{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LYVW4HWQOBWWG6CCKHB5637AZY","short_pith_number":"pith:LYVW4HWQ","canonical_record":{"source":{"id":"2412.15726","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T09:49:02Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"aad6a29439fd09e0996cfdf40bda4ae58b1d29d1b2917d73218846b62b8fa261","abstract_canon_sha256":"b76704af65263f969013facf75fd8b03ff8868da58a5eae9cce0c43bc37a9435"},"schema_version":"1.0"},"canonical_sha256":"5e2b6e1ed0706d63784251c3df6fe0ce0bc058b10ac25b333f095048d3a17af5","source":{"kind":"arxiv","id":"2412.15726","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15726","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15726v3","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15726","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"LYVW4HWQOBWW","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"LYVW4HWQOBWWG6CC","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"LYVW4HWQ","created_at":"2026-07-05T10:52:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LYVW4HWQOBWWG6CCKHB5637AZY","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15726","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T09:49:02Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"aad6a29439fd09e0996cfdf40bda4ae58b1d29d1b2917d73218846b62b8fa261","abstract_canon_sha256":"b76704af65263f969013facf75fd8b03ff8868da58a5eae9cce0c43bc37a9435"},"schema_version":"1.0"},"canonical_sha256":"5e2b6e1ed0706d63784251c3df6fe0ce0bc058b10ac25b333f095048d3a17af5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:17.363075Z","signature_b64":"wkwa5QbZCrlUVm4NbWcQNRpozWF4feUyPHHVcAEETanhaDroC7a7yXk1tx2PeYLI8PZ8f5BoaLgVs85YD3qbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e2b6e1ed0706d63784251c3df6fe0ce0bc058b10ac25b333f095048d3a17af5","last_reissued_at":"2026-07-05T10:52:17.362567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:17.362567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15726","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pp0WATUR8MOvA0GpGWYycBOBds9dKZKTV0nouy2JQOM+xG5t9Vcdttafm77OOlaPXFQIozg+3Fk6O9lJhTASAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:28:46.932213Z"},"content_sha256":"81ca83b4a1d1d7cde7b17263e604795851001a3e1cf70cea377d5b92797fa619","schema_version":"1.0","event_id":"sha256:81ca83b4a1d1d7cde7b17263e604795851001a3e1cf70cea377d5b92797fa619"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LYVW4HWQOBWWG6CCKHB5637AZY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-tuning Whisper on Low-Resource Languages for Real-World Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Claudio Paonessa, Daniel Perruchoud, Manfred Vogel, Reza kakooee, Vincenzo Timmel","submitted_at":"2024-12-20T09:49:02Z","abstract_excerpt":"This paper presents a new approach to fine-tuning OpenAI's Whisper model for low-resource languages by introducing a novel data generation method that converts sentence-level data into a long-form corpus, using Swiss German as a case study. Non-sentence-level data, which could improve the performance of long-form audio, is difficult to obtain and often restricted by copyright laws. Our method bridges this gap by transforming more accessible sentence-level data into a format that preserves the model's ability to handle long-form audio and perform segmentation without requiring non-sentence-leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15726","kind":"arxiv","version":3},"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/2412.15726/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":"2026-07-05T10:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Idmu5T3ZKb9J1iHkaKrZP0kMrg1wLaEI23Nwcvmhj0hK7+omYr2EbViCfZhSXZOg2G7NFVS0gAJolE6MLliCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:28:46.933085Z"},"content_sha256":"36abc8a48242c9136b68356a13b64ff712a7857dba938e76dfb4fae3a294a507","schema_version":"1.0","event_id":"sha256:36abc8a48242c9136b68356a13b64ff712a7857dba938e76dfb4fae3a294a507"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYVW4HWQOBWWG6CCKHB5637AZY/bundle.json","state_url":"https://pith.science/pith/LYVW4HWQOBWWG6CCKHB5637