{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CUTSL4EWZIBBYOPFZNXKKLA3T3","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":"d2f70bc251d3cf25bdc4dc6dcbaf1436c353ba3c57ab66ab881cc71ddad9fc6e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-03T19:46:13Z","title_canon_sha256":"653b0b845bf0da7ad901e8bb119f40278aea20b13f2bb7aadaa71fa728fede4b"},"schema_version":"1.0","source":{"id":"2608.02831","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02831","created_at":"2026-08-05T00:42:59Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02831v1","created_at":"2026-08-05T00:42:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02831","created_at":"2026-08-05T00:42:59Z"},{"alias_kind":"pith_short_12","alias_value":"CUTSL4EWZIBB","created_at":"2026-08-05T00:42:59Z"},{"alias_kind":"pith_short_16","alias_value":"CUTSL4EWZIBBYOPF","created_at":"2026-08-05T00:42:59Z"},{"alias_kind":"pith_short_8","alias_value":"CUTSL4EW","created_at":"2026-08-05T00:42:59Z"}],"graph_snapshots":[{"event_id":"sha256:562c0d1c742c985404483d032ad9d8432ebc80310627dd16d8fdfe38096b93e0","target":"graph","created_at":"2026-08-05T00:42:59Z","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/2608.02831/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio reasoning is essential for machine understanding of the acoustic world. Reinforcement learning with verifiable rewards can elicit such reasoning, yet existing reward designs are complementary in their limitations: outcome-based rewards supervise only the final answer and let the model reach it without attending to the audio, whereas process-based rewards score the reasoning itself but rely on coarse, hand-crafted, and fixed criteria that neither adapt to each question nor stay grounded in the acoustic evidence. Moreover, questions differ in what they demand, with some hinging on percepti","authors_text":"Dehai Min, Fangxu Yu, Ge Liu, Michael Xu, Philip S. Yu, Tao Feng, Tianyi Zhou, Weijia Xu, Zinan Lin","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-03T19:46:13Z","title":"Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02831","kind":"arxiv","version":1},"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:c9412cc38ee4e80b7ca061798e10d302307fc4c2dc183169a8b3b15a3e8c25f4","target":"record","created_at":"2026-08-05T00:42:59Z","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":"d2f70bc251d3cf25bdc4dc6dcbaf1436c353ba3c57ab66ab881cc71ddad9fc6e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-03T19:46:13Z","title_canon_sha256":"653b0b845bf0da7ad901e8bb119f40278aea20b13f2bb7aadaa71fa728fede4b"},"schema_version":"1.0","source":{"id":"2608.02831","kind":"arxiv","version":1}},"canonical_sha256":"152725f096ca021c39e5cb6ea52c1b9edd68b6bda860a2df3a451a91e225df9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"152725f096ca021c39e5cb6ea52c1b9edd68b6bda860a2df3a451a91e225df9b","first_computed_at":"2026-08-05T00:42:59.510316Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:42:59.510316Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EqT+65ZRAqYQZ5zgdvGSoDVtS84Q/OPvjs7MYCu6iystumzTdvFaqsh3Y2JiFFSD/KpqEJxz9zBygnbfyb05AQ==","signature_status":"signed_v1","signed_at":"2026-08-05T00:42:59.512914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02831","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9412cc38ee4e80b7ca061798e10d302307fc4c2dc183169a8b3b15a3e8c25f4","sha256:562c0d1c742c985404483d032ad9d8432ebc80310627dd16d8fdfe38096b93e0"],"state_sha256":"688f43a25152a9d6b3768a3ee2e3ee0ad90fc179ea24800d5ed6353fff669d51"}