{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Q3NFBQSJVHGQJ2S54ZUVSRMCXE","short_pith_number":"pith:Q3NFBQSJ","canonical_record":{"source":{"id":"2310.16621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T13:20:54Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"e62f89582a0c699fdfbd2f2e464c8122536c2a413676cbf108feb5091e03af1c","abstract_canon_sha256":"01dc86f51dd02283e5119d7ff2ca3922d61daf9bc2bf3c1ac9e98ec5060633ac"},"schema_version":"1.0"},"canonical_sha256":"86da50c249a9cd04ea5de669594582b901f26478b7b23918d37049d7f07d5d06","source":{"kind":"arxiv","id":"2310.16621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16621","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16621v1","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16621","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"Q3NFBQSJVHGQ","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"Q3NFBQSJVHGQJ2S5","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"Q3NFBQSJ","created_at":"2026-07-05T07:05:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Q3NFBQSJVHGQJ2S54ZUVSRMCXE","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T13:20:54Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"e62f89582a0c699fdfbd2f2e464c8122536c2a413676cbf108feb5091e03af1c","abstract_canon_sha256":"01dc86f51dd02283e5119d7ff2ca3922d61daf9bc2bf3c1ac9e98ec5060633ac"},"schema_version":"1.0"},"canonical_sha256":"86da50c249a9cd04ea5de669594582b901f26478b7b23918d37049d7f07d5d06","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:00.384873Z","signature_b64":"KbQhbf2++EpWGEnCgfkQFP0nOhdujCgmd9oWbtuAUQVGDBBEnmgRBG905v99K9T/PXrmg6HrYVVFyaQrPFrFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86da50c249a9cd04ea5de669594582b901f26478b7b23918d37049d7f07d5d06","last_reissued_at":"2026-07-05T07:05:00.384427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:00.384427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16621","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":"2026-07-05T07:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ik9i1RlKXiOrS1G3UPQy08iUHDqVPv8pi/KVKgL3yt3yHp+8Cnl3NIMYq8I7J9Y0uxcWS8w9L8iI3QWOgSWfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:23:33.655589Z"},"content_sha256":"4bc48907798012b5224d6793dade66d43dfe8003a722b0696087de2035d22f37","schema_version":"1.0","event_id":"sha256:4bc48907798012b5224d6793dade66d43dfe8003a722b0696087de2035d22f37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Q3NFBQSJVHGQJ2S54ZUVSRMCXE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ArTST: Arabic Text and Speech Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ajinkya Kulkarni, Amirbek Djanibekov, Hanan Aldarmaki, Hawau Olamide Toyin","submitted_at":"2023-10-25T13:20:54Z","abstract_excerpt":"We present ArTST, a pre-trained Arabic text and speech transformer for supporting open-source speech technologies for the Arabic language. The model architecture follows the unified-modal framework, SpeechT5, that was recently released for English, and is focused on Modern Standard Arabic (MSA), with plans to extend the model for dialectal and code-switched Arabic in future editions. We pre-trained the model from scratch on MSA speech and text data, and fine-tuned it for the following tasks: Automatic Speech Recognition (ASR), Text-To-Speech synthesis (TTS), and spoken dialect identification. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16621","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/2310.16621/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":"2026-07-05T07:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r4/3P1b0I9o4GqW3WUOG93RFs4PMOLEYzxtwjXBIC577Tok2JflOKTbhYT/JoQMKQEABpbH/gv7i2og+lUDPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:23:33.656135Z"},"content_sha256":"6c57bdf544d40aa410d927daeaaf7388a7c63cc8b1d8bea2d4e5109832fc1be9","schema_version":"1.0","event_id":"sha256:6c57bdf544d40aa410d927daeaaf7388a7c63cc8b1d8bea2d4e5109832fc1be9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/bundle.json","state_url":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/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":"2026-08-01T07:23:33Z","links":{"resolver":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE","bundle":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/bundle.json","state":"https://pith.science/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3NFBQSJVHGQJ2S54ZUVSRMCXE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q3NFBQSJVHGQJ2S54ZUVSRMCXE","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":"01dc86f51dd02283e5119d7ff2ca3922d61daf9bc2bf3c1ac9e98ec5060633ac","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T13:20:54Z","title_canon_sha256":"e62f89582a0c699fdfbd2f2e464c8122536c2a413676cbf108feb5091e03af1c"},"schema_version":"1.0","source":{"id":"2310.16621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16621","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16621v1","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16621","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"Q3NFBQSJVHGQ","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"Q3NFBQSJVHGQJ2S5","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"Q3NFBQSJ","created_at":"2026-07-05T07:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:6c57bdf544d40aa410d927daeaaf7388a7c63cc8b1d8bea2d4e5109832fc1be9","target":"graph","created_at":"2026-07-05T07:05:00Z","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/2310.16621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present ArTST, a pre-trained Arabic text and speech transformer for supporting open-source speech technologies for the Arabic language. The model architecture follows the unified-modal framework, SpeechT5, that was recently released for English, and is focused on Modern Standard Arabic (MSA), with plans to extend the model for dialectal and code-switched Arabic in future editions. We pre-trained the model from scratch on MSA speech and text data, and fine-tuned it for the following tasks: Automatic Speech Recognition (ASR), Text-To-Speech synthesis (TTS), and spoken dialect identification. ","authors_text":"Ajinkya Kulkarni, Amirbek Djanibekov, Hanan Aldarmaki, Hawau Olamide Toyin","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T13:20:54Z","title":"ArTST: Arabic Text and Speech Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16621","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":"sha256:4bc48907798012b5224d6793dade66d43dfe8003a722b0696087de2035d22f37","target":"record","created_at":"2026-07-05T07:05:00Z","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":"01dc86f51dd02283e5119d7ff2ca3922d61daf9bc2bf3c1ac9e98ec5060633ac","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T13:20:54Z","title_canon_sha256":"e62f89582a0c699fdfbd2f2e464c8122536c2a413676cbf108feb5091e03af1c"},"schema_version":"1.0","source":{"id":"2310.16621","kind":"arxiv","version":1}},"canonical_sha256":"86da50c249a9cd04ea5de669594582b901f26478b7b23918d37049d7f07d5d06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86da50c249a9cd04ea5de669594582b901f26478b7b23918d37049d7f07d5d06","first_computed_at":"2026-07-05T07:05:00.384427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:00.384427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KbQhbf2++EpWGEnCgfkQFP0nOhdujCgmd9oWbtuAUQVGDBBEnmgRBG905v99K9T/PXrmg6HrYVVFyaQrPFrFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:00.384873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bc48907798012b5224d6793dade66d43dfe8003a722b0696087de2035d22f37","sha256:6c57bdf544d40aa410d927daeaaf7388a7c63cc8b1d8bea2d4e5109832fc1be9"],"state_sha256":"692129f245749e6a7989466445cb363c9b6cd685213352b1d51472694018e9c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hy7mfaKvWKzXwtF3NizriyU3zx+qlPB8askabfIZmNm9NNYG4qJV0o7eCd4Z86DFfItlrEs/KSlUmWAhi4osDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:23:33.661238Z","bundle_sha256":"b11d130f4cdbc31af07783f71621bed2a936f4c63dafb8b40f8f1bf67f696858"}}