{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5OPCBCOHUWBUNE6APAWYGKVW6L","short_pith_number":"pith:5OPCBCOH","canonical_record":{"source":{"id":"2503.18485","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T09:39:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f33076188cedf0be97e409cc9b65cd0bd27800dbc7c3173c3cad15a9073aac48","abstract_canon_sha256":"58d863c065b42eeb18d2de1761766094a2a87eaec78cc5b168984f8cedeafff1"},"schema_version":"1.0"},"canonical_sha256":"eb9e2089c7a5834693c0782d832ab6f2f400490df43c5ec46f538c9f533981c9","source":{"kind":"arxiv","id":"2503.18485","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18485","created_at":"2026-07-05T10:41:01Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18485v2","created_at":"2026-07-05T10:41:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18485","created_at":"2026-07-05T10:41:01Z"},{"alias_kind":"pith_short_12","alias_value":"5OPCBCOHUWBU","created_at":"2026-07-05T10:41:01Z"},{"alias_kind":"pith_short_16","alias_value":"5OPCBCOHUWBUNE6A","created_at":"2026-07-05T10:41:01Z"},{"alias_kind":"pith_short_8","alias_value":"5OPCBCOH","created_at":"2026-07-05T10:41:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5OPCBCOHUWBUNE6APAWYGKVW6L","target":"record","payload":{"canonical_record":{"source":{"id":"2503.18485","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T09:39:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f33076188cedf0be97e409cc9b65cd0bd27800dbc7c3173c3cad15a9073aac48","abstract_canon_sha256":"58d863c065b42eeb18d2de1761766094a2a87eaec78cc5b168984f8cedeafff1"},"schema_version":"1.0"},"canonical_sha256":"eb9e2089c7a5834693c0782d832ab6f2f400490df43c5ec46f538c9f533981c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:01.046256Z","signature_b64":"g+YHHO/jLnvPou1yxs6FpZrl+VyS+LLOUGvmqArAeUOw7d9RB2w9VklyOjCDe+Whi+KmmQqsgoktbmCmei56AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb9e2089c7a5834693c0782d832ab6f2f400490df43c5ec46f538c9f533981c9","last_reissued_at":"2026-07-05T10:41:01.045710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:01.045710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.18485","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":"2026-07-05T10:41:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eHfEOxzQAx99CY2TNgA52Kz+WoDcdJ0TYMOFvEkrHJqYJZxKmxNCCDCV43j0WU9HWaV4cQabnE4x0hjoWm+DBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:28:10.490738Z"},"content_sha256":"578413dee7dd975d5cc933cf9a3c6a33f31d0cecee9741a2cff4ee1f2f6a4ee7","schema_version":"1.0","event_id":"sha256:578413dee7dd975d5cc933cf9a3c6a33f31d0cecee9741a2cff4ee1f2f6a4ee7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5OPCBCOHUWBUNE6APAWYGKVW6L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Whispering in Amharic: Fine-tuning Whisper for Low-resource Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alemu Belay Tessema, Bedru Yimam Ahmed, Dawit Ketema Gete, Henning Schreiber, Martin Semmann, Mohammed Oumer Adem, Robert Geislinger, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad, Sukairaj Hafiz Imam, Tadesse Amare Belay, Tadesse Destaw Belay, Umma Aliyu Musa, Yohannes Ayana Ejigu","submitted_at":"2025-03-24T09:39:41Z","abstract_excerpt":"This work explores fine-tuning OpenAI's Whisper automatic speech recognition (ASR) model for Amharic, a low-resource language, to improve transcription accuracy. While the foundational Whisper model struggles with Amharic due to limited representation in its training data, we fine-tune it using datasets like Mozilla Common Voice, FLEURS, and the BDU-speech dataset. The best-performing model, Whispersmall-am, significantly improves when finetuned on a mix of existing FLEURS data and new, unseen Amharic datasets. Training solely on new data leads to poor performance, but combining it with FLEURS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18485","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/2503.18485/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":"2026-07-05T10:41:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D6WSg4bN5ALgY+WM55HwLQhy0T0Ph2vrUNzUZtCfZgJRDoLQZvnW/Ves5mTXqisqg+7OBLXxskmvfzuNxxPBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:28:10.491252Z"},"content_sha256":"21c378ed0e605750f944ffd2c99a4ac27bf38c596845ba7e2d78fc43d07688ef","schema_version":"1.0","event_id":"sha256:21c378ed0e605750f944ffd2c99a4ac27bf38c596845ba7e2d78fc43d07688ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5OPCBCOHUWBUNE6APAWYGKVW6L/bundle.json","state_url":"https://