{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3NF7ZUAMLGQBPAGKZZJVO6HJKL","short_pith_number":"pith:3NF7ZUAM","schema_version":"1.0","canonical_sha256":"db4bfcd00c59a01780cace535778e952fc4030260fd89d65707c7a87d1c0e280","source":{"kind":"arxiv","id":"2405.00693","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Large Language Models in Human-Robot Interaction: A Critical Analysis of Potential and Pitfalls","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.RO","authors_text":"Jesse Atuhurra","submitted_at":"2024-03-26T15:36:40Z","abstract_excerpt":"The emergence of large language models (LLM) and, consequently, vision language models (VLM) has ignited new imaginations among robotics researchers. At this point, the range of applications to which LLM and VLM can be applied in human-robot interaction (HRI), particularly socially assistive robots (SARs), is unchartered territory. However, LLM and VLM present unprecedented opportunities and challenges for SAR integration. We aim to illuminate the opportunities and challenges when roboticists deploy LLM and VLM in SARs. First, we conducted a meta-study of more than 250 papers exploring 1) majo"},"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":"2405.00693","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-26T15:36:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"134a00a2e19173125c4d27b7a636b259b5fcc080ae53bddd9b6ccd169e361682","abstract_canon_sha256":"fac805da443956afbd4ba918d589c8f98c0b22749d6d31289ae64a8c878210d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:56.891768Z","signature_b64":"gI+9ZWuFmiSYIB9I17WHC6abJZmM7DzzcVAvp06/9PAncjSosd+kRRVtRWLwjFPowq5ikqxYDwPIe+ZbRhaEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db4bfcd00c59a01780cace535778e952fc4030260fd89d65707c7a87d1c0e280","last_reissued_at":"2026-07-05T09:40:56.891276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:56.891276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Large Language Models in Human-Robot Interaction: A Critical Analysis of Potential and Pitfalls","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.RO","authors_text":"Jesse Atuhurra","submitted_at":"2024-03-26T15:36:40Z","abstract_excerpt":"The emergence of large language models (LLM) and, consequently, vision language models (VLM) has ignited new imaginations among robotics researchers. At this point, the range of applications to which LLM and VLM can be applied in human-robot interaction (HRI), particularly socially assistive robots (SARs), is unchartered territory. However, LLM and VLM present unprecedented opportunities and challenges for SAR integration. We aim to illuminate the opportunities and challenges when roboticists deploy LLM and VLM in SARs. First, we conducted a meta-study of more than 250 papers exploring 1) majo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00693","kind":"arxiv","version":2},"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/2405.00693/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":"2405.00693","created_at":"2026-07-05T09:40:56.891338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00693v2","created_at":"2026-07-05T09:40:56.891338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00693","created_at":"2026-07-05T09:40:56.891338+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NF7ZUAMLGQB","created_at":"2026-07-05T09:40:56.891338+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NF7ZUAMLGQBPAGK","created_at":"2026-07-05T09:40:56.891338+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NF7ZUAM","created_at":"2026-07-05T09:40:56.891338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00530","citing_title":"From Technical Metrics to User Perception: A User Study of a Multimodal Human-Robot Interaction System for Object Detection and Grasping","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00963","citing_title":"Ablation Study of Multimodal Perception, Language Grounding, and Control for Human-Robot Interaction in an Object Detection and Grasping Task","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NF7ZUAMLGQBPAGKZZJVO6HJKL","json":"https://pith.science/pith/3NF7ZUAMLGQBPAGKZZJVO6HJKL.json","graph_json":"https://pith.science/api/pith-number/3NF7ZUAMLGQBPAGKZZJVO6HJKL/graph.json","events_json":"https://pith.science/api/pith-number/3NF7ZUAMLGQBPAGKZZJVO6HJKL/events.json","paper":"https://pith.science/paper/3NF7ZUAM"},"agent_actions":{"view_html":"https://pith.science/pith/3NF7ZUAMLGQBPAGKZZJVO6HJKL","download_json":"https://pith.science/pith/3NF7ZUAMLGQBPAGKZZJVO6HJKL.json","view_paper":"https://pith.science/paper/3NF7ZUAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00693&json=true","fetch_graph":"https://pith.science/api/pith-number/3NF7ZUAMLGQBPAGKZZJVO6HJKL/graph.json","fetch_events":"https://pith.science/api/pith-number/3NF7ZUAMLGQBPAGKZZJVO6HJKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NF7ZUAMLGQBPAGKZZJVO6HJKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NF7ZUAMLGQBPAGKZZJVO6HJKL/action/storage_attestation","attest_author":"https://pith.science/pith/3NF7ZUAMLGQBPAGKZZJVO6HJKL/action/author_attestation","sign_citation":"https://pith.science/pith/3NF7ZUAMLGQBPAGKZZJVO6HJKL/action/citation_signature","submit_replication":"https://pith.science/pith/3NF7ZUAMLGQBPAGKZZJVO6HJKL/action/replication_record"}},"created_at":"2026-07-05T09:40:56.891338+00:00","updated_at":"2026-07-05T09:40:56.891338+00:00"}