{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A2NVGEUQWOSKYYFSBGY4UMQ4PW","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":"d6c8198fdab233990e86ed6eac5f8b7439bc0b714dc39141f9c2cc599da51390","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-12T12:15:14Z","title_canon_sha256":"d5ea76fc070da0b422f32ef2eb08cb03a6b0832efd3de7e228498689281f9ca8"},"schema_version":"1.0","source":{"id":"2404.08424","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08424","created_at":"2026-07-05T10:45:51Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08424v3","created_at":"2026-07-05T10:45:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08424","created_at":"2026-07-05T10:45:51Z"},{"alias_kind":"pith_short_12","alias_value":"A2NVGEUQWOSK","created_at":"2026-07-05T10:45:51Z"},{"alias_kind":"pith_short_16","alias_value":"A2NVGEUQWOSKYYFS","created_at":"2026-07-05T10:45:51Z"},{"alias_kind":"pith_short_8","alias_value":"A2NVGEUQ","created_at":"2026-07-05T10:45:51Z"}],"graph_snapshots":[{"event_id":"sha256:7953881396fe745696a10de5332e3fee8124c6a2930a47cccc4f7118e036f44f","target":"graph","created_at":"2026-07-05T10:45:51Z","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/2404.08424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human intention-based systems enable robots to perceive and interpret user actions to interact with humans and adapt to their behavior proactively. Therefore, intention prediction is pivotal in creating a natural interaction with social robots in human-designed environments. In this paper, we examine using Large Language Models (LLMs) to infer human intention in a collaborative object categorization task with a physical robot. We propose a novel multimodal approach that integrates user non-verbal cues, like hand gestures, body poses, and facial expressions, with environment states and user ver","authors_text":"Hassan Ali, Philipp Allgeuer, Stefan Wermter","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-12T12:15:14Z","title":"Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08424","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:a0c3f085073a3e67c226d1e7174a5bf9fa82d11afea182d95c58d554ea1ab33b","target":"record","created_at":"2026-07-05T10:45:51Z","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":"d6c8198fdab233990e86ed6eac5f8b7439bc0b714dc39141f9c2cc599da51390","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-12T12:15:14Z","title_canon_sha256":"d5ea76fc070da0b422f32ef2eb08cb03a6b0832efd3de7e228498689281f9ca8"},"schema_version":"1.0","source":{"id":"2404.08424","kind":"arxiv","version":3}},"canonical_sha256":"069b531290b3a4ac60b209b1ca321c7d8f16b5f9b7780e4d4eae88f0cdba5383","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"069b531290b3a4ac60b209b1ca321c7d8f16b5f9b7780e4d4eae88f0cdba5383","first_computed_at":"2026-07-05T10:45:51.771331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:51.771331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RLYEw5PU60VFsZW4xdoDE3BwknoGJbmbG86RoIJCFg81aAtUEu1JH7tLhPcYFTHIeCIq8lpLiU8xV9p9CxT3Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:51.771816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.08424","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0c3f085073a3e67c226d1e7174a5bf9fa82d11afea182d95c58d554ea1ab33b","sha256:7953881396fe745696a10de5332e3fee8124c6a2930a47cccc4f7118e036f44f"],"state_sha256":"10f2fa5bc5aa58b368557278594ba1cb1e20cc8209d428bc535f0dc0df796e79"}