{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:44W7PYSDQ53C5BA6MLK4JPBTVV","short_pith_number":"pith:44W7PYSD","canonical_record":{"source":{"id":"2406.09717","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T04:55:30Z","cross_cats_sorted":[],"title_canon_sha256":"60288cc1a891d535c159f504c940d84d0a1b8f3593844b3192d80821c1ce89ff","abstract_canon_sha256":"d95d0b74b705d343895176cab2280c75b99f8a91579da7808e294b54819dc843"},"schema_version":"1.0"},"canonical_sha256":"e72df7e24387762e841e62d5c4bc33ad4c45bd95e80e9ee74f3338c7b2f44fe6","source":{"kind":"arxiv","id":"2406.09717","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09717","created_at":"2026-07-05T08:57:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09717v3","created_at":"2026-07-05T08:57:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09717","created_at":"2026-07-05T08:57:38Z"},{"alias_kind":"pith_short_12","alias_value":"44W7PYSDQ53C","created_at":"2026-07-05T08:57:38Z"},{"alias_kind":"pith_short_16","alias_value":"44W7PYSDQ53C5BA6","created_at":"2026-07-05T08:57:38Z"},{"alias_kind":"pith_short_8","alias_value":"44W7PYSD","created_at":"2026-07-05T08:57:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:44W7PYSDQ53C5BA6MLK4JPBTVV","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09717","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T04:55:30Z","cross_cats_sorted":[],"title_canon_sha256":"60288cc1a891d535c159f504c940d84d0a1b8f3593844b3192d80821c1ce89ff","abstract_canon_sha256":"d95d0b74b705d343895176cab2280c75b99f8a91579da7808e294b54819dc843"},"schema_version":"1.0"},"canonical_sha256":"e72df7e24387762e841e62d5c4bc33ad4c45bd95e80e9ee74f3338c7b2f44fe6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:38.949048Z","signature_b64":"AL0OOB20uPjJ9aeuJe+aufYzHurd0HwNSMYVYTjBSt+l/MyutHZE1NH4QfQEf0T5EaCrwUJi0jgB7eKkV5DnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e72df7e24387762e841e62d5c4bc33ad4c45bd95e80e9ee74f3338c7b2f44fe6","last_reissued_at":"2026-07-05T08:57:38.948572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:38.948572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09717","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yyU57OF9kMjm6y2nroRLlYGpm8o8osprwI4g4zfbIz4snigYUi7EhFSPB/2jWIVtQoHxy0+yj9hVjr8Yp6chCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:52:14.814317Z"},"content_sha256":"b3ea285ed4e59c5b17426bfb0b454434d172c58dbddedb8c7b81419ddc0cc5c6","schema_version":"1.0","event_id":"sha256:b3ea285ed4e59c5b17426bfb0b454434d172c58dbddedb8c7b81419ddc0cc5c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:44W7PYSDQ53C5BA6MLK4JPBTVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Khoi M. Le, Luu Anh Tuan, Trinh Pham","submitted_at":"2024-06-14T04:55:30Z","abstract_excerpt":"In this paper, we introduce UniBridge (Cross-Lingual Transfer Learning with Optimized Embeddings and Vocabulary), a comprehensive approach developed to improve the effectiveness of Cross-Lingual Transfer Learning, particularly in languages with limited resources. Our approach tackles two essential elements of a language model: the initialization of embeddings and the optimal vocabulary size. Specifically, we propose a novel embedding initialization method that leverages both lexical and semantic alignment for a language. In addition, we present a method for systematically searching for the opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09717","kind":"arxiv","version":3},"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/2406.09717/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":"2026-07-05T08:57:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mmseHXuCrcpgSs7anMcMf1EwxdFibiLoNIcaOmSuz9d2bsJzm1weHU51M7kpVl+KNEDVz+Hq8NUCjMsOEebCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:52:14.814946Z"},"content_sha256":"3ff0498ea1b56cdb1c2157a804edfc25204ea41c6ae9e9e97cd8c09397ae5b17","schema_version":"1.0","event_id":"sha256:3ff0498ea1b56cdb1c2157a804edfc25204ea41c6ae9e9e97cd8c09397ae5b17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/bundle