{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FRWAH3IQ7RUSLDAATCSS2XSBES","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":"ccfc06eae06c31c849351f111bad2ceced9330094d2016b63383e2d32a38452a","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-04-02T13:15:59Z","title_canon_sha256":"995d78ec06874dfab37fedd525e16e62f13bc630e55dfc8244befb1c12da1cfa"},"schema_version":"1.0","source":{"id":"2504.01708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01708","created_at":"2026-07-05T10:43:28Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01708v1","created_at":"2026-07-05T10:43:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01708","created_at":"2026-07-05T10:43:28Z"},{"alias_kind":"pith_short_12","alias_value":"FRWAH3IQ7RUS","created_at":"2026-07-05T10:43:28Z"},{"alias_kind":"pith_short_16","alias_value":"FRWAH3IQ7RUSLDAA","created_at":"2026-07-05T10:43:28Z"},{"alias_kind":"pith_short_8","alias_value":"FRWAH3IQ","created_at":"2026-07-05T10:43:28Z"}],"graph_snapshots":[{"event_id":"sha256:c507a9af91530faa3c2e9236b4f693eb3017f154245c23174296a49385729ba7","target":"graph","created_at":"2026-07-05T10:43:28Z","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/2504.01708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As human-robot collaboration advances, natural and flexible communication methods are essential for effective robot control. Traditional methods relying on a single modality or rigid rules struggle with noisy or misaligned data as well as with object descriptions that do not perfectly fit the predefined object names (e.g. 'Pick that red object'). We introduce TransforMerger, a transformer-based reasoning model that infers a structured action command for robotic manipulation based on fused voice and gesture inputs. Our approach merges multimodal data into a single unified sentence, which is the","authors_text":"Karla Stepanova, Petr Vanc","cross_cats":["cs.HC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-04-02T13:15:59Z","title":"TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01708","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:fb488d31979d2783b96fea1f22445c6fabfb43c80152d15a7c794b039511af33","target":"record","created_at":"2026-07-05T10:43:28Z","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":"ccfc06eae06c31c849351f111bad2ceced9330094d2016b63383e2d32a38452a","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-04-02T13:15:59Z","title_canon_sha256":"995d78ec06874dfab37fedd525e16e62f13bc630e55dfc8244befb1c12da1cfa"},"schema_version":"1.0","source":{"id":"2504.01708","kind":"arxiv","version":1}},"canonical_sha256":"2c6c03ed10fc69258c0098a52d5e4124bdbe510b1cedaf8ce550c89a3bd13065","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c6c03ed10fc69258c0098a52d5e4124bdbe510b1cedaf8ce550c89a3bd13065","first_computed_at":"2026-07-05T10:43:28.862648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:28.862648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5b2E5hrpnxjjkvGOmPjmJAVL3vU4J0vtxAwG1/sxm8RWpKs6/+hi6l6MJ9blmHJNUNvi1jlbQGM7kNADUe8ECA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:28.863080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb488d31979d2783b96fea1f22445c6fabfb43c80152d15a7c794b039511af33","sha256:c507a9af91530faa3c2e9236b4f693eb3017f154245c23174296a49385729ba7"],"state_sha256":"437612f6fd5ab59de2ea0757714966d56a6b0a20bc428695b181397dd4430c9c"}