{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WE2PJXJAZOLGZKWXMIWWL3SMAO","short_pith_number":"pith:WE2PJXJA","canonical_record":{"source":{"id":"2506.11403","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T02:04:33Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"d8e00d8ddcf0d3e8d3d911fdb3a2d19e375016a60d99f453f8ca59849bed46fc","abstract_canon_sha256":"404f8a8e12200346cb2584b60cdb5371caa26df7cc9878d6abfd393196d8f6e1"},"schema_version":"1.0"},"canonical_sha256":"b134f4dd20cb966caad7622d65ee4c039edceee9012e79af60c356910b404e38","source":{"kind":"arxiv","id":"2506.11403","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11403","created_at":"2026-07-05T11:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11403v1","created_at":"2026-07-05T11:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11403","created_at":"2026-07-05T11:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"WE2PJXJAZOLG","created_at":"2026-07-05T11:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"WE2PJXJAZOLGZKWX","created_at":"2026-07-05T11:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"WE2PJXJA","created_at":"2026-07-05T11:21:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WE2PJXJAZOLGZKWXMIWWL3SMAO","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11403","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T02:04:33Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"d8e00d8ddcf0d3e8d3d911fdb3a2d19e375016a60d99f453f8ca59849bed46fc","abstract_canon_sha256":"404f8a8e12200346cb2584b60cdb5371caa26df7cc9878d6abfd393196d8f6e1"},"schema_version":"1.0"},"canonical_sha256":"b134f4dd20cb966caad7622d65ee4c039edceee9012e79af60c356910b404e38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:03.777747Z","signature_b64":"1KqKvzAmD0YDWYweV9XozAeu/UEfOJKYWepYsDam+4MooTD6YJ7UntRo6U2RG+8aNR+67O4Umv4f1ZiJTMrvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b134f4dd20cb966caad7622d65ee4c039edceee9012e79af60c356910b404e38","last_reissued_at":"2026-07-05T11:21:03.777275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:03.777275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11403","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JqS2f6IXVWpjZvBApmEZS+6QqosoTy9FysMJXJm4FuSo8XT/SMPqyhVcjH4dV031snLj8rHWykaMwpq0Lh7kDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:00:17.113211Z"},"content_sha256":"282e03caaa6ea473c49e380a589e64fe32f836f5eefa988774994e0387a08705","schema_version":"1.0","event_id":"sha256:282e03caaa6ea473c49e380a589e64fe32f836f5eefa988774994e0387a08705"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WE2PJXJAZOLGZKWXMIWWL3SMAO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A correlation-permutation approach for speech-music encoders model merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Eng Siong Chng, Fabian Ritter-Gutierrez, Hung-yi Lee, Jeremy H.M Wong, Nancy F. Chen, Yi-Cheng Lin","submitted_at":"2025-06-13T02:04:33Z","abstract_excerpt":"Creating a unified speech and music model requires expensive pre-training. Model merging can instead create an unified audio model with minimal computational expense. However, direct merging is challenging when the models are not aligned in the weight space. Motivated by Git Re-Basin, we introduce a correlation-permutation approach that aligns a music encoder's internal layers with a speech encoder. We extend previous work to the case of merging transformer layers. The method computes a permutation matrix that maximizes the model's features-wise cross-correlations layer by layer, enabling effe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11403","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/2506.11403/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":"2026-07-05T11:21:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"utpNfewjUrixvroI1iAG50ccWX08VzIbCvorm2onbNPFNbg56rht0QJF8zFlnf5zNgaf9BgbX9HF+qToumhbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:00:17.113798Z"},"content_sha256":"08d38fd7eac51a6c7896bec4b5769527ba9f532a30f27a1d0a8c87d5805b392b","schema_version":"1.0","event_id":"sha256:08d38fd7eac51a6c7896bec4b5769527ba9f532a30f27a1d0a8c87d5805b392b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WE2PJXJAZOLGZKWXMIWWL3SMAO/bundle.json","state_url":"https://pith.science/pith/WE2PJXJAZOLGZKWXMIWWL3SMAO