{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YW6ELPN4XO43ZOBTGUMOJD47QB","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":"30689c14c49d17f927711280543220c8f0dfdc9c287628b48d6ae199c5856a50","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-25T16:01:38Z","title_canon_sha256":"e2e778015cefe73e4c00f14f675714a228349c4a319566141c1401b995cefceb"},"schema_version":"1.0","source":{"id":"2506.20566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20566","created_at":"2026-07-05T11:27:07Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20566v1","created_at":"2026-07-05T11:27:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20566","created_at":"2026-07-05T11:27:07Z"},{"alias_kind":"pith_short_12","alias_value":"YW6ELPN4XO43","created_at":"2026-07-05T11:27:07Z"},{"alias_kind":"pith_short_16","alias_value":"YW6ELPN4XO43ZOBT","created_at":"2026-07-05T11:27:07Z"},{"alias_kind":"pith_short_8","alias_value":"YW6ELPN4","created_at":"2026-07-05T11:27:07Z"}],"graph_snapshots":[{"event_id":"sha256:730146f21a6dfb9d6455e6dd17de0effcd029263bf5a1315e0c00225ac27292c","target":"graph","created_at":"2026-07-05T11:27:07Z","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/2506.20566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-time human perception is crucial for effective human-robot interaction (HRI). Large vision-language models (VLMs) offer promising generalizable perceptual capabilities but often suffer from high latency, which negatively impacts user experience and limits VLM applicability in real-world scenarios. To systematically study VLM capabilities in human perception for HRI and performance-latency trade-offs, we introduce HRIBench, a visual question-answering (VQA) benchmark designed to evaluate VLMs across a diverse set of human perceptual tasks critical for HRI. HRIBench covers five key domains:","authors_text":"Daniel Seita, Enyu Zhao, Jingzhen Wang, Kaleen Shrestha, Maja Matari\\'c, Mengxue Fu, Nathaniel Dennler, Xinyang Xu, Zhonghao Shi","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-25T16:01:38Z","title":"HRIBench: Benchmarking Vision-Language Models for Real-Time Human Perception in Human-Robot Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20566","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":"sha256:4050e01301ec178b84366d5f06b8fb1ab087722da52bdf1ac2258a4bf8325b7d","target":"record","created_at":"2026-07-05T11:27:07Z","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":"30689c14c49d17f927711280543220c8f0dfdc9c287628b48d6ae199c5856a50","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-25T16:01:38Z","title_canon_sha256":"e2e778015cefe73e4c00f14f675714a228349c4a319566141c1401b995cefceb"},"schema_version":"1.0","source":{"id":"2506.20566","kind":"arxiv","version":1}},"canonical_sha256":"c5bc45bdbcbbb9bcb8333518e48f9f8044cef10419d8bff9bdd0f20281f1ec12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5bc45bdbcbbb9bcb8333518e48f9f8044cef10419d8bff9bdd0f20281f1ec12","first_computed_at":"2026-07-05T11:27:07.957437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:07.957437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yvQlETHEj89/6Q2cAzfYBEIJiUiKSReSe2y/dzLKWJ1Wyxf+Sbrx5mudw/9nkc9Op+s0oPqEk/DqS19gyDRyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:07.957903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4050e01301ec178b84366d5f06b8fb1ab087722da52bdf1ac2258a4bf8325b7d","sha256:730146f21a6dfb9d6455e6dd17de0effcd029263bf5a1315e0c00225ac27292c"],"state_sha256":"14b22dfa1190e2f611499898423e0b9054a31a8c961807828dea88dfac292239"}