{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JTMYJBPPW6K4TCLPB4TGHDG6PG","short_pith_number":"pith:JTMYJBPP","schema_version":"1.0","canonical_sha256":"4cd98485efb795c9896f0f26638cde79b5e68f7774b1ad54a56a41b5666c0b1e","source":{"kind":"arxiv","id":"2503.22200","version":1},"attestation_state":"computed","paper":{"title":"Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaofan Ding, Haomin Zhang, Haoyu Wang, Sizhe Shan, Xinhan Di, Xiulong Liu, Zihao Chen","submitted_at":"2025-03-28T07:32:14Z","abstract_excerpt":"Creating high-quality sound effects from videos and text prompts requires precise alignment between visual and audio domains, both semantically and temporally, along with step-by-step guidance for professional audio generation. However, current state-of-the-art video-guided audio generation models often fall short of producing high-quality audio for both general and specialized use cases. To address this challenge, we introduce a multi-stage, multi-modal, end-to-end generative framework with Chain-of-Thought-like (CoT-like) guidance learning, termed Chain-of-Perform (CoP). First, we employ a t"},"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":"2503.22200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-28T07:32:14Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"b564f60f57609cc586591f4e4d4ed137d635327ae3154f73fc72bc87ff113b43","abstract_canon_sha256":"c5d73ee5478024eb811889ae29d429fc12b96c9c11dbbcc5df5793fbc1f4c17e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:03.234531Z","signature_b64":"TQd1qYcvAluW3fIXGEalmWayh/fyPBY7gRNcC0IKkciLqHzerauYftVvdUy50Rk5wTXtJGaMtwZc9Kfrj2XFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cd98485efb795c9896f0f26638cde79b5e68f7774b1ad54a56a41b5666c0b1e","last_reissued_at":"2026-07-05T10:41:03.234122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:03.234122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaofan Ding, Haomin Zhang, Haoyu Wang, Sizhe Shan, Xinhan Di, Xiulong Liu, Zihao Chen","submitted_at":"2025-03-28T07:32:14Z","abstract_excerpt":"Creating high-quality sound effects from videos and text prompts requires precise alignment between visual and audio domains, both semantically and temporally, along with step-by-step guidance for professional audio generation. However, current state-of-the-art video-guided audio generation models often fall short of producing high-quality audio for both general and specialized use cases. To address this challenge, we introduce a multi-stage, multi-modal, end-to-end generative framework with Chain-of-Thought-like (CoT-like) guidance learning, termed Chain-of-Perform (CoP). First, we employ a t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22200","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/2503.22200/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":"2503.22200","created_at":"2026-07-05T10:41:03.234180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22200v1","created_at":"2026-07-05T10:41:03.234180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22200","created_at":"2026-07-05T10:41:03.234180+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTMYJBPPW6K4","created_at":"2026-07-05T10:41:03.234180+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTMYJBPPW6K4TCLP","created_at":"2026-07-05T10:41:03.234180+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTMYJBPP","created_at":"2026-07-05T10:41:03.234180+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/JTMYJBPPW6K4TCLPB4TGHDG6PG","json":"https://pith.science/pith/JTMYJBPPW6K4TCLPB4TGHDG6PG.json","graph_json":"https://pith.science/api/pith-number/JTMYJBPPW6K4TCLPB4TGHDG6PG/graph.json","events_json":"https://pith.science/api/pith-number/JTMYJBPPW6K4TCLPB4TGHDG6PG/events.json","paper":"https://pith.science/paper/JTMYJBPP"},"agent_actions":{"view_html":"https://pith.science/pith/JTMYJBPPW6K4TCLPB4TGHDG6PG","download_json":"https://pith.science/pith/JTMYJBPPW6K4TCLPB4TGHDG6PG.json","view_paper":"https://pith.science/paper/JTMYJBPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22200&json=true","fetch_graph":"https://pith.science/api/pith-number/JTMYJBPPW6K4TCLPB4TGHDG6PG/graph.json","fetch_events":"https://pith.science/api/pith-number/JTMYJBPPW6K4TCLPB4TGHDG6PG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTMYJBPPW6K4TCLPB4TGHDG6PG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTMYJBPPW6K4TCLPB4TGHDG6PG/action/storage_attestation","attest_author":"https://pith.science/pith/JTMYJBPPW6K4TCLPB4TGHDG6PG/action/author_attestation","sign_citation":"https://pith.science/pith/JTMYJBPPW6K4TCLPB4TGHDG6PG/action/citation_signature","submit_replication":"https://pith.science/pith/JTMYJBPPW6K4TCLPB4TGHDG6PG/action/replication_record"}},"created_at":"2026-07-05T10:41:03.234180+00:00","updated_at":"2026-07-05T10:41:03.234180+00:00"}