{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7TBJ4MYTXSZ3SWL5NF7STYT6FP","short_pith_number":"pith:7TBJ4MYT","schema_version":"1.0","canonical_sha256":"fcc29e3313bcb3b9597d697f29e27e2be3331f54cbd9b7bacfc11accf1682149","source":{"kind":"arxiv","id":"2405.18503","version":3},"attestation_state":"computed","paper":{"title":"SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chieh-Hsin Lai, Dongjun Kim, Koichi Saito, Takashi Shibuya, Yuhta Takida, Yuki Mitsufuji, Zhi Zhong","submitted_at":"2024-05-28T18:14:52Z","abstract_excerpt":"Sound content creation, essential for multimedia works such as video games and films, often involves extensive trial-and-error, enabling creators to semantically reflect their artistic ideas and inspirations, which evolve throughout the creation process, into the sound. Recent high-quality diffusion-based Text-to-Sound (T2S) generative models provide valuable tools for creators. However, these models often suffer from slow inference speeds, imposing an undesirable burden that hinders the trial-and-error process. While existing T2S distillation models address this limitation through 1-step gene"},"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":"2405.18503","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-28T18:14:52Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"befae7091d9127a00e68e90a4c8b9a9b0dfa73e5ed8f08e61c02a69978748d7f","abstract_canon_sha256":"e0e4b937a21d63d01dc0c330fa8c606674bf8893fa0632eef5090b641f585c1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:10.628016Z","signature_b64":"S5FMSW4Ksvgz5V8/DU9BuXqAXaqyny9ZE6xp9sOgc7Em/xgvLMHlimVLhumWbTDxiXr04N+f/QbRc+i+eqiwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcc29e3313bcb3b9597d697f29e27e2be3331f54cbd9b7bacfc11accf1682149","last_reissued_at":"2026-07-05T10:27:10.627426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:10.627426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chieh-Hsin Lai, Dongjun Kim, Koichi Saito, Takashi Shibuya, Yuhta Takida, Yuki Mitsufuji, Zhi Zhong","submitted_at":"2024-05-28T18:14:52Z","abstract_excerpt":"Sound content creation, essential for multimedia works such as video games and films, often involves extensive trial-and-error, enabling creators to semantically reflect their artistic ideas and inspirations, which evolve throughout the creation process, into the sound. Recent high-quality diffusion-based Text-to-Sound (T2S) generative models provide valuable tools for creators. However, these models often suffer from slow inference speeds, imposing an undesirable burden that hinders the trial-and-error process. While existing T2S distillation models address this limitation through 1-step gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18503","kind":"arxiv","version":3},"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/2405.18503/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":"2405.18503","created_at":"2026-07-05T10:27:10.627517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18503v3","created_at":"2026-07-05T10:27:10.627517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18503","created_at":"2026-07-05T10:27:10.627517+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TBJ4MYTXSZ3","created_at":"2026-07-05T10:27:10.627517+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TBJ4MYTXSZ3SWL5","created_at":"2026-07-05T10:27:10.627517+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TBJ4MYT","created_at":"2026-07-05T10:27:10.627517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.06027","citing_title":"DreamAudio: Customized Text-to-Audio Generation with Diffusion Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TBJ4MYTXSZ3SWL5NF7STYT6FP","json":"https://pith.science/pith/7TBJ4MYTXSZ3SWL5NF7STYT6FP.json","graph_json":"https://pith.science/api/pith-number/7TBJ4MYTXSZ3SWL5NF7STYT6FP/graph.json","events_json":"https://pith.science/api/pith-number/7TBJ4MYTXSZ3SWL5NF7STYT6FP/events.json","paper":"https://pith.science/paper/7TBJ4MYT"},"agent_actions":{"view_html":"https://pith.science/pith/7TBJ4MYTXSZ3SWL5NF7STYT6FP","download_json":"https://pith.science/pith/7TBJ4MYTXSZ3SWL5NF7STYT6FP.json","view_paper":"https://pith.science/paper/7TBJ4MYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18503&json=true","fetch_graph":"https://pith.science/api/pith-number/7TBJ4MYTXSZ3SWL5NF7STYT6FP/graph.json","fetch_events":"https://pith.science/api/pith-number/7TBJ4MYTXSZ3SWL5NF7STYT6FP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TBJ4MYTXSZ3SWL5NF7STYT6FP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TBJ4MYTXSZ3SWL5NF7STYT6FP/action/storage_attestation","attest_author":"https://pith.science/pith/7TBJ4MYTXSZ3SWL5NF7STYT6FP/action/author_attestation","sign_citation":"https://pith.science/pith/7TBJ4MYTXSZ3SWL5NF7STYT6FP/action/citation_signature","submit_replication":"https://pith.science/pith/7TBJ4MYTXSZ3SWL5NF7STYT6FP/action/replication_record"}},"created_at":"2026-07-05T10:27:10.627517+00:00","updated_at":"2026-07-05T10:27:10.627517+00:00"}