{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6YQO53WX3Q22252V7BPBNGJEPG","short_pith_number":"pith:6YQO53WX","canonical_record":{"source":{"id":"2409.11252","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T15:00:31Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"bb2156df668fa497a588092f4345afe78f59467805f3348a157716dfe5777d17","abstract_canon_sha256":"a2df846631b8e2e4c262657de9380fc5bf12df06596c2c0a664e5d8be257f164"},"schema_version":"1.0"},"canonical_sha256":"f620eeeed7dc35ad7755f85e16992479ac6dfa8281c51c7d6c8ccd7beff42ffc","source":{"kind":"arxiv","id":"2409.11252","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11252","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11252v3","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11252","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"6YQO53WX3Q22","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"6YQO53WX3Q22252V","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"6YQO53WX","created_at":"2026-07-05T11:16:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6YQO53WX3Q22252V7BPBNGJEPG","target":"record","payload":{"canonical_record":{"source":{"id":"2409.11252","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T15:00:31Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"bb2156df668fa497a588092f4345afe78f59467805f3348a157716dfe5777d17","abstract_canon_sha256":"a2df846631b8e2e4c262657de9380fc5bf12df06596c2c0a664e5d8be257f164"},"schema_version":"1.0"},"canonical_sha256":"f620eeeed7dc35ad7755f85e16992479ac6dfa8281c51c7d6c8ccd7beff42ffc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:50.667390Z","signature_b64":"bcdMQdk1FnOiKZsT5r9pBoifQodjs9CdR+wbSx6QINxMmcTRoURvn68AGGBPiZdE32fl/500t0m+pNY9UPVZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f620eeeed7dc35ad7755f85e16992479ac6dfa8281c51c7d6c8ccd7beff42ffc","last_reissued_at":"2026-07-05T11:16:50.666820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:50.666820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.11252","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nXCEiqkA/qIDEw2Sem5EubXuCy9cOfeGCw91hfIBeUA8iBYswU1NW71Z0KdEL5l1sWEQHxPsko1F//qvZbESAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:01:55.624112Z"},"content_sha256":"60dd782c4138a65aa6b4a4a5c3e5423681d14231691bf6af655e891e6096f5c9","schema_version":"1.0","event_id":"sha256:60dd782c4138a65aa6b4a4a5c3e5423681d14231691bf6af655e891e6096f5c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6YQO53WX3Q22252V7BPBNGJEPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WER We Stand: Benchmarking Urdu ASR Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aamina Jamal Khan, Agha Ali Raza, Awais Athar, Mustafa Abbas, Samee Arif, Sualeha Farid","submitted_at":"2024-09-17T15:00:31Z","abstract_excerpt":"This paper presents a comprehensive evaluation of Urdu Automatic Speech Recognition (ASR) models. We analyze the performance of three ASR model families: Whisper, MMS, and Seamless-M4T using Word Error Rate (WER), along with a detailed examination of the most frequent wrong words and error types including insertions, deletions, and substitutions. Our analysis is conducted using two types of datasets, read speech and conversational speech. Notably, we present the first conversational speech dataset designed for benchmarking Urdu ASR models. We find that seamless-large outperforms other ASR mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11252","kind":"arxiv","version":3},"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/2409.11252/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":"2026-07-05T11:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AxVlrJgGLuR2f+IYxEKmYL/LLpR3gDW32KX9hDkyXOvqNu5o2Fstq1mEQG0OmZYMZ8Mp+IWrugv8SIu0F0lACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:01:55.624605Z"},"content_sha256":"b15060c6913b89eb56af95a870d33c6024fad1048cd48cf4563877bd5085d441","schema_version":"1.0","event_id":"sha256:b15060c6913b89eb56af95a870d33c6024fad1048cd48cf4563877bd5085d441"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YQO53WX3Q22252V7BPBNGJEPG/bundle.json","state_url":"https://pith.science/pith/6YQO53WX3Q22252V7BPBNGJEPