{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GJOG44Y5FGL5FYGA7HJVW6VI7U","short_pith_number":"pith:GJOG44Y5","schema_version":"1.0","canonical_sha256":"325c6e731d2997d2e0c0f9d35b7aa8fd1cc850e0253d5b22a62e92779444b11c","source":{"kind":"arxiv","id":"2506.21298","version":2},"attestation_state":"computed","paper":{"title":"Exploring Adapter Design Tradeoffs for Low Resource Music Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Atharva Mehta, Monojit Choudhury, Shivam Chauhan","submitted_at":"2025-06-26T14:18:39Z","abstract_excerpt":"Fine-tuning large-scale music generation models, such as MusicGen and Mustango, is a computationally expensive process, often requiring updates to billions of parameters and, therefore, significant hardware resources. Parameter-Efficient Fine-Tuning (PEFT) techniques, particularly adapter-based methods, have emerged as a promising alternative, enabling adaptation with minimal trainable parameters while preserving model performance. However, the design choices for adapters, including their architecture, placement, and size, are numerous, and it is unclear which of these combinations would produ"},"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":"2506.21298","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-26T14:18:39Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"881e7f1e619621f73ca2f23165cd34bd7df49f51dc338a8bb8cba10f7aed5685","abstract_canon_sha256":"4724dfdc417b9403daa92862ce625f933590119849b9dcf9060159b9418c70a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:31.000127Z","signature_b64":"bSrczPlxts5gnpLlVdc87j0UXnTsAjfkmqa+fYvL22pdoC5wUlzuvYFQup1lF2KPmBjh7T1xIOVRIkaTfDvqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"325c6e731d2997d2e0c0f9d35b7aa8fd1cc850e0253d5b22a62e92779444b11c","last_reissued_at":"2026-07-05T11:51:30.999658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:30.999658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Adapter Design Tradeoffs for Low Resource Music Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Atharva Mehta, Monojit Choudhury, Shivam Chauhan","submitted_at":"2025-06-26T14:18:39Z","abstract_excerpt":"Fine-tuning large-scale music generation models, such as MusicGen and Mustango, is a computationally expensive process, often requiring updates to billions of parameters and, therefore, significant hardware resources. Parameter-Efficient Fine-Tuning (PEFT) techniques, particularly adapter-based methods, have emerged as a promising alternative, enabling adaptation with minimal trainable parameters while preserving model performance. However, the design choices for adapters, including their architecture, placement, and size, are numerous, and it is unclear which of these combinations would produ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21298","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/2506.21298/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":"2506.21298","created_at":"2026-07-05T11:51:30.999715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21298v2","created_at":"2026-07-05T11:51:30.999715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21298","created_at":"2026-07-05T11:51:30.999715+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJOG44Y5FGL5","created_at":"2026-07-05T11:51:30.999715+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJOG44Y5FGL5FYGA","created_at":"2026-07-05T11:51:30.999715+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJOG44Y5","created_at":"2026-07-05T11:51:30.999715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14765","citing_title":"Persian MusicGen: A Large-Scale Dataset and Culturally-Aware Generative Model for Persian Music","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJOG44Y5FGL5FYGA7HJVW6VI7U","json":"https://pith.science/pith/GJOG44Y5FGL5FYGA7HJVW6VI7U.json","graph_json":"https://pith.science/api/pith-number/GJOG44Y5FGL5FYGA7HJVW6VI7U/graph.json","events_json":"https://pith.science/api/pith-number/GJOG44Y5FGL5FYGA7HJVW6VI7U/events.json","paper":"https://pith.science/paper/GJOG44Y5"},"agent_actions":{"view_html":"https://pith.science/pith/GJOG44Y5FGL5FYGA7HJVW6VI7U","download_json":"https://pith.science/pith/GJOG44Y5FGL5FYGA7HJVW6VI7U.json","view_paper":"https://pith.science/paper/GJOG44Y5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21298&json=true","fetch_graph":"https://pith.science/api/pith-number/GJOG44Y5FGL5FYGA7HJVW6VI7U/graph.json","fetch_events":"https://pith.science/api/pith-number/GJOG44Y5FGL5FYGA7HJVW6VI7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJOG44Y5FGL5FYGA7HJVW6VI7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJOG44Y5FGL5FYGA7HJVW6VI7U/action/storage_attestation","attest_author":"https://pith.science/pith/GJOG44Y5FGL5FYGA7HJVW6VI7U/action/author_attestation","sign_citation":"https://pith.science/pith/GJOG44Y5FGL5FYGA7HJVW6VI7U/action/citation_signature","submit_replication":"https://pith.science/pith/GJOG44Y5FGL5FYGA7HJVW6VI7U/action/replication_record"}},"created_at":"2026-07-05T11:51:30.999715+00:00","updated_at":"2026-07-05T11:51:30.999715+00:00"}