{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7MW6RI4LMHOZMT7ZIOI5KITJNZ","short_pith_number":"pith:7MW6RI4L","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"},"canonical_sha256":"fb2de8a38b61dd964ff94391d522696e6f4c94c9e9f8dae4c031839dc69d0a4b","source":{"kind":"arxiv","id":"2503.08540","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7MW6RI4LMHOZMT7ZIOI5KITJNZ","target":"record","payload":{"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"},"canonical_sha256":"fb2de8a38b61dd964ff94391d522696e6f4c94c9e9f8dae4c031839dc69d0a4b","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"},"source_kind":"arxiv","source_id":"2503.08540","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cXtztmAAzzzKnL8WmX75cJHmltmJwZCgwrFSfY6NDN2urf6+rhcJcfW8pb2yFsto+MURQJ95niSKMdD6NV69Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:50:53.304863Z"},"content_sha256":"41be9ecfc40d912fa2910717bafe92348ee98181ede7e8fa6480decf014b6349","schema_version":"1.0","event_id":"sha256:41be9ecfc40d912fa2910717bafe92348ee98181ede7e8fa6480decf014b6349"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7MW6RI4LMHOZMT7ZIOI5KITJNZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQv10hMBQ+IPBQ0GlM/2ZMJZV09ROLTm/X+H4Z5kVGcA15+7z7ORlZlRHE+e6Z9pAw6yVvfNpdj85Nb3XMtKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:50:53.305455Z"},"content_sha256":"826008811a9fd5ae47269d173dcba37ac59bcceac26eafd4e8638b3117d4ceb8","schema_version":"1.0","event_id":"sha256:826008811a9fd5ae47269d173dcba37ac59bcceac26eafd4e8638b3117d4ceb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/bundle.json","state_url":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/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":"2026-08-09T02:50:53Z","links":{"resolver":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ","bundle":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/bundle.json","state":"https://pith.science/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MW6RI4LMHOZMT7ZIOI5KITJNZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+mHqMLD5n/T9u9PQqs+FpcCQUAU96MX2bCTFv1789NatZvEJ2Qlb5GEmwrk4BV204VsXFQ/fKmyA4vFiwoXXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:50:53.310085Z","bundle_sha256":"1de2f3ba852ae271b7126fb0b8e29e23f4ed1029146a22568f3513b9774eaf4b"}}