pith.science/pith/5OPCBCOHUWBUNE6APAWYGKVW6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5OPCBCOHUWBUNE6APAWYGKVW6L/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":"2026-08-07T18:28:10Z","links":{"resolver":"https://pith.science/pith/5OPCBCOHUWBUNE6APAWYGKVW6L","bundle":"https://pith.science/pith/5OPCBCOHUWBUNE6APAWYGKVW6L/bundle.json","state":"https://pith.science/pith/5OPCBCOHUWBUNE6APAWYGKVW6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5OPCBCOHUWBUNE6APAWYGKVW6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5OPCBCOHUWBUNE6APAWYGKVW6L","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":"58d863c065b42eeb18d2de1761766094a2a87eaec78cc5b168984f8cedeafff1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T09:39:41Z","title_canon_sha256":"f33076188cedf0be97e409cc9b65cd0bd27800dbc7c3173c3cad15a9073aac48"},"schema_version":"1.0","source":{"id":"2503.18485","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18485","created_at":"2026-07-05T10:41:01Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18485v2","created_at":"2026-07-05T10:41:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18485","created_at":"2026-07-05T10:41:01Z"},{"alias_kind":"pith_short_12","alias_value":"5OPCBCOHUWBU","created_at":"2026-07-05T10:41:01Z"},{"alias_kind":"pith_short_16","alias_value":"5OPCBCOHUWBUNE6A","created_at":"2026-07-05T10:41:01Z"},{"alias_kind":"pith_short_8","alias_value":"5OPCBCOH","created_at":"2026-07-05T10:41:01Z"}],"graph_snapshots":[{"event_id":"sha256:21c378ed0e605750f944ffd2c99a4ac27bf38c596845ba7e2d78fc43d07688ef","target":"graph","created_at":"2026-07-05T10:41:01Z","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/2503.18485/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work explores fine-tuning OpenAI's Whisper automatic speech recognition (ASR) model for Amharic, a low-resource language, to improve transcription accuracy. While the foundational Whisper model struggles with Amharic due to limited representation in its training data, we fine-tune it using datasets like Mozilla Common Voice, FLEURS, and the BDU-speech dataset. The best-performing model, Whispersmall-am, significantly improves when finetuned on a mix of existing FLEURS data and new, unseen Amharic datasets. Training solely on new data leads to poor performance, but combining it with FLEURS","authors_text":"Alemu Belay Tessema, Bedru Yimam Ahmed, Dawit Ketema Gete, Henning Schreiber, Martin Semmann, Mohammed Oumer Adem, Robert Geislinger, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad, Sukairaj Hafiz Imam, Tadesse Amare Belay, Tadesse Destaw Belay, Umma Aliyu Musa, Yohannes Ayana Ejigu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T09:39:41Z","title":"Whispering in Amharic: Fine-tuning Whisper for Low-resource Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18485","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":"sha256:578413dee7dd975d5cc933cf9a3c6a33f31d0cecee9741a2cff4ee1f2f6a4ee7","target":"record","created_at":"2026-07-05T10:41:01Z","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":"58d863c065b42eeb18d2de1761766094a2a87eaec78cc5b168984f8cedeafff1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T09:39:41Z","title_canon_sha256":"f33076188cedf0be97e409cc9b65cd0bd27800dbc7c3173c3cad15a9073aac48"},"schema_version":"1.0","source":{"id":"2503.18485","kind":"arxiv","version":2}},"canonical_sha256":"eb9e2089c7a5834693c0782d832ab6f2f400490df43c5ec46f538c9f533981c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb9e2089c7a5834693c0782d832ab6f2f400490df43c5ec46f538c9f533981c9","first_computed_at":"2026-07-05T10:41:01.045710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:01.045710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g+YHHO/jLnvPou1yxs6FpZrl+VyS+LLOUGvmqArAeUOw7d9RB2w9VklyOjCDe+Whi+KmmQqsgoktbmCmei56AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:01.046256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.18485","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:578413dee7dd975d5cc933cf9a3c6a33f31d0cecee9741a2cff4ee1f2f6a4ee7","sha256:21c378ed0e605750f944ffd2c99a4ac27bf38c596845ba7e2d78fc43d07688ef"],"state_sha256":"6a1d4d80f777d0ca6b33b052a21e79f23cab2a44d9d503a9d0ec9aae2db0f4ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"88PoIB6LPf4kGnUFqwVLzoKboPUUsqxfIBt/wmfN0x+pj/VsiPJxLQtgJRW9/Lci7f8y3eJzVW4WcBL/HZHECw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:28:10.500535Z","bundle_sha256":"cedafa5ecb6284405fbda8043af617bd47b9360cc8398c7b384b43720f988c0b"}}