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WE2PJXJAZOLGZKWXMIWWL3SMAO/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":"2026-08-23T21:00:17Z","links":{"resolver":"https://pith.science/pith/WE2PJXJAZOLGZKWXMIWWL3SMAO","bundle":"https://pith.science/pith/WE2PJXJAZOLGZKWXMIWWL3SMAO/bundle.json","state":"https://pith.science/pith/WE2PJXJAZOLGZKWXMIWWL3SMAO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WE2PJXJAZOLGZKWXMIWWL3SMAO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WE2PJXJAZOLGZKWXMIWWL3SMAO","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":"404f8a8e12200346cb2584b60cdb5371caa26df7cc9878d6abfd393196d8f6e1","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T02:04:33Z","title_canon_sha256":"d8e00d8ddcf0d3e8d3d911fdb3a2d19e375016a60d99f453f8ca59849bed46fc"},"schema_version":"1.0","source":{"id":"2506.11403","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11403","created_at":"2026-07-05T11:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11403v1","created_at":"2026-07-05T11:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11403","created_at":"2026-07-05T11:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"WE2PJXJAZOLG","created_at":"2026-07-05T11:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"WE2PJXJAZOLGZKWX","created_at":"2026-07-05T11:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"WE2PJXJA","created_at":"2026-07-05T11:21:03Z"}],"graph_snapshots":[{"event_id":"sha256:08d38fd7eac51a6c7896bec4b5769527ba9f532a30f27a1d0a8c87d5805b392b","target":"graph","created_at":"2026-07-05T11:21:03Z","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/2506.11403/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Creating a unified speech and music model requires expensive pre-training. Model merging can instead create an unified audio model with minimal computational expense. However, direct merging is challenging when the models are not aligned in the weight space. Motivated by Git Re-Basin, we introduce a correlation-permutation approach that aligns a music encoder's internal layers with a speech encoder. We extend previous work to the case of merging transformer layers. The method computes a permutation matrix that maximizes the model's features-wise cross-correlations layer by layer, enabling effe","authors_text":"Eng Siong Chng, Fabian Ritter-Gutierrez, Hung-yi Lee, Jeremy H.M Wong, Nancy F. Chen, Yi-Cheng Lin","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T02:04:33Z","title":"A correlation-permutation approach for speech-music encoders model merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11403","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":"sha256:282e03caaa6ea473c49e380a589e64fe32f836f5eefa988774994e0387a08705","target":"record","created_at":"2026-07-05T11:21:03Z","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":"404f8a8e12200346cb2584b60cdb5371caa26df7cc9878d6abfd393196d8f6e1","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T02:04:33Z","title_canon_sha256":"d8e00d8ddcf0d3e8d3d911fdb3a2d19e375016a60d99f453f8ca59849bed46fc"},"schema_version":"1.0","source":{"id":"2506.11403","kind":"arxiv","version":1}},"canonical_sha256":"b134f4dd20cb966caad7622d65ee4c039edceee9012e79af60c356910b404e38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b134f4dd20cb966caad7622d65ee4c039edceee9012e79af60c356910b404e38","first_computed_at":"2026-07-05T11:21:03.777275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:03.777275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1KqKvzAmD0YDWYweV9XozAeu/UEfOJKYWepYsDam+4MooTD6YJ7UntRo6U2RG+8aNR+67O4Umv4f1ZiJTMrvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:03.777747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11403","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:282e03caaa6ea473c49e380a589e64fe32f836f5eefa988774994e0387a08705","sha256:08d38fd7eac51a6c7896bec4b5769527ba9f532a30f27a1d0a8c87d5805b392b"],"state_sha256":"7696caa926bb0f3c131f4f4238d58d1d3b9381111c5111bb4d689302e24c4386"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KgGQJ3UxKHJbULHpeW5wtCC4Zmxj+6hpNjo/cPgSpUPM3HkYZH5/A3uCGi/E122DPTMMfPiKV9TD3QSIoOQiBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T21:00:17.119713Z","bundle_sha256":"b0f34911284bc0ec275956bed902f0b12e5ec2df92ca3fb8ff84bcb900812b62"}}