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YQO53WX3Q22252V7BPBNGJEPG/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":"2026-08-22T05:01:55Z","links":{"resolver":"https://pith.science/pith/6YQO53WX3Q22252V7BPBNGJEPG","bundle":"https://pith.science/pith/6YQO53WX3Q22252V7BPBNGJEPG/bundle.json","state":"https://pith.science/pith/6YQO53WX3Q22252V7BPBNGJEPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YQO53WX3Q22252V7BPBNGJEPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6YQO53WX3Q22252V7BPBNGJEPG","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":"a2df846631b8e2e4c262657de9380fc5bf12df06596c2c0a664e5d8be257f164","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T15:00:31Z","title_canon_sha256":"bb2156df668fa497a588092f4345afe78f59467805f3348a157716dfe5777d17"},"schema_version":"1.0","source":{"id":"2409.11252","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11252","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11252v3","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11252","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"6YQO53WX3Q22","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"6YQO53WX3Q22252V","created_at":"2026-07-05T11:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"6YQO53WX","created_at":"2026-07-05T11:16:50Z"}],"graph_snapshots":[{"event_id":"sha256:b15060c6913b89eb56af95a870d33c6024fad1048cd48cf4563877bd5085d441","target":"graph","created_at":"2026-07-05T11:16:50Z","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/2409.11252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a comprehensive evaluation of Urdu Automatic Speech Recognition (ASR) models. We analyze the performance of three ASR model families: Whisper, MMS, and Seamless-M4T using Word Error Rate (WER), along with a detailed examination of the most frequent wrong words and error types including insertions, deletions, and substitutions. Our analysis is conducted using two types of datasets, read speech and conversational speech. Notably, we present the first conversational speech dataset designed for benchmarking Urdu ASR models. We find that seamless-large outperforms other ASR mode","authors_text":"Aamina Jamal Khan, Agha Ali Raza, Awais Athar, Mustafa Abbas, Samee Arif, Sualeha Farid","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T15:00:31Z","title":"WER We Stand: Benchmarking Urdu ASR Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11252","kind":"arxiv","version":3},"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":"sha256:60dd782c4138a65aa6b4a4a5c3e5423681d14231691bf6af655e891e6096f5c9","target":"record","created_at":"2026-07-05T11:16:50Z","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":"a2df846631b8e2e4c262657de9380fc5bf12df06596c2c0a664e5d8be257f164","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T15:00:31Z","title_canon_sha256":"bb2156df668fa497a588092f4345afe78f59467805f3348a157716dfe5777d17"},"schema_version":"1.0","source":{"id":"2409.11252","kind":"arxiv","version":3}},"canonical_sha256":"f620eeeed7dc35ad7755f85e16992479ac6dfa8281c51c7d6c8ccd7beff42ffc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f620eeeed7dc35ad7755f85e16992479ac6dfa8281c51c7d6c8ccd7beff42ffc","first_computed_at":"2026-07-05T11:16:50.666820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:50.666820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bcdMQdk1FnOiKZsT5r9pBoifQodjs9CdR+wbSx6QINxMmcTRoURvn68AGGBPiZdE32fl/500t0m+pNY9UPVZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:50.667390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11252","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60dd782c4138a65aa6b4a4a5c3e5423681d14231691bf6af655e891e6096f5c9","sha256:b15060c6913b89eb56af95a870d33c6024fad1048cd48cf4563877bd5085d441"],"state_sha256":"a7e0d459daae2b1bc0f2b038883043019589892298308cc513e53b8b899a9a3e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l4YGnw72cJpj5c727QLN5XrG7q7jRZVII8cEcZIt2QQk9+6w3k2TCk8f6rb2az1QhXORVHRvJ6j9ucj3tkQRAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T05:01:55.628612Z","bundle_sha256":"7b6ad0bb3c1606de5afd8eedbc9bf464d03ea40e930393df0f8944bc36ab8925"}}