{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EYSHON2YMCWBVSD5UBPNYRRUGV","short_pith_number":"pith:EYSHON2Y","schema_version":"1.0","canonical_sha256":"262477375860ac1ac87da05edc4634354c9e85a272e18169dd38599140f7f853","source":{"kind":"arxiv","id":"2606.07387","version":1},"attestation_state":"computed","paper":{"title":"Making the Most of Limited Data: Score-Aware Training for Text-to-Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chih-Pin Tan, Tzu-Hung Huang, Yun-Chen Cheng","submitted_at":"2026-06-05T15:24:36Z","abstract_excerpt":"State-of-the-art text-to-music generation systems rely on massive proprietary datasets and industrial-scale compute, making it impossible to disentangle architectural contributions from resource advantages. We propose \\textit{score-aware training}, which treats audio-caption alignment score as a direct supervision signal throughout the pipeline. Rather than discarding low-scoring segments, we repurpose them via a CLAP-conditioned Beta noise timestep schedule that routes them to high-noise training regimes, acting as an effective implicit regularizer. Complementarily, segment-level filtering re"},"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":"2606.07387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T15:24:36Z","cross_cats_sorted":[],"title_canon_sha256":"02a1792f32ab913c7ae8553f5e4c238fe088763edd535dfedc76227bb0d1e7a2","abstract_canon_sha256":"448fa62c8ace9adedcb2eaa2d3ba6e99c729d61020c2a980926054fe89a30c53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:23.995088Z","signature_b64":"0r9/4ZiKdMHVv61VMCUTymlvz022O7H+P/pKDNv+4dnpyxYBPe40Bd7ndJmkNMuXHfNxxw2NnnHOngcpH6yOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"262477375860ac1ac87da05edc4634354c9e85a272e18169dd38599140f7f853","last_reissued_at":"2026-06-08T01:05:23.994229Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:23.994229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making the Most of Limited Data: Score-Aware Training for Text-to-Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chih-Pin Tan, Tzu-Hung Huang, Yun-Chen Cheng","submitted_at":"2026-06-05T15:24:36Z","abstract_excerpt":"State-of-the-art text-to-music generation systems rely on massive proprietary datasets and industrial-scale compute, making it impossible to disentangle architectural contributions from resource advantages. We propose \\textit{score-aware training}, which treats audio-caption alignment score as a direct supervision signal throughout the pipeline. Rather than discarding low-scoring segments, we repurpose them via a CLAP-conditioned Beta noise timestep schedule that routes them to high-noise training regimes, acting as an effective implicit regularizer. Complementarily, segment-level filtering re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07387","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/2606.07387/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":"2606.07387","created_at":"2026-06-08T01:05:23.994370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07387v1","created_at":"2026-06-08T01:05:23.994370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07387","created_at":"2026-06-08T01:05:23.994370+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYSHON2YMCWB","created_at":"2026-06-08T01:05:23.994370+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYSHON2YMCWBVSD5","created_at":"2026-06-08T01:05:23.994370+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYSHON2Y","created_at":"2026-06-08T01:05:23.994370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYSHON2YMCWBVSD5UBPNYRRUGV","json":"https://pith.science/pith/EYSHON2YMCWBVSD5UBPNYRRUGV.json","graph_json":"https://pith.science/api/pith-number/EYSHON2YMCWBVSD5UBPNYRRUGV/graph.json","events_json":"https://pith.science/api/pith-number/EYSHON2YMCWBVSD5UBPNYRRUGV/events.json","paper":"https://pith.science/paper/EYSHON2Y"},"agent_actions":{"view_html":"https://pith.science/pith/EYSHON2YMCWBVSD5UBPNYRRUGV","download_json":"https://pith.science/pith/EYSHON2YMCWBVSD5UBPNYRRUGV.json","view_paper":"https://pith.science/paper/EYSHON2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07387&json=true","fetch_graph":"https://pith.science/api/pith-number/EYSHON2YMCWBVSD5UBPNYRRUGV/graph.json","fetch_events":"https://pith.science/api/pith-number/EYSHON2YMCWBVSD5UBPNYRRUGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYSHON2YMCWBVSD5UBPNYRRUGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYSHON2YMCWBVSD5UBPNYRRUGV/action/storage_attestation","attest_author":"https://pith.science/pith/EYSHON2YMCWBVSD5UBPNYRRUGV/action/author_attestation","sign_citation":"https://pith.science/pith/EYSHON2YMCWBVSD5UBPNYRRUGV/action/citation_signature","submit_replication":"https://pith.science/pith/EYSHON2YMCWBVSD5UBPNYRRUGV/action/replication_record"}},"created_at":"2026-06-08T01:05:23.994370+00:00","updated_at":"2026-06-08T01:05:23.994370+00:00"}