{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BB5H5OOLWXR2OA3YV53BIHENFG","short_pith_number":"pith:BB5H5OOL","schema_version":"1.0","canonical_sha256":"087a7eb9cbb5e3a70378af76141c8d2989168783054cd5f8560696f3cda4c2f2","source":{"kind":"arxiv","id":"2607.00530","version":1},"attestation_state":"computed","paper":{"title":"From Technical Metrics to User Perception: A User Study of a Multimodal Human-Robot Interaction System for Object Detection and Grasping","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jian Song, Shen Guanting, Tian Zi","submitted_at":"2026-07-01T07:19:00Z","abstract_excerpt":"Improvements in the technical performance of human--robot interaction (HRI) systems do not automatically translate into differences that human users can detect during live interaction. This paper investigates whether a 15 percentage point gain in end-to-end task success (from 75% in a multimodal baseline system to 90% in an improved configuration identified through a prior ablation study) is sufficient to produce consistent and measurable differences in user perception. The baseline system combines Whisper for speech recognition, Florence-2 for open-vocabulary object detection, LLaMA 3.1 for a"},"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":"2607.00530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-01T07:19:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"16f17992495294e6e00e61d35e53bdcd3e10d2d5e7c9119eef156bf5bfb07e37","abstract_canon_sha256":"f20e14c128ba41c8d670eec325d8b117c96791ae3e0dc70475241c3c527f9f31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:46.746080Z","signature_b64":"b0UfKIQuGkj7mfPx4NDXCR/wEOi7+/yEkmZmIwyaa4N8g9TprOFeW6ZGRwLhTV9WB1vW8VZSS3h8VKS8xbBfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"087a7eb9cbb5e3a70378af76141c8d2989168783054cd5f8560696f3cda4c2f2","last_reissued_at":"2026-07-02T01:17:46.745659Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:46.745659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Technical Metrics to User Perception: A User Study of a Multimodal Human-Robot Interaction System for Object Detection and Grasping","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jian Song, Shen Guanting, Tian Zi","submitted_at":"2026-07-01T07:19:00Z","abstract_excerpt":"Improvements in the technical performance of human--robot interaction (HRI) systems do not automatically translate into differences that human users can detect during live interaction. This paper investigates whether a 15 percentage point gain in end-to-end task success (from 75% in a multimodal baseline system to 90% in an improved configuration identified through a prior ablation study) is sufficient to produce consistent and measurable differences in user perception. The baseline system combines Whisper for speech recognition, Florence-2 for open-vocabulary object detection, LLaMA 3.1 for a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00530","kind":"arxiv","version":1},"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/2607.00530/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":"2607.00530","created_at":"2026-07-02T01:17:46.745739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00530v1","created_at":"2026-07-02T01:17:46.745739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00530","created_at":"2026-07-02T01:17:46.745739+00:00"},{"alias_kind":"pith_short_12","alias_value":"BB5H5OOLWXR2","created_at":"2026-07-02T01:17:46.745739+00:00"},{"alias_kind":"pith_short_16","alias_value":"BB5H5OOLWXR2OA3Y","created_at":"2026-07-02T01:17:46.745739+00:00"},{"alias_kind":"pith_short_8","alias_value":"BB5H5OOL","created_at":"2026-07-02T01:17:46.745739+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BB5H5OOLWXR2OA3YV53BIHENFG","json":"https://pith.science/pith/BB5H5OOLWXR2OA3YV53BIHENFG.json","graph_json":"https://pith.science/api/pith-number/BB5H5OOLWXR2OA3YV53BIHENFG/graph.json","events_json":"https://pith.science/api/pith-number/BB5H5OOLWXR2OA3YV53BIHENFG/events.json","paper":"https://pith.science/paper/BB5H5OOL"},"agent_actions":{"view_html":"https://pith.science/pith/BB5H5OOLWXR2OA3YV53BIHENFG","download_json":"https://pith.science/pith/BB5H5OOLWXR2OA3YV53BIHENFG.json","view_paper":"https://pith.science/paper/BB5H5OOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00530&json=true","fetch_graph":"https://pith.science/api/pith-number/BB5H5OOLWXR2OA3YV53BIHENFG/graph.json","fetch_events":"https://pith.science/api/pith-number/BB5H5OOLWXR2OA3YV53BIHENFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BB5H5OOLWXR2OA3YV53BIHENFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BB5H5OOLWXR2OA3YV53BIHENFG/action/storage_attestation","attest_author":"https://pith.science/pith/BB5H5OOLWXR2OA3YV53BIHENFG/action/author_attestation","sign_citation":"https://pith.science/pith/BB5H5OOLWXR2OA3YV53BIHENFG/action/citation_signature","submit_replication":"https://pith.science/pith/BB5H5OOLWXR2OA3YV53BIHENFG/action/replication_record"}},"created_at":"2026-07-02T01:17:46.745739+00:00","updated_at":"2026-07-02T01:17:46.745739+00:00"}