{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YVOE6NEI6FIVIMVVFOBZ4NGCHT","short_pith_number":"pith:YVOE6NEI","schema_version":"1.0","canonical_sha256":"c55c4f3488f1515432b52b839e34c23ce707302b9f3515a2e1edf7678813d663","source":{"kind":"arxiv","id":"2607.01669","version":1},"attestation_state":"computed","paper":{"title":"UT-AISTimprt submission for ICME 2026 Grand Challenge on Academic Text-to-Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Satoru Fukayama, Shunsuke Yoshida, Yu-Hua Chen","submitted_at":"2026-07-02T03:51:01Z","abstract_excerpt":"This work investigates the effect of batch sampling strategies during training for text-to-audio music generation under low-data and small-scale model settings. This paper describes our approach and findings for the ICME 2026 Grand Challenge on Academic Text-to-Music Generation. Training data are clustered using either text embeddings or audio embeddings, and samples with similar characteristics are grouped within the same mini-batch to mitigate gradient interference. The effects of modality and cluster granularity on clustering are analyzed. Results show that clustering based on text embeddin"},"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":"2607.01669","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-02T03:51:01Z","cross_cats_sorted":[],"title_canon_sha256":"59f12d7bbbb957649d123fdf36cbae89f1f9f411792a6a52034e8a13681d85cd","abstract_canon_sha256":"ff393685ed2e3b21368ee9cb6c43c3df1114f8c818143256b16725a3ca1c2ae5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:26.202252Z","signature_b64":"VajRow9E+5pL43KDIUh8d0a9T+oU+SkbIuJ5O2e9T5mI+Hc+nNW0LtfDO+kLgb9mEI4PzyqkKyRwoqz62h7fDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c55c4f3488f1515432b52b839e34c23ce707302b9f3515a2e1edf7678813d663","last_reissued_at":"2026-07-03T01:17:26.201738Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:26.201738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UT-AISTimprt submission for ICME 2026 Grand Challenge on Academic Text-to-Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Satoru Fukayama, Shunsuke Yoshida, Yu-Hua Chen","submitted_at":"2026-07-02T03:51:01Z","abstract_excerpt":"This work investigates the effect of batch sampling strategies during training for text-to-audio music generation under low-data and small-scale model settings. This paper describes our approach and findings for the ICME 2026 Grand Challenge on Academic Text-to-Music Generation. Training data are clustered using either text embeddings or audio embeddings, and samples with similar characteristics are grouped within the same mini-batch to mitigate gradient interference. The effects of modality and cluster granularity on clustering are analyzed. Results show that clustering based on text embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01669","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/2607.01669/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":"2607.01669","created_at":"2026-07-03T01:17:26.201806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01669v1","created_at":"2026-07-03T01:17:26.201806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01669","created_at":"2026-07-03T01:17:26.201806+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVOE6NEI6FIV","created_at":"2026-07-03T01:17:26.201806+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVOE6NEI6FIVIMVV","created_at":"2026-07-03T01:17:26.201806+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVOE6NEI","created_at":"2026-07-03T01:17:26.201806+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/YVOE6NEI6FIVIMVVFOBZ4NGCHT","json":"https://pith.science/pith/YVOE6NEI6FIVIMVVFOBZ4NGCHT.json","graph_json":"https://pith.science/api/pith-number/YVOE6NEI6FIVIMVVFOBZ4NGCHT/graph.json","events_json":"https://pith.science/api/pith-number/YVOE6NEI6FIVIMVVFOBZ4NGCHT/events.json","paper":"https://pith.science/paper/YVOE6NEI"},"agent_actions":{"view_html":"https://pith.science/pith/YVOE6NEI6FIVIMVVFOBZ4NGCHT","download_json":"https://pith.science/pith/YVOE6NEI6FIVIMVVFOBZ4NGCHT.json","view_paper":"https://pith.science/paper/YVOE6NEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01669&json=true","fetch_graph":"https://pith.science/api/pith-number/YVOE6NEI6FIVIMVVFOBZ4NGCHT/graph.json","fetch_events":"https://pith.science/api/pith-number/YVOE6NEI6FIVIMVVFOBZ4NGCHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVOE6NEI6FIVIMVVFOBZ4NGCHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVOE6NEI6FIVIMVVFOBZ4NGCHT/action/storage_attestation","attest_author":"https://pith.science/pith/YVOE6NEI6FIVIMVVFOBZ4NGCHT/action/author_attestation","sign_citation":"https://pith.science/pith/YVOE6NEI6FIVIMVVFOBZ4NGCHT/action/citation_signature","submit_replication":"https://pith.science/pith/YVOE6NEI6FIVIMVVFOBZ4NGCHT/action/replication_record"}},"created_at":"2026-07-03T01:17:26.201806+00:00","updated_at":"2026-07-03T01:17:26.201806+00:00"}