{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JLZVCZETFERYNQQVBX2A4NQWUE","short_pith_number":"pith:JLZVCZET","schema_version":"1.0","canonical_sha256":"4af3516493292386c2150df40e3616a106b8b06f55c665290cdf8791d10a8675","source":{"kind":"arxiv","id":"2506.08570","version":3},"attestation_state":"computed","paper":{"title":"Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Felix Kreuk, Or Tal, Yossi Adi","submitted_at":"2025-06-10T08:37:45Z","abstract_excerpt":"Recent progress in text-to-music generation has enabled models to synthesize high-quality musical segments, full compositions, and even respond to fine-grained control signals, e.g. chord progressions. State-of-the-art (SOTA) systems differ significantly in many dimensions, such as training datasets, modeling paradigms, and architectural choices. This diversity complicates efforts to evaluate models fairly and identify which design choices influence performance the most. While factors like data and architecture are important, in this study we focus exclusively on the modeling paradigm. We cond"},"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":"2506.08570","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-10T08:37:45Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"ad5bf9938f9dbe9b73bc6662c41bba9512b48cacdfa2c16d9a7c7246f7861796","abstract_canon_sha256":"72a0c40488fe25f404307b1849cf0e7f1a9c2da29b39a079a0a18bfb1d39549f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:36.235881Z","signature_b64":"XLTTWXzIRdAFhNNupGuXSQm2Z6pB/C8I8/n8ek3N6XSl/37vBS91QM9HNgJcgPx5enxcS45nAXKpfss2Ep05AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4af3516493292386c2150df40e3616a106b8b06f55c665290cdf8791d10a8675","last_reissued_at":"2026-07-05T12:04:36.235321Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:36.235321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Felix Kreuk, Or Tal, Yossi Adi","submitted_at":"2025-06-10T08:37:45Z","abstract_excerpt":"Recent progress in text-to-music generation has enabled models to synthesize high-quality musical segments, full compositions, and even respond to fine-grained control signals, e.g. chord progressions. State-of-the-art (SOTA) systems differ significantly in many dimensions, such as training datasets, modeling paradigms, and architectural choices. This diversity complicates efforts to evaluate models fairly and identify which design choices influence performance the most. While factors like data and architecture are important, in this study we focus exclusively on the modeling paradigm. We cond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08570","kind":"arxiv","version":3},"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/2506.08570/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":"2506.08570","created_at":"2026-07-05T12:04:36.235393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08570v3","created_at":"2026-07-05T12:04:36.235393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08570","created_at":"2026-07-05T12:04:36.235393+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLZVCZETFERY","created_at":"2026-07-05T12:04:36.235393+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLZVCZETFERYNQQV","created_at":"2026-07-05T12:04:36.235393+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLZVCZET","created_at":"2026-07-05T12:04:36.235393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22717","citing_title":"Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLZVCZETFERYNQQVBX2A4NQWUE","json":"https://pith.science/pith/JLZVCZETFERYNQQVBX2A4NQWUE.json","graph_json":"https://pith.science/api/pith-number/JLZVCZETFERYNQQVBX2A4NQWUE/graph.json","events_json":"https://pith.science/api/pith-number/JLZVCZETFERYNQQVBX2A4NQWUE/events.json","paper":"https://pith.science/paper/JLZVCZET"},"agent_actions":{"view_html":"https://pith.science/pith/JLZVCZETFERYNQQVBX2A4NQWUE","download_json":"https://pith.science/pith/JLZVCZETFERYNQQVBX2A4NQWUE.json","view_paper":"https://pith.science/paper/JLZVCZET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08570&json=true","fetch_graph":"https://pith.science/api/pith-number/JLZVCZETFERYNQQVBX2A4NQWUE/graph.json","fetch_events":"https://pith.science/api/pith-number/JLZVCZETFERYNQQVBX2A4NQWUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLZVCZETFERYNQQVBX2A4NQWUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLZVCZETFERYNQQVBX2A4NQWUE/action/storage_attestation","attest_author":"https://pith.science/pith/JLZVCZETFERYNQQVBX2A4NQWUE/action/author_attestation","sign_citation":"https://pith.science/pith/JLZVCZETFERYNQQVBX2A4NQWUE/action/citation_signature","submit_replication":"https://pith.science/pith/JLZVCZETFERYNQQVBX2A4NQWUE/action/replication_record"}},"created_at":"2026-07-05T12:04:36.235393+00:00","updated_at":"2026-07-05T12:04:36.235393+00:00"}