{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E6OQQ45BXRSTB47XYO5CAURKOS","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":"10f9bb5c83fa3424de1e6a0bf3d8da17afe08e7708ba65a51f5351a7b5520e9d","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T10:01:37Z","title_canon_sha256":"01b95e6ed9f3afda105c63c68ba35c8c65ace28952d19374a339a6c7dfc6688a"},"schema_version":"1.0","source":{"id":"2505.14151","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14151","created_at":"2026-07-05T11:15:21Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14151v3","created_at":"2026-07-05T11:15:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14151","created_at":"2026-07-05T11:15:21Z"},{"alias_kind":"pith_short_12","alias_value":"E6OQQ45BXRST","created_at":"2026-07-05T11:15:21Z"},{"alias_kind":"pith_short_16","alias_value":"E6OQQ45BXRSTB47X","created_at":"2026-07-05T11:15:21Z"},{"alias_kind":"pith_short_8","alias_value":"E6OQQ45B","created_at":"2026-07-05T11:15:21Z"}],"graph_snapshots":[{"event_id":"sha256:d4d4a7a98cf0b67b425c3a66bc2361711233580fb16aee04e178689f6274370c","target":"graph","created_at":"2026-07-05T11:15:21Z","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/2505.14151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given the audio-visual clip of the speaker, facial reaction generation aims to predict the listener's facial reactions. The challenge lies in capturing the relevance between video and audio while balancing appropriateness, realism, and diversity. While prior works have mostly focused on uni-modal inputs or simplified reaction mappings, recent approaches such as PerFRDiff have explored multi-modal inputs and the one-to-many nature of appropriate reaction mappings. In this work, we propose the Facial Reaction Diffusion (ReactDiff) framework that uniquely integrates a Multi-Modality Transformer w","authors_text":"Honglin Xiong, Jiaming Li, Qian Wang, Sheng Wang, Xin Wang, Yitao Zhu, Zixu Zhuang","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T10:01:37Z","title":"ReactDiff: Latent Diffusion for Facial Reaction Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14151","kind":"arxiv","version":3},"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":"sha256:1a1e5a5d3d1c2d1200e76558d3087eb310b0a748d8b9cb4edab415ac3757cb0a","target":"record","created_at":"2026-07-05T11:15:21Z","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":"10f9bb5c83fa3424de1e6a0bf3d8da17afe08e7708ba65a51f5351a7b5520e9d","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T10:01:37Z","title_canon_sha256":"01b95e6ed9f3afda105c63c68ba35c8c65ace28952d19374a339a6c7dfc6688a"},"schema_version":"1.0","source":{"id":"2505.14151","kind":"arxiv","version":3}},"canonical_sha256":"279d0873a1bc6530f3f7c3ba20522a74a4c1148022a5ae2ca3fa90dfe29692a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"279d0873a1bc6530f3f7c3ba20522a74a4c1148022a5ae2ca3fa90dfe29692a2","first_computed_at":"2026-07-05T11:15:21.165150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:21.165150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a3jLBcZUy+w1XqmEnOFik9Y1Tj3N/7X8m2+jOHXGOsEWPiDw7vThhK8PLOxc+UBU/Ma5WO4hdaX747XvA1PkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:21.165573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14151","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a1e5a5d3d1c2d1200e76558d3087eb310b0a748d8b9cb4edab415ac3757cb0a","sha256:d4d4a7a98cf0b67b425c3a66bc2361711233580fb16aee04e178689f6274370c"],"state_sha256":"98057b3df2d1cc16f8b8da6352f9615d3e9da0a5b3b9f2c72a7e812b52daa1ef"}