{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7MW6RI4LMHOZMT7ZIOI5KITJNZ","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":"3b6824199d51a258805459a4ddedd609106405b31206eb60ab2535ea5a10578b","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-11T15:29:00Z","title_canon_sha256":"0e952c1dede5ac7cfac20c9d3e1ee2eaf63b4eb972bbe57947fbcec991e6f16d"},"schema_version":"1.0","source":{"id":"2503.08540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08540","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08540v1","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08540","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"7MW6RI4LMHOZ","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"7MW6RI4LMHOZMT7Z","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"7MW6RI4L","created_at":"2026-07-05T10:29:01Z"}],"graph_snapshots":[{"event_id":"sha256:826008811a9fd5ae47269d173dcba37ac59bcceac26eafd4e8638b3117d4ceb8","target":"graph","created_at":"2026-07-05T10:29:01Z","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/2503.08540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bhiksha Raj, Rita Singh, Satvik Dixit, Soham Deshmukh","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-11T15:29:00Z","title":"Mellow: a small audio language model for reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08540","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":"sha256:41be9ecfc40d912fa2910717bafe92348ee98181ede7e8fa6480decf014b6349","target":"record","created_at":"2026-07-05T10:29:01Z","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":"3b6824199d51a258805459a4ddedd609106405b31206eb60ab2535ea5a10578b","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-11T15:29:00Z","title_canon_sha256":"0e952c1dede5ac7cfac20c9d3e1ee2eaf63b4eb972bbe57947fbcec991e6f16d"},"schema_version":"1.0","source":{"id":"2503.08540","kind":"arxiv","version":1}},"canonical_sha256":"fb2de8a38b61dd964ff94391d522696e6f4c94c9e9f8dae4c031839dc69d0a4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb2de8a38b61dd964ff94391d522696e6f4c94c9e9f8dae4c031839dc69d0a4b","first_computed_at":"2026-07-05T10:29:01.811285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:01.811285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o4VLvt8aqo3av52Jlof0+8rmcspEUk8g0XtgP8iNTNZLYErMIYepjmjPZSmp/v76qouOoNnobm9gf0jBn5IICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:01.812140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41be9ecfc40d912fa2910717bafe92348ee98181ede7e8fa6480decf014b6349","sha256:826008811a9fd5ae47269d173dcba37ac59bcceac26eafd4e8638b3117d4ceb8"],"state_sha256":"21515e950343f9cf88a55247b0830d440ee6f8440a4f7193b2119ed212edef16"}