{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JTMYJBPPW6K4TCLPB4TGHDG6PG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c5d73ee5478024eb811889ae29d429fc12b96c9c11dbbcc5df5793fbc1f4c17e","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-28T07:32:14Z","title_canon_sha256":"b564f60f57609cc586591f4e4d4ed137d635327ae3154f73fc72bc87ff113b43"},"schema_version":"1.0","source":{"id":"2503.22200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22200","created_at":"2026-07-05T10:41:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22200v1","created_at":"2026-07-05T10:41:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22200","created_at":"2026-07-05T10:41:03Z"},{"alias_kind":"pith_short_12","alias_value":"JTMYJBPPW6K4","created_at":"2026-07-05T10:41:03Z"},{"alias_kind":"pith_short_16","alias_value":"JTMYJBPPW6K4TCLP","created_at":"2026-07-05T10:41:03Z"},{"alias_kind":"pith_short_8","alias_value":"JTMYJBPP","created_at":"2026-07-05T10:41:03Z"}],"graph_snapshots":[{"event_id":"sha256:bca48c2d47e5c103169fba58fa2ecc3d75d7e2db7ce443722f1b9e60d5e36360","target":"graph","created_at":"2026-07-05T10:41:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.22200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chaofan Ding, Haomin Zhang, Haoyu Wang, Sizhe Shan, Xinhan Di, Xiulong Liu, Zihao Chen","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-28T07:32:14Z","title":"Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22200","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:34b42a8bff4bf65e7919f74f29edf1181e2df43d7861cee6fa8d4db5d24fcfa1","target":"record","created_at":"2026-07-05T10:41:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c5d73ee5478024eb811889ae29d429fc12b96c9c11dbbcc5df5793fbc1f4c17e","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-28T07:32:14Z","title_canon_sha256":"b564f60f57609cc586591f4e4d4ed137d635327ae3154f73fc72bc87ff113b43"},"schema_version":"1.0","source":{"id":"2503.22200","kind":"arxiv","version":1}},"canonical_sha256":"4cd98485efb795c9896f0f26638cde79b5e68f7774b1ad54a56a41b5666c0b1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cd98485efb795c9896f0f26638cde79b5e68f7774b1ad54a56a41b5666c0b1e","first_computed_at":"2026-07-05T10:41:03.234122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:03.234122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TQd1qYcvAluW3fIXGEalmWayh/fyPBY7gRNcC0IKkciLqHzerauYftVvdUy50Rk5wTXtJGaMtwZc9Kfrj2XFDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:03.234531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34b42a8bff4bf65e7919f74f29edf1181e2df43d7861cee6fa8d4db5d24fcfa1","sha256:bca48c2d47e5c103169fba58fa2ecc3d75d7e2db7ce443722f1b9e60d5e36360"],"state_sha256":"4ccfa37e9dc0179f1fe63be58089190a96321d27dc9f355e513aaed7ee55b2e8"}