{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:POBKBMGZHCS5BK74CBW2PEEEMH","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":"cfccfd166b2e7eb7c603e24b26a413985a440757a15b4cc848e3b29cdd9bc9f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T15:05:00Z","title_canon_sha256":"98a4ed53c987b6662fdd9f8fc093e9545de044a640625d99f7821780f64a7689"},"schema_version":"1.0","source":{"id":"2605.19950","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19950","created_at":"2026-05-20T02:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19950v1","created_at":"2026-05-20T02:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19950","created_at":"2026-05-20T02:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"POBKBMGZHCS5","created_at":"2026-05-20T02:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"POBKBMGZHCS5BK74","created_at":"2026-05-20T02:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"POBKBMGZ","created_at":"2026-05-20T02:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:191c1a6ff9260a3043a789e8230d2cc5577531036a236ae3ac6de0b23f83a666","target":"graph","created_at":"2026-05-20T02:05:56Z","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/2605.19950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans infer emotions by integrating observed multimodal cues with expectations about how affective states may unfold. Existing multimodal large language models (MLLMs), however, often treat emotion recognition as static fusion over complete audiovisual-text inputs, leaving affective dynamics implicit. We propose AffectVerse, a Qwen2.5-Omni-based model equipped with an Emotion World Module (EWM), an action-free representation-level module for short-horizon latent affective prediction. \\rev{EWM contains three modules: 1) Cross-Modal Temporal Imagination predicts future video/audio representatio","authors_text":"Bo Zhao, Fanghua Ye, Sicheng Zhao, Xiaojiang Peng, Yixin Ji, Zitong Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T15:05:00Z","title":"AffectVerse: Emotional World Models for Multimodal Affective Computing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19950","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":"sha256:7e8c1a9f9ed5e548368919b6db4f26be37af84c0b07ef07c7cb6548db1dfde18","target":"record","created_at":"2026-05-20T02:05:56Z","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":"cfccfd166b2e7eb7c603e24b26a413985a440757a15b4cc848e3b29cdd9bc9f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T15:05:00Z","title_canon_sha256":"98a4ed53c987b6662fdd9f8fc093e9545de044a640625d99f7821780f64a7689"},"schema_version":"1.0","source":{"id":"2605.19950","kind":"arxiv","version":1}},"canonical_sha256":"7b82a0b0d938a5d0abfc106da7908461d97ed70fee19e2b2f3e1bf7cfd0ebfae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b82a0b0d938a5d0abfc106da7908461d97ed70fee19e2b2f3e1bf7cfd0ebfae","first_computed_at":"2026-05-20T02:05:56.683820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:05:56.683820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zsNE5W9TwCSqNPT1PB+tXqCHfX/Ctd6T6fyHGp3DKPfMkxGqh73uSBKx/vclPSU0zfdKiglgNz9l3hxGSaoWAg==","signature_status":"signed_v1","signed_at":"2026-05-20T02:05:56.684489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19950","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e8c1a9f9ed5e548368919b6db4f26be37af84c0b07ef07c7cb6548db1dfde18","sha256:191c1a6ff9260a3043a789e8230d2cc5577531036a236ae3ac6de0b23f83a666"],"state_sha256":"96c0f6ee4d572607e86de719ff9699bf751491be8c0b6f80e67d31c2815c3ff9"}