{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:63VJHMWYG5EOWERTS4HRHNVWND","short_pith_number":"pith:63VJHMWY","schema_version":"1.0","canonical_sha256":"f6ea93b2d83748eb1233970f13b6b668fc82184c75133f020f8ddc2c460fb7ed","source":{"kind":"arxiv","id":"2605.18916","version":1},"attestation_state":"computed","paper":{"title":"CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Gyubin Lee, Juhan Nam, Junwon Lee","submitted_at":"2026-05-18T05:42:06Z","abstract_excerpt":"We investigate Counterfactual Video Foley Generation, which aims to adopt a sound-source identity that contradicts the visual evidence while remaining temporally synchronized to a silent video. Existing Video&Text-to-Audio (VT2A) models struggle with this, often remaining anchored to the visually implied sound source when video and text contents disagree. We present ConterFlow, an inference-time dual-phase sampling scheme for pretrained flow-matching VT2A models. Phase 1 builds a video-derived temporal structure while suppressing the visually implied source; Phase 2 drops video conditioning to"},"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":"2605.18916","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2026-05-18T05:42:06Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"2b4f4c3161bb8f4157a8df74f7190ebafac168d6e11ea1c77304db3a82769e6c","abstract_canon_sha256":"5a4eadf5054ff8bd87409c6b7e792f73f6b525657a0e0c16d452911a02dee9e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:31.958914Z","signature_b64":"MBhNPlybt27DBPhb7b8cOzywwOBgacJjKn813o8YdMwiTdRTgMGQlTe9SQNpEpSifMofoTylkJr2KmkB8AyIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6ea93b2d83748eb1233970f13b6b668fc82184c75133f020f8ddc2c460fb7ed","last_reissued_at":"2026-05-20T00:06:31.958139Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:31.958139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Gyubin Lee, Juhan Nam, Junwon Lee","submitted_at":"2026-05-18T05:42:06Z","abstract_excerpt":"We investigate Counterfactual Video Foley Generation, which aims to adopt a sound-source identity that contradicts the visual evidence while remaining temporally synchronized to a silent video. Existing Video&Text-to-Audio (VT2A) models struggle with this, often remaining anchored to the visually implied sound source when video and text contents disagree. We present ConterFlow, an inference-time dual-phase sampling scheme for pretrained flow-matching VT2A models. Phase 1 builds a video-derived temporal structure while suppressing the visually implied source; Phase 2 drops video conditioning to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18916","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/2605.18916/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":"2605.18916","created_at":"2026-05-20T00:06:31.958259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18916v1","created_at":"2026-05-20T00:06:31.958259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18916","created_at":"2026-05-20T00:06:31.958259+00:00"},{"alias_kind":"pith_short_12","alias_value":"63VJHMWYG5EO","created_at":"2026-05-20T00:06:31.958259+00:00"},{"alias_kind":"pith_short_16","alias_value":"63VJHMWYG5EOWERT","created_at":"2026-05-20T00:06:31.958259+00:00"},{"alias_kind":"pith_short_8","alias_value":"63VJHMWY","created_at":"2026-05-20T00:06:31.958259+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/63VJHMWYG5EOWERTS4HRHNVWND","json":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND.json","graph_json":"https://pith.science/api/pith-number/63VJHMWYG5EOWERTS4HRHNVWND/graph.json","events_json":"https://pith.science/api/pith-number/63VJHMWYG5EOWERTS4HRHNVWND/events.json","paper":"https://pith.science/paper/63VJHMWY"},"agent_actions":{"view_html":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND","download_json":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND.json","view_paper":"https://pith.science/paper/63VJHMWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18916&json=true","fetch_graph":"https://pith.science/api/pith-number/63VJHMWYG5EOWERTS4HRHNVWND/graph.json","fetch_events":"https://pith.science/api/pith-number/63VJHMWYG5EOWERTS4HRHNVWND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND/action/storage_attestation","attest_author":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND/action/author_attestation","sign_citation":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND/action/citation_signature","submit_replication":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND/action/replication_record"}},"created_at":"2026-05-20T00:06:31.958259+00:00","updated_at":"2026-05-20T00:06:31.958259+00:00"}