{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GJMAZEHJKFLN47XU4ODUGND7DJ","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":"578db1a4fcafec70cde614541fe39da7a5900d5d13ed1dfb608d6a4ebcb33e0c","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-19T15:20:32Z","title_canon_sha256":"13a19edfb63e8da1826b8749e539efb3ac99493ea7853c52b87c7943fe587293"},"schema_version":"1.0","source":{"id":"2505.13237","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13237","created_at":"2026-07-05T11:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13237v3","created_at":"2026-07-05T11:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13237","created_at":"2026-07-05T11:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"GJMAZEHJKFLN","created_at":"2026-07-05T11:58:29Z"},{"alias_kind":"pith_short_16","alias_value":"GJMAZEHJKFLN47XU","created_at":"2026-07-05T11:58:29Z"},{"alias_kind":"pith_short_8","alias_value":"GJMAZEHJ","created_at":"2026-07-05T11:58:29Z"}],"graph_snapshots":[{"event_id":"sha256:d9fa92ea48bec8d13468ad89369b75a053aac252104ddadcb0492a4117f346e3","target":"graph","created_at":"2026-07-05T11:58:29Z","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/2505.13237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chih-Kai Yang, Hung-yi Lee, Neo Ho, Yen-Ting Piao","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-19T15:20:32Z","title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13237","kind":"arxiv","version":3},"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":"sha256:8bba27387bf34c805c4fb05408702977354dd3570906813525c0dfd35e1803fc","target":"record","created_at":"2026-07-05T11:58:29Z","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":"578db1a4fcafec70cde614541fe39da7a5900d5d13ed1dfb608d6a4ebcb33e0c","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-19T15:20:32Z","title_canon_sha256":"13a19edfb63e8da1826b8749e539efb3ac99493ea7853c52b87c7943fe587293"},"schema_version":"1.0","source":{"id":"2505.13237","kind":"arxiv","version":3}},"canonical_sha256":"32580c90e95156de7ef4e38743347f1a4a7111029fb893747e1a8d3fa51a4db1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32580c90e95156de7ef4e38743347f1a4a7111029fb893747e1a8d3fa51a4db1","first_computed_at":"2026-07-05T11:58:29.365391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:29.365391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5SgSaAeWYikfk6F4XplY2tuxC0rpZ9e8ohfNy8VOLjmmM/lpnb1T7ckuoCPX8PBGIxOL3SVveSmgByPzXxBMBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:29.365857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13237","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bba27387bf34c805c4fb05408702977354dd3570906813525c0dfd35e1803fc","sha256:d9fa92ea48bec8d13468ad89369b75a053aac252104ddadcb0492a4117f346e3"],"state_sha256":"cfc5cc06bcb6d5349bff8ab57b5cb352e02cf997f4eb92195564819c1de58895"}