{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "agostinelli-et-al-musiclm-text-conditioning-2023", "title": "Agostinelli et al.: MusicLM text-conditioned hierarchical music generation", "summary": "Connected joint music-text representations to hierarchical audio-token generation, allowing text/melody conditioning with mostly audio-only model training and releasing the MusicCaps evaluation resource.", "boundary": "Inherits AudioLM hierarchy and MuLan representation learning rather than inventing either. Original method/resource bundle is one contribution; subjective quality and multi-minute coherence are source-reported and not guarantees.", "area": "Text-conditioned generative music", "topic": "Artificial intelligence", "year": 2023, "lane": "HUMAN", "result": "EMPIRICAL", "package_id": "agostinelli-et-al-musiclm-text-conditioning-2023", "target": { "record_id": "urn:uuid:336ed518-64e6-4d79-a6c8-f9981ab136ce", "version": 1, "content_hash": "sha256:815fd58d110651e224c727c2af77c14c4ce707e093fcf34b3410810ad4ac7bd1" }, "humans": [ "Andrea Agostinelli", "Timo I. Denk", "Zalán Borsos", "Jesse Engel", "Mauro Verzetti", "Antoine Caillon", "Qingqing Huang", "Aren Jansen", "Adam Roberts", "Marco Tagliasacchi", "Matt Sharifi", "Neil Zeghidour", "Christian Frank" ], "authors_complete": true, "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.", "agents": [], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "cur20261015-arxiv-2301-11325v1", "title": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" }, { "id": "cur20261015-support-agostinelli-et-al-musiclm-text-conditioning-2023", "title": "Agostinelli et al.: MusicLM text-conditioned hierarchical music generation — institutional/author source", "url": "https://google-research.github.io/seanet/musiclm/examples/" } ], "points": "125000", "published_grade": { "id": "agostinelli-et-al-musiclm-text-conditioning-2023", "entry_id": "agostinelli-et-al-musiclm-text-conditioning-2023", "band": "A", "modifier": null, "target": { "record_id": "urn:uuid:336ed518-64e6-4d79-a6c8-f9981ab136ce", "version": 1, "content_hash": "sha256:815fd58d110651e224c727c2af77c14c4ce707e093fcf34b3410810ad4ac7bd1" }, "what_changed": "Connected joint music-text representations to hierarchical audio-token generation, allowing text/melody conditioning with mostly audio-only model training and releasing the MusicCaps evaluation resource.", "scope": "Connected joint music-text representations to hierarchical audio-token generation, allowing text/melody conditioning with mostly audio-only model training and releasing the MusicCaps evaluation resource. Inherits AudioLM hierarchy and MuLan representation learning rather than inventing either. Original method/resource bundle is one contribution; subjective quality and multi-minute coherence are source-reported and not guarantees.", "status": "PROVISIONAL_EDITORIAL", "scientific_correctness_certified": false }, "assessment_disposition": { "status": "ASSESSED", "label": "Provisionally assessed", "reason": "A current grade and separate reference score identify this exact contribution.", "target": { "record_id": "urn:uuid:336ed518-64e6-4d79-a6c8-f9981ab136ce", "version": 1, "content_hash": "sha256:815fd58d110651e224c727c2af77c14c4ce707e093fcf34b3410810ad4ac7bd1" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": null, "published_at": "2026-10-16T00:00:00Z", "publisher": { "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33", "role": "WRS_EDITORIAL_PUBLICATION" }, "record": { "contributors": [ { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Andrea Agostinelli", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Timo I. Denk", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Zalán Borsos", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jesse Engel", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Mauro Verzetti", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Antoine Caillon", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Qingqing Huang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Aren Jansen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Adam Roberts", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Marco Tagliasacchi", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Matt Sharifi", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Neil Zeghidour", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Christian Frank", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-1", "kind": "source_reference", "source": { "citation": "Agostinelli et al.: MusicLM text-conditioned hierarchical music generation — institutional/author source", "url": "https://google-research.github.io/seanet/musiclm/examples/" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Inherits AudioLM hierarchy and MuLan representation learning rather