{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZJMRNHJBUGFADSTIULVBO5DLTD","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":"cefedc02afa98b806f5997bed7b8a57de2fd3e21dbf8c070c228ca8ecd37442a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T17:35:20Z","title_canon_sha256":"53ec3ea193517ae2bf2d9e736864a42f28b4168e00e96111328b4e8053ea3564"},"schema_version":"1.0","source":{"id":"2607.21550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21550","created_at":"2026-07-24T01:24:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21550v1","created_at":"2026-07-24T01:24:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21550","created_at":"2026-07-24T01:24:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZJMRNHJBUGFA","created_at":"2026-07-24T01:24:39Z"},{"alias_kind":"pith_short_16","alias_value":"ZJMRNHJBUGFADSTI","created_at":"2026-07-24T01:24:39Z"},{"alias_kind":"pith_short_8","alias_value":"ZJMRNHJB","created_at":"2026-07-24T01:24:39Z"}],"graph_snapshots":[{"event_id":"sha256:7c307e0b9adb168c89edb2efea48a051a29c66e37065f7459f02681f615a928c","target":"graph","created_at":"2026-07-24T01:24:39Z","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/2607.21550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in deep logical reasoning, primarily due to the scarcity of high-quality audio reasoning data. To bridge this gap, we propose X$^3$-OPD, a cross-modal on-policy distillation framework that transfers reasoning capabilities from a powerful text teacher to an audio-language student. During training, the student generates reasoning trajectories conditioned on its own acoustic perception, while the teacher provides token-level guidance using matched text","authors_text":"Di Cao, Dongjie Fu, Shengpeng Ji, Tao Jin, Wenxu Jia, Xize Cheng, Yifu Chen, Yu Zhang, Zihan Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T17:35:20Z","title":"X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21550","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:aaa0918432ec11cd1b8a42564eb661585a88741ef6b1265d04be96ec66dfddff","target":"record","created_at":"2026-07-24T01:24:39Z","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":"cefedc02afa98b806f5997bed7b8a57de2fd3e21dbf8c070c228ca8ecd37442a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T17:35:20Z","title_canon_sha256":"53ec3ea193517ae2bf2d9e736864a42f28b4168e00e96111328b4e8053ea3564"},"schema_version":"1.0","source":{"id":"2607.21550","kind":"arxiv","version":1}},"canonical_sha256":"ca59169d21a18a01ca68a2ea17746b98e7602f3b69968b4b1c2ff442000f10db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca59169d21a18a01ca68a2ea17746b98e7602f3b69968b4b1c2ff442000f10db","first_computed_at":"2026-07-24T01:24:39.077048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:24:39.077048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1sZePgRJV0CkGp5NlD+32vi+MLE9SddxiLPX0wjWvGE4H0Twompde9ToilwRKo3oFftSuZzfKiITd0PnGDovAg==","signature_status":"signed_v1","signed_at":"2026-07-24T01:24:39.077969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaa0918432ec11cd1b8a42564eb661585a88741ef6b1265d04be96ec66dfddff","sha256:7c307e0b9adb168c89edb2efea48a051a29c66e37065f7459f02681f615a928c"],"state_sha256":"f073d0fd00f90c931bb59fac0071a04d2b572413e2830db860ede2c5a16c9f48"}