{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:H2QXIR62CHKWEQCAP42FTRZPSP","short_pith_number":"pith:H2QXIR62","canonical_record":{"source":{"id":"2508.01006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T18:16:37Z","cross_cats_sorted":[],"title_canon_sha256":"e0e3a0356c74fa1d1b1c1ebbfd35afc9f02770ddd8184fe0efc022cc75a6f322","abstract_canon_sha256":"a43a2c8a3a1235325204166d1ee0ca93316bf110520b81f8b28d13a3f253acb6"},"schema_version":"1.0"},"canonical_sha256":"3ea17447da11d56240407f3459c72f93e5a60027e369e76b9c8ad3fc3d857e88","source":{"kind":"arxiv","id":"2508.01006","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01006","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01006v1","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01006","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"pith_short_12","alias_value":"H2QXIR62CHKW","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"pith_short_16","alias_value":"H2QXIR62CHKWEQCA","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"pith_short_8","alias_value":"H2QXIR62","created_at":"2026-07-05T11:47:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:H2QXIR62CHKWEQCAP42FTRZPSP","target":"record","payload":{"canonical_record":{"source":{"id":"2508.01006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T18:16:37Z","cross_cats_sorted":[],"title_canon_sha256":"e0e3a0356c74fa1d1b1c1ebbfd35afc9f02770ddd8184fe0efc022cc75a6f322","abstract_canon_sha256":"a43a2c8a3a1235325204166d1ee0ca93316bf110520b81f8b28d13a3f253acb6"},"schema_version":"1.0"},"canonical_sha256":"3ea17447da11d56240407f3459c72f93e5a60027e369e76b9c8ad3fc3d857e88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:31.655998Z","signature_b64":"QNFYy+kY6x/7vBoxr2kWaMoeC0tNptzIBuE35XAM0vds/UU1mjYNy2toGB5JXq8j4U+axKWRtmKxa8WZpZf+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ea17447da11d56240407f3459c72f93e5a60027e369e76b9c8ad3fc3d857e88","last_reissued_at":"2026-07-05T11:47:31.655496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:31.655496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.01006","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":"2026-07-05T11:47:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JYRvBxN6dyInNql97HRZVZsKXxu0ehA23P91pdG/1BDlGfeH6MEMXDeOFQWh/ctXq1KEsTIQRZNks4x1+bMZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:47:09.486117Z"},"content_sha256":"4fb764f7aba307fb414229877cf14371df7cc3953eeb2cf8eff4af21a1ec53a6","schema_version":"1.0","event_id":"sha256:4fb764f7aba307fb414229877cf14371df7cc3953eeb2cf8eff4af21a1ec53a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:H2QXIR62CHKWEQCAP42FTRZPSP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian Dillon, Farah Adeeba, Hassan Sajjad, Rajesh Bhatt","submitted_at":"2025-08-01T18:16:37Z","abstract_excerpt":"Multilingual Large Language Models (LLMs) have shown remarkable performance across various languages; however, they often include significantly less data for low-resource languages such as Urdu compared to high-resource languages like English. To assess the linguistic knowledge of LLMs in Urdu, we present the Urdu Benchmark of Linguistic Minimal Pairs (UrBLiMP) i.e. pairs of minimally different sentences that contrast in grammatical acceptability. UrBLiMP comprises 5,696 minimal pairs targeting ten core syntactic phenomena, carefully curated using the Urdu Treebank and diverse Urdu text corpor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01006","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/2508.01006/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":"2026-07-05T11:47:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XKUt4z5+SCcHVeNCN9u0H0ouCHIoBEBCLx4fShOxtvESXbvptm9blDZdImfLPOSLNN7SbIFC+8nwiiF1BNXbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:47:09.486671Z"},"content_sha256":"89ab693150e97a810cfb90b9af8f804958c9b8e83c95eb6a62d9f825fd23bc8b","schema_version":"1.0","event_id":"sha256:89ab693150e97a810cfb90b9af8f804958c9b8e83c95eb6a62d9f825fd23bc8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2QXIR62CHKWEQCAP42FTRZPSP/bundle.json","state_url":"https