{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YL6HVVUW75DGJOREIQ5SBFUCHH","short_pith_number":"pith:YL6HVVUW","schema_version":"1.0","canonical_sha256":"c2fc7ad696ff4664ba24443b20968239cc28e017070528db3ec3a9df048dba5e","source":{"kind":"arxiv","id":"2506.17886","version":2},"attestation_state":"computed","paper":{"title":"GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Elio Quinton, Gy\\\"orgy Fazekas, Julien Guinot","submitted_at":"2025-06-22T03:30:27Z","abstract_excerpt":"Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area. Less attention has been given to making these systems controllable and interactive for users. In text-music retrieval, the ambiguity of freeform language creates a many-to-many mapping, often resulting in inflexible or unsatisfying results.\n  We introduce Generative Diffusion Retriever (GDR), a novel framework that leverages diffusion models to generate queries in a retrieval-optimized latent space. This enables con"},"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":"2506.17886","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-22T03:30:27Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fcc61f981acdd2cc5a0942141619ec418d830dfb550ad7939a7281ec65e721b7","abstract_canon_sha256":"6909cbe626f93456d158b3bf5643606649741bc0f1d89a99c1ea8d3ea4e2891e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:32.917542Z","signature_b64":"cWW2j2oY4NIISLlyOzM7s49mgaNcfqjGItRjl7jSq1+7nwnhvsiQAITcg12wvsLs+Wa2x/Dm654KKypc4XT9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2fc7ad696ff4664ba24443b20968239cc28e017070528db3ec3a9df048dba5e","last_reissued_at":"2026-07-05T11:26:32.916980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:32.916980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Elio Quinton, Gy\\\"orgy Fazekas, Julien Guinot","submitted_at":"2025-06-22T03:30:27Z","abstract_excerpt":"Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area. Less attention has been given to making these systems controllable and interactive for users. In text-music retrieval, the ambiguity of freeform language creates a many-to-many mapping, often resulting in inflexible or unsatisfying results.\n  We introduce Generative Diffusion Retriever (GDR), a novel framework that leverages diffusion models to generate queries in a retrieval-optimized latent space. This enables con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17886","kind":"arxiv","version":2},"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/2506.17886/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":"2506.17886","created_at":"2026-07-05T11:26:32.917050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17886v2","created_at":"2026-07-05T11:26:32.917050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17886","created_at":"2026-07-05T11:26:32.917050+00:00"},{"alias_kind":"pith_short_12","alias_value":"YL6HVVUW75DG","created_at":"2026-07-05T11:26:32.917050+00:00"},{"alias_kind":"pith_short_16","alias_value":"YL6HVVUW75DGJORE","created_at":"2026-07-05T11:26:32.917050+00:00"},{"alias_kind":"pith_short_8","alias_value":"YL6HVVUW","created_at":"2026-07-05T11:26:32.917050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.15423","citing_title":"GaiaFlow: Semantic-Guided Diffusion Tuning for Carbon-Frugal Search","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YL6HVVUW75DGJOREIQ5SBFUCHH","json":"https://pith.science/pith/YL6HVVUW75DGJOREIQ5SBFUCHH.json","graph_json":"https://pith.science/api/pith-number/YL6HVVUW75DGJOREIQ5SBFUCHH/graph.json","events_json":"https://pith.science/api/pith-number/YL6HVVUW75DGJOREIQ5SBFUCHH/events.json","paper":"https://pith.science/paper/YL6HVVUW"},"agent_actions":{"view_html":"https://pith.science/pith/YL6HVVUW75DGJOREIQ5SBFUCHH","download_json":"https://pith.science/pith/YL6HVVUW75DGJOREIQ5SBFUCHH.json","view_paper":"https://pith.science/paper/YL6HVVUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17886&json=true","fetch_graph":"https://pith.science/api/pith-number/YL6HVVUW75DGJOREIQ5SBFUCHH/graph.json","fetch_events":"https://pith.science/api/pith-number/YL6HVVUW75DGJOREIQ5SBFUCHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YL6HVVUW75DGJOREIQ5SBFUCHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YL6HVVUW75DGJOREIQ5SBFUCHH/action/storage_attestation","attest_author":"https://pith.science/pith/YL6HVVUW75DGJOREIQ5SBFUCHH/action/author_attestation","sign_citation":"https://pith.science/pith/YL6HVVUW75DGJOREIQ5SBFUCHH/action/citation_signature","submit_replication":"https://pith.science/pith/YL6HVVUW75DGJOREIQ5SBFUCHH/action/replication_record"}},"created_at":"2026-07-05T11:26:32.917050+00:00","updated_at":"2026-07-05T11:26:32.917050+00:00"}