{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2PTCPRWPPEHY5JQR3GCFRPTZGK","short_pith_number":"pith:2PTCPRWP","schema_version":"1.0","canonical_sha256":"d3e627c6cf790f8ea611d98458be7932ac7b4e5119c421ba3818cf408f95cc24","source":{"kind":"arxiv","id":"2606.06444","version":1},"attestation_state":"computed","paper":{"title":"USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander H. Liu, Amit Chhetri, Anton Ratnarajah, Heng-Jui Chang, James Glass, Mrudula Athi, Saurabhchand Bhati","submitted_at":"2026-06-04T17:42:05Z","abstract_excerpt":"Audio encoders are critical to modern audio applications as large language models (LLMs) increasingly rely on a single encoder for diverse inputs. While self-supervised learning (SSL) has yielded strong domain-specific encoders like speech or music experts, multi-domain approaches like USAD and SPEAR remain limited in coverage and evaluation. Recent studies also suggest supervised encoders align better with audio LLMs. We present USAD 2.0, a universal encoder integrating knowledge from both SSL and supervised foundation models. USAD 2.0 introduces domain-aware distillation to address teacher m"},"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":"2606.06444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-04T17:42:05Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"64da78d46afa3144c1e0bd3c3fd0dff1cbe166e28347a0942510079c11df8833","abstract_canon_sha256":"05d44057d0bf03dd9a3989dd2832039df571b3f0fe906559d601f9f7a1b94b6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:45.741611Z","signature_b64":"kPqvx0TxEubNmhDUxc8M7bi2/pPcV/2aqMTCR+8ryVsXyd+GQqsoC01XUQg99lXTbt4yaAnoveCDpBfF2Y3OAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3e627c6cf790f8ea611d98458be7932ac7b4e5119c421ba3818cf408f95cc24","last_reissued_at":"2026-06-05T01:15:45.741193Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:45.741193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander H. Liu, Amit Chhetri, Anton Ratnarajah, Heng-Jui Chang, James Glass, Mrudula Athi, Saurabhchand Bhati","submitted_at":"2026-06-04T17:42:05Z","abstract_excerpt":"Audio encoders are critical to modern audio applications as large language models (LLMs) increasingly rely on a single encoder for diverse inputs. While self-supervised learning (SSL) has yielded strong domain-specific encoders like speech or music experts, multi-domain approaches like USAD and SPEAR remain limited in coverage and evaluation. Recent studies also suggest supervised encoders align better with audio LLMs. We present USAD 2.0, a universal encoder integrating knowledge from both SSL and supervised foundation models. USAD 2.0 introduces domain-aware distillation to address teacher m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06444","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/2606.06444/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":"2606.06444","created_at":"2026-06-05T01:15:45.741251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06444v1","created_at":"2026-06-05T01:15:45.741251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06444","created_at":"2026-06-05T01:15:45.741251+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PTCPRWPPEHY","created_at":"2026-06-05T01:15:45.741251+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PTCPRWPPEHY5JQR","created_at":"2026-06-05T01:15:45.741251+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PTCPRWP","created_at":"2026-06-05T01:15:45.741251+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/2PTCPRWPPEHY5JQR3GCFRPTZGK","json":"https://pith.science/pith/2PTCPRWPPEHY5JQR3GCFRPTZGK.json","graph_json":"https://pith.science/api/pith-number/2PTCPRWPPEHY5JQR3GCFRPTZGK/graph.json","events_json":"https://pith.science/api/pith-number/2PTCPRWPPEHY5JQR3GCFRPTZGK/events.json","paper":"https://pith.science/paper/2PTCPRWP"},"agent_actions":{"view_html":"https://pith.science/pith/2PTCPRWPPEHY5JQR3GCFRPTZGK","download_json":"https://pith.science/pith/2PTCPRWPPEHY5JQR3GCFRPTZGK.json","view_paper":"https://pith.science/paper/2PTCPRWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06444&json=true","fetch_graph":"https://pith.science/api/pith-number/2PTCPRWPPEHY5JQR3GCFRPTZGK/graph.json","fetch_events":"https://pith.science/api/pith-number/2PTCPRWPPEHY5JQR3GCFRPTZGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PTCPRWPPEHY5JQR3GCFRPTZGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PTCPRWPPEHY5JQR3GCFRPTZGK/action/storage_attestation","attest_author":"https://pith.science/pith/2PTCPRWPPEHY5JQR3GCFRPTZGK/action/author_attestation","sign_citation":"https://pith.science/pith/2PTCPRWPPEHY5JQR3GCFRPTZGK/action/citation_signature","submit_replication":"https://pith.science/pith/2PTCPRWPPEHY5JQR3GCFRPTZGK/action/replication_record"}},"created_at":"2026-06-05T01:15:45.741251+00:00","updated_at":"2026-06-05T01:15:45.741251+00:00"}