{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:26NKQVLBYMHWSYHW34IVCF72AK","short_pith_number":"pith:26NKQVLB","schema_version":"1.0","canonical_sha256":"d79aa85561c30f6960f6df115117fa02827a5212e5a08968e027c4a48dfadd60","source":{"kind":"arxiv","id":"1806.02901","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic FastText for Multi-Sense Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Andrew Gordon Wilson, Anima Anandkumar, Ben Athiwaratkun","submitted_at":"2018-06-07T20:57:22Z","abstract_excerpt":"We introduce Probabilistic FastText, a new model for word embeddings that can capture multiple word senses, sub-word structure, and uncertainty information. In particular, we represent each word with a Gaussian mixture density, where the mean of a mixture component is given by the sum of n-grams. This representation allows the model to share statistical strength across sub-word structures (e.g. Latin roots), producing accurate representations of rare, misspelt, or even unseen words. Moreover, each component of the mixture can capture a different word sense. Probabilistic FastText outperforms b"},"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":"1806.02901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-07T20:57:22Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"31f05f2a7e8bcbd6b49bf2e1912e5fd40f43e039cdff34be9dc7604e7398e4ae","abstract_canon_sha256":"f51bf8920a31872f5d7f706959fb2fb736a23134392d61dce5e01567733f2568"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:54.410974Z","signature_b64":"CN0CLXxIvj1/ukGl6OgMwwNgGpAm53QNBUzhZD3rhVWLGxAzgSDZbWwLDpyS41Kxga14FwbSFj3vTTbUBlnTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d79aa85561c30f6960f6df115117fa02827a5212e5a08968e027c4a48dfadd60","last_reissued_at":"2026-05-18T00:13:54.410219Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:54.410219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic FastText for Multi-Sense Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Andrew Gordon Wilson, Anima Anandkumar, Ben Athiwaratkun","submitted_at":"2018-06-07T20:57:22Z","abstract_excerpt":"We introduce Probabilistic FastText, a new model for word embeddings that can capture multiple word senses, sub-word structure, and uncertainty information. In particular, we represent each word with a Gaussian mixture density, where the mean of a mixture component is given by the sum of n-grams. This representation allows the model to share statistical strength across sub-word structures (e.g. Latin roots), producing accurate representations of rare, misspelt, or even unseen words. Moreover, each component of the mixture can capture a different word sense. Probabilistic FastText outperforms b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02901","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":"1806.02901","created_at":"2026-05-18T00:13:54.410309+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.02901v1","created_at":"2026-05-18T00:13:54.410309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02901","created_at":"2026-05-18T00:13:54.410309+00:00"},{"alias_kind":"pith_short_12","alias_value":"26NKQVLBYMHW","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"26NKQVLBYMHWSYHW","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"26NKQVLB","created_at":"2026-05-18T12:31:59.375834+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/26NKQVLBYMHWSYHW34IVCF72AK","json":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK.json","graph_json":"https://pith.science/api/pith-number/26NKQVLBYMHWSYHW34IVCF72AK/graph.json","events_json":"https://pith.science/api/pith-number/26NKQVLBYMHWSYHW34IVCF72AK/events.json","paper":"https://pith.science/paper/26NKQVLB"},"agent_actions":{"view_html":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK","download_json":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK.json","view_paper":"https://pith.science/paper/26NKQVLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.02901&json=true","fetch_graph":"https://pith.science/api/pith-number/26NKQVLBYMHWSYHW34IVCF72AK/graph.json","fetch_events":"https://pith.science/api/pith-number/26NKQVLBYMHWSYHW34IVCF72AK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK/action/storage_attestation","attest_author":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK/action/author_attestation","sign_citation":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK/action/citation_signature","submit_replication":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK/action/replication_record"}},"created_at":"2026-05-18T00:13:54.410309+00:00","updated_at":"2026-05-18T00:13:54.410309+00:00"}