{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CM7C76WGTPR4YTMLO2PLRK6ITY","short_pith_number":"pith:CM7C76WG","canonical_record":{"source":{"id":"2309.11327","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-20T13:56:27Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"6f89148581f8b30107ebd352e4a81765e1de01324f3aa5f358b81658fdcacec7","abstract_canon_sha256":"1598d5d2493111eaccdad4d26d3e4876533511a032b3e0021a3783d1606ff0c8"},"schema_version":"1.0"},"canonical_sha256":"133e2ffac69be3cc4d8b769eb8abc89e0d646834023d6ee4d3f4482af9597578","source":{"kind":"arxiv","id":"2309.11327","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11327","created_at":"2026-07-05T06:53:45Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11327v2","created_at":"2026-07-05T06:53:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11327","created_at":"2026-07-05T06:53:45Z"},{"alias_kind":"pith_short_12","alias_value":"CM7C76WGTPR4","created_at":"2026-07-05T06:53:45Z"},{"alias_kind":"pith_short_16","alias_value":"CM7C76WGTPR4YTML","created_at":"2026-07-05T06:53:45Z"},{"alias_kind":"pith_short_8","alias_value":"CM7C76WG","created_at":"2026-07-05T06:53:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CM7C76WGTPR4YTMLO2PLRK6ITY","target":"record","payload":{"canonical_record":{"source":{"id":"2309.11327","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-20T13:56:27Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"6f89148581f8b30107ebd352e4a81765e1de01324f3aa5f358b81658fdcacec7","abstract_canon_sha256":"1598d5d2493111eaccdad4d26d3e4876533511a032b3e0021a3783d1606ff0c8"},"schema_version":"1.0"},"canonical_sha256":"133e2ffac69be3cc4d8b769eb8abc89e0d646834023d6ee4d3f4482af9597578","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:45.454085Z","signature_b64":"QHqB5mpfX3j7JqO8jvx2Tuu2XlqJkVqqg91pJ1u58RnqIP3nmujcrNIdw/rb4AF/6kdRHYv/4eHU2YxmnBIjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"133e2ffac69be3cc4d8b769eb8abc89e0d646834023d6ee4d3f4482af9597578","last_reissued_at":"2026-07-05T06:53:45.453691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:45.453691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.11327","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:53:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+sCkpzRA6i9cgWWorTsz4kN6j+/6kxAb8Zo+sqghmeFZrT/9jJGgkjPsbToBptdzqzeafo/P/bBpYTN8JGHLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:50:34.471408Z"},"content_sha256":"f1cf4a66ab64dbf49974a90056fa63b665f2e91d845a7a7644e879e831233bab","schema_version":"1.0","event_id":"sha256:f1cf4a66ab64dbf49974a90056fa63b665f2e91d845a7a7644e879e831233bab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CM7C76WGTPR4YTMLO2PLRK6ITY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Data Collection and Unsupervised Learning for Code-switched Tunisian Arabic Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ahmed Amine Ben Abdallah, Amir Kanoun, Ata Kabboudi, Salah Zaiem","submitted_at":"2023-09-20T13:56:27Z","abstract_excerpt":"Crafting an effective Automatic Speech Recognition (ASR) solution for dialects demands innovative approaches that not only address the data scarcity issue but also navigate the intricacies of linguistic diversity. In this paper, we address the aforementioned ASR challenge, focusing on the Tunisian dialect. First, textual and audio data is collected and in some cases annotated. Second, we explore self-supervision, semi-supervision and few-shot code-switching approaches to push the state-of-the-art on different Tunisian test sets; covering different acoustic, linguistic and prosodic conditions. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11327","kind":"arxiv","version":2},"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/2309.11327/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":"2026-07-05T06:53:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qcrifd+Fr11rDuTmHqxXKOiDBDHogI6+ty+fls1t0tgf7Vbhy+27Mh6E6OpncgFzDuT58EZ4jZsIloI5uqORDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:50:34.471962Z"},"content_sha256":"3f7b274134f5f5097589d8e37c42df36d160ab8444dd86324583af1467a4b43a","schema_version":"1.0","event_id":"sha256:3f7b274134f5f5097589d8e37c42df36d160ab8444dd86324583af1467a4b43a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CM7C76WGTPR4YTMLO2PLRK6ITY/bundle.json","state_url":"https://pith.science