{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QCSSJS5F7PPMK65YG2TUQGQ4CK","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":"b2a397ac2c1e27870196bde1b1d1f376926cb3489de83246d479ccaa9a5a3faf","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-14T08:43:53Z","title_canon_sha256":"a0d80d85c8a7488cbfccf28b280f9533197906f65c6867a009f3f7c413718f3d"},"schema_version":"1.0","source":{"id":"2503.11197","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11197","created_at":"2026-07-05T11:02:42Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11197v4","created_at":"2026-07-05T11:02:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11197","created_at":"2026-07-05T11:02:42Z"},{"alias_kind":"pith_short_12","alias_value":"QCSSJS5F7PPM","created_at":"2026-07-05T11:02:42Z"},{"alias_kind":"pith_short_16","alias_value":"QCSSJS5F7PPMK65Y","created_at":"2026-07-05T11:02:42Z"},{"alias_kind":"pith_short_8","alias_value":"QCSSJS5F","created_at":"2026-07-05T11:02:42Z"}],"graph_snapshots":[{"event_id":"sha256:53fb6b24ab8f592516b7b388413025ad89f7570e6a1f788defd6b1047b5166eb","target":"graph","created_at":"2026-07-05T11:02:42Z","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/2503.11197/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively applied to visual multimodal tasks. However, the audio modality has largely been overlooked in these developments. Thus, we conduct a series of RL explorations in audio understanding and reasoning, specifically focusing on the audio question answering (AQA) task. We leverage the group relative policy optimization (GRPO) algorithm to Qwen2-Audio-7B-Instruct, and our experiments demonstrated state-of-the-art performanc","authors_text":"Gang Li, Heinrich Dinkel, Jian Luan, Jizhong Liu, Junbo Zhang, Yadong Niu","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-14T08:43:53Z","title":"Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11197","kind":"arxiv","version":4},"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:f60358344ae4cf7ed740897c4efefc976e5974bac326a6f21d98158eca679eb0","target":"record","created_at":"2026-07-05T11:02:42Z","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":"b2a397ac2c1e27870196bde1b1d1f376926cb3489de83246d479ccaa9a5a3faf","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-14T08:43:53Z","title_canon_sha256":"a0d80d85c8a7488cbfccf28b280f9533197906f65c6867a009f3f7c413718f3d"},"schema_version":"1.0","source":{"id":"2503.11197","kind":"arxiv","version":4}},"canonical_sha256":"80a524cba5fbdec57bb836a7481a1c12811469216095956baf0dd22dc92fe771","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80a524cba5fbdec57bb836a7481a1c12811469216095956baf0dd22dc92fe771","first_computed_at":"2026-07-05T11:02:42.643458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:42.643458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/ef8Nvt2mmhGZhEtbQx2Kn3jBDZuQ/l1gaOMfvo4seNaH+NSnRuJ9WxNLRAfDoj/eOmmmA+4/YD3+YdAhkMsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:42.644013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.11197","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f60358344ae4cf7ed740897c4efefc976e5974bac326a6f21d98158eca679eb0","sha256:53fb6b24ab8f592516b7b388413025ad89f7570e6a1f788defd6b1047b5166eb"],"state_sha256":"7cd3ab2d6cf4d4c29e21a4fa7235ff8b7d02c782b0fce614007a0a25c06e8ca0"}