{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XWCSD4DVZKCKZ6DRS2KM3INQPJ","short_pith_number":"pith:XWCSD4DV","canonical_record":{"source":{"id":"2507.06378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T20:32:26Z","cross_cats_sorted":[],"title_canon_sha256":"17a2c35cc588380a2192c07a1854d80cf8caf37dacce46a5f7b072271b2e83f0","abstract_canon_sha256":"36459e746e1e1a47ae487b114957726c7e8322eabdd244492edf8b5eac9401a5"},"schema_version":"1.0"},"canonical_sha256":"bd8521f075ca84acf8719694cda1b07a5249989e50ee570288964c3c76e8c11d","source":{"kind":"arxiv","id":"2507.06378","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06378","created_at":"2026-07-05T11:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06378v1","created_at":"2026-07-05T11:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06378","created_at":"2026-07-05T11:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"XWCSD4DVZKCK","created_at":"2026-07-05T11:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"XWCSD4DVZKCKZ6DR","created_at":"2026-07-05T11:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"XWCSD4DV","created_at":"2026-07-05T11:34:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XWCSD4DVZKCKZ6DRS2KM3INQPJ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T20:32:26Z","cross_cats_sorted":[],"title_canon_sha256":"17a2c35cc588380a2192c07a1854d80cf8caf37dacce46a5f7b072271b2e83f0","abstract_canon_sha256":"36459e746e1e1a47ae487b114957726c7e8322eabdd244492edf8b5eac9401a5"},"schema_version":"1.0"},"canonical_sha256":"bd8521f075ca84acf8719694cda1b07a5249989e50ee570288964c3c76e8c11d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:14.692039Z","signature_b64":"42keGbFeqPobymXCeywaVO3HQ/11AMu58aG8LdwjdMVOe2kb/Qc/j17UF/HMD427YwqBaKyD27CAKl1V4nh/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd8521f075ca84acf8719694cda1b07a5249989e50ee570288964c3c76e8c11d","last_reissued_at":"2026-07-05T11:34:14.691598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:14.691598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06378","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":"2026-07-05T11:34:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QRU+kGgBg8bO27NzsYzecMjZadzNn04c9/F+p6zYxcPP6M6hmKLE6Xo/bSx2RqFyddEXICe3LRHtAxuJDZBpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:23:00.447702Z"},"content_sha256":"9294b9b001c60b7ca21765a3481855624167fcb3dc548c1167f2c7aa5329e77b","schema_version":"1.0","event_id":"sha256:9294b9b001c60b7ca21765a3481855624167fcb3dc548c1167f2c7aa5329e77b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XWCSD4DVZKCKZ6DRS2KM3INQPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Morphological Alignment of Tokenizers in 70 Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brendan O'Connor, Catherine Arnett, Marisa Hudspeth","submitted_at":"2025-07-08T20:32:26Z","abstract_excerpt":"While tokenization is a key step in language modeling, with effects on model training and performance, it remains unclear how to effectively evaluate tokenizer quality. One proposed dimension of tokenizer quality is the extent to which tokenizers preserve linguistically meaningful subwords, aligning token boundaries with morphological boundaries within a word. We expand MorphScore (Arnett & Bergen, 2025), which previously covered 22 languages, to support a total of 70 languages. The updated MorphScore offers more flexibility in evaluation and addresses some of the limitations of the original v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06378","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/2507.06378/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":"2026-07-05T11:34:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jfUbhDR7HVu9vzOF6MkNgSQgLxYlGa+ECN755p4VKeocTxvZZD7bjsjvWBgJkHjMA0AVBe4cJrRUX8pRKdAYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:23:00.448262Z"},"content_sha256":"b32ccd45a0b862af1f0a0086d8bcc54dc5bb04cc33b8ffbbe1991ee5abacb32e","schema_version":"1.0","event_id":"sha256:b32ccd45a0b862af1f0a0086d8bcc54dc5bb04cc33b8ffbbe1991ee5abacb32e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XWCSD4DVZKCKZ6DRS2KM3INQPJ/bundle.json","state_url":"https://pith.science/pith/XWCSD4DVZKCKZ6DRS2KM3INQPