{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OKRP4FJMWUSKQA2YOHDZOAXN7C","short_pith_number":"pith:OKRP4FJM","canonical_record":{"source":{"id":"2408.04303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T08:37:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb527d9da28eec04ef73f7cbb8304ac0f391500cfdd249d099b83941bc39466b","abstract_canon_sha256":"cd3f3bf72bc2cf1be13f3555f06e79cb131eaf850c784d13a649108d6092b7f5"},"schema_version":"1.0"},"canonical_sha256":"72a2fe152cb524a8035871c79702edf888854dec53e701769a2dc07a4adb3080","source":{"kind":"arxiv","id":"2408.04303","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04303","created_at":"2026-07-05T08:53:31Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04303v1","created_at":"2026-07-05T08:53:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04303","created_at":"2026-07-05T08:53:31Z"},{"alias_kind":"pith_short_12","alias_value":"OKRP4FJMWUSK","created_at":"2026-07-05T08:53:31Z"},{"alias_kind":"pith_short_16","alias_value":"OKRP4FJMWUSKQA2Y","created_at":"2026-07-05T08:53:31Z"},{"alias_kind":"pith_short_8","alias_value":"OKRP4FJM","created_at":"2026-07-05T08:53:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OKRP4FJMWUSKQA2YOHDZOAXN7C","target":"record","payload":{"canonical_record":{"source":{"id":"2408.04303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T08:37:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb527d9da28eec04ef73f7cbb8304ac0f391500cfdd249d099b83941bc39466b","abstract_canon_sha256":"cd3f3bf72bc2cf1be13f3555f06e79cb131eaf850c784d13a649108d6092b7f5"},"schema_version":"1.0"},"canonical_sha256":"72a2fe152cb524a8035871c79702edf888854dec53e701769a2dc07a4adb3080","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:31.409993Z","signature_b64":"qNQOAyaabuay+dd+uwaqdcJ0KiwAs1mtSdN6QQS/s8AYtAfde0ocTzissPebZUwUKVdvkEPdJXKk69tVy1eyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72a2fe152cb524a8035871c79702edf888854dec53e701769a2dc07a4adb3080","last_reissued_at":"2026-07-05T08:53:31.409513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:31.409513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.04303","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":"2026-07-05T08:53:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hLCw2IDEPIwYUdfxcLiueUa+hZpIdVxKf7+ufl+EguhLJVaVp1vv38Kx/A9JPX16oZAxaDynoIY/xtM/NcNXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:36:39.362608Z"},"content_sha256":"39331dbcc0f745f6b52da7f7828c7fc121d7edf71096c27e9916205516dd2aa7","schema_version":"1.0","event_id":"sha256:39331dbcc0f745f6b52da7f7828c7fc121d7edf71096c27e9916205516dd2aa7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OKRP4FJMWUSKQA2YOHDZOAXN7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alfiya Khabibullina, Fran\\c{c}ois Remy, Hayastan Avetisyan, Miryam de Lhoneux, Pieter Delobelle, Thomas Demeester","submitted_at":"2024-08-08T08:37:28Z","abstract_excerpt":"The development of monolingual language models for low and mid-resource languages continues to be hindered by the difficulty in sourcing high-quality training data. In this study, we present a novel cross-lingual vocabulary transfer strategy, trans-tokenization, designed to tackle this challenge and enable more efficient language adaptation. Our approach focuses on adapting a high-resource monolingual LLM to an unseen target language by initializing the token embeddings of the target language using a weighted average of semantically similar token embeddings from the source language. For this, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04303","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/2408.04303/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":"2026-07-05T08:53:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lut0pxjv5GPgkwd7M2XGUtwgkUanjZ5tV9s0etDqbjS2Ppg7iV/aMeQzrp3NNK0CLRyDuSjVtTqxQkzROLOeDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:36:39.362984Z"},"content_sha256":"44335157384db8e34c4918a59210968bbbe1cfaf48afa379b83a2204a2be939c","schema_version":"1.0","event_id":"sha256:44335157384db8e34c4918a59210968bbbe1cfaf48afa379b83a2204a2be939c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKRP4FJMWUSKQA2YOHDZOAXN7C/bundle.json","state_url":"https://pith.science/pith/OKRP4FJMWUSKQA2YOHDZOAXN7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKRP4FJMWUSKQA2YOHDZOAXN7C/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":"2026-08-04T03:36:39Z","links":{"resolver":"https://pith.science/pith/OKRP4FJMWUSKQA2YOHDZOAXN7C","bundle":"https://pith.science/pith/OKRP4FJMWUSKQA2YOHDZOAXN7C/bundle.json","state":"https://pith.science/pith/OKRP4FJMWUSKQA2YOHDZOAXN7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKRP4FJMWUSKQA2YOHDZOAXN7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OKRP4FJMWUSKQA2YOHDZOAXN7C","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":"cd3f3bf72bc2cf1be13f3555f06e79cb131eaf850c784d13a649108d6092b7f5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T08:37:28Z","title_canon_sha256":"bb527d9da28eec04ef73f7cbb8304ac0f391500cfdd249d099b83941bc39466b"},"schema_version":"1.0","source":{"id":"2408.04303","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04303","created_at":"2026-07-05T08:53:31Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04303v1","created_at":"2026-07-05T08:53:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04303","created_at":"2026-07-05T08:53:31Z"},{"alias_kind":"pith_short_12","alias_value":"OKRP4FJMWUSK","created_at":"2026-07-05T08:53:31Z"},{"alias_kind":"pith_short_16","alias_value":"OKRP4FJMWUSKQA2Y","created_at":"2026-07-05T08:53:31Z"},{"alias_kind":"pith_short_8","alias_value":"OKRP4FJM","created_at":"2026-07-05T08:53:31Z"}],"graph_snapshots":[{"event_id":"sha256:44335157384db8e34c4918a59210968bbbe1cfaf48afa379b83a2204a2be939c","target":"graph","created_at":"2026-07-05T08:53:31Z","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/2408.04303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of monolingual language models for low and mid-resource languages continues to be hindered by the difficulty in sourcing high-quality training data. In this study, we present a novel cross-lingual vocabulary transfer strategy, trans-tokenization, designed to tackle this challenge and enable more efficient language adaptation. Our approach focuses on adapting a high-resource monolingual LLM to an unseen target language by initializing the token embeddings of the target language using a weighted average of semantically similar token embeddings from the source language. For this, ","authors_text":"Alfiya Khabibullina, Fran\\c{c}ois Remy, Hayastan Avetisyan, Miryam de Lhoneux, Pieter Delobelle, Thomas Demeester","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T08:37:28Z","title":"Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04303","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":"sha256:39331dbcc0f745f6b52da7f7828c7fc121d7edf71096c27e9916205516dd2aa7","target":"record","created_at":"2026-07-05T08:53:31Z","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":"cd3f3bf72bc2cf1be13f3555f06e79cb131eaf850c784d13a649108d6092b7f5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-08T08:37:28Z","title_canon_sha256":"bb527d9da28eec04ef73f7cbb8304ac0f391500cfdd249d099b83941bc39466b"},"schema_version":"1.0","source":{"id":"2408.04303","kind":"arxiv","version":1}},"canonical_sha256":"72a2fe152cb524a8035871c79702edf888854dec53e701769a2dc07a4adb3080","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72a2fe152cb524a8035871c79702edf888854dec53e701769a2dc07a4adb3080","first_computed_at":"2026-07-05T08:53:31.409513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:31.409513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qNQOAyaabuay+dd+uwaqdcJ0KiwAs1mtSdN6QQS/s8AYtAfde0ocTzissPebZUwUKVdvkEPdJXKk69tVy1eyAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:31.409993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04303","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39331dbcc0f745f6b52da7f7828c7fc121d7edf71096c27e9916205516dd2aa7","sha256:44335157384db8e34c4918a59210968bbbe1cfaf48afa379b83a2204a2be939c"],"state_sha256":"226188e76ac8c14e946cd889b6b3076c40921ae7180860830279b9bbc4a37c9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ixyesZwSuDrkdx+V/9yggpB35/nCEIulaWH5Ibs99o7Y2nAwupFYJCjTzkm6T+bDRkx2Jo8f+b/wdeE0Rv5CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:36:39.365544Z","bundle_sha256":"cdb247ecb321bb79ceff66d8c53e9e896c9b35f765609bc34066c6eab3267721"}}