{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O2W3WOB4I6WXL62HAJ74YJBQAW","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":"0a0cda442fa264b99c1f75074f0689d89d2f98f83fb1e2a182042abbd21db82a","cross_cats_sorted":["cs.HC","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-25T19:36:45Z","title_canon_sha256":"37da506da415169ce0406c12062aa9ea60ea065492fb51731040fd837cc0fdfa"},"schema_version":"1.0","source":{"id":"2506.20795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20795","created_at":"2026-07-05T11:27:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20795v1","created_at":"2026-07-05T11:27:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20795","created_at":"2026-07-05T11:27:34Z"},{"alias_kind":"pith_short_12","alias_value":"O2W3WOB4I6WX","created_at":"2026-07-05T11:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"O2W3WOB4I6WXL62H","created_at":"2026-07-05T11:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"O2W3WOB4","created_at":"2026-07-05T11:27:34Z"}],"graph_snapshots":[{"event_id":"sha256:843fdb963d0f74a61c99b5ae32a793d1bbedef2f0805c52ffbf6d097cba35f3a","target":"graph","created_at":"2026-07-05T11:27:34Z","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/2506.20795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gestures enable non-verbal human-robot communication, especially in noisy environments like agile production. Traditional deep learning-based gesture recognition relies on task-specific architectures using images, videos, or skeletal pose estimates as input. Meanwhile, Vision Foundation Models (VFMs) and Vision Language Models (VLMs) with their strong generalization abilities offer potential to reduce system complexity by replacing dedicated task-specific modules. This study investigates adapting such models for dynamic, full-body gesture recognition, comparing V-JEPA (a state-of-the-art VFM),","authors_text":"Anton Burenko, Bastian Leibe, Dennis Mack, Louis Markert, Onur Alp Culha, Stephanie K\\\"as, Timm Linder","cross_cats":["cs.HC","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-25T19:36:45Z","title":"How do Foundation Models Compare to Skeleton-Based Approaches for Gesture Recognition in Human-Robot Interaction?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20795","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":"sha256:8505d5309a7ef0024ff2139b6b368c35d20e6b3a9d3b154e3873833128543575","target":"record","created_at":"2026-07-05T11:27:34Z","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":"0a0cda442fa264b99c1f75074f0689d89d2f98f83fb1e2a182042abbd21db82a","cross_cats_sorted":["cs.HC","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-25T19:36:45Z","title_canon_sha256":"37da506da415169ce0406c12062aa9ea60ea065492fb51731040fd837cc0fdfa"},"schema_version":"1.0","source":{"id":"2506.20795","kind":"arxiv","version":1}},"canonical_sha256":"76adbb383c47ad75fb47027fcc2430059681f74608835a5cf6a1092b7182da1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76adbb383c47ad75fb47027fcc2430059681f74608835a5cf6a1092b7182da1b","first_computed_at":"2026-07-05T11:27:34.164276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:34.164276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oLwY8RN9DBnAHNIwl3WfeUebRVrSSLyiBC5hKEPgFydQxMhNLPDxc5dGGQwz1wdVD/SOvWVK9pf3BZyTJsGEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:34.164804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8505d5309a7ef0024ff2139b6b368c35d20e6b3a9d3b154e3873833128543575","sha256:843fdb963d0f74a61c99b5ae32a793d1bbedef2f0805c52ffbf6d097cba35f3a"],"state_sha256":"2ac642d96f45c08eb14b872efcabe7ef5e215beee81cec53bec8b74f06f39433"}