{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN","short_pith_number":"pith:JMQ4OR4Y","schema_version":"1.0","canonical_sha256":"4b21c74798e0b3e8dc60cc6d40e7ce5b407a5cb7668204b4c478c6de5c3429ae","source":{"kind":"arxiv","id":"2410.04906","version":1},"attestation_state":"computed","paper":{"title":"Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Gennaro Vessio, Giovanna Castellano, Ivan Rinaldi, Nicola Fanelli","submitted_at":"2024-10-07T10:48:08Z","abstract_excerpt":"Artificial Intelligence and generative models have revolutionized music creation, with many models leveraging textual or visual prompts for guidance. However, existing image-to-music models are limited to simple images, lacking the capability to generate music from complex digitized artworks. To address this gap, we introduce $\\mathcal{A}\\textit{rt2}\\mathcal{M}\\textit{us}$, a novel model designed to create music from digitized artworks or text inputs. $\\mathcal{A}\\textit{rt2}\\mathcal{M}\\textit{us}$ extends the AudioLDM~2 architecture, a text-to-audio model, and employs our newly curated datase"},"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":"2410.04906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2024-10-07T10:48:08Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"5f535dd8df43a68ad82701aaec3d17f7fedb83106533e1d0d9b770118689e17d","abstract_canon_sha256":"a46df8c517ed6aecb00e0cb054f57f1ff34063652211903301619157c11d4e6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:29.412858Z","signature_b64":"OtAxaRqJEo1ZuI2cCz8X5l0lGkl2xokPWZxLU/tO8HIRzT2JjvnfXX+NmjMv7K5QUmBekZFqw4dlyOdkFhF2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b21c74798e0b3e8dc60cc6d40e7ce5b407a5cb7668204b4c478c6de5c3429ae","last_reissued_at":"2026-07-05T11:45:29.412342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:29.412342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Gennaro Vessio, Giovanna Castellano, Ivan Rinaldi, Nicola Fanelli","submitted_at":"2024-10-07T10:48:08Z","abstract_excerpt":"Artificial Intelligence and generative models have revolutionized music creation, with many models leveraging textual or visual prompts for guidance. However, existing image-to-music models are limited to simple images, lacking the capability to generate music from complex digitized artworks. To address this gap, we introduce $\\mathcal{A}\\textit{rt2}\\mathcal{M}\\textit{us}$, a novel model designed to create music from digitized artworks or text inputs. $\\mathcal{A}\\textit{rt2}\\mathcal{M}\\textit{us}$ extends the AudioLDM~2 architecture, a text-to-audio model, and employs our newly curated datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04906","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/2410.04906/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":"2410.04906","created_at":"2026-07-05T11:45:29.412405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04906v1","created_at":"2026-07-05T11:45:29.412405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04906","created_at":"2026-07-05T11:45:29.412405+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMQ4OR4Y4CZ6","created_at":"2026-07-05T11:45:29.412405+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMQ4OR4Y4CZ6RXDA","created_at":"2026-07-05T11:45:29.412405+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMQ4OR4Y","created_at":"2026-07-05T11:45:29.412405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13509","citing_title":"Visualizing the Invisible: A Generative AR System for Intuitive Multi-Modal Sensor Data Presentation","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN","json":"https://pith.science/pith/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN.json","graph_json":"https://pith.science/api/pith-number/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN/graph.json","events_json":"https://pith.science/api/pith-number/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN/events.json","paper":"https://pith.science/paper/JMQ4OR4Y"},"agent_actions":{"view_html":"https://pith.science/pith/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN","download_json":"https://pith.science/pith/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN.json","view_paper":"https://pith.science/paper/JMQ4OR4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04906&json=true","fetch_graph":"https://pith.science/api/pith-number/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN/graph.json","fetch_events":"https://pith.science/api/pith-number/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN/action/storage_attestation","attest_author":"https://pith.science/pith/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN/action/author_attestation","sign_citation":"https://pith.science/pith/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN/action/citation_signature","submit_replication":"https://pith.science/pith/JMQ4OR4Y4CZ6RXDAZRWUBZ6OLN/action/replication_record"}},"created_at":"2026-07-05T11:45:29.412405+00:00","updated_at":"2026-07-05T11:45:29.412405+00:00"}