{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y75M6RVZHQ6UVUIUVNMLWUYQRF","short_pith_number":"pith:Y75M6RVZ","schema_version":"1.0","canonical_sha256":"c7facf46b93c3d4ad114ab58bb5310897832358034b0afc979fc906e52c97bd3","source":{"kind":"arxiv","id":"2212.09255","version":1},"attestation_state":"computed","paper":{"title":"Multi hash embeddings in spaCy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adriane Boyd, \\'Akos K\\'ad\\'ar, Anders S{\\o}gaard, Lester James Miranda, Matthew Honnibal, Sofie Van Landeghem","submitted_at":"2022-12-19T06:03:04Z","abstract_excerpt":"The distributed representation of symbols is one of the key technologies in machine learning systems today, playing a pivotal role in modern natural language processing. Traditional word embeddings associate a separate vector with each word. While this approach is simple and leads to good performance, it requires a lot of memory for representing a large vocabulary. To reduce the memory footprint, the default embedding layer in spaCy is a hash embeddings layer. It is a stochastic approximation of traditional embeddings that provides unique vectors for a large number of words without explicitly "},"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":"2212.09255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T06:03:04Z","cross_cats_sorted":[],"title_canon_sha256":"9f0c6a9c925c21fa0fa048e7a464b4f34c934442da4ca5d4ec19d252250dc365","abstract_canon_sha256":"78b27049b9fe32482e7ee6735e8d6aab824117939ec50af5ffeb4a9cfde88c97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:20.006943Z","signature_b64":"Ft3jDRFmy4LODSQOMGFkHPcmKsHvZTjmFXZasGOEYNCyueV6Kj+xK/PJIDKPekU4VefFeAkHWwmHh+55hoEADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7facf46b93c3d4ad114ab58bb5310897832358034b0afc979fc906e52c97bd3","last_reissued_at":"2026-07-05T05:26:20.006417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:20.006417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi hash embeddings in spaCy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adriane Boyd, \\'Akos K\\'ad\\'ar, Anders S{\\o}gaard, Lester James Miranda, Matthew Honnibal, Sofie Van Landeghem","submitted_at":"2022-12-19T06:03:04Z","abstract_excerpt":"The distributed representation of symbols is one of the key technologies in machine learning systems today, playing a pivotal role in modern natural language processing. Traditional word embeddings associate a separate vector with each word. While this approach is simple and leads to good performance, it requires a lot of memory for representing a large vocabulary. To reduce the memory footprint, the default embedding layer in spaCy is a hash embeddings layer. It is a stochastic approximation of traditional embeddings that provides unique vectors for a large number of words without explicitly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09255","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.09255/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2212.09255","created_at":"2026-07-05T05:26:20.006482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09255v1","created_at":"2026-07-05T05:26:20.006482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09255","created_at":"2026-07-05T05:26:20.006482+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y75M6RVZHQ6U","created_at":"2026-07-05T05:26:20.006482+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y75M6RVZHQ6UVUIU","created_at":"2026-07-05T05:26:20.006482+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y75M6RVZ","created_at":"2026-07-05T05:26:20.006482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20428","citing_title":"The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation Project","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF","json":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF.json","graph_json":"https://pith.science/api/pith-number/Y75M6RVZHQ6UVUIUVNMLWUYQRF/graph.json","events_json":"https://pith.science/api/pith-number/Y75M6RVZHQ6UVUIUVNMLWUYQRF/events.json","paper":"https://pith.science/paper/Y75M6RVZ"},"agent_actions":{"view_html":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF","download_json":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF.json","view_paper":"https://pith.science/paper/Y75M6RVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09255&json=true","fetch_graph":"https://pith.science/api/pith-number/Y75M6RVZHQ6UVUIUVNMLWUYQRF/graph.json","fetch_events":"https://pith.science/api/pith-number/Y75M6RVZHQ6UVUIUVNMLWUYQRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/action/storage_attestation","attest_author":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/action/author_attestation","sign_citation":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/action/citation_signature","submit_replication":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/action/replication_record"}},"created_at":"2026-07-05T05:26:20.006482+00:00","updated_at":"2026-07-05T05:26:20.006482+00:00"}