.json","state_url":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/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":"2026-08-05T20:52:14Z","links":{"resolver":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV","bundle":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/bundle.json","state":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:44W7PYSDQ53C5BA6MLK4JPBTVV","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":"d95d0b74b705d343895176cab2280c75b99f8a91579da7808e294b54819dc843","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T04:55:30Z","title_canon_sha256":"60288cc1a891d535c159f504c940d84d0a1b8f3593844b3192d80821c1ce89ff"},"schema_version":"1.0","source":{"id":"2406.09717","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09717","created_at":"2026-07-05T08:57:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09717v3","created_at":"2026-07-05T08:57:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09717","created_at":"2026-07-05T08:57:38Z"},{"alias_kind":"pith_short_12","alias_value":"44W7PYSDQ53C","created_at":"2026-07-05T08:57:38Z"},{"alias_kind":"pith_short_16","alias_value":"44W7PYSDQ53C5BA6","created_at":"2026-07-05T08:57:38Z"},{"alias_kind":"pith_short_8","alias_value":"44W7PYSD","created_at":"2026-07-05T08:57:38Z"}],"graph_snapshots":[{"event_id":"sha256:3ff0498ea1b56cdb1c2157a804edfc25204ea41c6ae9e9e97cd8c09397ae5b17","target":"graph","created_at":"2026-07-05T08:57:38Z","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/2406.09717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce UniBridge (Cross-Lingual Transfer Learning with Optimized Embeddings and Vocabulary), a comprehensive approach developed to improve the effectiveness of Cross-Lingual Transfer Learning, particularly in languages with limited resources. Our approach tackles two essential elements of a language model: the initialization of embeddings and the optimal vocabulary size. Specifically, we propose a novel embedding initialization method that leverages both lexical and semantic alignment for a language. In addition, we present a method for systematically searching for the opt","authors_text":"Khoi M. Le, Luu Anh Tuan, Trinh Pham","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T04:55:30Z","title":"UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09717","kind":"arxiv","version":3},"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:b3ea285ed4e59c5b17426bfb0b454434d172c58dbddedb8c7b81419ddc0cc5c6","target":"record","created_at":"2026-07-05T08:57:38Z","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":"d95d0b74b705d343895176cab2280c75b99f8a91579da7808e294b54819dc843","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T04:55:30Z","title_canon_sha256":"60288cc1a891d535c159f504c940d84d0a1b8f3593844b3192d80821c1ce89ff"},"schema_version":"1.0","source":{"id":"2406.09717","kind":"arxiv","version":3}},"canonical_sha256":"e72df7e24387762e841e62d5c4bc33ad4c45bd95e80e9ee74f3338c7b2f44fe6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e72df7e24387762e841e62d5c4bc33ad4c45bd95e80e9ee74f3338c7b2f44fe6","first_computed_at":"2026-07-05T08:57:38.948572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:38.948572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AL0OOB20uPjJ9aeuJe+aufYzHurd0HwNSMYVYTjBSt+l/MyutHZE1NH4QfQEf0T5EaCrwUJi0jgB7eKkV5DnBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:38.949048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09717","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3ea285ed4e59c5b17426bfb0b454434d172c58dbddedb8c7b81419ddc0cc5c6","sha256:3ff0498ea1b56cdb1c2157a804edfc25204ea41c6ae9e9e97cd8c09397ae5b17"],"state_sha256":"4ea9f43a7cdd4af85d1e75c32458512067168e240753f523e34197afe6a36a8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xhEm2jbs0Js1lEtsjdgTphe8wFXN7LJvVittEJhBwDH5FB3K2LK7OXG3o9jJsjiw6MBhUEwz/Jn2AKPCfa/QDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:52:14.820103Z","bundle_sha256":"1862dad63e507c32c5c82331d1cba93289c54093e74a60f185f8a8e28b64e1a1"}}