{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3VJBIKB7JXGMSXDQDAGVF6HMAE","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":"d506b10650ff057a351c8ae9174e6930a62321c4e5574995d5f16de400aa47d0","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-06-02T05:41:41Z","title_canon_sha256":"34fa23ef83028f243164335597eb896657d6f82c41be2edc2c3fdb00f4c447d0"},"schema_version":"1.0","source":{"id":"2606.03183","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03183","created_at":"2026-06-03T01:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03183v1","created_at":"2026-06-03T01:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03183","created_at":"2026-06-03T01:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"3VJBIKB7JXGM","created_at":"2026-06-03T01:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"3VJBIKB7JXGMSXDQ","created_at":"2026-06-03T01:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"3VJBIKB7","created_at":"2026-06-03T01:05:34Z"}],"graph_snapshots":[{"event_id":"sha256:539b2aa5facaa15be1f896c1dcf0e57b2d6b193c9025184bc54be2f1c6fe3a6f","target":"graph","created_at":"2026-06-03T01:05:34Z","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/2606.03183/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Joint audio-video generation aims to synthesize realistic audio-video pairs that are both semantically aligned with text prompts and precisely synchronized. While existing joint audio-video generation models often require substantial training resources to improve fidelity, Inference-Time Scaling (ITS) has recently emerged as a promising training-free alternative in single-modality domains. However, extending ITS from a single modality to multimodal domains is non-trivial, as it requires balancing multiple heterogeneous objectives. In this paper, we present the first comprehensive study of ITS ","authors_text":"Inkyu Shin, Jaemin Jung, Joon Son Chung, Kyeongha Rho","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-06-02T05:41:41Z","title":"Inference-Time Scaling for Joint Audio-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03183","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:b79fa15b2e64657b79cefba10ccd782c93556a7f04ba0fcdf5a66bf0a2e34f84","target":"record","created_at":"2026-06-03T01:05:34Z","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":"d506b10650ff057a351c8ae9174e6930a62321c4e5574995d5f16de400aa47d0","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-06-02T05:41:41Z","title_canon_sha256":"34fa23ef83028f243164335597eb896657d6f82c41be2edc2c3fdb00f4c447d0"},"schema_version":"1.0","source":{"id":"2606.03183","kind":"arxiv","version":1}},"canonical_sha256":"dd5214283f4dccc95c70180d52f8ec011d0e5f4215808568ffd62f59f9c5979f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd5214283f4dccc95c70180d52f8ec011d0e5f4215808568ffd62f59f9c5979f","first_computed_at":"2026-06-03T01:05:34.290769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:34.290769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fEpNLT8/Qq246mJ1zzZ9ihBZ1J3UPEu361Eeu1uq/mcRZGHSY9xBsDBaI7MKbpExkjUzMeXXZV6wZ3NPE0LJAg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:34.291164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03183","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b79fa15b2e64657b79cefba10ccd782c93556a7f04ba0fcdf5a66bf0a2e34f84","sha256:539b2aa5facaa15be1f896c1dcf0e57b2d6b193c9025184bc54be2f1c6fe3a6f"],"state_sha256":"143b8534f96af7b5174c07bb2f353f8456f7f9a3cd8302b2bdb6a0751a5a069e"}