{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KSFYIE5MXBAGDGX7BEFQLR43QC","short_pith_number":"pith:KSFYIE5M","schema_version":"1.0","canonical_sha256":"548b8413acb840619aff090b05c79b80af1cdadf0bd25d8e3d47fe27849c818c","source":{"kind":"arxiv","id":"2607.17079","version":1},"attestation_state":"computed","paper":{"title":"SALMONN-2: Advancing General-Purpose Hearing Abilities with Self-Supervised Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Baoxiang Li, Changli Tang, Chao Zhang, Guangzhi Sun, Philip Woodland, Siyin Wang, Siyuan Hou, Terumi Chiba, Wen Wu, Wenyi Yu, Xiaoyu Yang, Xuenan Xu, Ziyang Zhang","submitted_at":"2026-07-19T05:05:49Z","abstract_excerpt":"Recent audio large language models (ALLMs) are typically built upon audio encoders trained with large amounts of supervised data. Since self-supervised learning (SSL) audio encoder models are known to learn general-purpose and transferable representations, we investigate whether general-purpose SSL audio representations can serve as an effective foundation for ALLMs. We present SALMONN-2, an ALLM built upon a unified SSL encoder. To better exploit the hierarchical representations learned by SSL encoders, we propose a multi-layer feature fusion (MLF) adapter that aggregates information from all"},"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":"2607.17079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-19T05:05:49Z","cross_cats_sorted":[],"title_canon_sha256":"af3e8b8b61049d54db3039c7d49b52bb269e9af113449dd7e9db8cc9dd7e02b6","abstract_canon_sha256":"9f26ee88ee417a2e83e2f2874147435669a8dee68a8284195d063c67c21b8103"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:13.861521Z","signature_b64":"iiLBfxCbpBBJPmVhE1m5sB1faU8gg4Gbh0zbiO/H+YAcZVQq5uaw4rtmXSBoXiPiYGcz42qAPA7Ua5B+LVTfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"548b8413acb840619aff090b05c79b80af1cdadf0bd25d8e3d47fe27849c818c","last_reissued_at":"2026-07-21T01:21:13.860668Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:13.860668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SALMONN-2: Advancing General-Purpose Hearing Abilities with Self-Supervised Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Baoxiang Li, Changli Tang, Chao Zhang, Guangzhi Sun, Philip Woodland, Siyin Wang, Siyuan Hou, Terumi Chiba, Wen Wu, Wenyi Yu, Xiaoyu Yang, Xuenan Xu, Ziyang Zhang","submitted_at":"2026-07-19T05:05:49Z","abstract_excerpt":"Recent audio large language models (ALLMs) are typically built upon audio encoders trained with large amounts of supervised data. Since self-supervised learning (SSL) audio encoder models are known to learn general-purpose and transferable representations, we investigate whether general-purpose SSL audio representations can serve as an effective foundation for ALLMs. We present SALMONN-2, an ALLM built upon a unified SSL encoder. To better exploit the hierarchical representations learned by SSL encoders, we propose a multi-layer feature fusion (MLF) adapter that aggregates information from all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17079","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/2607.17079/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":"2607.17079","created_at":"2026-07-21T01:21:13.861103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17079v1","created_at":"2026-07-21T01:21:13.861103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17079","created_at":"2026-07-21T01:21:13.861103+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSFYIE5MXBAG","created_at":"2026-07-21T01:21:13.861103+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSFYIE5MXBAGDGX7","created_at":"2026-07-21T01:21:13.861103+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSFYIE5M","created_at":"2026-07-21T01:21:13.861103+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/KSFYIE5MXBAGDGX7BEFQLR43QC","json":"https://pith.science/pith/KSFYIE5MXBAGDGX7BEFQLR43QC.json","graph_json":"https://pith.science/api/pith-number/KSFYIE5MXBAGDGX7BEFQLR43QC/graph.json","events_json":"https://pith.science/api/pith-number/KSFYIE5MXBAGDGX7BEFQLR43QC/events.json","paper":"https://pith.science/paper/KSFYIE5M"},"agent_actions":{"view_html":"https://pith.science/pith/KSFYIE5MXBAGDGX7BEFQLR43QC","download_json":"https://pith.science/pith/KSFYIE5MXBAGDGX7BEFQLR43QC.json","view_paper":"https://pith.science/paper/KSFYIE5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17079&json=true","fetch_graph":"https://pith.science/api/pith-number/KSFYIE5MXBAGDGX7BEFQLR43QC/graph.json","fetch_events":"https://pith.science/api/pith-number/KSFYIE5MXBAGDGX7BEFQLR43QC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSFYIE5MXBAGDGX7BEFQLR43QC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSFYIE5MXBAGDGX7BEFQLR43QC/action/storage_attestation","attest_author":"https://pith.science/pith/KSFYIE5MXBAGDGX7BEFQLR43QC/action/author_attestation","sign_citation":"https://pith.science/pith/KSFYIE5MXBAGDGX7BEFQLR43QC/action/citation_signature","submit_replication":"https://pith.science/pith/KSFYIE5MXBAGDGX7BEFQLR43QC/action/replication_record"}},"created_at":"2026-07-21T01:21:13.861103+00:00","updated_at":"2026-07-21T01:21:13.861103+00:00"}