{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZS3H3R4ACSIVINPES7ARJRAC3E","short_pith_number":"pith:ZS3H3R4A","canonical_record":{"source":{"id":"2506.05899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-06T09:12:51Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"7045b017c7c73aded621bc5d0f8b0c5a11312c1b7600273c44f5b2a2fa53afcb","abstract_canon_sha256":"bed39547298de304d5d0fe39c943ab06c478566d1c73162bc7753a97f10cfb77"},"schema_version":"1.0"},"canonical_sha256":"ccb67dc78014915435e497c114c402d90920bf524e2f156e12e6281d27af9b1b","source":{"kind":"arxiv","id":"2506.05899","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05899","created_at":"2026-07-05T11:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05899v1","created_at":"2026-07-05T11:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05899","created_at":"2026-07-05T11:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZS3H3R4ACSIV","created_at":"2026-07-05T11:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZS3H3R4ACSIVINPE","created_at":"2026-07-05T11:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZS3H3R4A","created_at":"2026-07-05T11:17:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZS3H3R4ACSIVINPES7ARJRAC3E","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-06T09:12:51Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"7045b017c7c73aded621bc5d0f8b0c5a11312c1b7600273c44f5b2a2fa53afcb","abstract_canon_sha256":"bed39547298de304d5d0fe39c943ab06c478566d1c73162bc7753a97f10cfb77"},"schema_version":"1.0"},"canonical_sha256":"ccb67dc78014915435e497c114c402d90920bf524e2f156e12e6281d27af9b1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:12.374545Z","signature_b64":"MEc1p5PdMogIJxZnViK5rXl2KPGfx5ECIoZOVungGdTAdr4H7ZHnZ0DCr1R+6w2v1gzF0S7RzWzfiZSIKf8gCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccb67dc78014915435e497c114c402d90920bf524e2f156e12e6281d27af9b1b","last_reissued_at":"2026-07-05T11:17:12.373959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:12.373959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05899","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":"2026-07-05T11:17:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F/WqCGpBOcU08NPu62Pkf7RhEi4dPUzv74eVxIoIpWu0GtNyv5tr+jkksZRJ2gk598vt/gU74UykxGug5TWABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:10:21.400901Z"},"content_sha256":"d5e8a9f398169df9ad2de5fe6a579ab0594b5c06266349272c66db8b603f290f","schema_version":"1.0","event_id":"sha256:d5e8a9f398169df9ad2de5fe6a579ab0594b5c06266349272c66db8b603f290f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZS3H3R4ACSIVINPES7ARJRAC3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jakaria Islam Emon, Kazi Tamanna Alam, Md. Abu Salek","submitted_at":"2025-06-06T09:12:51Z","abstract_excerpt":"Mean Opinion Score (MOS) prediction for text to music systems requires evaluating both overall musical quality and text prompt alignment. This paper introduces WhisQ, a multimodal architecture that addresses this dual-assessment challenge through sequence level co-attention and optimal transport regularization. WhisQ employs the Whisper Base pretrained model for temporal audio encoding and Qwen 3, a 0.6B Small Language Model (SLM), for text encoding, with both maintaining sequence structure for fine grained cross-modal modeling. The architecture features specialized prediction pathways: OMQ is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05899","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/2506.05899/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":"2026-07-05T11:17:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"omnpj+o+7qOBUYYVV405RvFUmtj8l/M5bGYkTRFTJf0/6JPwiere84GPARKeL3Rnb9wXCwYiyG/0tJ/oK/0ZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:10:21.401448Z"},"content_sha256":"01a10ac49f7c15baaf99807a5bb2800ae66eb82b5874a48f02b90af3d25803cc","schema_version":"1.0","event_id":"sha256:01a10ac49f7c15baaf99807a5bb2800ae66eb82b5874a48f02b90af3d25803cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZS3H3R4ACSIVINPES7ARJRAC3E/bundle.json","state_url":"https://pith.science/pith/ZS3H3R4ACSIVINPES7ARJRAC3