{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3XBVZCJQ32HMYJ77FS4MB2CA6P","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":"64059e596c7871c30fa0b7deef606e5b8257d5f2de05dc7aa110cf5377ecaa1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T11:45:29Z","title_canon_sha256":"7357d85abc734d22d0cf6501843a07419a9d66c84ca0d5753ce68451d4dec08c"},"schema_version":"1.0","source":{"id":"2310.03477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03477","created_at":"2026-07-05T06:57:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03477v1","created_at":"2026-07-05T06:57:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03477","created_at":"2026-07-05T06:57:34Z"},{"alias_kind":"pith_short_12","alias_value":"3XBVZCJQ32HM","created_at":"2026-07-05T06:57:34Z"},{"alias_kind":"pith_short_16","alias_value":"3XBVZCJQ32HMYJ77","created_at":"2026-07-05T06:57:34Z"},{"alias_kind":"pith_short_8","alias_value":"3XBVZCJQ","created_at":"2026-07-05T06:57:34Z"}],"graph_snapshots":[{"event_id":"sha256:db17f73c432c163c1d92ed9f1b2dd216dbfaa7f50e1b1ea3dd5eadd9410b7911","target":"graph","created_at":"2026-07-05T06:57:34Z","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/2310.03477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training monolingual language models for low and mid-resource languages is made challenging by limited and often inadequate pretraining data. In this study, we propose a novel model conversion strategy to address this issue, adapting high-resources monolingual language models to a new target language. By generalizing over a word translation dictionary encompassing both the source and target languages, we map tokens from the target tokenizer to semantically similar tokens from the source language tokenizer. This one-to-many token mapping improves tremendously the initialization of the embedding","authors_text":"Bettina Berendt, Fran\\c{c}ois Remy, Kris Demuynck, Pieter Delobelle, Thomas Demeester","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T11:45:29Z","title":"Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03477","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:dbd75f88e8689ff914e586ff5d7094603675d7e6746739581c9ae54230f9684d","target":"record","created_at":"2026-07-05T06:57:34Z","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":"64059e596c7871c30fa0b7deef606e5b8257d5f2de05dc7aa110cf5377ecaa1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T11:45:29Z","title_canon_sha256":"7357d85abc734d22d0cf6501843a07419a9d66c84ca0d5753ce68451d4dec08c"},"schema_version":"1.0","source":{"id":"2310.03477","kind":"arxiv","version":1}},"canonical_sha256":"ddc35c8930de8ecc27ff2cb8c0e840f3e644d3ebe1415e75b04fd068f8ce79a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddc35c8930de8ecc27ff2cb8c0e840f3e644d3ebe1415e75b04fd068f8ce79a0","first_computed_at":"2026-07-05T06:57:34.139262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:34.139262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M7xCgfHvA9jRoXyLBGo6w4hLOewrZp7cXgM5gOy/yAgCBg7LkgJtcCSMKvXDZxwlf5xANuotwo9l33h7MNxvAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:34.139900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbd75f88e8689ff914e586ff5d7094603675d7e6746739581c9ae54230f9684d","sha256:db17f73c432c163c1d92ed9f1b2dd216dbfaa7f50e1b1ea3dd5eadd9410b7911"],"state_sha256":"823a7d3a1d4637f1f8fb626326b193d1af8cf463fbf785e66f60fb99d34e476f"}