{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7IUYO5LZBNKFJ2W34E66WT3TKS","short_pith_number":"pith:7IUYO5LZ","schema_version":"1.0","canonical_sha256":"fa298775790b5454eadbe13deb4f735490aa0bea79e9e512e51852e4e6267a95","source":{"kind":"arxiv","id":"2409.10999","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Guangzhi Sun, Kasima Tharnpipitchai, Kunat Pipatanakul, Potsawee Manakul, Warit Sirichotedumrong","submitted_at":"2024-09-17T09:04:03Z","abstract_excerpt":"Audio language models process audio inputs using textual prompts for tasks like speech recognition and audio captioning. Although built on multilingual pre-trained components, most are trained primarily on English, limiting their usability for other languages. This paper evaluates audio language models on Thai, a low-resource language, and finds that they lack emergent cross-lingual abilities despite their multilingual foundations. To address this, we explore data mixtures that optimize audio language models for both a target language and English while integrating audio comprehension and speec"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.10999","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T09:04:03Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"0b4850db475d6d8069ec099a870dc45baf3480c8e7f0cc268088a5b84a1e54d1","abstract_canon_sha256":"a811f35947853b090341b260afac587da7ce895bef384c4e5c791143dbc4a315"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:00.692774Z","signature_b64":"Q0Kv64jQGON8cfyPj2VLzEv8SjbyZ7wARWE92X3MTxohznIfsK2Gain/aqsiA4rKxO1nrMA/nMm4yCG1rSSKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa298775790b5454eadbe13deb4f735490aa0bea79e9e512e51852e4e6267a95","last_reissued_at":"2026-07-05T11:08:00.692219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:00.692219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Guangzhi Sun, Kasima Tharnpipitchai, Kunat Pipatanakul, Potsawee Manakul, Warit Sirichotedumrong","submitted_at":"2024-09-17T09:04:03Z","abstract_excerpt":"Audio language models process audio inputs using textual prompts for tasks like speech recognition and audio captioning. Although built on multilingual pre-trained components, most are trained primarily on English, limiting their usability for other languages. This paper evaluates audio language models on Thai, a low-resource language, and finds that they lack emergent cross-lingual abilities despite their multilingual foundations. To address this, we explore data mixtures that optimize audio language models for both a target language and English while integrating audio comprehension and speec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10999","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/2409.10999/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.10999","created_at":"2026-07-05T11:08:00.692287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10999v2","created_at":"2026-07-05T11:08:00.692287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10999","created_at":"2026-07-05T11:08:00.692287+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IUYO5LZBNKF","created_at":"2026-07-05T11:08:00.692287+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IUYO5LZBNKFJ2W3","created_at":"2026-07-05T11:08:00.692287+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IUYO5LZ","created_at":"2026-07-05T11:08:00.692287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15418","citing_title":"LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IUYO5LZBNKFJ2W34E66WT3TKS","json":"https://pith.science/pith/7IUYO5LZBNKFJ2W34E66WT3TKS.json","graph_json":"https://pith.science/api/pith-number/7IUYO5LZBNKFJ2W34E66WT3TKS/graph.json","events_json":"https://pith.science/api/pith-number/7IUYO5LZBNKFJ2W34E66WT3TKS/events.json","paper":"https://pith.science/paper/7IUYO5LZ"},"agent_actions":{"view_html":"https://pith.science/pith/7IUYO5LZBNKFJ2W34E66WT3TKS","download_json":"https://pith.science/pith/7IUYO5LZBNKFJ2W34E66WT3TKS.json","view_paper":"https://pith.science/paper/7IUYO5LZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10999&json=true","fetch_graph":"https://pith.science/api/pith-number/7IUYO5LZBNKFJ2W34E66WT3TKS/graph.json","fetch_events":"https://pith.science/api/pith-number/7IUYO5LZBNKFJ2W34E66WT3TKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IUYO5LZBNKFJ2W34E66WT3TKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IUYO5LZBNKFJ2W34E66WT3TKS/action/storage_attestation","attest_author":"https://pith.science/pith/7IUYO5LZBNKFJ2W34E66WT3TKS/action/author_attestation","sign_citation":"https://pith.science/pith/7IUYO5LZBNKFJ2W34E66WT3TKS/action/citation_signature","submit_replication":"https://pith.science/pith/7IUYO5LZBNKFJ2W34E66WT3TKS/action/replication_record"}},"created_at":"2026-07-05T11:08:00.692287+00:00","updated_at":"2026-07-05T11:08:00.692287+00:00"}