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZS3H3R4ACSIVINPES7ARJRAC3E/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":"2026-08-08T04:10:21Z","links":{"resolver":"https://pith.science/pith/ZS3H3R4ACSIVINPES7ARJRAC3E","bundle":"https://pith.science/pith/ZS3H3R4ACSIVINPES7ARJRAC3E/bundle.json","state":"https://pith.science/pith/ZS3H3R4ACSIVINPES7ARJRAC3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZS3H3R4ACSIVINPES7ARJRAC3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZS3H3R4ACSIVINPES7ARJRAC3E","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":"bed39547298de304d5d0fe39c943ab06c478566d1c73162bc7753a97f10cfb77","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-06T09:12:51Z","title_canon_sha256":"7045b017c7c73aded621bc5d0f8b0c5a11312c1b7600273c44f5b2a2fa53afcb"},"schema_version":"1.0","source":{"id":"2506.05899","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05899","created_at":"2026-07-05T11:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05899v1","created_at":"2026-07-05T11:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05899","created_at":"2026-07-05T11:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZS3H3R4ACSIV","created_at":"2026-07-05T11:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZS3H3R4ACSIVINPE","created_at":"2026-07-05T11:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZS3H3R4A","created_at":"2026-07-05T11:17:12Z"}],"graph_snapshots":[{"event_id":"sha256:01a10ac49f7c15baaf99807a5bb2800ae66eb82b5874a48f02b90af3d25803cc","target":"graph","created_at":"2026-07-05T11:17:12Z","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/2506.05899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mean Opinion Score (MOS) prediction for text to music systems requires evaluating both overall musical quality and text prompt alignment. This paper introduces WhisQ, a multimodal architecture that addresses this dual-assessment challenge through sequence level co-attention and optimal transport regularization. WhisQ employs the Whisper Base pretrained model for temporal audio encoding and Qwen 3, a 0.6B Small Language Model (SLM), for text encoding, with both maintaining sequence structure for fine grained cross-modal modeling. The architecture features specialized prediction pathways: OMQ is","authors_text":"Jakaria Islam Emon, Kazi Tamanna Alam, Md. Abu Salek","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-06T09:12:51Z","title":"WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05899","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:d5e8a9f398169df9ad2de5fe6a579ab0594b5c06266349272c66db8b603f290f","target":"record","created_at":"2026-07-05T11:17:12Z","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":"bed39547298de304d5d0fe39c943ab06c478566d1c73162bc7753a97f10cfb77","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-06T09:12:51Z","title_canon_sha256":"7045b017c7c73aded621bc5d0f8b0c5a11312c1b7600273c44f5b2a2fa53afcb"},"schema_version":"1.0","source":{"id":"2506.05899","kind":"arxiv","version":1}},"canonical_sha256":"ccb67dc78014915435e497c114c402d90920bf524e2f156e12e6281d27af9b1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccb67dc78014915435e497c114c402d90920bf524e2f156e12e6281d27af9b1b","first_computed_at":"2026-07-05T11:17:12.373959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:12.373959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MEc1p5PdMogIJxZnViK5rXl2KPGfx5ECIoZOVungGdTAdr4H7ZHnZ0DCr1R+6w2v1gzF0S7RzWzfiZSIKf8gCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:12.374545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05899","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5e8a9f398169df9ad2de5fe6a579ab0594b5c06266349272c66db8b603f290f","sha256:01a10ac49f7c15baaf99807a5bb2800ae66eb82b5874a48f02b90af3d25803cc"],"state_sha256":"c7cf35773264c596c7017e9a28f05400a8083d36084f92d4fa94a3a53cd2048b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hvCWJJjh4dhJ+zbQ+VujIy4oF4IYAAkVFZBuxbq+EnkCyVVNXcoEtCXj9eAqdlf1058fIj+mwfisioMFPSZCCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:10:21.406309Z","bundle_sha256":"07833f61f226612807f08424ed33a4d88776967dcaa43a35824379b94a169c96"}}