{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2PEPIXAG5DAENWWFUXQRLRVDFB","short_pith_number":"pith:2PEPIXAG","canonical_record":{"source":{"id":"2605.26935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:28:20Z","cross_cats_sorted":[],"title_canon_sha256":"2ad72d7276c8a92db3212042ccf7b294a18ca036276c1def904b27cee3235788","abstract_canon_sha256":"90396ee05a73ac63bcf786a29013df48c5dc5f1c1e87ccde6a9c7a3eb2072169"},"schema_version":"1.0"},"canonical_sha256":"d3c8f45c06e8c046dac5a5e115c6a3287a53ea2f53de9d9e9f95077b2f8a5ee3","source":{"kind":"arxiv","id":"2605.26935","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26935","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26935v1","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26935","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"2PEPIXAG5DAE","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"2PEPIXAG5DAENWWF","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"2PEPIXAG","created_at":"2026-05-27T01:06:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2PEPIXAG5DAENWWFUXQRLRVDFB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.26935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:28:20Z","cross_cats_sorted":[],"title_canon_sha256":"2ad72d7276c8a92db3212042ccf7b294a18ca036276c1def904b27cee3235788","abstract_canon_sha256":"90396ee05a73ac63bcf786a29013df48c5dc5f1c1e87ccde6a9c7a3eb2072169"},"schema_version":"1.0"},"canonical_sha256":"d3c8f45c06e8c046dac5a5e115c6a3287a53ea2f53de9d9e9f95077b2f8a5ee3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:20.693515Z","signature_b64":"W1bYS0txsDGLWqOWUkTAwi7OqOFbR2GljV6E7YbxNhmO/O4pUu7HNISn+svWANr3IvzbrTr/KSppBqdxn5q2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3c8f45c06e8c046dac5a5e115c6a3287a53ea2f53de9d9e9f95077b2f8a5ee3","last_reissued_at":"2026-05-27T01:06:20.692974Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:20.692974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.26935","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":"2026-05-27T01:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2dg+clX51rmKODSJshdmB5a0XsBXrjYD5W92tjPoTKBcmSeF1dZWB79ulaJGkBsVWkH9Yim8qvQqMREFHP/bDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T22:56:05.763539Z"},"content_sha256":"64987d0d2bd32c2eaf8621093a688382f2f5ba0083c231e55745b25b790b64b1","schema_version":"1.0","event_id":"sha256:64987d0d2bd32c2eaf8621093a688382f2f5ba0083c231e55745b25b790b64b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2PEPIXAG5DAENWWFUXQRLRVDFB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DunbaaBERT: From Sacrifice to Semantics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iffat Maab, Raphael Schmitt, Waleed Jamil","submitted_at":"2026-05-26T12:28:20Z","abstract_excerpt":"Large language models have achieved strong performance across many NLP tasks, yet Urdu remains comparatively underexplored due to limited resources and fragmented evaluation settings. To address this gap, we introduce DunbaaBERT, a family of Urdu RoBERTa-base models trained from scratch with Byte-BPE vocabularies of 32k, 52k, and 96k tokens on a deduplicated 17GB Urdu corpus. We evaluate DunbaaBERT across intrinsic and downstream Urdu NLP benchmarks covering linguistic acceptability, news classification, offensive language detection, and sentiment analysis while analyzing vocabulary-size effec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26935","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/2605.26935/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":"2026-05-27T01:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"izQaeOkWKPSXeyGuGIe9RINcrTQMtsqmPkQs5SSBaf6kCT6slFXDKZUwaPOnNdc+OAi9hBinwerz4kQc6kxFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T22:56:05.763936Z"},"content_sha256":"cd663e3c0fbe2de7dca2c7dc7abb8d7ec4d1681648017c00d489906126b6b8ca","schema_version":"1.0","event_id":"sha256:cd663e3c0fbe2de7dca2c7dc7abb8d7ec4d1681648017c00d489906126b6b8ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2PEPIXAG5DAENWWFUXQRLRVDFB/bundle.json","state_url":"https://pith.science/pith/2PEPIXAG5DAENWWFUXQRLRVDFB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2PEPIXAG5DAENWWFUXQRLRVDFB/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":"2026-07-01T22:56:05Z","links":{"resolver":"https://pith.science/pith/2PEPIXAG5DAENWWFUXQRLRVDFB","bundle":"https://pith.science/pith/2PEPIXAG5DAENWWFUXQRLRVDFB/bundle.json","state":"https://pith.science/pith/2PEPIXAG5DAENWWFUXQRLRVDFB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2PEPIXAG5DAENWWFUXQRLRVDFB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2PEPIXAG5DAENWWFUXQRLRVDFB","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":"90396ee05a73ac63bcf786a29013df48c5dc5f1c1e87ccde6a9c7a3eb2072169","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:28:20Z","title_canon_sha256":"2ad72d7276c8a92db3212042ccf7b294a18ca036276c1def904b27cee3235788"},"schema_version":"1.0","source":{"id":"2605.26935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26935","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26935v1","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26935","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"2PEPIXAG5DAE","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"2PEPIXAG5DAENWWF","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"2PEPIXAG","created_at":"2026-05-27T01:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:cd663e3c0fbe2de7dca2c7dc7abb8d7ec4d1681648017c00d489906126b6b8ca","target":"graph","created_at":"2026-05-27T01:06:20Z","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/2605.26935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have achieved strong performance across many NLP tasks, yet Urdu remains comparatively underexplored due to limited resources and fragmented evaluation settings. To address this gap, we introduce DunbaaBERT, a family of Urdu RoBERTa-base models trained from scratch with Byte-BPE vocabularies of 32k, 52k, and 96k tokens on a deduplicated 17GB Urdu corpus. We evaluate DunbaaBERT across intrinsic and downstream Urdu NLP benchmarks covering linguistic acceptability, news classification, offensive language detection, and sentiment analysis while analyzing vocabulary-size effec","authors_text":"Iffat Maab, Raphael Schmitt, Waleed Jamil","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:28:20Z","title":"DunbaaBERT: From Sacrifice to Semantics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26935","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":"sha256:64987d0d2bd32c2eaf8621093a688382f2f5ba0083c231e55745b25b790b64b1","target":"record","created_at":"2026-05-27T01:06:20Z","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":"90396ee05a73ac63bcf786a29013df48c5dc5f1c1e87ccde6a9c7a3eb2072169","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:28:20Z","title_canon_sha256":"2ad72d7276c8a92db3212042ccf7b294a18ca036276c1def904b27cee3235788"},"schema_version":"1.0","source":{"id":"2605.26935","kind":"arxiv","version":1}},"canonical_sha256":"d3c8f45c06e8c046dac5a5e115c6a3287a53ea2f53de9d9e9f95077b2f8a5ee3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3c8f45c06e8c046dac5a5e115c6a3287a53ea2f53de9d9e9f95077b2f8a5ee3","first_computed_at":"2026-05-27T01:06:20.692974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:20.692974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W1bYS0txsDGLWqOWUkTAwi7OqOFbR2GljV6E7YbxNhmO/O4pUu7HNISn+svWANr3IvzbrTr/KSppBqdxn5q2Aw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:20.693515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64987d0d2bd32c2eaf8621093a688382f2f5ba0083c231e55745b25b790b64b1","sha256:cd663e3c0fbe2de7dca2c7dc7abb8d7ec4d1681648017c00d489906126b6b8ca"],"state_sha256":"ff1bdf68bf03335f95894b01c691a58f3cd5b27242b381fabbb8799c978c8831"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kN194Dt0pEzL5gLcRr0YkDEGvYcTnkd7zojg+vR4pFjlToiYjbKma13E+6/gaeUYC1SnB9v+YgPqXdqr6abKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T22:56:05.766689Z","bundle_sha256":"facf992af97d0ee626ba1fc796d125f0dd62ab0d120d37603d708a478836d930"}}