{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ETSPL4NI4U2OBFQHME35OPF66Y","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":"5370a4d5923a5c43e5f4d93f75ed9d490b4c9b28b792031a86814d851bc51f41","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-19T15:51:53Z","title_canon_sha256":"b0163be3205b91f063b3defb8b17b686cc8a34d2cb15fdb62ade80f4a077e65e"},"schema_version":"1.0","source":{"id":"2505.13270","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13270","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13270v1","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13270","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"ETSPL4NI4U2O","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"ETSPL4NI4U2OBFQH","created_at":"2026-07-05T11:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"ETSPL4NI","created_at":"2026-07-05T11:05:27Z"}],"graph_snapshots":[{"event_id":"sha256:608716f33b70efdfc759c7c60bc445d8cad064539ff2260c49863680ab7c5e81","target":"graph","created_at":"2026-07-05T11:05:27Z","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/2505.13270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the progress in self-supervised learning (SSL) for speech and music, existing models treat these domains separately, limiting their capacity for unified audio understanding. A unified model is desirable for applications that require general representations, e.g. audio large language models. Nonetheless, directly training a general model for speech and music is computationally expensive. Knowledge Distillation of teacher ensembles may be a natural solution, but we posit that decoupling the distillation of the speech and music SSL models allows for more flexibility. Thus, we propose to l","authors_text":"Eng Siong Chng, Fabian Ritter-Gutierrez, Hung-yi Lee, Jeremy H.M Wong, Jui-Chiang Wei, Nancy F. Chen, Yi-Cheng Lin","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-19T15:51:53Z","title":"Distilling a speech and music encoder with task arithmetic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13270","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:bb114c873fb281d8f23c688ba7a4612e74b1c058bfe5f8cf0f86e72ff9595f42","target":"record","created_at":"2026-07-05T11:05:27Z","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":"5370a4d5923a5c43e5f4d93f75ed9d490b4c9b28b792031a86814d851bc51f41","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-19T15:51:53Z","title_canon_sha256":"b0163be3205b91f063b3defb8b17b686cc8a34d2cb15fdb62ade80f4a077e65e"},"schema_version":"1.0","source":{"id":"2505.13270","kind":"arxiv","version":1}},"canonical_sha256":"24e4f5f1a8e534e096076137d73cbef6364b9009f14c4686fb18f9cadb290ac2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24e4f5f1a8e534e096076137d73cbef6364b9009f14c4686fb18f9cadb290ac2","first_computed_at":"2026-07-05T11:05:27.572731Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:27.572731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"we0MF2MCvuFhHdlJcvlHAXxl8zfR1bTOYwr7dCN7yB5pl4o3t43yin3tJOaJ5FNW5QsrbCpZJB5Jv2mNmSATBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:27.573186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13270","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb114c873fb281d8f23c688ba7a4612e74b1c058bfe5f8cf0f86e72ff9595f42","sha256:608716f33b70efdfc759c7c60bc445d8cad064539ff2260c49863680ab7c5e81"],"state_sha256":"e59479c7f9e21797f3cc04aef8a324995ee27555183401e7693ed91a5b32e2ad"}