://pith.science/pith/H2QXIR62CHKWEQCAP42FTRZPSP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2QXIR62CHKWEQCAP42FTRZPSP/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":"2026-08-08T19:47:09Z","links":{"resolver":"https://pith.science/pith/H2QXIR62CHKWEQCAP42FTRZPSP","bundle":"https://pith.science/pith/H2QXIR62CHKWEQCAP42FTRZPSP/bundle.json","state":"https://pith.science/pith/H2QXIR62CHKWEQCAP42FTRZPSP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2QXIR62CHKWEQCAP42FTRZPSP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H2QXIR62CHKWEQCAP42FTRZPSP","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":"a43a2c8a3a1235325204166d1ee0ca93316bf110520b81f8b28d13a3f253acb6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T18:16:37Z","title_canon_sha256":"e0e3a0356c74fa1d1b1c1ebbfd35afc9f02770ddd8184fe0efc022cc75a6f322"},"schema_version":"1.0","source":{"id":"2508.01006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01006","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01006v1","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01006","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"pith_short_12","alias_value":"H2QXIR62CHKW","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"pith_short_16","alias_value":"H2QXIR62CHKWEQCA","created_at":"2026-07-05T11:47:31Z"},{"alias_kind":"pith_short_8","alias_value":"H2QXIR62","created_at":"2026-07-05T11:47:31Z"}],"graph_snapshots":[{"event_id":"sha256:89ab693150e97a810cfb90b9af8f804958c9b8e83c95eb6a62d9f825fd23bc8b","target":"graph","created_at":"2026-07-05T11:47:31Z","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/2508.01006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual Large Language Models (LLMs) have shown remarkable performance across various languages; however, they often include significantly less data for low-resource languages such as Urdu compared to high-resource languages like English. To assess the linguistic knowledge of LLMs in Urdu, we present the Urdu Benchmark of Linguistic Minimal Pairs (UrBLiMP) i.e. pairs of minimally different sentences that contrast in grammatical acceptability. UrBLiMP comprises 5,696 minimal pairs targeting ten core syntactic phenomena, carefully curated using the Urdu Treebank and diverse Urdu text corpor","authors_text":"Brian Dillon, Farah Adeeba, Hassan Sajjad, Rajesh Bhatt","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T18:16:37Z","title":"UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01006","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":"sha256:4fb764f7aba307fb414229877cf14371df7cc3953eeb2cf8eff4af21a1ec53a6","target":"record","created_at":"2026-07-05T11:47:31Z","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":"a43a2c8a3a1235325204166d1ee0ca93316bf110520b81f8b28d13a3f253acb6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T18:16:37Z","title_canon_sha256":"e0e3a0356c74fa1d1b1c1ebbfd35afc9f02770ddd8184fe0efc022cc75a6f322"},"schema_version":"1.0","source":{"id":"2508.01006","kind":"arxiv","version":1}},"canonical_sha256":"3ea17447da11d56240407f3459c72f93e5a60027e369e76b9c8ad3fc3d857e88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ea17447da11d56240407f3459c72f93e5a60027e369e76b9c8ad3fc3d857e88","first_computed_at":"2026-07-05T11:47:31.655496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:31.655496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QNFYy+kY6x/7vBoxr2kWaMoeC0tNptzIBuE35XAM0vds/UU1mjYNy2toGB5JXq8j4U+axKWRtmKxa8WZpZf+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:31.655998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fb764f7aba307fb414229877cf14371df7cc3953eeb2cf8eff4af21a1ec53a6","sha256:89ab693150e97a810cfb90b9af8f804958c9b8e83c95eb6a62d9f825fd23bc8b"],"state_sha256":"00903a993e0f1ae843db631c9536f6c8b2aa1850841bc8ff11d77587249e8e1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5JgRyg1bTKwrqEBoMnYCrcSrnmBlxl5g8yL9XQeBH3id6+SfGZvzx+wMxluI14aERZlj2yiDKjwXuYUmPAkSCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:47:09.490716Z","bundle_sha256":"2947590eb34c4a2561a0d46895639daebbfefd3d6758d9f40cb262578828c8c6"}}