{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y32ZSMFPZQX4YXFSLXSLR7MMEJ","short_pith_number":"pith:Y32ZSMFP","canonical_record":{"source":{"id":"2506.08967","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-10T16:37:39Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"42fd8ba7ba93af36f060c7249a3934b9ea222166c0b709b83a099f7e760b5450","abstract_canon_sha256":"b911f025d4cc3fdb6972f1affd05b8ccd65ba4db1f185cb76bf430fe43995fa6"},"schema_version":"1.0"},"canonical_sha256":"c6f59930afcc2fcc5cb25de4b8fd8c2279259bf09372607f397de74ed28179c1","source":{"kind":"arxiv","id":"2506.08967","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08967","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08967v2","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08967","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"pith_short_12","alias_value":"Y32ZSMFPZQX4","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"pith_short_16","alias_value":"Y32ZSMFPZQX4YXFS","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"pith_short_8","alias_value":"Y32ZSMFP","created_at":"2026-07-05T11:20:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y32ZSMFPZQX4YXFSLXSLR7MMEJ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08967","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-10T16:37:39Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"42fd8ba7ba93af36f060c7249a3934b9ea222166c0b709b83a099f7e760b5450","abstract_canon_sha256":"b911f025d4cc3fdb6972f1affd05b8ccd65ba4db1f185cb76bf430fe43995fa6"},"schema_version":"1.0"},"canonical_sha256":"c6f59930afcc2fcc5cb25de4b8fd8c2279259bf09372607f397de74ed28179c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:56.395337Z","signature_b64":"+MEdCpvglPRAqctti+OSeFaEgqQRC9GZhxg0LwCPTWM0R462kX3q4HSEV1on1Zu86GrRwhZ0kJG8i/mcNXu0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6f59930afcc2fcc5cb25de4b8fd8c2279259bf09372607f397de74ed28179c1","last_reissued_at":"2026-07-05T11:20:56.394771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:56.394771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08967","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:20:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g4zq5YYCKFm1x2w00XrHgFCf3YOqPSJ/2UpFGG3mgRkyYSIK5Pk1PKyYYZKSZtzhoJAzxlVu3Diq5iF1343ICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:58:15.894721Z"},"content_sha256":"d8d70d3aceefeda38dc6acb0f8257bc51c1cd01789497343a7f40b3d35ac92c0","schema_version":"1.0","event_id":"sha256:d8d70d3aceefeda38dc6acb0f8257bc51c1cd01789497343a7f40b3d35ac92c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y32ZSMFPZQX4YXFSLXSLR7MMEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ailin Huang, Bingxin Li, Bin Wang, Binxing Jiao, Bo Li, Boyong Wu, Bruce Wang, Buyun Ma, Changxin Miao, Changyi Wan, Chao Yan, Chengli Feng, Chen Hu, Chen Xu, Dapeng Shi, Daxin Jiang, Dingyuan Hu, Enle Liu, Guanzhe Huang, Gulin Yan, Hanpeng Hu, Haonan Jia, Heng Wang, Heung-Yeung Shum, Hongyuan Wang, Hongyu Zhou, Jiahao Gong, Jianjian Sun, Jiansheng Chen, Jiaoren Wu, Jie Wu, Jie Yang, Jingbei Li, Jing Li, Joanna Wang, Junzhe Lin, Kaixiang Li, Lei Xia, Longlong Gu, Ming Li, Mingrui Chen, Nie Hao, Peng Liu, Ranchen Ming, Ruihang Miao, Shaoliang Pang, Shilei Jiang, Shuchang Zhou, Siqi Liu, Song Yuan, Tiancheng Cao, Tian Fei, Wang You, Wen Li, Wenqing He, Xiangyu Zhang, Xi Chen, Xinhao Zhang, Xuelin Zhang, Xuerui Yang, Xu Zhao, Yanbo Yu, Yechang Huang, Yibo Zhu, Yinmin Zhong, Yuanwei Liang, Yuanwei Lu, Yuxiang Yang, Yuxiang Zhang, Yu Zhou, Zheng Ge, Zheng Gong, Zhewei Huang, Zidong Yang, Zili Zhang, Zixin Zhang","submitted_at":"2025-06-10T16:37:39Z","abstract_excerpt":"Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate natural speech responses directly, hindering seamless audio interactions. To address this, we introduce Step-Audio-AQAA, a fully end-to-end LALM designed for Audio Query-Audio Answer (AQAA) tasks. The model integrates a dual-codebook audio tokenizer for linguistic and semantic feature extraction, a 130-billion-parameter backbone LLM and a neural vocoder for high-fidelity speech synthesis. Our post-training approach