{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QYNU5A55ASOUGDMS3GR72B5S2Q","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":"33da85bed94409c819d85f490b4f91f287ff928418f4d91dd5debbdacd0ec438","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T15:16:34Z","title_canon_sha256":"d00fd72ce6dde6016dcb85c773f2d80c7a816d6fc4e4067ba43801ff59fe4ad0"},"schema_version":"1.0","source":{"id":"2502.17239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17239","created_at":"2026-07-05T10:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17239v1","created_at":"2026-07-05T10:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17239","created_at":"2026-07-05T10:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"QYNU5A55ASOU","created_at":"2026-07-05T10:19:07Z"},{"alias_kind":"pith_short_16","alias_value":"QYNU5A55ASOUGDMS","created_at":"2026-07-05T10:19:07Z"},{"alias_kind":"pith_short_8","alias_value":"QYNU5A55","created_at":"2026-07-05T10:19:07Z"}],"graph_snapshots":[{"event_id":"sha256:d0e45e9ba54624928f058bc86902e5e3eff6e4e2c2ad3c648965c013a7684303","target":"graph","created_at":"2026-07-05T10:19:07Z","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/2502.17239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Baichuan-Audio, an end-to-end audio large language model that seamlessly integrates audio understanding and generation. It features a text-guided aligned speech generation mechanism, enabling real-time speech interaction with both comprehension and generation capabilities. Baichuan-Audio leverages a pre-trained ASR model, followed by multi-codebook discretization of speech at a frame rate of 12.5 Hz. This multi-codebook setup ensures that speech tokens retain both semantic and acoustic information. To further enhance modeling, an independent audio head is employed to process audio","authors_text":"Da Pan, Guosheng Dong, Haoze Sun, Jianhua Xu, Jun Liu, MingAn Lin, Mingrui Wang, Tao Zhang, Tianpeng Li, Weipeng Chen, Yuanbo Fang, Zehuan Li, Zenan Zhou, Zheng Liang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T15:16:34Z","title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17239","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":"sha256:4d2675c4f51379e20e543093ecd43c41c61d0b5b6daadd509b03fc4ab6c353b7","target":"record","created_at":"2026-07-05T10:19:07Z","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":"33da85bed94409c819d85f490b4f91f287ff928418f4d91dd5debbdacd0ec438","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T15:16:34Z","title_canon_sha256":"d00fd72ce6dde6016dcb85c773f2d80c7a816d6fc4e4067ba43801ff59fe4ad0"},"schema_version":"1.0","source":{"id":"2502.17239","kind":"arxiv","version":1}},"canonical_sha256":"861b4e83bd049d430d92d9a3fd07b2d436134e1ec8af8f4803b313b4413e056e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"861b4e83bd049d430d92d9a3fd07b2d436134e1ec8af8f4803b313b4413e056e","first_computed_at":"2026-07-05T10:19:07.572146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:07.572146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o1n6ouwuVB+v2Dusdh1vmGEcGMYSWrmNJWyvWPilKs7NKrTiL8jatEVR9LZaY4DSUXlsYe0ZHf3CmMyWvg7fAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:07.572655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d2675c4f51379e20e543093ecd43c41c61d0b5b6daadd509b03fc4ab6c353b7","sha256:d0e45e9ba54624928f058bc86902e5e3eff6e4e2c2ad3c648965c013a7684303"],"state_sha256":"817c426404dc313ef84d9fcf9309a1bfa0229d9bba5f17166a4a28fc69de7b15"}