{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RMLUVRQQOGHRE7MKEQLGT6HLWP","short_pith_number":"pith:RMLUVRQQ","canonical_record":{"source":{"id":"2502.06468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T13:50:12Z","cross_cats_sorted":[],"title_canon_sha256":"407fc184b94ae3e52ecc7a1792c9f53179286cbeef51222e09e5067ff8e5b32b","abstract_canon_sha256":"51b7011ba3a678e184ba4b4e1278cb80ced3fa8ff5e23b0bb944d06d17c449ff"},"schema_version":"1.0"},"canonical_sha256":"8b174ac610718f127d8a241669f8ebb3e697256deeb85f8afcda18991c85c8bc","source":{"kind":"arxiv","id":"2502.06468","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06468","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06468v1","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06468","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"pith_short_12","alias_value":"RMLUVRQQOGHR","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"pith_short_16","alias_value":"RMLUVRQQOGHRE7MK","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"pith_short_8","alias_value":"RMLUVRQQ","created_at":"2026-07-05T10:12:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RMLUVRQQOGHRE7MKEQLGT6HLWP","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T13:50:12Z","cross_cats_sorted":[],"title_canon_sha256":"407fc184b94ae3e52ecc7a1792c9f53179286cbeef51222e09e5067ff8e5b32b","abstract_canon_sha256":"51b7011ba3a678e184ba4b4e1278cb80ced3fa8ff5e23b0bb944d06d17c449ff"},"schema_version":"1.0"},"canonical_sha256":"8b174ac610718f127d8a241669f8ebb3e697256deeb85f8afcda18991c85c8bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:06.971740Z","signature_b64":"LAg6HZB586qYU/dlvX+ftL4/Vsht0AyEBhtrVw2wV09DhlQn34WD3Kuq/Jf9XM/AAsMcJcMffPmmK7CIH5bGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b174ac610718f127d8a241669f8ebb3e697256deeb85f8afcda18991c85c8bc","last_reissued_at":"2026-07-05T10:12:06.971276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:06.971276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06468","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":"2026-07-05T10:12:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YNHl0cL1UfJK7V5t4yR5V1zF97dc+SCkZ3tXvTGtelK5f8VfDA98UMqYStEjg7Lh1s3YkxT8r71baRLPgjPeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:12:59.856801Z"},"content_sha256":"2b37f6d59cddeb142ccab7a68eb659313b1443c4636197c2435d4d2ce6a8377d","schema_version":"1.0","event_id":"sha256:2b37f6d59cddeb142ccab7a68eb659313b1443c4636197c2435d4d2ce6a8377d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RMLUVRQQOGHRE7MKEQLGT6HLWP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Literal Token Overlap: Token Alignability for Multilinguality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Fraser, Jind\\v{r}ich Libovick\\'y, Katharina H\\\"ammerl, Tomasz Limisiewicz","submitted_at":"2025-02-10T13:50:12Z","abstract_excerpt":"Previous work has considered token overlap, or even similarity of token distributions, as predictors for multilinguality and cross-lingual knowledge transfer in language models. However, these very literal metrics assign large distances to language pairs with different scripts, which can nevertheless show good cross-linguality. This limits the explanatory strength of token overlap for knowledge transfer between language pairs that use distinct scripts or follow different orthographic conventions. In this paper, we propose subword token alignability as a new way to understand the impact and qua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06468","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/2502.06468/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":"2026-07-05T10:12:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LEUN4GbHrKcxkD2ee/4C5PdgitmdyHuCz71B3Kcb/0jQhi/YtvOsUk/tLgjarabvOzVANLJoqRLuBC96majHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:12:59.857355Z"},"content_sha256":"ada24508dae66e859452c70fcb90e5a37b3407af11f5a1e9560d12c82b2cea55","schema_version":"1.0","event_id":"sha256:ada24508dae66e859452c70fcb90e5a37b3407af11f5a1e9560d12c82b2cea55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMLUVRQQOGHRE7MKEQLGT6HLWP/bundle.json","state_url":"https://pith.science/pith