{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Y75M6RVZHQ6UVUIUVNMLWUYQRF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"78b27049b9fe32482e7ee6735e8d6aab824117939ec50af5ffeb4a9cfde88c97","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T06:03:04Z","title_canon_sha256":"9f0c6a9c925c21fa0fa048e7a464b4f34c934442da4ca5d4ec19d252250dc365"},"schema_version":"1.0","source":{"id":"2212.09255","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09255","created_at":"2026-07-05T05:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09255v1","created_at":"2026-07-05T05:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09255","created_at":"2026-07-05T05:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"Y75M6RVZHQ6U","created_at":"2026-07-05T05:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"Y75M6RVZHQ6UVUIU","created_at":"2026-07-05T05:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"Y75M6RVZ","created_at":"2026-07-05T05:26:20Z"}],"graph_snapshots":[{"event_id":"sha256:5bfd8b2351f5f7ef465c7a5ceabf6ec458324d6e6be0ad795bc1dacfecf822e3","target":"graph","created_at":"2026-07-05T05:26:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2212.09255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Adriane Boyd, \\'Akos K\\'ad\\'ar, Anders S{\\o}gaard, Lester James Miranda, Matthew Honnibal, Sofie Van Landeghem","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T06:03:04Z","title":"Multi hash embeddings in spaCy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09255","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c07e946ae741b27617e21164c75b8813bc60ba74ffef6805fc8e2c796da66ff1","target":"record","created_at":"2026-07-05T05:26:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"78b27049b9fe32482e7ee6735e8d6aab824117939ec50af5ffeb4a9cfde88c97","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T06:03:04Z","title_canon_sha256":"9f0c6a9c925c21fa0fa048e7a464b4f34c934442da4ca5d4ec19d252250dc365"},"schema_version":"1.0","source":{"id":"2212.09255","kind":"arxiv","version":1}},"canonical_sha256":"c7facf46b93c3d4ad114ab58bb5310897832358034b0afc979fc906e52c97bd3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7facf46b93c3d4ad114ab58bb5310897832358034b0afc979fc906e52c97bd3","first_computed_at":"2026-07-05T05:26:20.006417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:20.006417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ft3jDRFmy4LODSQOMGFkHPcmKsHvZTjmFXZasGOEYNCyueV6Kj+xK/PJIDKPekU4VefFeAkHWwmHh+55hoEADg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:20.006943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09255","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c07e946ae741b27617e21164c75b8813bc60ba74ffef6805fc8e2c796da66ff1","sha256:5bfd8b2351f5f7ef465c7a5ceabf6ec458324d6e6be0ad795bc1dacfecf822e3"],"state_sha256":"ae37aeb2895cc2ecc99186a412eb437c1cb7cfd58ee13f09d071e441f0fba27c"}