXN2JM","created_at":"2026-05-18T12:31:21.493067+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/IVCXN2JM2A6V4MD2Z5ER3KPOMO","json":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO.json","graph_json":"https://pith.science/api/pith-number/IVCXN2JM2A6V4MD2Z5ER3KPOMO/graph.json","events_json":"https://pith.science/api/pith-number/IVCXN2JM2A6V4MD2Z5ER3KPOMO/events.json","paper":"https://pith.science/paper/IVCXN2JM"},"agent_actions":{"view_html":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO","download_json":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO.json","view_paper":"https://pith.science/paper/IVCXN2JM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09405&json=true","fetch_graph":"https://pith.science/api/pith-number/IVCXN2JM2A6V4MD2Z5ER3KPOMO/graph.json","fetch_events":"https://pith.science/api/pith-number/IVCXN2JM2A6V4MD2Z5ER3KPOMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/action/storage_attestation","attest_author":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/action/author_attestation","sign_citation":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/action/citation_signature","submit_replication":"https://pith.science/pith/IVCXN2JM2A6V4MD2Z5ER3KPOMO/action/replication_record"}},"created_at":"2026-05-18T00:27:08.534795+00:00","updated_at":"2026-05-18T00:27:08.534795+00:00"}