{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:36NBI6DQWCHW5TURMK4BDPXFVF","short_pith_number":"pith:36NBI6DQ","canonical_record":{"source":{"id":"2109.05772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T08:31:01Z","cross_cats_sorted":[],"title_canon_sha256":"41b23abe702b46b0163168e51b1fcab1cf7efb6b114e9f08285d56873062b034","abstract_canon_sha256":"32753c56c81e4b913065921564af0c443480ba956478af99e17e944a96f46ea0"},"schema_version":"1.0"},"canonical_sha256":"df9a147870b08f6ece9162b811bee5a950a89bff6f5e32f8f415463c7b9bae2d","source":{"kind":"arxiv","id":"2109.05772","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05772","created_at":"2026-07-05T03:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05772v1","created_at":"2026-07-05T03:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05772","created_at":"2026-07-05T03:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"36NBI6DQWCHW","created_at":"2026-07-05T03:13:42Z"},{"alias_kind":"pith_short_16","alias_value":"36NBI6DQWCHW5TUR","created_at":"2026-07-05T03:13:42Z"},{"alias_kind":"pith_short_8","alias_value":"36NBI6DQ","created_at":"2026-07-05T03:13:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:36NBI6DQWCHW5TURMK4BDPXFVF","target":"record","payload":{"canonical_record":{"source":{"id":"2109.05772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T08:31:01Z","cross_cats_sorted":[],"title_canon_sha256":"41b23abe702b46b0163168e51b1fcab1cf7efb6b114e9f08285d56873062b034","abstract_canon_sha256":"32753c56c81e4b913065921564af0c443480ba956478af99e17e944a96f46ea0"},"schema_version":"1.0"},"canonical_sha256":"df9a147870b08f6ece9162b811bee5a950a89bff6f5e32f8f415463c7b9bae2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:42.277165Z","signature_b64":"4Wta/zHC30Hcvksrl4jQSsQnfHGBtUELqQJwAftzrUkvGLcx+xhjmlCe49XZkjtjaWb+MCcN8fkfVs0TpJeGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df9a147870b08f6ece9162b811bee5a950a89bff6f5e32f8f415463c7b9bae2d","last_reissued_at":"2026-07-05T03:13:42.276815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:42.276815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.05772","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":"2026-07-05T03:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7UyAy/6QHqJuM95rH6zvBR1GD4K6ex06+JPeASLEwnrM3J0FzxEPs1JgSNKKHh+5WWRhYhPCJf7cD1ZCs8ouBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:54:44.077927Z"},"content_sha256":"a7a1550ceef71222f6aac7be36aab298dd5a2071fc4e0ecb60376b528705e0d2","schema_version":"1.0","event_id":"sha256:a7a1550ceef71222f6aac7be36aab298dd5a2071fc4e0ecb60376b528705e0d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:36NBI6DQWCHW5TURMK4BDPXFVF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonis Maronikolakis, Hinrich Sch\\\"utze, Philipp Dufter","submitted_at":"2021-09-13T08:31:01Z","abstract_excerpt":"The size of the vocabulary is a central design choice in large pretrained language models, with respect to both performance and memory requirements. Typically, subword tokenization algorithms such as byte pair encoding and WordPiece are used. In this work, we investigate the compatibility of tokenizations for multilingual static and contextualized embedding spaces and propose a measure that reflects the compatibility of tokenizations across languages. Our goal is to prevent incompatible tokenizations, e.g., \"wine\" (word-level) in English vs.\\ \"v i n\" (character-level) in French, which make it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05772","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/2109.05772/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":"2026-07-05T03:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yIEdMlwbQKRa0GPvcQEI2Z2mZQAqGbffsym/CV49Qvm1/p/+XX2Qtbb/pgpLCGBhqeBzXMz3jwlfk/q9KjcUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:54:44.078853Z"},"content_sha256":"1f38f7170193960cb8bee95115416041520232abe5df2dc8a4d0c42d5e18f4c7","schema_version":"1.0","event_id":"sha256:1f38f7170193960cb8bee95115416041520232abe5df2dc8a4d0c42d5e18f4c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36NBI6DQWCHW5TURMK4BDPXFVF/bundle.json","state_url":"https://pith.science/pith/36NBI6DQWCHW5TURMK4