than inventing either. Original method/resource bundle is one contribution; subjective quality and multi-minute coherence are source-reported and not guarantees.", "domain": "Text-conditioned generative music" }, "sources": [ { "citation": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1" }, { "citation": "Agostinelli et al.: MusicLM text-conditioned hierarchical music generation — institutional/author source", "url": "https://google-research.github.io/seanet/musiclm/examples/" } ], "statement": "# Agostinelli et al.: MusicLM text-conditioned hierarchical music generation\n\nConnected joint music-text representations to hierarchical audio-token generation, allowing text/melody conditioning with mostly audio-only model training and releasing the MusicCaps evaluation resource.\n\n## Scientific scope\n\nInherits AudioLM hierarchy and MuLan representation learning rather than inventing either. Original method/resource bundle is one contribution; subjective quality and multi-minute coherence are source-reported and not guarantees.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nAndrea Agostinelli; Timo I. Denk; Zalán Borsos; Jesse Engel; Mauro Verzetti; Antoine Caillon; Qingqing Huang; Aren Jansen; Adam Roberts; Marco Tagliasacchi; Matt Sharifi; Neil Zeghidour; Christian Frank\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [MusicLM: Generating Music From Text](https://arxiv.org/abs/2301.11325v1)\n- [Agostinelli et al.: MusicLM text-conditioned hierarchical music generation — institutional/author source](https://google-research.github.io/seanet/musiclm/examples/)\n", "summary": "Connected joint music-text representations to hierarchical audio-token generation, allowing text/melody conditioning with mostly audio-only model training and releasing the MusicCaps evaluation resource.", "title": "Agostinelli et al.: MusicLM text-conditioned hierarchical music generation" }, "record_id": "urn:uuid:336ed518-64e6-4d79-a6c8-f9981ab136ce", "version": 1, "source_ref": { "record_id": "urn:uuid:336ed518-64e6-4d79-a6c8-f9981ab136ce", "version": 1, "content_hash": "sha256:815fd58d110651e224c727c2af77c14c4ce707e093fcf34b3410810ad4ac7bd1" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:2c02a9c09dfc118ae5bfe5c05f2a5d42f974af86560e038f91b73e93cce31304" }, "target": { "record_id": "urn:uuid:336ed518-64e6-4d79-a6c8-f9981ab136ce", "version": 1, "content_hash": "sha256:815fd58d110651e224c727c2af77c14c4ce707e093fcf34b3410810ad4ac7bd1" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "agostinelli-et-al-musiclm-text-conditioning-2023", "entry_id": "agostinelli-et-al-musiclm-text-conditioning-2023", "revision": 1, "title": "Agostinelli et al.: MusicLM text-conditioned hierarchical music generation", "context": "Text-conditioned generative music", "track": "Human-designed research method or resource", "band": "A", "modifier": null, "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-16", "evidence_cutoff": "2026-10-16", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Connected joint music-text representations to hierarchical audio-token generation, allowing text/melody conditioning with mostly audio-only model training and releasing the MusicCaps evaluation resource.", "scope": "Connected joint music-text representations to hierarchical audio-token generation, allowing text/melody conditioning with mostly audio-only model training and releasing the MusicCaps evaluation resource. Inherits AudioLM hierarchy and MuLan representation learning rather than inventing either. Original method/resource bundle is one contribution; subjective quality and multi-minute coherence are source-reported and not guarantees.", "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits AudioLM hierarchy and MuLan representation learning rather than inventing either. Original method/resource bundle is one contribution; subjective quality and multi-minute coherence are source-reported and not guarantees.", "references": [ { "title": "MusicLM: Generating Music From Text", "url": "https://arxiv.org/abs/2301.11325v1", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." }, { "title": "Agostinelli et al.: MusicLM text-conditioned hierarchical music generation — institutional/author source", "url": "https://google-research.github.io/seanet/musiclm/examples/", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." } ], "roles": [ { "who": "Source-listed authors and technical contributors", "credit": "SCIENCE", "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities." } ], "target": { "record_id": "urn:uuid:336ed518-64e6-4d79-a6c8-f9981ab136ce", "version": 1, "content_hash": "sha256:815fd58d110651e224c727c2af77c14c4ce707e093fcf34b3410810ad4ac7bd1" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "125000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }