{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FPD4LHEXR5KYKNC2UJZCVBWNHT","short_pith_number":"pith:FPD4LHEX","canonical_record":{"source":{"id":"2606.22274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T23:51:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"077ead7b1ca701b110da20dd98aafb4756971804f4f1b91589b9380669163649","abstract_canon_sha256":"8df4439e296015792d5597143fedb6c04c600b16da3f27460e5c11aa770f0a65"},"schema_version":"1.0"},"canonical_sha256":"2bc7c59c978f5585345aa2722a86cd3cf8d51b1d10c6bfb4be8b35e3be2af09d","source":{"kind":"arxiv","id":"2606.22274","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22274","created_at":"2026-06-23T02:13:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22274v1","created_at":"2026-06-23T02:13:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22274","created_at":"2026-06-23T02:13:33Z"},{"alias_kind":"pith_short_12","alias_value":"FPD4LHEXR5KY","created_at":"2026-06-23T02:13:33Z"},{"alias_kind":"pith_short_16","alias_value":"FPD4LHEXR5KYKNC2","created_at":"2026-06-23T02:13:33Z"},{"alias_kind":"pith_short_8","alias_value":"FPD4LHEX","created_at":"2026-06-23T02:13:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FPD4LHEXR5KYKNC2UJZCVBWNHT","target":"record","payload":{"canonical_record":{"source":{"id":"2606.22274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T23:51:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"077ead7b1ca701b110da20dd98aafb4756971804f4f1b91589b9380669163649","abstract_canon_sha256":"8df4439e296015792d5597143fedb6c04c600b16da3f27460e5c11aa770f0a65"},"schema_version":"1.0"},"canonical_sha256":"2bc7c59c978f5585345aa2722a86cd3cf8d51b1d10c6bfb4be8b35e3be2af09d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:33.646393Z","signature_b64":"EvUFvSl2nrA1xWtqTqLAEcuf9aUrwWlAKiiVmi0FVPZfS83ET9CgIp1ZgazeNkg+t4cYwHDv66Vo5kdo3OFABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bc7c59c978f5585345aa2722a86cd3cf8d51b1d10c6bfb4be8b35e3be2af09d","last_reissued_at":"2026-06-23T02:13:33.645986Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:33.645986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.22274","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":"2026-06-23T02:13:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PcoAfnHAnCJAkpjUS7HlOLqILWyT9O5FF8s3WQcb9atR8131HVzuGInzX+JlP140pYZXNnwEoWwYM6z8SyVuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T23:07:30.326577Z"},"content_sha256":"de63f5ddd55628e938036ea46ecae17888c97e49200251b7105680ea79183201","schema_version":"1.0","event_id":"sha256:de63f5ddd55628e938036ea46ecae17888c97e49200251b7105680ea79183201"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FPD4LHEXR5KYKNC2UJZCVBWNHT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Speech to Text Corpora: Evaluating ASR-Based Data Acquisition for Low-Resource Fongbe and Hausa","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mahounan Pericles Adjovi, Prasenjit Mitra, Roald Eiselen, Victor Olufemi","submitted_at":"2026-06-20T23:51:55Z","abstract_excerpt":"Low-resource African languages lack text corpora needed for language model training. We investigate whether ASR pipelines can extend text resources for two typologically distinct West African languages: Fongbe (tonal, diacritic-rich) and Hausa (non-tonal). We fine-tune MMS-300M on a curated 12.3-hour Fongbe dataset, achieving 9.48% WER on the ALFFA benchmark - a 78% relative reduction from the prior 44.04% baseline - while preserving tonal diacritics critical to the language. For Hausa, we apply an existing fine-tuned Whisper-Small model. We catalog 1,553 YouTube videos (236 hours) and process"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22274","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/2606.22274/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":"2026-06-23T02:13:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7yTwFXhijd9ks7zB9qWg4E5O2U6pXcEMWfZITGDBcDejhJyOm6KAm8shmvObC+2aGfQTw52JYy+B4KlTJEADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T23:07:30.326946Z"},"content_sha256":"509e4d4ceba1ddb708838945b1329f4a1f70a43faf15a9090b409da5c9a4647d","schema_version":"1.0","event_id":"sha256:509e4d4ceba1ddb708838945b1329f4a1f70a43faf15a9090b409da5c9a4647d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPD4LHEXR5KYKNC2UJZCVBWNHT/bundle.json","state_url":"https://pith.science/pith/FPD4LHEXR5KYKNC2UJZCVBWNHT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPD4LHEXR5KYKNC2UJZCVBWNHT/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":"2026-06-29T23:07:30Z","links":{"resolver":"https://pith.science/pith/FPD4LHEXR5KYKNC2UJZCVBWNHT","bundle":"https://pith.science/pith/FPD4LHEXR5KYKNC2UJZCVBWNHT/bundle.json","state":"https://pith.science/pith/FPD4LHEXR5KYKNC2UJZCVBWNHT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPD4LHEXR5KYKNC2UJZCVBWNHT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FPD4LHEXR5KYKNC2UJZCVBWNHT","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":"8df4439e296015792d5597143fedb6c04c600b16da3f27460e5c11aa770f0a65","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T23:51:55Z","title_canon_sha256":"077ead7b1ca701b110da20dd98aafb4756971804f4f1b91589b9380669163649"},"schema_version":"1.0","source":{"id":"2606.22274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22274","created_at":"2026-06-23T02:13:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22274v1","created_at":"2026-06-23T02:13:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22274","created_at":"2026-06-23T02:13:33Z"},{"alias_kind":"pith_short_12","alias_value":"FPD4LHEXR5KY","created_at":"2026-06-23T02:13:33Z"},{"alias_kind":"pith_short_16","alias_value":"FPD4LHEXR5KYKNC2","created_at":"2026-06-23T02:13:33Z"},{"alias_kind":"pith_short_8","alias_value":"FPD4LHEX","created_at":"2026-06-23T02:13:33Z"}],"graph_snapshots":[{"event_id":"sha256:509e4d4ceba1ddb708838945b1329f4a1f70a43faf15a9090b409da5c9a4647d","target":"graph","created_at":"2026-06-23T02:13:33Z","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/2606.22274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low-resource African languages lack text corpora needed for language model training. We investigate whether ASR pipelines can extend text resources for two typologically distinct West African languages: Fongbe (tonal, diacritic-rich) and Hausa (non-tonal). We fine-tune MMS-300M on a curated 12.3-hour Fongbe dataset, achieving 9.48% WER on the ALFFA benchmark - a 78% relative reduction from the prior 44.04% baseline - while preserving tonal diacritics critical to the language. For Hausa, we apply an existing fine-tuned Whisper-Small model. We catalog 1,553 YouTube videos (236 hours) and process","authors_text":"Mahounan Pericles Adjovi, Prasenjit Mitra, Roald Eiselen, Victor Olufemi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T23:51:55Z","title":"From Speech to Text Corpora: Evaluating ASR-Based Data Acquisition for Low-Resource Fongbe and Hausa"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22274","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:de63f5ddd55628e938036ea46ecae17888c97e49200251b7105680ea79183201","target":"record","created_at":"2026-06-23T02:13:33Z","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":"8df4439e296015792d5597143fedb6c04c600b16da3f27460e5c11aa770f0a65","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T23:51:55Z","title_canon_sha256":"077ead7b1ca701b110da20dd98aafb4756971804f4f1b91589b9380669163649"},"schema_version":"1.0","source":{"id":"2606.22274","kind":"arxiv","version":1}},"canonical_sha256":"2bc7c59c978f5585345aa2722a86cd3cf8d51b1d10c6bfb4be8b35e3be2af09d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bc7c59c978f5585345aa2722a86cd3cf8d51b1d10c6bfb4be8b35e3be2af09d","first_computed_at":"2026-06-23T02:13:33.645986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:33.645986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EvUFvSl2nrA1xWtqTqLAEcuf9aUrwWlAKiiVmi0FVPZfS83ET9CgIp1ZgazeNkg+t4cYwHDv66Vo5kdo3OFABw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:33.646393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de63f5ddd55628e938036ea46ecae17888c97e49200251b7105680ea79183201","sha256:509e4d4ceba1ddb708838945b1329f4a1f70a43faf15a9090b409da5c9a4647d"],"state_sha256":"256f502dad06c00d86ce6a0802cc7999203fd5cc6c75b38563024b082267695f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7WUHFBGjzXkWe43AyAYbFL3CJzEzioNFd5xAz15ay/w2fpcJrnL7BWcH2Hq2kertJuPciMlQlsmRIEraSNMBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T23:07:30.329039Z","bundle_sha256":"9e6abce27cea563570b527c97d3774cdd128248e12d0d2d47f7e6913d9b5f33d"}}