{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GJMAZEHJKFLN47XU4ODUGND7DJ","short_pith_number":"pith:GJMAZEHJ","schema_version":"1.0","canonical_sha256":"32580c90e95156de7ef4e38743347f1a4a7111029fb893747e1a8d3fa51a4db1","source":{"kind":"arxiv","id":"2505.13237","version":3},"attestation_state":"computed","paper":{"title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chih-Kai Yang, Hung-yi Lee, Neo Ho, Yen-Ting Piao","submitted_at":"2025-05-19T15:20:32Z","abstract_excerpt":"Large audio-language models (LALMs) extend the large language models with multimodal understanding in speech, audio, etc. While their performances on speech and audio-processing tasks are extensively studied, their reasoning abilities remain underexplored. Particularly, their multi-hop reasoning, the ability to recall and integrate multiple facts, lacks systematic evaluation. Existing benchmarks focus on general speech and audio-processing tasks, conversational abilities, and fairness but overlook this aspect. To bridge this gap, we introduce SAKURA, a benchmark assessing LALMs' multi-hop reas"},"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":"2505.13237","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-19T15:20:32Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"13a19edfb63e8da1826b8749e539efb3ac99493ea7853c52b87c7943fe587293","abstract_canon_sha256":"578db1a4fcafec70cde614541fe39da7a5900d5d13ed1dfb608d6a4ebcb33e0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:29.365857Z","signature_b64":"5SgSaAeWYikfk6F4XplY2tuxC0rpZ9e8ohfNy8VOLjmmM/lpnb1T7ckuoCPX8PBGIxOL3SVveSmgByPzXxBMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32580c90e95156de7ef4e38743347f1a4a7111029fb893747e1a8d3fa51a4db1","last_reissued_at":"2026-07-05T11:58:29.365391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:29.365391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chih-Kai Yang, Hung-yi Lee, Neo Ho, Yen-Ting Piao","submitted_at":"2025-05-19T15:20:32Z","abstract_excerpt":"Large audio-language models (LALMs) extend the large language models with multimodal understanding in speech, audio, etc. While their performances on speech and audio-processing tasks are extensively studied, their reasoning abilities remain underexplored. Particularly, their multi-hop reasoning, the ability to recall and integrate multiple facts, lacks systematic evaluation. Existing benchmarks focus on general speech and audio-processing tasks, conversational abilities, and fairness but overlook this aspect. To bridge this gap, we introduce SAKURA, a benchmark assessing LALMs' multi-hop reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13237","kind":"arxiv","version":3},"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/2505.13237/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":"2505.13237","created_at":"2026-07-05T11:58:29.365458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13237v3","created_at":"2026-07-05T11:58:29.365458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13237","created_at":"2026-07-05T11:58:29.365458+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJMAZEHJKFLN","created_at":"2026-07-05T11:58:29.365458+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJMAZEHJKFLN47XU","created_at":"2026-07-05T11:58:29.365458+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJMAZEHJ","created_at":"2026-07-05T11:58:29.365458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06014","citing_title":"Escaping the Procrustean Bed: Groupwise Orthogonal Connectors for Audio-Language Models","ref_index":10,"is_internal_anchor":true},{"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":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":185,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21008","citing_title":"A Survey of Audio Reasoning in Multimodal Foundation Models","ref_index":131,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJMAZEHJKFLN47XU4ODUGND7DJ","json":"https://pith.science/pith/GJMAZEHJKFLN47XU4ODUGND7DJ.json","graph_json":"https://pith.science/api/pith-number/GJMAZEHJKFLN47XU4ODUGND7DJ/graph.json","events_json":"https://pith.science/api/pith-number/GJMAZEHJKFLN47XU4ODUGND7DJ/events.json","paper":"https://pith.science/paper/GJMAZEHJ"},"agent_actions":{"view_html":"https://pith.science/pith/GJMAZEHJKFLN47XU4ODUGND7DJ","download_json":"https://pith.science/pith/GJMAZEHJKFLN47XU4ODUGND7DJ.json","view_paper":"https://pith.science/paper/GJMAZEHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13237&json=true","fetch_graph":"https://pith.science/api/pith-number/GJMAZEHJKFLN47XU4ODUGND7DJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GJMAZEHJKFLN47XU4ODUGND7DJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJMAZEHJKFLN47XU4ODUGND7DJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJMAZEHJKFLN47XU4ODUGND7DJ/action/storage_attestation","attest_author":"https://pith.science/pith/GJMAZEHJKFLN47XU4ODUGND7DJ/action/author_attestation","sign_citation":"https://pith.science/pith/GJMAZEHJKFLN47XU4ODUGND7DJ/action/citation_signature","submit_replication":"https://pith.science/pith/GJMAZEHJKFLN47XU4ODUGND7DJ/action/replication_record"}},"created_at":"2026-07-05T11:58:29.365458+00:00","updated_at":"2026-07-05T11:58:29.365458+00:00"}