{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K2EN4VXTQGYUCBRKWSW4IHJTX6","short_pith_number":"pith:K2EN4VXT","schema_version":"1.0","canonical_sha256":"5688de56f381b141062ab4adc41d33bf8cb244e788355b56903b7fb0ba152fe5","source":{"kind":"arxiv","id":"2508.02018","version":1},"attestation_state":"computed","paper":{"title":"SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ling Chen, Meng Fang, Wanqi Yang, Yanda Li, Yunchao Wei","submitted_at":"2025-08-04T03:28:04Z","abstract_excerpt":"Large audio-language models (LALMs) have achieved near-human performance in sentence-level transcription and emotion recognition. However, existing evaluations focus mainly on surface-level perception, leaving the capacity of models for contextual and inference-driven reasoning in speech-based scenarios insufficiently examined. To address this gap, we introduce SpeechR, a unified benchmark for evaluating reasoning over speech in large audio-language models. SpeechR evaluates models along three key dimensions: factual retrieval, procedural inference, and normative judgment. It includes three di"},"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":"2508.02018","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-04T03:28:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"38ce29c85cca6cf72c6bd1af5e336ef5db54cdafef059875fa193dcc61ac677b","abstract_canon_sha256":"b83b2b12b8ce399381e6b2bc17503525b6244c070f98334a89783324c26eb20c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:49.637698Z","signature_b64":"meUugNz6gYfQlstr1YrkojPBCiJA8Z6nI4eJbo50n/VuuTJGOytyUSxEa4+g9VKZFgojhV5akbjMh87Ct8VhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5688de56f381b141062ab4adc41d33bf8cb244e788355b56903b7fb0ba152fe5","last_reissued_at":"2026-07-05T11:47:49.637111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:49.637111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ling Chen, Meng Fang, Wanqi Yang, Yanda Li, Yunchao Wei","submitted_at":"2025-08-04T03:28:04Z","abstract_excerpt":"Large audio-language models (LALMs) have achieved near-human performance in sentence-level transcription and emotion recognition. However, existing evaluations focus mainly on surface-level perception, leaving the capacity of models for contextual and inference-driven reasoning in speech-based scenarios insufficiently examined. To address this gap, we introduce SpeechR, a unified benchmark for evaluating reasoning over speech in large audio-language models. SpeechR evaluates models along three key dimensions: factual retrieval, procedural inference, and normative judgment. It includes three di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02018","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/2508.02018/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":"2508.02018","created_at":"2026-07-05T11:47:49.637177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02018v1","created_at":"2026-07-05T11:47:49.637177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02018","created_at":"2026-07-05T11:47:49.637177+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2EN4VXTQGYU","created_at":"2026-07-05T11:47:49.637177+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2EN4VXTQGYUCBRK","created_at":"2026-07-05T11:47:49.637177+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2EN4VXT","created_at":"2026-07-05T11:47:49.637177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11260","citing_title":"RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08194","citing_title":"GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30899","citing_title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24401","citing_title":"All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06897","citing_title":"MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2EN4VXTQGYUCBRKWSW4IHJTX6","json":"https://pith.science/pith/K2EN4VXTQGYUCBRKWSW4IHJTX6.json","graph_json":"https://pith.science/api/pith-number/K2EN4VXTQGYUCBRKWSW4IHJTX6/graph.json","events_json":"https://pith.science/api/pith-number/K2EN4VXTQGYUCBRKWSW4IHJTX6/events.json","paper":"https://pith.science/paper/K2EN4VXT"},"agent_actions":{"view_html":"https://pith.science/pith/K2EN4VXTQGYUCBRKWSW4IHJTX6","download_json":"https://pith.science/pith/K2EN4VXTQGYUCBRKWSW4IHJTX6.json","view_paper":"https://pith.science/paper/K2EN4VXT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02018&json=true","fetch_graph":"https://pith.science/api/pith-number/K2EN4VXTQGYUCBRKWSW4IHJTX6/graph.json","fetch_events":"https://pith.science/api/pith-number/K2EN4VXTQGYUCBRKWSW4IHJTX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2EN4VXTQGYUCBRKWSW4IHJTX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2EN4VXTQGYUCBRKWSW4IHJTX6/action/storage_attestation","attest_author":"https://pith.science/pith/K2EN4VXTQGYUCBRKWSW4IHJTX6/action/author_attestation","sign_citation":"https://pith.science/pith/K2EN4VXTQGYUCBRKWSW4IHJTX6/action/citation_signature","submit_replication":"https://pith.science/pith/K2EN4VXTQGYUCBRKWSW4IHJTX6/action/replication_record"}},"created_at":"2026-07-05T11:47:49.637177+00:00","updated_at":"2026-07-05T11:47:49.637177+00:00"}