BDPXFVF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36NBI6DQWCHW5TURMK4BDPXFVF/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":"2026-08-15T22:54:44Z","links":{"resolver":"https://pith.science/pith/36NBI6DQWCHW5TURMK4BDPXFVF","bundle":"https://pith.science/pith/36NBI6DQWCHW5TURMK4BDPXFVF/bundle.json","state":"https://pith.science/pith/36NBI6DQWCHW5TURMK4BDPXFVF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36NBI6DQWCHW5TURMK4BDPXFVF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:36NBI6DQWCHW5TURMK4BDPXFVF","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":"32753c56c81e4b913065921564af0c443480ba956478af99e17e944a96f46ea0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T08:31:01Z","title_canon_sha256":"41b23abe702b46b0163168e51b1fcab1cf7efb6b114e9f08285d56873062b034"},"schema_version":"1.0","source":{"id":"2109.05772","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05772","created_at":"2026-07-05T03:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05772v1","created_at":"2026-07-05T03:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05772","created_at":"2026-07-05T03:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"36NBI6DQWCHW","created_at":"2026-07-05T03:13:42Z"},{"alias_kind":"pith_short_16","alias_value":"36NBI6DQWCHW5TUR","created_at":"2026-07-05T03:13:42Z"},{"alias_kind":"pith_short_8","alias_value":"36NBI6DQ","created_at":"2026-07-05T03:13:42Z"}],"graph_snapshots":[{"event_id":"sha256:1f38f7170193960cb8bee95115416041520232abe5df2dc8a4d0c42d5e18f4c7","target":"graph","created_at":"2026-07-05T03:13:42Z","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/2109.05772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The size of the vocabulary is a central design choice in large pretrained language models, with respect to both performance and memory requirements. Typically, subword tokenization algorithms such as byte pair encoding and WordPiece are used. In this work, we investigate the compatibility of tokenizations for multilingual static and contextualized embedding spaces and propose a measure that reflects the compatibility of tokenizations across languages. Our goal is to prevent incompatible tokenizations, e.g., \"wine\" (word-level) in English vs.\\ \"v i n\" (character-level) in French, which make it ","authors_text":"Antonis Maronikolakis, Hinrich Sch\\\"utze, Philipp Dufter","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T08:31:01Z","title":"Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05772","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:a7a1550ceef71222f6aac7be36aab298dd5a2071fc4e0ecb60376b528705e0d2","target":"record","created_at":"2026-07-05T03:13:42Z","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":"32753c56c81e4b913065921564af0c443480ba956478af99e17e944a96f46ea0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T08:31:01Z","title_canon_sha256":"41b23abe702b46b0163168e51b1fcab1cf7efb6b114e9f08285d56873062b034"},"schema_version":"1.0","source":{"id":"2109.05772","kind":"arxiv","version":1}},"canonical_sha256":"df9a147870b08f6ece9162b811bee5a950a89bff6f5e32f8f415463c7b9bae2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df9a147870b08f6ece9162b811bee5a950a89bff6f5e32f8f415463c7b9bae2d","first_computed_at":"2026-07-05T03:13:42.276815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:42.276815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Wta/zHC30Hcvksrl4jQSsQnfHGBtUELqQJwAftzrUkvGLcx+xhjmlCe49XZkjtjaWb+MCcN8fkfVs0TpJeGCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:42.277165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.05772","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7a1550ceef71222f6aac7be36aab298dd5a2071fc4e0ecb60376b528705e0d2","sha256:1f38f7170193960cb8bee95115416041520232abe5df2dc8a4d0c42d5e18f4c7"],"state_sha256":"6d595cbafff0bcc45fdc9a7a0e7aabd3edc87545fce8e1e74d38245911ee333e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oaKbPTv33SSkEXUoTiJRuUwJ78Yae3s63kAv1jCuxPVsaWPWOcF70PXuCsSKQiVqh2F+Ih9icOpmQJCRrlUeCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T22:54:44.084853Z","bundle_sha256":"84636a9368163671ffed02dde5a4834ec69cccb3f06d53affde7589de10e3996"}}