{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JVPKRD5VLJAXXF52HNVR3QVFJX","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":"eb834a4c3754f4db9b6c5654fa6f81a3c9773a7e04d85dce947944cd3f7b7cf1","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:20:01Z","title_canon_sha256":"6b05f9277c6ee9dcafb49d32f4f8de35705fc3c74eb30a940aed53bfc13a8c64"},"schema_version":"1.0","source":{"id":"2605.30256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30256","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30256v1","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30256","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"pith_short_12","alias_value":"JVPKRD5VLJAX","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"pith_short_16","alias_value":"JVPKRD5VLJAXXF52","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"pith_short_8","alias_value":"JVPKRD5V","created_at":"2026-05-29T02:06:14Z"}],"graph_snapshots":[{"event_id":"sha256:b81f3403499c4ea00f56b321ef1c3f75acbc7c2f6ad4e31c64927ba24ad0fa6d","target":"graph","created_at":"2026-05-29T02:06:14Z","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/2605.30256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural human conversation is full-duplex and audio-visual: people simultaneously speak and listen while continuously interpreting and producing nonverbal cues, such as nods, smiles, and gestures. To support successful human-agent interaction, agents must model full-duplex audiovisual conversation; however, existing full-duplex benchmarks evaluate only speech. In this work, we present VideoFDB, the first benchmark to evaluate full-duplex audio-visual-to-audio-visual (AV2AV) conversational agents. VideoFDB contributes (i) 237 dyadic clips spanning 11 nonverbal conversational dynamics from real-","authors_text":"Amrita Mazumdar, Julia Wang, Koki Nagano, Nikhil Srihari, Rajarshi Roy, Seonwook Park, Shalini De Mello, Shengze Wang, Yuhao Zhou","cross_cats":["cs.CL","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:20:01Z","title":"VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30256","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":"sha256:164b2abbf73bae0e22257d03aabb38ea51e16c62ae49529aeba4d72bd615a047","target":"record","created_at":"2026-05-29T02:06:14Z","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":"eb834a4c3754f4db9b6c5654fa6f81a3c9773a7e04d85dce947944cd3f7b7cf1","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:20:01Z","title_canon_sha256":"6b05f9277c6ee9dcafb49d32f4f8de35705fc3c74eb30a940aed53bfc13a8c64"},"schema_version":"1.0","source":{"id":"2605.30256","kind":"arxiv","version":1}},"canonical_sha256":"4d5ea88fb55a417b97ba3b6b1dc2a54ddb85754fedcd75a7fc5be79557512601","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d5ea88fb55a417b97ba3b6b1dc2a54ddb85754fedcd75a7fc5be79557512601","first_computed_at":"2026-05-29T02:06:14.209830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:14.209830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sS52b0OI4seCfBLNltprXGZ+/jU3+wFrARrFeUjXKXKg89QU1pTcRncJwV6PI8Chl9UWt8SAEEqzOSb5vPCAAw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:14.210258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:164b2abbf73bae0e22257d03aabb38ea51e16c62ae49529aeba4d72bd615a047","sha256:b81f3403499c4ea00f56b321ef1c3f75acbc7c2f6ad4e31c64927ba24ad0fa6d"],"state_sha256":"7fa2332d73477a3b11b8c6b24a4c7c25e3aeed330c7305b83aeba25b2ce73488"}