{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GH45YJIPPUENZM6Z3GCABSNHVG","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":"9d7c79e3d0d0eb3d96725b5c976b1a3f28c331efbb7ef590779eba13e41885c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-07T01:10:11Z","title_canon_sha256":"3e3bc0a56df2f934db475a2a2b7f92abf651c7cff17393dcefafb60dbcd9fd7d"},"schema_version":"1.0","source":{"id":"2606.08393","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08393","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08393v1","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08393","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"GH45YJIPPUEN","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"GH45YJIPPUENZM6Z","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"GH45YJIP","created_at":"2026-06-09T01:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:75469c1838869e31dd5a78d727c327c08447acd93bf4f0c515308028cc5f8d63","target":"graph","created_at":"2026-06-09T01:05:35Z","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/2606.08393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-to-audio (V2A) generation must jointly satisfy audiovisual alignment, semantic consistency, temporal synchronization, and perceptual quality. While prior work has mainly focused on model architecture, multimodal conditioning, and training objectives, inference-time alignment for V2A remains underexplored. In this paper, we study inference-time alignment for flow-matching-based V2A generation and formulate it as a search problem. We propose Sequential Monte Carlo Inference-Time Alignment (SMC-ITA), which combines lookahead-based reward estimation and sequential Monte Carlo resampling to r","authors_text":"Chunfeng Wang, Haoyu Zhang, Irene Li, Xingjian Du, Yusuke Iwasawa, Yutaka Matsuo, Yuta Oshima","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-07T01:10:11Z","title":"SMC-ITA: Sequential Monte Carlo Inference-Time Alignment for Video-to-Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08393","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":"sha256:7b0a9528d66aee9294f801e1cae464e45b3a1211f0385498fd566ffc85977237","target":"record","created_at":"2026-06-09T01:05:35Z","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":"9d7c79e3d0d0eb3d96725b5c976b1a3f28c331efbb7ef590779eba13e41885c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-07T01:10:11Z","title_canon_sha256":"3e3bc0a56df2f934db475a2a2b7f92abf651c7cff17393dcefafb60dbcd9fd7d"},"schema_version":"1.0","source":{"id":"2606.08393","kind":"arxiv","version":1}},"canonical_sha256":"31f9dc250f7d08dcb3d9d98400c9a7a9b6331737c2d6c47c081b5707debcd114","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31f9dc250f7d08dcb3d9d98400c9a7a9b6331737c2d6c47c081b5707debcd114","first_computed_at":"2026-06-09T01:05:35.519924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:35.519924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0JMNxDnmgn1KRB1Sif0VuImkze/Xx9DZ1aBjiqS8o9hP7TXNNrbW5PczpidxAyc0kTiEm1i3fIrYokYq1sggDA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:35.520347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08393","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b0a9528d66aee9294f801e1cae464e45b3a1211f0385498fd566ffc85977237","sha256:75469c1838869e31dd5a78d727c327c08447acd93bf4f0c515308028cc5f8d63"],"state_sha256":"476c49ac4281c2a1fd461403684f9bf19084b08d5a1e8a0fa75d2dc41060b056"}