{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IFF4UWGW7SHXFBW75YBJHLZZGC","short_pith_number":"pith:IFF4UWGW","canonical_record":{"source":{"id":"2606.22478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T12:40:16Z","cross_cats_sorted":[],"title_canon_sha256":"9a6fb3e4d2f64d5085aecaed7ed04d735bb9fba49e8433a9b54e47e90e60e04c","abstract_canon_sha256":"3e77cc7dd519d675460f44c0fe48a42d0aa3d9979e2f62cc58442ca00aeb9037"},"schema_version":"1.0"},"canonical_sha256":"414bca58d6fc8f7286dfee0293af39308f158bd15b98c1b16e2e062c3a707cb2","source":{"kind":"arxiv","id":"2606.22478","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22478","created_at":"2026-06-23T02:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22478v1","created_at":"2026-06-23T02:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22478","created_at":"2026-06-23T02:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"IFF4UWGW7SHX","created_at":"2026-06-23T02:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"IFF4UWGW7SHXFBW7","created_at":"2026-06-23T02:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"IFF4UWGW","created_at":"2026-06-23T02:13:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IFF4UWGW7SHXFBW75YBJHLZZGC","target":"record","payload":{"canonical_record":{"source":{"id":"2606.22478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T12:40:16Z","cross_cats_sorted":[],"title_canon_sha256":"9a6fb3e4d2f64d5085aecaed7ed04d735bb9fba49e8433a9b54e47e90e60e04c","abstract_canon_sha256":"3e77cc7dd519d675460f44c0fe48a42d0aa3d9979e2f62cc58442ca00aeb9037"},"schema_version":"1.0"},"canonical_sha256":"414bca58d6fc8f7286dfee0293af39308f158bd15b98c1b16e2e062c3a707cb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:39.419060Z","signature_b64":"Us24GtKjMX5OziGU8s+wt9e+n23BeQ4xmvR3ppGCsiNz1LhK10b0emg++g5kke323uYSkmr/OOKNKM/3ygFFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"414bca58d6fc8f7286dfee0293af39308f158bd15b98c1b16e2e062c3a707cb2","last_reissued_at":"2026-06-23T02:13:39.418654Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:39.418654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.22478","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":"2026-06-23T02:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M2pOfvgdXCp1bCnrbOZohqQBtEFaPo48DxWBEhw5CjcEY3P0J5p9urHm77viCvxxWGti3O5XFLP9CU8nssY/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T15:43:30.053838Z"},"content_sha256":"122a9a04674d31f0c1ae04be12602143b3bd8157773899539e84f9efa6cfc137","schema_version":"1.0","event_id":"sha256:122a9a04674d31f0c1ae04be12602143b3bd8157773899539e84f9efa6cfc137"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IFF4UWGW7SHXFBW75YBJHLZZGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ROMEVA: Geometry-Preserving Vocabulary Expansion for Roman Urdu Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afsheen Asif, Mahnoor Khan, Mehwish Fatima, Milhan Afzal Khan, Seemab Latif","submitted_at":"2026-06-21T12:40:16Z","abstract_excerpt":"Multilingual Language Models like mBERT are widely used for low-resource NLP, yet their adaptation to morphologically inconsistent languages such as Roman Urdu remains underexplored. Roman Urdu spelling variation causes severe sub-word fragmentation, averaging 1.50 sub-words per token. We propose \\textit{ROMEVA} (Roman Urdu Embedding-preserving Vocabulary Adaptation), which combines sub-word-average initialization and a PCA-guided anchor loss to stabilize embeddings during vocabulary expansion. Using a 36,130-comment Roman Urdu corpus, we add 500 highly fragmented tokens to mBERT and compare n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22478","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/2606.22478/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":"2026-06-23T02:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NlTc8MP+Os5YV7P6ijR2ytJRNrLtzn8w6Prjbz/of8h5YnSZ+a5S0DGHZJojMck2MGbvALyMHDbeU93UHNTOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T15:43:30.054209Z"},"content_sha256":"cfb21f91b31901935b6a1c24887e2f0a3d925d0019b5982e651247661d46a227","schema_version":"1.0","event_id":"sha256:cfb21f91b31901935b6a1c24887e2f0a3d925d0019b5982e651247661d46a227"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IFF4UWGW7SHXFBW75YBJHLZZGC/bundle.json