{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7MW6RI4LMHOZMT7ZIOI5KITJNZ","short_pith_number":"pith:7MW6RI4L","schema_version":"1.0","canonical_sha256":"fb2de8a38b61dd964ff94391d522696e6f4c94c9e9f8dae4c031839dc69d0a4b","source":{"kind":"arxiv","id":"2503.08540","version":1},"attestation_state":"computed","paper":{"title":"Mellow: a small audio language model for reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bhiksha Raj, Rita Singh, Satvik Dixit, Soham Deshmukh","submitted_at":"2025-03-11T15:29:00Z","abstract_excerpt":"Multimodal Audio-Language Models (ALMs) can understand and reason over both audio and text. Typically, reasoning performance correlates with model size, with the best results achieved by models exceeding 8 billion parameters. However, no prior work has explored enabling small audio-language models to perform reasoning tasks, despite the potential applications for edge devices. To address this gap, we introduce Mellow, a small Audio-Language Model specifically designed for reasoning. Mellow achieves state-of-the-art performance among existing small audio-language models and surpasses several la"},"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":"2503.08540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-11T15:29:00Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"0e952c1dede5ac7cfac20c9d3e1ee2eaf63b4eb972bbe57947fbcec991e6f16d","abstract_canon_sha256":"3b6824199d51a258805459a4ddedd609106405b31206eb60ab2535ea5a10578b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:01.812140Z","signature_b64":"o4VLvt8aqo3av52Jlof0+8rmcspEUk8g0XtgP8iNTNZLYErMIYepjmjPZSmp/v76qouOoNnobm9gf0jBn5IICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb2de8a38b61dd964ff94391d522696e6f4c94c9e9f8dae4c031839dc69d0a4b","last_reissued_at":"2026-07-05T10:29:01.811285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:01.811285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mellow: a small audio language model for reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bhiksha Raj, Rita Singh, Satvik Dixit, Soham Deshmukh","submitted_at":"2025-03-11T15:29:00Z","abstract_excerpt":"Multimodal Audio-Language Models (ALMs) can understand and reason over both audio and text. Typically, reasoning performance correlates with model size, with the best results achieved by models exceeding 8 billion parameters. However, no prior work has explored enabling small audio-language models to perform reasoning tasks, despite the potential applications for edge devices. To address this gap, we introduce Mellow, a small Audio-Language Model specifically designed for reasoning. Mellow achieves state-of-the-art performance among existing small audio-language models and surpasses several la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08540","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/2503.08540/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":"2503.08540","created_at":"2026-07-05T10:29:01.811425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08540v1","created_at":"2026-07-05T10:29:01.811425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08540","created_at":"2026-07-05T10:29:01.811425+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MW6RI4LMHOZ","created_at":"2026-07-05T10:29:01.811425+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MW6RI4LMHOZMT7Z","created_at":"2026-07-05T10:29:01.811425+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MW6RI4L","created_at":"2026-07-05T10:29:01.811425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":144,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12527","citing_title":"Audio-Cogito: Towards Deep Audio Reasoning in Large Audio Language Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15849","citing_title":"TinyMU: A Compact Audio-Language Model for Music Understanding","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ","json":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ.json","graph_json":"https://pith.science/api/pith-number/7MW6RI4LMHOZMT7ZIOI5KITJNZ/graph.json","events_json":"https://pith.science/api/pith-number/7MW6RI4LMHOZMT7ZIOI5KITJNZ/events.json","paper":"https://pith.science/paper/7MW6RI4L"},"agent_actions":{"view_html":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ","download_json":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ.json","view_paper":"https://pith.science/paper/7MW6RI4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08540&json=true","fetch_graph":"https://pith.science/api/pith-number/7MW6RI4LMHOZMT7ZIOI5KITJNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7MW6RI4LMHOZMT7ZIOI5KITJNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/action/storage_attestation","attest_author":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/action/author_attestation","sign_citation":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/action/citation_signature","submit_replication":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/action/replication_record"}},"created_at":"2026-07-05T10:29:01.811425+00:00","updated_at":"2026-07-05T10:29:01.811425+00:00"}