{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:63VJHMWYG5EOWERTS4HRHNVWND","short_pith_number":"pith:63VJHMWY","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"},"canonical_sha256":"f6ea93b2d83748eb1233970f13b6b668fc82184c75133f020f8ddc2c460fb7ed","source":{"kind":"arxiv","id":"2605.18916","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18916","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18916v1","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18916","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"63VJHMWYG5EO","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"63VJHMWYG5EOWERT","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"63VJHMWY","created_at":"2026-05-20T00:06:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:63VJHMWYG5EOWERTS4HRHNVWND","target":"record","payload":{"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"},"canonical_sha256":"f6ea93b2d83748eb1233970f13b6b668fc82184c75133f020f8ddc2c460fb7ed","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"},"source_kind":"arxiv","source_id":"2605.18916","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0UqJ5A2/6MDwE1EAOrRcL7j+ut1C15xodqEEyWIt23nHTlXxZW0g8hIlQ1uXchK5Tc+W3vZVxGn2BehF6E/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:38:56.530106Z"},"content_sha256":"d942a6b2b8a987bb4957b326fe0809f279a08eed6bc3b932284adaf993b9ab89","schema_version":"1.0","event_id":"sha256:d942a6b2b8a987bb4957b326fe0809f279a08eed6bc3b932284adaf993b9ab89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:63VJHMWYG5EOWERTS4HRHNVWND","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjGtR6r2y/Fn3U1qIkIaHvL0s3KUnxDRcTRkhdrBXZibl3wLhK8uR2NJrSMLJcGWeZt1+Ct1z2E976VrvY7nAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:38:56.530869Z"},"content_sha256":"8bd2f4860216f2d1e10ba860f90d9907573ab9a952698eb62f29b47391355611","schema_version":"1.0","event_id":"sha256:8bd2f4860216f2d1e10ba860f90d9907573ab9a952698eb62f29b47391355611"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND/bundle.json","state_url":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/63VJHMWYG5EOWERTS4HRHNVWND/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-06T11:38:56Z","links":{"resolver":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND","bundle":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND/bundle.json","state":"https://pith.science/pith/63VJHMWYG5EOWERTS4HRHNVWND/state.json","well_known_bundle":"https://pith.science/.well-known/pith/63VJHMWYG5EOWERTS4HRHNVWND/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:63VJHMWYG5EOWERTS4HRHNVWND","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":"5a4eadf5054ff8bd87409c6b7e792f73f6b525657a0e0c16d452911a02dee9e0","cross_cats_sorted":["cs.AI","cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2026-05-18T05:42:06Z","title_canon_sha256":"2b4f4c3161bb8f4157a8df74f7190ebafac168d6e11ea1c77304db3a82769e6c"},"schema_version":"1.0","source":{"id":"2605.18916","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18916","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18916v1","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18916","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"63VJHMWYG5EO","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"63VJHMWYG5EOWERT","created_at":"2026-05-20T00:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"63VJHMWY","created_at":"2026-05-20T00:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:8bd2f4860216f2d1e10ba860f90d9907573ab9a952698eb62f29b47391355611","target":"graph","created_at":"2026-05-20T00:06:31Z","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/2605.18916/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gyubin Lee, Juhan Nam, Junwon Lee","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2026-05-18T05:42:06Z","title":"CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18916","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:d942a6b2b8a987bb4957b326fe0809f279a08eed6bc3b932284adaf993b9ab89","target":"record","created_at":"2026-05-20T00:06:31Z","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":"5a4eadf5054ff8bd87409c6b7e792f73f6b525657a0e0c16d452911a02dee9e0","cross_cats_sorted":["cs.AI","cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2026-05-18T05:42:06Z","title_canon_sha256":"2b4f4c3161bb8f4157a8df74f7190ebafac168d6e11ea1c77304db3a82769e6c"},"schema_version":"1.0","source":{"id":"2605.18916","kind":"arxiv","version":1}},"canonical_sha256":"f6ea93b2d83748eb1233970f13b6b668fc82184c75133f020f8ddc2c460fb7ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6ea93b2d83748eb1233970f13b6b668fc82184c75133f020f8ddc2c460fb7ed","first_computed_at":"2026-05-20T00:06:31.958139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:31.958139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MBhNPlybt27DBPhb7b8cOzywwOBgacJjKn813o8YdMwiTdRTgMGQlTe9SQNpEpSifMofoTylkJr2KmkB8AyIAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:31.958914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18916","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d942a6b2b8a987bb4957b326fe0809f279a08eed6bc3b932284adaf993b9ab89","sha256:8bd2f4860216f2d1e10ba860f90d9907573ab9a952698eb62f29b47391355611"],"state_sha256":"5f600fa01929a525af3f474c81c01aec2fd184613ffebbe5877dc265a3d710ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gcrmAmJtJjx1plFaQNd3H4vO4hT2b03waSMvJoS6EVQPWuLRDY1tSKVc7GkSy5qGjR9VGmSw3lQT/1xVRJ6FAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T11:38:56.534828Z","bundle_sha256":"20d662d2b7f928b6a4ce2b1c5fd9c915a0051915fef591b31d5d595b3f4312f1"}}