{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UDZ6Y2KSD3FFTG2DLWC4PNKP4C","short_pith_number":"pith:UDZ6Y2KS","schema_version":"1.0","canonical_sha256":"a0f3ec69521eca599b435d85c7b54fe0b9d71294b55143d6c3a066254f87d689","source":{"kind":"arxiv","id":"2505.13032","version":1},"attestation_state":"computed","paper":{"title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Yang, Emmanouil Benetos, Eng-Siong Chng, Guanrou Yang, Haina Zhu, Jian Cong, Jianwei Yu, Kai Li, Kai Yu, Keliang Li, Minghao Liu, Ruibin Yuan, Ruiyang Xu, Siyou Li, Tianrui Wang, Wei Xue, Wenxi Chen, Xie Chen, Xinfeng Li, Xiquan Li, Yanqiao Zhu, Yihao Wu, Yinghao Ma, Yi-Wen Chao, Yuanzhe Chen, Yuping Wang, Yuxuan Wang, Yuzhe Liang, Zheng Lian, Zhikang Niu, Zhisheng Zheng, Zhuo Chen, Ziyang Ma, Ziya Zhou","submitted_at":"2025-05-19T12:18:42Z","abstract_excerpt":"We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through iterative error corrections and quality checks to ensure high quality. Unlike existing benchmarks that are limited to specific domains of sound, music, or speech, MMAR extends them to a broad spectrum of real-world audio scenarios, including mixed-modality combinations of sound, music, and speech. Each"},"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":"2505.13032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-19T12:18:42Z","cross_cats_sorted":["cs.CL","cs.MM","eess.AS"],"title_canon_sha256":"aadbdcd02e5b532afcd28382d8fa3083f14247cfae96274e94c81391c803e56d","abstract_canon_sha256":"0e0c5472b5c6c5a1cfb629f8f12ab895c30b1f5744b0de33145ba70672a5c30e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:14.080196Z","signature_b64":"QPdo+iAc4MWcYr/9hLnbfG9C1muDt+UZjeWsrE8giuJAum7w/CiFN3rSPIjJXBrPunC7e7yk38lqZ6X9o4BYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f3ec69521eca599b435d85c7b54fe0b9d71294b55143d6c3a066254f87d689","last_reissued_at":"2026-07-05T11:05:14.079713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:14.079713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Yang, Emmanouil Benetos, Eng-Siong Chng, Guanrou Yang, Haina Zhu, Jian Cong, Jianwei Yu, Kai Li, Kai Yu, Keliang Li, Minghao Liu, Ruibin Yuan, Ruiyang Xu, Siyou Li, Tianrui Wang, Wei Xue, Wenxi Chen, Xie Chen, Xinfeng Li, Xiquan Li, Yanqiao Zhu, Yihao Wu, Yinghao Ma, Yi-Wen Chao, Yuanzhe Chen, Yuping Wang, Yuxuan Wang, Yuzhe Liang, Zheng Lian, Zhikang Niu, Zhisheng Zheng, Zhuo Chen, Ziyang Ma, Ziya Zhou","submitted_at":"2025-05-19T12:18:42Z","abstract_excerpt":"We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through iterative error corrections and quality checks to ensure high quality. Unlike existing benchmarks that are limited to specific domains of sound, music, or speech, MMAR extends them to a broad spectrum of real-world audio scenarios, including mixed-modality combinations of sound, music, and speech. Each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13032","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/2505.13032/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":"2505.13032","created_at":"2026-07-05T11:05:14.079774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13032v1","created_at":"2026-07-05T11:05:14.079774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13032","created_at":"2026-07-05T11:05:14.079774+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDZ6Y2KSD3FF","created_at":"2026-07-05T11:05:14.079774+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDZ6Y2KSD3FFTG2D","created_at":"2026-07-05T11:05:14.079774+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDZ6Y2KS","created_at":"2026-07-05T11:05:14.079774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25391","citing_title":"From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17417","citing_title":"A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11260","citing_title":"RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08425","citing_title":"TinyGiantALM: A Compact Audio-Language Model for Intent-Aware Reasoning under Resource Constraints","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07264","citing_title":"VISA: A Visual Information Strengthened Audio-Reasoning System for the Interspeech 2026 ARC Agent Track","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18273","citing_title":"Continuous Audio Thinking for Large Audio Language Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01802","citing_title":"MOSS-Audio Technical Report","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30899","citing_title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23954","citing_title":"EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27741","citing_title":"Escape the Language Prior: Mitigating Late-Stage Modality Collapse in Audio Reasoning via Modality-Aware Policy Optimization","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28480","citing_title":"Audio-Mind: An Auditable Agentic Framework for Audio Understanding","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01016","citing_title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":184,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21008","citing_title":"A Survey of Audio Reasoning in Multimodal Foundation Models","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23511","citing_title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00626","citing_title":"When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02731","citing_title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12248","citing_title":"AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07064","citing_title":"OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14607","citing_title":"ViMU: Benchmarking Video Metaphorical Understanding","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12036","citing_title":"Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25591","citing_title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06631","citing_title":"Task-Aware Answer Preservation under Audio Compression for Large Audio Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08209","citing_title":"OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12527","citing_title":"Audio-Cogito: Towards Deep Audio Reasoning in Large Audio Language Models","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDZ6Y2KSD3FFTG2DLWC4PNKP4C","json":"https://pith.science/pith/UDZ6Y2KSD3FFTG2DLWC4PNKP4C.json","graph_json":"https://pith.science/api/pith-number/UDZ6Y2KSD3FFTG2DLWC4PNKP4C/graph.json","events_json":"https://pith.science/api/pith-number/UDZ6Y2KSD3FFTG2DLWC4PNKP4C/events.json","paper":"https://pith.science/paper/UDZ6Y2KS"},"agent_actions":{"view_html":"https://pith.science/pith/UDZ6Y2KSD3FFTG2DLWC4PNKP4C","download_json":"https://pith.science/pith/UDZ6Y2KSD3FFTG2DLWC4PNKP4C.json","view_paper":"https://pith.science/paper/UDZ6Y2KS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13032&json=true","fetch_graph":"https://pith.science/api/pith-number/UDZ6Y2KSD3FFTG2DLWC4PNKP4C/graph.json","fetch_events":"https://pith.science/api/pith-number/UDZ6Y2KSD3FFTG2DLWC4PNKP4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDZ6Y2KSD3FFTG2DLWC4PNKP4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDZ6Y2KSD3FFTG2DLWC4PNKP4C/action/storage_attestation","attest_author":"https://pith.science/pith/UDZ6Y2KSD3FFTG2DLWC4PNKP4C/action/author_attestation","sign_citation":"https://pith.science/pith/UDZ6Y2KSD3FFTG2DLWC4PNKP4C/action/citation_signature","submit_replication":"https://pith.science/pith/UDZ6Y2KSD3FFTG2DLWC4PNKP4C/action/replication_record"}},"created_at":"2026-07-05T11:05:14.079774+00:00","updated_at":"2026-07-05T11:05:14.079774+00:00"}