{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UOTFZVG66PPOFDVV3O76B7ZRMQ","short_pith_number":"pith:UOTFZVG6","canonical_record":{"source":{"id":"2507.13977","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T14:42:18Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e91bab027102517706604baeabba00d692380be2681d0da8297fa5c409ff9bc7","abstract_canon_sha256":"37242e9d017a19adfe709e32f2c4a7e26c21aacbf0e9286cb34c74d7be705c6e"},"schema_version":"1.0"},"canonical_sha256":"a3a65cd4def3dee28eb5dbbfe0ff31641fd228d6b9e557d9abfaa79165a6f0dc","source":{"kind":"arxiv","id":"2507.13977","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13977","created_at":"2026-07-05T11:39:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13977v1","created_at":"2026-07-05T11:39:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13977","created_at":"2026-07-05T11:39:26Z"},{"alias_kind":"pith_short_12","alias_value":"UOTFZVG66PPO","created_at":"2026-07-05T11:39:26Z"},{"alias_kind":"pith_short_16","alias_value":"UOTFZVG66PPOFDVV","created_at":"2026-07-05T11:39:26Z"},{"alias_kind":"pith_short_8","alias_value":"UOTFZVG6","created_at":"2026-07-05T11:39:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UOTFZVG66PPOFDVV3O76B7ZRMQ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13977","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T14:42:18Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e91bab027102517706604baeabba00d692380be2681d0da8297fa5c409ff9bc7","abstract_canon_sha256":"37242e9d017a19adfe709e32f2c4a7e26c21aacbf0e9286cb34c74d7be705c6e"},"schema_version":"1.0"},"canonical_sha256":"a3a65cd4def3dee28eb5dbbfe0ff31641fd228d6b9e557d9abfaa79165a6f0dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:26.363607Z","signature_b64":"jDR0H/7zJwQltjY3MUoiWzsEK9/Rg7Paq8IQUzpFI8yL/A9bOgp66vqvxalWY4izVuBescyTPhHTaEn0moSoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a65cd4def3dee28eb5dbbfe0ff31641fd228d6b9e557d9abfaa79165a6f0dc","last_reissued_at":"2026-07-05T11:39:26.363138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:26.363138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13977","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":"2026-07-05T11:39:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GSe1yn8uFwtvYOlDteH3mceliJUotaFMnkgh9tmLWXZ+8X2ogEDk93FwlHa1cQAfzEc1FSg+DQUOhssCCrh+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:31:00.419891Z"},"content_sha256":"fce5d9eb7fa77c20c526169bafdf254b200cd364eb8f7b21310dc7eb03054d56","schema_version":"1.0","event_id":"sha256:fce5d9eb7fa77c20c526169bafdf254b200cd364eb8f7b21310dc7eb03054d56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UOTFZVG66PPOFDVV3O76B7ZRMQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Enas Albasiri, Lilit Grigoryan, Nikolay Karpov, Vitaly Lavrukhin","submitted_at":"2025-07-18T14:42:18Z","abstract_excerpt":"Despite Arabic being one of the most widely spoken languages, the development of Arabic Automatic Speech Recognition (ASR) systems faces significant challenges due to the language's complexity, and only a limited number of public Arabic ASR models exist. While much of the focus has been on Modern Standard Arabic (MSA), there is considerably less attention given to the variations within the language. This paper introduces a universal methodology for Arabic speech and text processing designed to address unique challenges of the language. Using this methodology, we train two novel models based on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13977","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/2507.13977/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":"2026-07-05T11:39:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ANpc/1L7fmr9SxFfyEp52myZDanm1LJ77MWJ6sbYoHBxHgdtLqLBsBJej3w4y5uifn/saYHiUKpMQncHTmNjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:31:00.420265Z"},"content_sha256":"649f483f84c55647cdbe9df577452c3d9b15105c9e66fa8c52687df5d0174db5","schema_version":"1.0","event_id":"sha256:649f483f84c55647cdbe9df577452c3d9b15105c9e66fa8c52687df5d0174db5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOTFZVG66PPOFDVV3O76B7ZRMQ/bundle.json","state_url":"https://pith.science/pith/UOTFZVG66PPOFDVV3O76B7ZRMQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOTFZVG66PPOFDVV3O76B7ZRMQ/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":"2026-07-06T10:31:00Z","links":{"resolver":"https://pith.science/pith/UOTFZVG66PPOFDVV3O76B7ZRMQ","bundle":"https://pith.science/pith/UOTFZVG66PPOFDVV3O76B7ZRMQ/bundle.json","state":"https://pith.science/pith/UOTFZVG66PPOFDVV3O76B7ZRMQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOTFZVG66PPOFDVV3O76B7ZRMQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UOTFZVG66PPOFDVV3O76B7ZRMQ","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":"37242e9d017a19adfe709e32f2c4a7e26c21aacbf0e9286cb34c74d7be705c6e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T14:42:18Z","title_canon_sha256":"e91bab027102517706604baeabba00d692380be2681d0da8297fa5c409ff9bc7"},"schema_version":"1.0","source":{"id":"2507.13977","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13977","created_at":"2026-07-05T11:39:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13977v1","created_at":"2026-07-05T11:39:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13977","created_at":"2026-07-05T11:39:26Z"},{"alias_kind":"pith_short_12","alias_value":"UOTFZVG66PPO","created_at":"2026-07-05T11:39:26Z"},{"alias_kind":"pith_short_16","alias_value":"UOTFZVG66PPOFDVV","created_at":"2026-07-05T11:39:26Z"},{"alias_kind":"pith_short_8","alias_value":"UOTFZVG6","created_at":"2026-07-05T11:39:26Z"}],"graph_snapshots":[{"event_id":"sha256:649f483f84c55647cdbe9df577452c3d9b15105c9e66fa8c52687df5d0174db5","target":"graph","created_at":"2026-07-05T11:39:26Z","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/2507.13977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite Arabic being one of the most widely spoken languages, the development of Arabic Automatic Speech Recognition (ASR) systems faces significant challenges due to the language's complexity, and only a limited number of public Arabic ASR models exist. While much of the focus has been on Modern Standard Arabic (MSA), there is considerably less attention given to the variations within the language. This paper introduces a universal methodology for Arabic speech and text processing designed to address unique challenges of the language. Using this methodology, we train two novel models based on","authors_text":"Boris Ginsburg, Enas Albasiri, Lilit Grigoryan, Nikolay Karpov, Vitaly Lavrukhin","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T14:42:18Z","title":"Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13977","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:fce5d9eb7fa77c20c526169bafdf254b200cd364eb8f7b21310dc7eb03054d56","target":"record","created_at":"2026-07-05T11:39:26Z","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":"37242e9d017a19adfe709e32f2c4a7e26c21aacbf0e9286cb34c74d7be705c6e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-18T14:42:18Z","title_canon_sha256":"e91bab027102517706604baeabba00d692380be2681d0da8297fa5c409ff9bc7"},"schema_version":"1.0","source":{"id":"2507.13977","kind":"arxiv","version":1}},"canonical_sha256":"a3a65cd4def3dee28eb5dbbfe0ff31641fd228d6b9e557d9abfaa79165a6f0dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3a65cd4def3dee28eb5dbbfe0ff31641fd228d6b9e557d9abfaa79165a6f0dc","first_computed_at":"2026-07-05T11:39:26.363138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:26.363138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jDR0H/7zJwQltjY3MUoiWzsEK9/Rg7Paq8IQUzpFI8yL/A9bOgp66vqvxalWY4izVuBescyTPhHTaEn0moSoAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:26.363607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13977","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fce5d9eb7fa77c20c526169bafdf254b200cd364eb8f7b21310dc7eb03054d56","sha256:649f483f84c55647cdbe9df577452c3d9b15105c9e66fa8c52687df5d0174db5"],"state_sha256":"6ce9ee7b90d79949d66963bec26ba8d00b309a646f175b51ced71ad6210c8c41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eoORYxRVhISA6M+2lkjG0oLXCqGEm+NQFZZkNaPwL7d8kpXQW1UaQhUEc865TTuZo+BV/8ym0XrCbDABeI6zCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:31:00.422159Z","bundle_sha256":"060d5285c490e3f4aded3fa457e029b9e8e66c52618488101b8cd29684de1be4"}}