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XWCSD4DVZKCKZ6DRS2KM3INQPJ/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":"2026-08-08T16:23:00Z","links":{"resolver":"https://pith.science/pith/XWCSD4DVZKCKZ6DRS2KM3INQPJ","bundle":"https://pith.science/pith/XWCSD4DVZKCKZ6DRS2KM3INQPJ/bundle.json","state":"https://pith.science/pith/XWCSD4DVZKCKZ6DRS2KM3INQPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XWCSD4DVZKCKZ6DRS2KM3INQPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XWCSD4DVZKCKZ6DRS2KM3INQPJ","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":"36459e746e1e1a47ae487b114957726c7e8322eabdd244492edf8b5eac9401a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T20:32:26Z","title_canon_sha256":"17a2c35cc588380a2192c07a1854d80cf8caf37dacce46a5f7b072271b2e83f0"},"schema_version":"1.0","source":{"id":"2507.06378","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06378","created_at":"2026-07-05T11:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06378v1","created_at":"2026-07-05T11:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06378","created_at":"2026-07-05T11:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"XWCSD4DVZKCK","created_at":"2026-07-05T11:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"XWCSD4DVZKCKZ6DR","created_at":"2026-07-05T11:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"XWCSD4DV","created_at":"2026-07-05T11:34:14Z"}],"graph_snapshots":[{"event_id":"sha256:b32ccd45a0b862af1f0a0086d8bcc54dc5bb04cc33b8ffbbe1991ee5abacb32e","target":"graph","created_at":"2026-07-05T11:34:14Z","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/2507.06378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While tokenization is a key step in language modeling, with effects on model training and performance, it remains unclear how to effectively evaluate tokenizer quality. One proposed dimension of tokenizer quality is the extent to which tokenizers preserve linguistically meaningful subwords, aligning token boundaries with morphological boundaries within a word. We expand MorphScore (Arnett & Bergen, 2025), which previously covered 22 languages, to support a total of 70 languages. The updated MorphScore offers more flexibility in evaluation and addresses some of the limitations of the original v","authors_text":"Brendan O'Connor, Catherine Arnett, Marisa Hudspeth","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T20:32:26Z","title":"Evaluating Morphological Alignment of Tokenizers in 70 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06378","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":"sha256:9294b9b001c60b7ca21765a3481855624167fcb3dc548c1167f2c7aa5329e77b","target":"record","created_at":"2026-07-05T11:34:14Z","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":"36459e746e1e1a47ae487b114957726c7e8322eabdd244492edf8b5eac9401a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T20:32:26Z","title_canon_sha256":"17a2c35cc588380a2192c07a1854d80cf8caf37dacce46a5f7b072271b2e83f0"},"schema_version":"1.0","source":{"id":"2507.06378","kind":"arxiv","version":1}},"canonical_sha256":"bd8521f075ca84acf8719694cda1b07a5249989e50ee570288964c3c76e8c11d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd8521f075ca84acf8719694cda1b07a5249989e50ee570288964c3c76e8c11d","first_computed_at":"2026-07-05T11:34:14.691598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:14.691598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"42keGbFeqPobymXCeywaVO3HQ/11AMu58aG8LdwjdMVOe2kb/Qc/j17UF/HMD427YwqBaKyD27CAKl1V4nh/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:14.692039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06378","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9294b9b001c60b7ca21765a3481855624167fcb3dc548c1167f2c7aa5329e77b","sha256:b32ccd45a0b862af1f0a0086d8bcc54dc5bb04cc33b8ffbbe1991ee5abacb32e"],"state_sha256":"bfbc948f60ee74e8096b702c35a7c4a70c6626b299053b09c6376076b57e5627"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uVsHfhBJfmDbvEgB8mW0+nZC5NTjUt0STrOuWW4nWpbVnoUMU8mD/0qBMpJ5GMcb62As/bnZL4PL4O6L+h4wBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:23:00.454867Z","bundle_sha256":"e531c9b2bd2c84330b8dbb86562aaed1b8912c2838d289c2eb5f942a42e80d9e"}}