","state_url":"https://pith.science/pith/IFF4UWGW7SHXFBW75YBJHLZZGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IFF4UWGW7SHXFBW75YBJHLZZGC/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":"2026-06-29T15:43:30Z","links":{"resolver":"https://pith.science/pith/IFF4UWGW7SHXFBW75YBJHLZZGC","bundle":"https://pith.science/pith/IFF4UWGW7SHXFBW75YBJHLZZGC/bundle.json","state":"https://pith.science/pith/IFF4UWGW7SHXFBW75YBJHLZZGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IFF4UWGW7SHXFBW75YBJHLZZGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IFF4UWGW7SHXFBW75YBJHLZZGC","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":"3e77cc7dd519d675460f44c0fe48a42d0aa3d9979e2f62cc58442ca00aeb9037","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T12:40:16Z","title_canon_sha256":"9a6fb3e4d2f64d5085aecaed7ed04d735bb9fba49e8433a9b54e47e90e60e04c"},"schema_version":"1.0","source":{"id":"2606.22478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22478","created_at":"2026-06-23T02:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22478v1","created_at":"2026-06-23T02:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22478","created_at":"2026-06-23T02:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"IFF4UWGW7SHX","created_at":"2026-06-23T02:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"IFF4UWGW7SHXFBW7","created_at":"2026-06-23T02:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"IFF4UWGW","created_at":"2026-06-23T02:13:39Z"}],"graph_snapshots":[{"event_id":"sha256:cfb21f91b31901935b6a1c24887e2f0a3d925d0019b5982e651247661d46a227","target":"graph","created_at":"2026-06-23T02:13:39Z","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/2606.22478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual Language Models like mBERT are widely used for low-resource NLP, yet their adaptation to morphologically inconsistent languages such as Roman Urdu remains underexplored. Roman Urdu spelling variation causes severe sub-word fragmentation, averaging 1.50 sub-words per token. We propose \\textit{ROMEVA} (Roman Urdu Embedding-preserving Vocabulary Adaptation), which combines sub-word-average initialization and a PCA-guided anchor loss to stabilize embeddings during vocabulary expansion. Using a 36,130-comment Roman Urdu corpus, we add 500 highly fragmented tokens to mBERT and compare n","authors_text":"Afsheen Asif, Mahnoor Khan, Mehwish Fatima, Milhan Afzal Khan, Seemab Latif","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T12:40:16Z","title":"ROMEVA: Geometry-Preserving Vocabulary Expansion for Roman Urdu Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22478","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":"sha256:122a9a04674d31f0c1ae04be12602143b3bd8157773899539e84f9efa6cfc137","target":"record","created_at":"2026-06-23T02:13:39Z","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":"3e77cc7dd519d675460f44c0fe48a42d0aa3d9979e2f62cc58442ca00aeb9037","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T12:40:16Z","title_canon_sha256":"9a6fb3e4d2f64d5085aecaed7ed04d735bb9fba49e8433a9b54e47e90e60e04c"},"schema_version":"1.0","source":{"id":"2606.22478","kind":"arxiv","version":1}},"canonical_sha256":"414bca58d6fc8f7286dfee0293af39308f158bd15b98c1b16e2e062c3a707cb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"414bca58d6fc8f7286dfee0293af39308f158bd15b98c1b16e2e062c3a707cb2","first_computed_at":"2026-06-23T02:13:39.418654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:39.418654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Us24GtKjMX5OziGU8s+wt9e+n23BeQ4xmvR3ppGCsiNz1LhK10b0emg++g5kke323uYSkmr/OOKNKM/3ygFFAg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:39.419060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:122a9a04674d31f0c1ae04be12602143b3bd8157773899539e84f9efa6cfc137","sha256:cfb21f91b31901935b6a1c24887e2f0a3d925d0019b5982e651247661d46a227"],"state_sha256":"dc885a986fa1ce8194e76ec6b7f95188d5b377ad7a16d2cd08f61b74408983ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CD4YJvlgGfEp3ELzmRwd2gLhjbQaE1Ebr/AXhRFtoIypirYlgi88KJ7DEz19XIzdYGELtcdL4YzZSLzlopbzAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T15:43:30.056331Z","bundle_sha256":"99fe41f8806aece0135d0ac1bcbd658cfea427a8f674f566de7edaf1bcdf08b3"}}