{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RMZC5LJSWYPN26ICYRF3C5VYFI","short_pith_number":"pith:RMZC5LJS","canonical_record":{"source":{"id":"2304.08865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-18T09:58:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d2ab1f0edb2c1a68c71d39622152e2af2ce6c0be9dc41b338c4a6fda25ca6635","abstract_canon_sha256":"4ee6a4ddee1ac2f779ebec11558f05daa5f8d3ab926d4bf128d751d33f3b99b3"},"schema_version":"1.0"},"canonical_sha256":"8b322ead32b61edd7902c44bb176b82a34e7b2cb2d8f35fe3c08545b5d11fcf6","source":{"kind":"arxiv","id":"2304.08865","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08865","created_at":"2026-07-05T06:02:14Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08865v1","created_at":"2026-07-05T06:02:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08865","created_at":"2026-07-05T06:02:14Z"},{"alias_kind":"pith_short_12","alias_value":"RMZC5LJSWYPN","created_at":"2026-07-05T06:02:14Z"},{"alias_kind":"pith_short_16","alias_value":"RMZC5LJSWYPN26IC","created_at":"2026-07-05T06:02:14Z"},{"alias_kind":"pith_short_8","alias_value":"RMZC5LJS","created_at":"2026-07-05T06:02:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RMZC5LJSWYPN26ICYRF3C5VYFI","target":"record","payload":{"canonical_record":{"source":{"id":"2304.08865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-18T09:58:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d2ab1f0edb2c1a68c71d39622152e2af2ce6c0be9dc41b338c4a6fda25ca6635","abstract_canon_sha256":"4ee6a4ddee1ac2f779ebec11558f05daa5f8d3ab926d4bf128d751d33f3b99b3"},"schema_version":"1.0"},"canonical_sha256":"8b322ead32b61edd7902c44bb176b82a34e7b2cb2d8f35fe3c08545b5d11fcf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:14.467830Z","signature_b64":"+iUzJnhccxKTrMOaXRhNpWTKhgqazWQ+8RrbpOzXD9FoYZC0bzRuF1+MH6OeDNiA8crMMyF+fBgRUi7XbzVLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b322ead32b61edd7902c44bb176b82a34e7b2cb2d8f35fe3c08545b5d11fcf6","last_reissued_at":"2026-07-05T06:02:14.467423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:14.467423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.08865","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":"2026-07-05T06:02:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GvUC7yYZ+zwOyG7mZany7PCiqDOXqL26fh3+hdspzn64GZwQYMD94VTUgP575fJNZBC6DZi4kFclYoIltRs/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:20:12.533973Z"},"content_sha256":"6e792c796632c3748cd4d9e3c6fd1af3f61849fd8fff84b28d5f9dea8c3b3c0b","schema_version":"1.0","event_id":"sha256:6e792c796632c3748cd4d9e3c6fd1af3f61849fd8fff84b28d5f9dea8c3b3c0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RMZC5LJSWYPN26ICYRF3C5VYFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Romanization-based Large-scale Adaptation of Multilingual Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Ivan Vuli\\'c, Jonas Pfeiffer, Sebastian Ruder, Sukannya Purkayastha","submitted_at":"2023-04-18T09:58:34Z","abstract_excerpt":"Large multilingual pretrained language models (mPLMs) have become the de facto state of the art for cross-lingual transfer in NLP. However, their large-scale deployment to many languages, besides pretraining data scarcity, is also hindered by the increase in vocabulary size and limitations in their parameter budget. In order to boost the capacity of mPLMs to deal with low-resource and unseen languages, we explore the potential of leveraging transliteration on a massive scale. In particular, we explore the UROMAN transliteration tool, which provides mappings from UTF-8 to Latin characters for a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08865","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/2304.08865/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":"2026-07-05T06:02:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hpBjfPNmIBDtwqNOamo3/T/YemJQ6hbHzT+hMO1729DBqUIp0vr5MqFBzFi4w2e0xGmcwXrpvXln9Grr4f70Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:20:12.534523Z"},"content_sha256":"bfc96bdf53e246cb57385df0d15877d206f0043242a2e16ad1437cf18ee81648","schema_version":"1.0","event_id":"sha256:bfc96bdf53e246cb57385df0d15877d206f0043242a2e16ad1437cf18ee81648"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMZC5LJSWYPN26ICYRF3C5VYFI/bundle.json","