AZY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYVW4HWQOBWWG6CCKHB5637AZY/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":"2026-08-17T05:28:46Z","links":{"resolver":"https://pith.science/pith/LYVW4HWQOBWWG6CCKHB5637AZY","bundle":"https://pith.science/pith/LYVW4HWQOBWWG6CCKHB5637AZY/bundle.json","state":"https://pith.science/pith/LYVW4HWQOBWWG6CCKHB5637AZY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYVW4HWQOBWWG6CCKHB5637AZY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LYVW4HWQOBWWG6CCKHB5637AZY","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":"b76704af65263f969013facf75fd8b03ff8868da58a5eae9cce0c43bc37a9435","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T09:49:02Z","title_canon_sha256":"aad6a29439fd09e0996cfdf40bda4ae58b1d29d1b2917d73218846b62b8fa261"},"schema_version":"1.0","source":{"id":"2412.15726","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15726","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15726v3","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15726","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"LYVW4HWQOBWW","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"LYVW4HWQOBWWG6CC","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"LYVW4HWQ","created_at":"2026-07-05T10:52:17Z"}],"graph_snapshots":[{"event_id":"sha256:36abc8a48242c9136b68356a13b64ff712a7857dba938e76dfb4fae3a294a507","target":"graph","created_at":"2026-07-05T10:52:17Z","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/2412.15726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a new approach to fine-tuning OpenAI's Whisper model for low-resource languages by introducing a novel data generation method that converts sentence-level data into a long-form corpus, using Swiss German as a case study. Non-sentence-level data, which could improve the performance of long-form audio, is difficult to obtain and often restricted by copyright laws. Our method bridges this gap by transforming more accessible sentence-level data into a format that preserves the model's ability to handle long-form audio and perform segmentation without requiring non-sentence-leve","authors_text":"Claudio Paonessa, Daniel Perruchoud, Manfred Vogel, Reza kakooee, Vincenzo Timmel","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T09:49:02Z","title":"Fine-tuning Whisper on Low-Resource Languages for Real-World Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15726","kind":"arxiv","version":3},"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":"sha256:81ca83b4a1d1d7cde7b17263e604795851001a3e1cf70cea377d5b92797fa619","target":"record","created_at":"2026-07-05T10:52:17Z","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":"b76704af65263f969013facf75fd8b03ff8868da58a5eae9cce0c43bc37a9435","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T09:49:02Z","title_canon_sha256":"aad6a29439fd09e0996cfdf40bda4ae58b1d29d1b2917d73218846b62b8fa261"},"schema_version":"1.0","source":{"id":"2412.15726","kind":"arxiv","version":3}},"canonical_sha256":"5e2b6e1ed0706d63784251c3df6fe0ce0bc058b10ac25b333f095048d3a17af5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e2b6e1ed0706d63784251c3df6fe0ce0bc058b10ac25b333f095048d3a17af5","first_computed_at":"2026-07-05T10:52:17.362567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:17.362567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wkwa5QbZCrlUVm4NbWcQNRpozWF4feUyPHHVcAEETanhaDroC7a7yXk1tx2PeYLI8PZ8f5BoaLgVs85YD3qbBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:17.363075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15726","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81ca83b4a1d1d7cde7b17263e604795851001a3e1cf70cea377d5b92797fa619","sha256:36abc8a48242c9136b68356a13b64ff712a7857dba938e76dfb4fae3a294a507"],"state_sha256":"a4414cd6034de26e7154383743f297d9dab7f017fc4250e9733dcaaff864db58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vI7eeWi3tUMQOTrph+Gl6QdyL2Bdu/0xOGi+AschciYiISkltk75RY8Ols63IrQWhQqusElJbBIG4kkdDCX2Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T05:28:46.947692Z","bundle_sha256":"fdecd1c249fba21d2d6f24aec2bb30d573901323124c66b8c665a8ac00d41189"}}