{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MPVT2QMV6HYBKT3NDOS3XYAG56","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":"ee3614d4f83be638dc5c9831d404561c843d27ac1c0a0eee3f1947ad430c4366","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T13:41:26Z","title_canon_sha256":"86346e4424e976e8eee4cad33cd73609704cda6787e80279aeb508c9339095f4"},"schema_version":"1.0","source":{"id":"2504.15900","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15900","created_at":"2026-07-05T10:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15900v3","created_at":"2026-07-05T10:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15900","created_at":"2026-07-05T10:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"MPVT2QMV6HYB","created_at":"2026-07-05T10:55:34Z"},{"alias_kind":"pith_short_16","alias_value":"MPVT2QMV6HYBKT3N","created_at":"2026-07-05T10:55:34Z"},{"alias_kind":"pith_short_8","alias_value":"MPVT2QMV","created_at":"2026-07-05T10:55:34Z"}],"graph_snapshots":[{"event_id":"sha256:1dc5320f7322f05536cd530174b9d90930513d94df844994d1129baa96f7f095","target":"graph","created_at":"2026-07-05T10:55:34Z","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/2504.15900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work shows that reinforcement learning(RL) can markedly sharpen the reasoning ability of large language models (LLMs) by prompting them to \"think before answering.\" Yet whether and how these gains transfer to audio-language reasoning remains largely unexplored. We extend the Group-Relative Policy Optimization (GRPO) framework from DeepSeek-R1 to a Large Audio-Language Model (LALM), and construct a 32k sample multiple-choice corpus. Using a two-stage regimen supervised fine-tuning on structured and unstructured chains-of-thought, followed by curriculum-guided GRPO, we systematically comp","authors_text":"Cheng Wen, Shuaijiang Zhao, Tingwei Guo, Wei Zou, Xiangang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T13:41:26Z","title":"SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15900","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":"sha256:2e45d1b355f57672420691ac2e5d7912c783c30e270d4bdaf39ff4360fefb2ab","target":"record","created_at":"2026-07-05T10:55:34Z","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":"ee3614d4f83be638dc5c9831d404561c843d27ac1c0a0eee3f1947ad430c4366","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T13:41:26Z","title_canon_sha256":"86346e4424e976e8eee4cad33cd73609704cda6787e80279aeb508c9339095f4"},"schema_version":"1.0","source":{"id":"2504.15900","kind":"arxiv","version":3}},"canonical_sha256":"63eb3d4195f1f0154f6d1ba5bbe006efa08b41e9af55725b7dd4f3792e555e31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63eb3d4195f1f0154f6d1ba5bbe006efa08b41e9af55725b7dd4f3792e555e31","first_computed_at":"2026-07-05T10:55:34.823537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:34.823537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AN6yntmYPIKKcjHst4ChBTGtotILC4X4WC2lBTF/EUP+gbFzi91gFWHqcPFp85Izcydx6jjgTBD8uvIn5tmiDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:34.824037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15900","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e45d1b355f57672420691ac2e5d7912c783c30e270d4bdaf39ff4360fefb2ab","sha256:1dc5320f7322f05536cd530174b9d90930513d94df844994d1129baa96f7f095"],"state_sha256":"96cd126c252fa3c21480aca44dbeb1c4ddae9d3c15f3d04147234c2ad6b716a6"}