{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GH45YJIPPUENZM6Z3GCABSNHVG","short_pith_number":"pith:GH45YJIP","schema_version":"1.0","canonical_sha256":"31f9dc250f7d08dcb3d9d98400c9a7a9b6331737c2d6c47c081b5707debcd114","source":{"kind":"arxiv","id":"2606.08393","version":1},"attestation_state":"computed","paper":{"title":"SMC-ITA: Sequential Monte Carlo Inference-Time Alignment for Video-to-Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chunfeng Wang, Haoyu Zhang, Irene Li, Xingjian Du, Yusuke Iwasawa, Yutaka Matsuo, Yuta Oshima","submitted_at":"2026-06-07T01:10:11Z","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"},"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":"2606.08393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-07T01:10:11Z","cross_cats_sorted":[],"title_canon_sha256":"3e3bc0a56df2f934db475a2a2b7f92abf651c7cff17393dcefafb60dbcd9fd7d","abstract_canon_sha256":"9d7c79e3d0d0eb3d96725b5c976b1a3f28c331efbb7ef590779eba13e41885c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:35.520347Z","signature_b64":"0JMNxDnmgn1KRB1Sif0VuImkze/Xx9DZ1aBjiqS8o9hP7TXNNrbW5PczpidxAyc0kTiEm1i3fIrYokYq1sggDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31f9dc250f7d08dcb3d9d98400c9a7a9b6331737c2d6c47c081b5707debcd114","last_reissued_at":"2026-06-09T01:05:35.519924Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:35.519924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMC-ITA: Sequential Monte Carlo Inference-Time Alignment for Video-to-Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chunfeng Wang, Haoyu Zhang, Irene Li, Xingjian Du, Yusuke Iwasawa, Yutaka Matsuo, Yuta Oshima","submitted_at":"2026-06-07T01:10:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08393","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/2606.08393/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":"2606.08393","created_at":"2026-06-09T01:05:35.519984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08393v1","created_at":"2026-06-09T01:05:35.519984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08393","created_at":"2026-06-09T01:05:35.519984+00:00"},{"alias_kind":"pith_short_12","alias_value":"GH45YJIPPUEN","created_at":"2026-06-09T01:05:35.519984+00:00"},{"alias_kind":"pith_short_16","alias_value":"GH45YJIPPUENZM6Z","created_at":"2026-06-09T01:05:35.519984+00:00"},{"alias_kind":"pith_short_8","alias_value":"GH45YJIP","created_at":"2026-06-09T01:05:35.519984+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/GH45YJIPPUENZM6Z3GCABSNHVG","json":"https://pith.science/pith/GH45YJIPPUENZM6Z3GCABSNHVG.json","graph_json":"https://pith.science/api/pith-number/GH45YJIPPUENZM6Z3GCABSNHVG/graph.json","events_json":"https://pith.science/api/pith-number/GH45YJIPPUENZM6Z3GCABSNHVG/events.json","paper":"https://pith.science/paper/GH45YJIP"},"agent_actions":{"view_html":"https://pith.science/pith/GH45YJIPPUENZM6Z3GCABSNHVG","download_json":"https://pith.science/pith/GH45YJIPPUENZM6Z3GCABSNHVG.json","view_paper":"https://pith.science/paper/GH45YJIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08393&json=true","fetch_graph":"https://pith.science/api/pith-number/GH45YJIPPUENZM6Z3GCABSNHVG/graph.json","fetch_events":"https://pith.science/api/pith-number/GH45YJIPPUENZM6Z3GCABSNHVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GH45YJIPPUENZM6Z3GCABSNHVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GH45YJIPPUENZM6Z3GCABSNHVG/action/storage_attestation","attest_author":"https://pith.science/pith/GH45YJIPPUENZM6Z3GCABSNHVG/action/author_attestation","sign_citation":"https://pith.science/pith/GH45YJIPPUENZM6Z3GCABSNHVG/action/citation_signature","submit_replication":"https://pith.science/pith/GH45YJIPPUENZM6Z3GCABSNHVG/action/replication_record"}},"created_at":"2026-06-09T01:05:35.519984+00:00","updated_at":"2026-06-09T01:05:35.519984+00:00"}