/RMLUVRQQOGHRE7MKEQLGT6HLWP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMLUVRQQOGHRE7MKEQLGT6HLWP/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":"2026-08-09T07:12:59Z","links":{"resolver":"https://pith.science/pith/RMLUVRQQOGHRE7MKEQLGT6HLWP","bundle":"https://pith.science/pith/RMLUVRQQOGHRE7MKEQLGT6HLWP/bundle.json","state":"https://pith.science/pith/RMLUVRQQOGHRE7MKEQLGT6HLWP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMLUVRQQOGHRE7MKEQLGT6HLWP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RMLUVRQQOGHRE7MKEQLGT6HLWP","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":"51b7011ba3a678e184ba4b4e1278cb80ced3fa8ff5e23b0bb944d06d17c449ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T13:50:12Z","title_canon_sha256":"407fc184b94ae3e52ecc7a1792c9f53179286cbeef51222e09e5067ff8e5b32b"},"schema_version":"1.0","source":{"id":"2502.06468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06468","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06468v1","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06468","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"pith_short_12","alias_value":"RMLUVRQQOGHR","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"pith_short_16","alias_value":"RMLUVRQQOGHRE7MK","created_at":"2026-07-05T10:12:06Z"},{"alias_kind":"pith_short_8","alias_value":"RMLUVRQQ","created_at":"2026-07-05T10:12:06Z"}],"graph_snapshots":[{"event_id":"sha256:ada24508dae66e859452c70fcb90e5a37b3407af11f5a1e9560d12c82b2cea55","target":"graph","created_at":"2026-07-05T10:12:06Z","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/2502.06468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous work has considered token overlap, or even similarity of token distributions, as predictors for multilinguality and cross-lingual knowledge transfer in language models. However, these very literal metrics assign large distances to language pairs with different scripts, which can nevertheless show good cross-linguality. This limits the explanatory strength of token overlap for knowledge transfer between language pairs that use distinct scripts or follow different orthographic conventions. In this paper, we propose subword token alignability as a new way to understand the impact and qua","authors_text":"Alexander Fraser, Jind\\v{r}ich Libovick\\'y, Katharina H\\\"ammerl, Tomasz Limisiewicz","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T13:50:12Z","title":"Beyond Literal Token Overlap: Token Alignability for Multilinguality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06468","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":"sha256:2b37f6d59cddeb142ccab7a68eb659313b1443c4636197c2435d4d2ce6a8377d","target":"record","created_at":"2026-07-05T10:12:06Z","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":"51b7011ba3a678e184ba4b4e1278cb80ced3fa8ff5e23b0bb944d06d17c449ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T13:50:12Z","title_canon_sha256":"407fc184b94ae3e52ecc7a1792c9f53179286cbeef51222e09e5067ff8e5b32b"},"schema_version":"1.0","source":{"id":"2502.06468","kind":"arxiv","version":1}},"canonical_sha256":"8b174ac610718f127d8a241669f8ebb3e697256deeb85f8afcda18991c85c8bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b174ac610718f127d8a241669f8ebb3e697256deeb85f8afcda18991c85c8bc","first_computed_at":"2026-07-05T10:12:06.971276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:06.971276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LAg6HZB586qYU/dlvX+ftL4/Vsht0AyEBhtrVw2wV09DhlQn34WD3Kuq/Jf9XM/AAsMcJcMffPmmK7CIH5bGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:06.971740Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b37f6d59cddeb142ccab7a68eb659313b1443c4636197c2435d4d2ce6a8377d","sha256:ada24508dae66e859452c70fcb90e5a37b3407af11f5a1e9560d12c82b2cea55"],"state_sha256":"8ffdfd12759817133b09607f7585bb3c58435c1e9bd0e0b7e4b517cf0861d688"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6gpVx5HQy/7PU4fVPxuLxFCxjiAdCcoblBVPq1YbrgnKLDmGeJ0QpORHa/MaVfQ2YPde7q8X1oa7A0Ibq0PCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:12:59.862585Z","bundle_sha256":"6762756f1801f91c586c9904854cef12aa3d5e58c38129022028a5cac2bb6ce7"}}