{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A2NVGEUQWOSKYYFSBGY4UMQ4PW","short_pith_number":"pith:A2NVGEUQ","schema_version":"1.0","canonical_sha256":"069b531290b3a4ac60b209b1ca321c7d8f16b5f9b7780e4d4eae88f0cdba5383","source":{"kind":"arxiv","id":"2404.08424","version":3},"attestation_state":"computed","paper":{"title":"Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.RO","authors_text":"Hassan Ali, Philipp Allgeuer, Stefan Wermter","submitted_at":"2024-04-12T12:15:14Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.08424","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-12T12:15:14Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"d5ea76fc070da0b422f32ef2eb08cb03a6b0832efd3de7e228498689281f9ca8","abstract_canon_sha256":"d6c8198fdab233990e86ed6eac5f8b7439bc0b714dc39141f9c2cc599da51390"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:51.771816Z","signature_b64":"RLYEw5PU60VFsZW4xdoDE3BwknoGJbmbG86RoIJCFg81aAtUEu1JH7tLhPcYFTHIeCIq8lpLiU8xV9p9CxT3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"069b531290b3a4ac60b209b1ca321c7d8f16b5f9b7780e4d4eae88f0cdba5383","last_reissued_at":"2026-07-05T10:45:51.771331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:51.771331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.RO","authors_text":"Hassan Ali, Philipp Allgeuer, Stefan Wermter","submitted_at":"2024-04-12T12:15:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08424","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.08424/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.08424","created_at":"2026-07-05T10:45:51.771388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08424v3","created_at":"2026-07-05T10:45:51.771388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08424","created_at":"2026-07-05T10:45:51.771388+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2NVGEUQWOSK","created_at":"2026-07-05T10:45:51.771388+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2NVGEUQWOSKYYFS","created_at":"2026-07-05T10:45:51.771388+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2NVGEUQ","created_at":"2026-07-05T10:45:51.771388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18153","citing_title":"Leveraging AI for Direct Bystander Intervention Against Cyberbullying","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A2NVGEUQWOSKYYFSBGY4UMQ4PW","json":"https://pith.science/pith/A2NVGEUQWOSKYYFSBGY4UMQ4PW.json","graph_json":"https://pith.science/api/pith-number/A2NVGEUQWOSKYYFSBGY4UMQ4PW/graph.json","events_json":"https://pith.science/api/pith-number/A2NVGEUQWOSKYYFSBGY4UMQ4PW/events.json","paper":"https://pith.science/paper/A2NVGEUQ"},"agent_actions":{"view_html":"https://pith.science/pith/A2NVGEUQWOSKYYFSBGY4UMQ4PW","download_json":"https://pith.science/pith/A2NVGEUQWOSKYYFSBGY4UMQ4PW.json","view_paper":"https://pith.science/paper/A2NVGEUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08424&json=true","fetch_graph":"https://pith.science/api/pith-number/A2NVGEUQWOSKYYFSBGY4UMQ4PW/graph.json","fetch_events":"https://pith.science/api/pith-number/A2NVGEUQWOSKYYFSBGY4UMQ4PW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2NVGEUQWOSKYYFSBGY4UMQ4PW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2NVGEUQWOSKYYFSBGY4UMQ4PW/action/storage_attestation","attest_author":"https://pith.science/pith/A2NVGEUQWOSKYYFSBGY4UMQ4PW/action/author_attestation","sign_citation":"https://pith.science/pith/A2NVGEUQWOSKYYFSBGY4UMQ4PW/action/citation_signature","submit_replication":"https://pith.science/pith/A2NVGEUQWOSKYYFSBGY4UMQ4PW/action/replication_record"}},"created_at":"2026-07-05T10:45:51.771388+00:00","updated_at":"2026-07-05T10:45:51.771388+00:00"}