{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NP43E2VXUEWKO3DAFERBZADKWT","short_pith_number":"pith:NP43E2VX","canonical_record":{"source":{"id":"2504.08792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T15:18:34Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"259aaf75bae7422554d5cacb40554d0e2fc52452f3cb70e2e1154c78157a8d1d","abstract_canon_sha256":"61139f79fa7c47556fb8471d90fac6db99993ffbae6bd9c4a8e8f64766a52449"},"schema_version":"1.0"},"canonical_sha256":"6bf9b26ab7a12ca76c6029221c806ab4f26462d98f123850766a99abeabe6e2f","source":{"kind":"arxiv","id":"2504.08792","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08792","created_at":"2026-07-05T10:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08792v1","created_at":"2026-07-05T10:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08792","created_at":"2026-07-05T10:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"NP43E2VXUEWK","created_at":"2026-07-05T10:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"NP43E2VXUEWKO3DA","created_at":"2026-07-05T10:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"NP43E2VX","created_at":"2026-07-05T10:47:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NP43E2VXUEWKO3DAFERBZADKWT","target":"record","payload":{"canonical_record":{"source":{"id":"2504.08792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T15:18:34Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"259aaf75bae7422554d5cacb40554d0e2fc52452f3cb70e2e1154c78157a8d1d","abstract_canon_sha256":"61139f79fa7c47556fb8471d90fac6db99993ffbae6bd9c4a8e8f64766a52449"},"schema_version":"1.0"},"canonical_sha256":"6bf9b26ab7a12ca76c6029221c806ab4f26462d98f123850766a99abeabe6e2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:59.382373Z","signature_b64":"/9rCuC66H34NlhPx4wEqrB/Y0pYUGBC0eQjFOPdoj5lwH3XZTGVQLPFo7wBXJQlaOjhhvelkVi/JkfZJKLOsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bf9b26ab7a12ca76c6029221c806ab4f26462d98f123850766a99abeabe6e2f","last_reissued_at":"2026-07-05T10:47:59.381898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:59.381898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.08792","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":"2026-07-05T10:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CuvSWBdWBQIx6ika3h39RV6nVEDq44i4IJHCP2Qn7kUCTz5E9TJBNuyXoq5os/1VPw5zmbmbfyD/aQyDGI9GDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:08:53.531789Z"},"content_sha256":"d794eced618f33da2886564f70e79769ca719b641a043d7bbacafe4ea1d031ef","schema_version":"1.0","event_id":"sha256:d794eced618f33da2886564f70e79769ca719b641a043d7bbacafe4ea1d031ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NP43E2VXUEWKO3DAFERBZADKWT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing NER Performance in Low-Resource Pakistani Languages using Cross-Lingual Data Augmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Thamar Solorio, Toqeer Ehsan","submitted_at":"2025-04-07T15:18:34Z","abstract_excerpt":"Named Entity Recognition (NER), a fundamental task in Natural Language Processing (NLP), has shown significant advancements for high-resource languages. However, due to a lack of annotated datasets and limited representation in Pre-trained Language Models (PLMs), it remains understudied and challenging for low-resource languages. To address these challenges, we propose a data augmentation technique that generates culturally plausible sentences and experiments on four low-resource Pakistani languages; Urdu, Shahmukhi, Sindhi, and Pashto. By fine-tuning multilingual masked Large Language Models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08792","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/2504.08792/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":"2026-07-05T10:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"axuXxA9A7DtcsOz9iHGY1MeWyCQ81t2HxhkWrYurODGDFXhDiqyo+NMnUtFQBf7icrrd9Fp8PevwGaQuxHdDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:08:53.532091Z"},"content_sha256":"0f57582756dc7745116d93ca5224801ce72955c9a2d035aee113012daab20aae","schema_version":"1.0","event_id":"sha256:0f57582756dc7745116d93ca5224801ce72955c9a2d035aee113012daab20aae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT/bundle.json","state_url":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NP43E2VXUEWKO3DAFERBZADKWT/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":"2026-08-05T06:08:53Z","links":{"resolver":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT","bundle":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT/bundle.json","state":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NP43E2VXUEWKO3DAFERBZADKWT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NP43E2VXUEWKO3DAFERBZADKWT","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":"61139f79fa7c47556fb8471d90fac6db99993ffbae6bd9c4a8e8f64766a52449","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T15:18:34Z","title_canon_sha256":"259aaf75bae7422554d5cacb40554d0e2fc52452f3cb70e2e1154c78157a8d1d"},"schema_version":"1.0","source":{"id":"2504.08792","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08792","created_at":"2026-07-05T10:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08792v1","created_at":"2026-07-05T10:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08792","created_at":"2026-07-05T10:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"NP43E2VXUEWK","created_at":"2026-07-05T10:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"NP43E2VXUEWKO3DA","created_at":"2026-07-05T10:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"NP43E2VX","created_at":"2026-07-05T10:47:59Z"}],"graph_snapshots":[{"event_id":"sha256:0f57582756dc7745116d93ca5224801ce72955c9a2d035aee113012daab20aae","target":"graph","created_at":"2026-07-05T10:47:59Z","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/2504.08792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Named Entity Recognition (NER), a fundamental task in Natural Language Processing (NLP), has shown significant advancements for high-resource languages. However, due to a lack of annotated datasets and limited representation in Pre-trained Language Models (PLMs), it remains understudied and challenging for low-resource languages. To address these challenges, we propose a data augmentation technique that generates culturally plausible sentences and experiments on four low-resource Pakistani languages; Urdu, Shahmukhi, Sindhi, and Pashto. By fine-tuning multilingual masked Large Language Models ","authors_text":"Thamar Solorio, Toqeer Ehsan","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T15:18:34Z","title":"Enhancing NER Performance in Low-Resource Pakistani Languages using Cross-Lingual Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08792","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:d794eced618f33da2886564f70e79769ca719b641a043d7bbacafe4ea1d031ef","target":"record","created_at":"2026-07-05T10:47:59Z","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":"61139f79fa7c47556fb8471d90fac6db99993ffbae6bd9c4a8e8f64766a52449","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T15:18:34Z","title_canon_sha256":"259aaf75bae7422554d5cacb40554d0e2fc52452f3cb70e2e1154c78157a8d1d"},"schema_version":"1.0","source":{"id":"2504.08792","kind":"arxiv","version":1}},"canonical_sha256":"6bf9b26ab7a12ca76c6029221c806ab4f26462d98f123850766a99abeabe6e2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bf9b26ab7a12ca76c6029221c806ab4f26462d98f123850766a99abeabe6e2f","first_computed_at":"2026-07-05T10:47:59.381898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:59.381898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/9rCuC66H34NlhPx4wEqrB/Y0pYUGBC0eQjFOPdoj5lwH3XZTGVQLPFo7wBXJQlaOjhhvelkVi/JkfZJKLOsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:59.382373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.08792","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d794eced618f33da2886564f70e79769ca719b641a043d7bbacafe4ea1d031ef","sha256:0f57582756dc7745116d93ca5224801ce72955c9a2d035aee113012daab20aae"],"state_sha256":"73a8ad9916e115fdd0f59d6b2df4dbfaebbb670082a135aba2a7a713289fc2e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oEZ3hRrTYW7cacu0E8QaWJCGQ/MqG8d1xLJJBxMG9JGuQlyVlCpzNnMyYx0m9vWTHBTSnx1C+/SB495Jq59fCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:08:53.535757Z","bundle_sha256":"df06a245291a43ec10f12ea84180d0b9651d8de3587d04946d04321967d470df"}}