emp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08967","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.08967/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:20:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Enjp0ZaXHIGl4hAF+Bk4p7V838q+W6fg6lUbTW7MdUPhTBzG1x5GA7oeYfGoahrq9j23qOc1me2WwiINenOEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:58:15.895245Z"},"content_sha256":"f4f8ef8fa4142794b53dd55ee80a9a5431b238cb3dca812fc1d4de484a90b1fa","schema_version":"1.0","event_id":"sha256:f4f8ef8fa4142794b53dd55ee80a9a5431b238cb3dca812fc1d4de484a90b1fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y32ZSMFPZQX4YXFSLXSLR7MMEJ/bundle.json","state_url":"https://pith.science/pith/Y32ZSMFPZQX4YXFSLXSLR7MMEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y32ZSMFPZQX4YXFSLXSLR7MMEJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T19:58:15Z","links":{"resolver":"https://pith.science/pith/Y32ZSMFPZQX4YXFSLXSLR7MMEJ","bundle":"https://pith.science/pith/Y32ZSMFPZQX4YXFSLXSLR7MMEJ/bundle.json","state":"https://pith.science/pith/Y32ZSMFPZQX4YXFSLXSLR7MMEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y32ZSMFPZQX4YXFSLXSLR7MMEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y32ZSMFPZQX4YXFSLXSLR7MMEJ","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":"b911f025d4cc3fdb6972f1affd05b8ccd65ba4db1f185cb76bf430fe43995fa6","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-10T16:37:39Z","title_canon_sha256":"42fd8ba7ba93af36f060c7249a3934b9ea222166c0b709b83a099f7e760b5450"},"schema_version":"1.0","source":{"id":"2506.08967","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08967","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08967v2","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08967","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"pith_short_12","alias_value":"Y32ZSMFPZQX4","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"pith_short_16","alias_value":"Y32ZSMFPZQX4YXFS","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"pith_short_8","alias_value":"Y32ZSMFP","created_at":"2026-07-05T11:20:56Z"}],"graph_snapshots":[{"event_id":"sha256:f4f8ef8fa4142794b53dd55ee80a9a5431b238cb3dca812fc1d4de484a90b1fa","target":"graph","created_at":"2026-07-05T11:20:56Z","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/2506.08967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate natural speech responses directly, hindering seamless audio interactions. To address this, we introduce Step-Audio-AQAA, a fully end-to-end LALM designed for Audio Query-Audio Answer (AQAA) tasks. The model integrates a dual-codebook audio tokenizer for linguistic and semantic feature extraction, a 130-billion-parameter backbone LLM and a neural vocoder for high-fidelity speech synthesis. Our post-training approach emp","authors_text":"Ailin Huang, Bingxin Li, Bin Wang, Binxing Jiao, Bo Li, Boyong Wu, Bruce Wang, Buyun Ma, Changxin Miao, Changyi Wan, Chao Yan, Chengli Feng, Chen Hu, Chen Xu, Dapeng Shi, Daxin Jiang, Dingyuan Hu, Enle Liu, Guanzhe Huang, Gulin Yan, Hanpeng Hu, Haonan Jia, Heng Wang, Heung-Yeung Shum, Hongyuan Wang, Hongyu Zhou, Jiahao Gong, Jianjian Sun, Jiansheng Chen, Jiaoren Wu, Jie Wu, Jie Yang, Jingbei Li, Jing Li, Joanna Wang, Junzhe Lin, Kaixiang Li, Lei Xia, Longlong Gu, Ming Li, Mingrui Chen, Nie Hao, Peng Liu, Ranchen Ming, Ruihang Miao, Shaoliang Pang, Shilei Jiang, Shuchang Zhou, Siqi Liu, Song Yuan, Tiancheng Cao, Tian Fei, Wang You, Wen Li, Wenqing He, Xiangyu Zhang, Xi Chen, Xinhao Zhang, Xuelin Zhang, Xuerui Yang, Xu Zhao, Yanbo Yu, Yechang Huang, Yibo Zhu, Yinmin Zhong, Yuanwei Liang, Yuanwei Lu, Yuxiang Yang, Yuxiang Zhang, Yu Zhou, Zheng Ge, Zheng Gong, Zhewei Huang, Zidong Yang, Zili Zhang, Zixin Zhang","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-10T16:37:39Z","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08967","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:d8d70d3aceefeda38dc6acb0f8257bc51c1cd01789497343a7f40b3d35ac92c0","target":"record","created_at":"2026-07-05T11:20:56Z","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":"b911f025d4cc3fdb6972f1affd05b8ccd65ba4db1f185cb76bf430fe43995fa6","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-10T16:37:39Z","title_canon_sha256":"42fd8ba7ba93af36f060c7249a3934b9ea222166c0b709b83a099f7e760b5450"},"schema_version":"1.0","source":{"id":"2506.08967","kind":"arxiv","version":2}},"canonical_sha256":"c6f59930afcc2fcc5cb25de4b8fd8c2279259bf09372607f397de74ed28179c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6f59930afcc2fcc5cb25de4b8fd8c2279259bf09372607f397de74ed28179c1","first_computed_at":"2026-07-05T11:20:56.394771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:56.394771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+MEdCpvglPRAqctti+OSeFaEgqQRC9GZhxg0LwCPTWM0R462kX3q4HSEV1on1Zu86GrRwhZ0kJG8i/mcNXu0AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:56.395337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08967","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8d70d3aceefeda38dc6acb0f8257bc51c1cd01789497343a7f40b3d35ac92c0","sha256:f4f8ef8fa4142794b53dd55ee80a9a5431b238cb3dca812fc1d4de484a90b1fa"],"state_sha256":"ef7157a8fa5070a0ce2927ca40cf500c6a64dea2f0eae8b8cfad72ca9713e3ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nYwWxGSilA37YOUk+2t/5ddBEY+6xxxnuVN+W9XINm6A9XZwJAn3rRM2Bi86QrnbdVzwie5/h2WyHHuVDTRLCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:58:15.899477Z","bundle_sha256":"770f1b0c45e678020a53b9bab09977fada27c93d08c60f0086a9b91ccb554e7a"}}