{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Y75M6RVZHQ6UVUIUVNMLWUYQRF","short_pith_number":"pith:Y75M6RVZ","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"},"canonical_sha256":"c7facf46b93c3d4ad114ab58bb5310897832358034b0afc979fc906e52c97bd3","source":{"kind":"arxiv","id":"2212.09255","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Y75M6RVZHQ6UVUIUVNMLWUYQRF","target":"record","payload":{"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"},"canonical_sha256":"c7facf46b93c3d4ad114ab58bb5310897832358034b0afc979fc906e52c97bd3","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"},"source_kind":"arxiv","source_id":"2212.09255","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:26:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tczu2Xg2gfZzOvp8GPvLdyXUWZC/6Pjwbp23AMaXorHpN8K8d+MZ7b8ZOHVdaa0sQIsJxHm5OcIfjMWU290CBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:11:20.815299Z"},"content_sha256":"c07e946ae741b27617e21164c75b8813bc60ba74ffef6805fc8e2c796da66ff1","schema_version":"1.0","event_id":"sha256:c07e946ae741b27617e21164c75b8813bc60ba74ffef6805fc8e2c796da66ff1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Y75M6RVZHQ6UVUIUVNMLWUYQRF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:26:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2oSm1aLtfJUxlnolcLc79eQeGh3nO6kBc0GG/eAAzOXCRtXJwbIOh2RQEl8QORLI70LQr4gZqotFqb+w1n0ZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:11:20.815845Z"},"content_sha256":"5bfd8b2351f5f7ef465c7a5ceabf6ec458324d6e6be0ad795bc1dacfecf822e3","schema_version":"1.0","event_id":"sha256:5bfd8b2351f5f7ef465c7a5ceabf6ec458324d6e6be0ad795bc1dacfecf822e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/bundle.json","state_url":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T16:11:20Z","links":{"resolver":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF","bundle":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/bundle.json","state":"https://pith.science/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y75M6RVZHQ6UVUIUVNMLWUYQRF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i6EUoGqlKH/kOtJaZpoXgTM7l+W11Jtd7PhPubKhSO8OM7aWk2AoNImzLFB/0uuB19BECbu3KNUFi65kmWpRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:11:20.821194Z","bundle_sha256":"37e0c130274296107db00c3293dfa3181e1f76041dfd0c864c14db7ec935247d"}}