state_url":"https://pith.science/pith/RMZC5LJSWYPN26ICYRF3C5VYFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMZC5LJSWYPN26ICYRF3C5VYFI/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":"2026-08-07T07:20:12Z","links":{"resolver":"https://pith.science/pith/RMZC5LJSWYPN26ICYRF3C5VYFI","bundle":"https://pith.science/pith/RMZC5LJSWYPN26ICYRF3C5VYFI/bundle.json","state":"https://pith.science/pith/RMZC5LJSWYPN26ICYRF3C5VYFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMZC5LJSWYPN26ICYRF3C5VYFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RMZC5LJSWYPN26ICYRF3C5VYFI","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":"4ee6a4ddee1ac2f779ebec11558f05daa5f8d3ab926d4bf128d751d33f3b99b3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-18T09:58:34Z","title_canon_sha256":"d2ab1f0edb2c1a68c71d39622152e2af2ce6c0be9dc41b338c4a6fda25ca6635"},"schema_version":"1.0","source":{"id":"2304.08865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08865","created_at":"2026-07-05T06:02:14Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08865v1","created_at":"2026-07-05T06:02:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08865","created_at":"2026-07-05T06:02:14Z"},{"alias_kind":"pith_short_12","alias_value":"RMZC5LJSWYPN","created_at":"2026-07-05T06:02:14Z"},{"alias_kind":"pith_short_16","alias_value":"RMZC5LJSWYPN26IC","created_at":"2026-07-05T06:02:14Z"},{"alias_kind":"pith_short_8","alias_value":"RMZC5LJS","created_at":"2026-07-05T06:02:14Z"}],"graph_snapshots":[{"event_id":"sha256:bfc96bdf53e246cb57385df0d15877d206f0043242a2e16ad1437cf18ee81648","target":"graph","created_at":"2026-07-05T06:02:14Z","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/2304.08865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multilingual pretrained language models (mPLMs) have become the de facto state of the art for cross-lingual transfer in NLP. However, their large-scale deployment to many languages, besides pretraining data scarcity, is also hindered by the increase in vocabulary size and limitations in their parameter budget. In order to boost the capacity of mPLMs to deal with low-resource and unseen languages, we explore the potential of leveraging transliteration on a massive scale. In particular, we explore the UROMAN transliteration tool, which provides mappings from UTF-8 to Latin characters for a","authors_text":"Iryna Gurevych, Ivan Vuli\\'c, Jonas Pfeiffer, Sebastian Ruder, Sukannya Purkayastha","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-18T09:58:34Z","title":"Romanization-based Large-scale Adaptation of Multilingual Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08865","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":"sha256:6e792c796632c3748cd4d9e3c6fd1af3f61849fd8fff84b28d5f9dea8c3b3c0b","target":"record","created_at":"2026-07-05T06:02:14Z","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":"4ee6a4ddee1ac2f779ebec11558f05daa5f8d3ab926d4bf128d751d33f3b99b3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-18T09:58:34Z","title_canon_sha256":"d2ab1f0edb2c1a68c71d39622152e2af2ce6c0be9dc41b338c4a6fda25ca6635"},"schema_version":"1.0","source":{"id":"2304.08865","kind":"arxiv","version":1}},"canonical_sha256":"8b322ead32b61edd7902c44bb176b82a34e7b2cb2d8f35fe3c08545b5d11fcf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b322ead32b61edd7902c44bb176b82a34e7b2cb2d8f35fe3c08545b5d11fcf6","first_computed_at":"2026-07-05T06:02:14.467423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:14.467423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+iUzJnhccxKTrMOaXRhNpWTKhgqazWQ+8RrbpOzXD9FoYZC0bzRuF1+MH6OeDNiA8crMMyF+fBgRUi7XbzVLCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:14.467830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e792c796632c3748cd4d9e3c6fd1af3f61849fd8fff84b28d5f9dea8c3b3c0b","sha256:bfc96bdf53e246cb57385df0d15877d206f0043242a2e16ad1437cf18ee81648"],"state_sha256":"554b858c05889076ea30d4f0cde9b0d084446b912f284ca0117b2f08f2b9998f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MgkWnFctzeCps3UuCQthI1DzjgG1e9rTIAAw+xzwoPhRxb0h2GRJ+bpXH5tnnvm8+ZoEILz9c6dSqz8cv0r7Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:20:12.543659Z","bundle_sha256":"4d4288f70e077653fd993a138e3d992bf38c1958a968b9f2c7a482230f5930fd"}}