{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BUVY2XMUD7KCRELQJ7IYWGOXJG","short_pith_number":"pith:BUVY2XMU","schema_version":"1.0","canonical_sha256":"0d2b8d5d941fd42891704fd18b19d749bd210e7f00f414011f17cfb295ca7f80","source":{"kind":"arxiv","id":"2607.05196","version":1},"attestation_state":"computed","paper":{"title":"Unified Audio Intelligence Without Regressing on Text Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andrew Tao, Arushi Goel, Boxin Wang, Bryan Catanzaro, Dongfu Jiang, Jaehyeon Kim, Jonathan Raiman, Mohammad Shoeybi, Rajarshi Roy, Sang-gil Lee, Sreyan Ghosh, Sungwon Kim, Tuomas Rintamaki, Wei Ping, Wenliang Dai, Yang Chen, Yangyi Chen, Zhifeng Kong, Zhuolin Yang, Zihan Liu","submitted_at":"2026-07-06T15:11:57Z","abstract_excerpt":"Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM. Audex adopts a simple unified design with a single Transformer decoder: audio inputs are encoded and projected into the text embedding space, while text tokens and quantized audio output tokens are treated uniformly during generation. This architecture enables strong audio-text fusion, seamless multimodal generation, and compatibility with standa"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.05196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T15:11:57Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"1e41b2867706585e0d8ff1b2b7dd6fc29fedf45e558b7bfe0ecfd7b335398089","abstract_canon_sha256":"940fc5fe9e2d68095ea483308dfde5c5abc423c3a71699196e778c3acb511678"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:19.449874Z","signature_b64":"Kl0RibrIssRaM7gn0JSBPl3Gs7QwwKS8a0tKvQBWDKoU18dmdXv9wQgAm7E3FWHCZL/UB4h1ofvWBoN8GD2FDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d2b8d5d941fd42891704fd18b19d749bd210e7f00f414011f17cfb295ca7f80","last_reissued_at":"2026-07-07T03:19:19.449396Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:19.449396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Audio Intelligence Without Regressing on Text Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andrew Tao, Arushi Goel, Boxin Wang, Bryan Catanzaro, Dongfu Jiang, Jaehyeon Kim, Jonathan Raiman, Mohammad Shoeybi, Rajarshi Roy, Sang-gil Lee, Sreyan Ghosh, Sungwon Kim, Tuomas Rintamaki, Wei Ping, Wenliang Dai, Yang Chen, Yangyi Chen, Zhifeng Kong, Zhuolin Yang, Zihan Liu","submitted_at":"2026-07-06T15:11:57Z","abstract_excerpt":"Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM. Audex adopts a simple unified design with a single Transformer decoder: audio inputs are encoded and projected into the text embedding space, while text tokens and quantized audio output tokens are treated uniformly during generation. This architecture enables strong audio-text fusion, seamless multimodal generation, and compatibility with standa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05196","kind":"arxiv","version":1},"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/2607.05196/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.05196","created_at":"2026-07-07T03:19:19.449453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05196v1","created_at":"2026-07-07T03:19:19.449453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05196","created_at":"2026-07-07T03:19:19.449453+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUVY2XMUD7KC","created_at":"2026-07-07T03:19:19.449453+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUVY2XMUD7KCRELQ","created_at":"2026-07-07T03:19:19.449453+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUVY2XMU","created_at":"2026-07-07T03:19:19.449453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUVY2XMUD7KCRELQJ7IYWGOXJG","json":"https://pith.science/pith/BUVY2XMUD7KCRELQJ7IYWGOXJG.json","graph_json":"https://pith.science/api/pith-number/BUVY2XMUD7KCRELQJ7IYWGOXJG/graph.json","events_json":"https://pith.science/api/pith-number/BUVY2XMUD7KCRELQJ7IYWGOXJG/events.json","paper":"https://pith.science/paper/BUVY2XMU"},"agent_actions":{"view_html":"https://pith.science/pith/BUVY2XMUD7KCRELQJ7IYWGOXJG","download_json":"https://pith.science/pith/BUVY2XMUD7KCRELQJ7IYWGOXJG.json","view_paper":"https://pith.science/paper/BUVY2XMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05196&json=true","fetch_graph":"https://pith.science/api/pith-number/BUVY2XMUD7KCRELQJ7IYWGOXJG/graph.json","fetch_events":"https://pith.science/api/pith-number/BUVY2XMUD7KCRELQJ7IYWGOXJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUVY2XMUD7KCRELQJ7IYWGOXJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUVY2XMUD7KCRELQJ7IYWGOXJG/action/storage_attestation","attest_author":"https://pith.science/pith/BUVY2XMUD7KCRELQJ7IYWGOXJG/action/author_attestation","sign_citation":"https://pith.science/pith/BUVY2XMUD7KCRELQJ7IYWGOXJG/action/citation_signature","submit_replication":"https://pith.science/pith/BUVY2XMUD7KCRELQJ7IYWGOXJG/action/replication_record"}},"created_at":"2026-07-07T03:19:19.449453+00:00","updated_at":"2026-07-07T03:19:19.449453+00:00"}