/pith/CM7C76WGTPR4YTMLO2PLRK6ITY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CM7C76WGTPR4YTMLO2PLRK6ITY/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":"2026-08-08T21:50:34Z","links":{"resolver":"https://pith.science/pith/CM7C76WGTPR4YTMLO2PLRK6ITY","bundle":"https://pith.science/pith/CM7C76WGTPR4YTMLO2PLRK6ITY/bundle.json","state":"https://pith.science/pith/CM7C76WGTPR4YTMLO2PLRK6ITY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CM7C76WGTPR4YTMLO2PLRK6ITY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CM7C76WGTPR4YTMLO2PLRK6ITY","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":"1598d5d2493111eaccdad4d26d3e4876533511a032b3e0021a3783d1606ff0c8","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-20T13:56:27Z","title_canon_sha256":"6f89148581f8b30107ebd352e4a81765e1de01324f3aa5f358b81658fdcacec7"},"schema_version":"1.0","source":{"id":"2309.11327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11327","created_at":"2026-07-05T06:53:45Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11327v2","created_at":"2026-07-05T06:53:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11327","created_at":"2026-07-05T06:53:45Z"},{"alias_kind":"pith_short_12","alias_value":"CM7C76WGTPR4","created_at":"2026-07-05T06:53:45Z"},{"alias_kind":"pith_short_16","alias_value":"CM7C76WGTPR4YTML","created_at":"2026-07-05T06:53:45Z"},{"alias_kind":"pith_short_8","alias_value":"CM7C76WG","created_at":"2026-07-05T06:53:45Z"}],"graph_snapshots":[{"event_id":"sha256:3f7b274134f5f5097589d8e37c42df36d160ab8444dd86324583af1467a4b43a","target":"graph","created_at":"2026-07-05T06:53:45Z","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/2309.11327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Crafting an effective Automatic Speech Recognition (ASR) solution for dialects demands innovative approaches that not only address the data scarcity issue but also navigate the intricacies of linguistic diversity. In this paper, we address the aforementioned ASR challenge, focusing on the Tunisian dialect. First, textual and audio data is collected and in some cases annotated. Second, we explore self-supervision, semi-supervision and few-shot code-switching approaches to push the state-of-the-art on different Tunisian test sets; covering different acoustic, linguistic and prosodic conditions. ","authors_text":"Ahmed Amine Ben Abdallah, Amir Kanoun, Ata Kabboudi, Salah Zaiem","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-20T13:56:27Z","title":"Leveraging Data Collection and Unsupervised Learning for Code-switched Tunisian Arabic Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11327","kind":"arxiv","version":2},"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:f1cf4a66ab64dbf49974a90056fa63b665f2e91d845a7a7644e879e831233bab","target":"record","created_at":"2026-07-05T06:53:45Z","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":"1598d5d2493111eaccdad4d26d3e4876533511a032b3e0021a3783d1606ff0c8","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-20T13:56:27Z","title_canon_sha256":"6f89148581f8b30107ebd352e4a81765e1de01324f3aa5f358b81658fdcacec7"},"schema_version":"1.0","source":{"id":"2309.11327","kind":"arxiv","version":2}},"canonical_sha256":"133e2ffac69be3cc4d8b769eb8abc89e0d646834023d6ee4d3f4482af9597578","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"133e2ffac69be3cc4d8b769eb8abc89e0d646834023d6ee4d3f4482af9597578","first_computed_at":"2026-07-05T06:53:45.453691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:45.453691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QHqB5mpfX3j7JqO8jvx2Tuu2XlqJkVqqg91pJ1u58RnqIP3nmujcrNIdw/rb4AF/6kdRHYv/4eHU2YxmnBIjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:45.454085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.11327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1cf4a66ab64dbf49974a90056fa63b665f2e91d845a7a7644e879e831233bab","sha256:3f7b274134f5f5097589d8e37c42df36d160ab8444dd86324583af1467a4b43a"],"state_sha256":"26e012d3048e863e9805dc77b424a5a2bb1c7771ae1226f408e3a975c845d1d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CsxaRb/12FEWmlG0oMJ74yTL7VIPt7bVALU+JgVQpH0HSIzay3arW8yE1ZCZ6rDtFKKYnGyyx+U0mz3Qato6BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:50:34.476958Z","bundle_sha256":"aad9bea0b6f130ab166acfcba85ed205304d09c11b8935728fc6e52377b14197"}}