{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3DYL27DS2QNHIOYMYZ4LMKSTHK","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":"cf3d0e52ed88500de1bd0c7767fc6083560d005120c84a4741f6963206578047","cross_cats_sorted":["cs.AI","cs.CL","cs.MA","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-01-14T12:06:50Z","title_canon_sha256":"b86d87f75aebdd879c383f6c60cda290b868f254574258d9f69f6dfe6ced8966"},"schema_version":"1.0","source":{"id":"2601.09413","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.09413","created_at":"2026-05-20T00:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2601.09413v2","created_at":"2026-05-20T00:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09413","created_at":"2026-05-20T00:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"3DYL27DS2QNH","created_at":"2026-05-20T00:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"3DYL27DS2QNHIOYM","created_at":"2026-05-20T00:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"3DYL27DS","created_at":"2026-05-20T00:05:40Z"}],"graph_snapshots":[{"event_id":"sha256:bd152d3b57146af9017f3a42e26fdd3ceeef6a31101bc6ac13876e6b909bb5d0","target":"graph","created_at":"2026-05-20T00:05:40Z","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/2601.09413/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a voice-agentic framework that learns one critical omni-understanding skill: knowing when to trust itself versus when to consult external audio perception. Our work is motivated by a crucial yet counterintuitive finding: naively fine-tuning an omni-model on both speech recognition and external sound understanding tasks often degrades performance, as the model can be easily misled by noisy hypotheses. To address this, our framework, Speech-Hands, recasts the problem as an explicit self-reflection decision. This learnable reflection primitive proves effective in preventing the model","authors_text":"Ankita Pasad, Arushi Goel, Boris Ginsburg, Chao-Han Huck Yang, Chenhui Chu, Hanrong Ye, Jinchuan Tian, Kunal Dhawan, Rafael Valle, Ryo Hachiuma, Shinji Watanabe, Shizhe Diao, Sreyan Ghosh, Szu-Wei Fu, Yu-Chiang Frank Wang, Yusuke Hirota, Zhehuai Chen, Zhen Wan","cross_cats":["cs.AI","cs.CL","cs.MA","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-01-14T12:06:50Z","title":"Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.09413","kind":"arxiv","version":2},"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":"sha256:10c76821bedcddeade38ac6ff02ecab5c550bdc0150d2de9fa9304c7a73cbc39","target":"record","created_at":"2026-05-20T00:05:40Z","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":"cf3d0e52ed88500de1bd0c7767fc6083560d005120c84a4741f6963206578047","cross_cats_sorted":["cs.AI","cs.CL","cs.MA","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-01-14T12:06:50Z","title_canon_sha256":"b86d87f75aebdd879c383f6c60cda290b868f254574258d9f69f6dfe6ced8966"},"schema_version":"1.0","source":{"id":"2601.09413","kind":"arxiv","version":2}},"canonical_sha256":"d8f0bd7c72d41a743b0cc678b62a533a8cae261f261b6d89ded324a119f9a9f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8f0bd7c72d41a743b0cc678b62a533a8cae261f261b6d89ded324a119f9a9f0","first_computed_at":"2026-05-20T00:05:40.490250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:40.490250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B0uhQ5Xh0TiJzz77VOuMV41qe8l1pLAvlb7gTdoN6se6Oug2LJi5FAZjP3C4CsQ8XJmMYkFYjfNNEibrpytNAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:40.490934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.09413","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10c76821bedcddeade38ac6ff02ecab5c550bdc0150d2de9fa9304c7a73cbc39","sha256:bd152d3b57146af9017f3a42e26fdd3ceeef6a31101bc6ac13876e6b909bb5d0"],"state_sha256":"a0d781296c2ce32a49b9ef5adc64ac7ffb90b895574a1d10085aa16454b31a6e"}