{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7TVTQ43SE35GETFQGQMVEZNAHV","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":"30775d302a5fb53e0da60609764eb2a71792c8209dfa484574c8a97a1fdac2a2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-13T13:02:02Z","title_canon_sha256":"01d5a91e32895bda6d5ae992d1cd0dcb5ad5181288ae3d60a3a389127a462214"},"schema_version":"1.0","source":{"id":"2604.11417","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11417","created_at":"2026-05-20T00:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11417v4","created_at":"2026-05-20T00:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11417","created_at":"2026-05-20T00:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"7TVTQ43SE35G","created_at":"2026-05-20T00:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"7TVTQ43SE35GETFQ","created_at":"2026-05-20T00:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"7TVTQ43S","created_at":"2026-05-20T00:03:11Z"}],"graph_snapshots":[{"event_id":"sha256:e085b0fdb13bb7e6d2f764e1ba43048331ca48e87c7d83ac441b2f005c24b045","target":"graph","created_at":"2026-05-20T00:03:11Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The lightweight transformer outperforms GPT-4o in both semantic gesture placement classification and intensity regression on the BEAT2 dataset, while remaining computationally compact and suitable for real-time deployment on embodied agents."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That text and emotion labels alone are sufficient to accurately predict iconic gestures without audio cues, and that the BEAT2 dataset captures representative real-world co-speech behavior for this task."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Lightweight transformer predicts iconic gesture placement and intensity from text and emotion for robot co-speech, outperforming GPT-4o on BEAT2 without audio input."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A lightweight transformer predicts iconic gestures for robots from text and emotion alone, outperforming GPT-4o on the BEAT2 dataset."}],"snapshot_sha256":"e13555ac88faff9d6a167b6bc9b727932bb317d1b4b28eb79bc2d15f1b28fd12"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.11417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Co-speech gestures increase engagement and improve speech understanding. Most data-driven robot systems generate rhythmic beat-like motion, yet few integrate semantic emphasis. To address this, we propose a lightweight transformer that derives iconic gesture placement and intensity from text and emotion alone, requiring no audio input at inference time. The model outperforms GPT-4o in both semantic gesture placement classification and intensity regression on the BEAT2 dataset, while remaining computationally compact and suitable for real-time deployment on embodied agents.","authors_text":"Christian Arzate Cruz, Edwin C. Montiel-Vazquez, Giorgos Giannakakis, Randy Gomez, Stefanos Gkikas, Thomas Kassiotis","cross_cats":["cs.AI"],"headline":"A lightweight transformer predicts iconic gestures for robots from text and emotion alone, outperforming GPT-4o on the BEAT2 dataset.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-13T13:02:02Z","title":"Efficient Emotion-Aware Iconic Gesture Prediction for Robot Co-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.11417","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-13T06:48:52.143415Z","id":"400ba12e-c16c-4b60-93fc-490d5230b479","model_set":{"reader":"grok-4.3"},"one_line_summary":"Lightweight transformer predicts iconic gesture placement and intensity from text and emotion for robot co-speech, outperforming GPT-4o on BEAT2 without audio input.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A lightweight transformer predicts iconic gestures for robots from text and emotion alone, outperforming GPT-4o on the BEAT2 dataset.","strongest_claim":"The lightweight transformer outperforms GPT-4o in both semantic gesture placement classification and intensity regression on the BEAT2 dataset, while remaining computationally compact and suitable for real-time deployment on embodied agents.","weakest_assumption":"That text and emotion labels alone are sufficient to accurately predict iconic gestures without audio cues, and that the BEAT2 dataset captures representative real-world co-speech behavior for this task."}},"verdict_id":"400ba12e-c16c-4b60-93fc-490d5230b479"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:265db48f2a14a13491dba6bf4a0445b2ae5419993e23dca8f50c6ded055b818a","target":"record","created_at":"2026-05-20T00:03:11Z","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":"30775d302a5fb53e0da60609764eb2a71792c8209dfa484574c8a97a1fdac2a2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-13T13:02:02Z","title_canon_sha256":"01d5a91e32895bda6d5ae992d1cd0dcb5ad5181288ae3d60a3a389127a462214"},"schema_version":"1.0","source":{"id":"2604.11417","kind":"arxiv","version":4}},"canonical_sha256":"fceb38737226fa624cb034195265a03d7d5b9565dee3a935a35776c41fbef9ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fceb38737226fa624cb034195265a03d7d5b9565dee3a935a35776c41fbef9ef","first_computed_at":"2026-05-20T00:03:11.131473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:11.131473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v619cTRjFtZXMXzkI5oIymVFIIyI4MtZm5Il4hMjbp1CD6My4Zgj3qHoRevmpuA6u872yqdJIEdKKQjOQwukCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:11.132292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.11417","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:265db48f2a14a13491dba6bf4a0445b2ae5419993e23dca8f50c6ded055b818a","sha256:e085b0fdb13bb7e6d2f764e1ba43048331ca48e87c7d83ac441b2f005c24b045"],"state_sha256":"f952b6faaca5bb281372ee04a18dc449242e86e98e260d6ed8707a1b6ced3e7d"}