{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GXO3356LJOZ2TGJUXRHPRFOSIG","short_pith_number":"pith:GXO3356L","schema_version":"1.0","canonical_sha256":"35ddbdf7cb4bb3a99934bc4ef895d2418f68a22175ff086e3b288f131f9188d5","source":{"kind":"arxiv","id":"2606.02277","version":1},"attestation_state":"computed","paper":{"title":"RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bailing Wang, Bin Yu, Changti Wu, Cong Huang, Haishan Liu, Kai Chen, Ruina Hu, Shijie Lian, Xiaopeng Lin, Yao Zhang, Yuliang Wei, Zhaolong Shen","submitted_at":"2026-06-01T14:02:37Z","abstract_excerpt":"Vision-language-action (VLA) models are built on the premise that semantic understanding from pretrained language or vision-language backbones should guide robot action prediction. Yet robot fine-tuning is optimized as imitation over task-specific action distributions, and many evaluations can be solved through visual or instruction-action shortcuts. We introduce RoboSemanticBench (RSB), an embodied benchmark for diagnosing semantic grounding in action prediction: whether post-trained VLA models can use complex instruction semantics to select and manipulate the correct physical target. In each"},"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":"2606.02277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-01T14:02:37Z","cross_cats_sorted":[],"title_canon_sha256":"7c4cbe3f68b6e38b5794aba68cbc8faffde6e1d72b9e50ef6a9b3082e5bc21d4","abstract_canon_sha256":"c94468b9fe9d033156105b076ecb00654a9da92dd76aa350d6bdd4232f8ac53c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:54.889491Z","signature_b64":"MZlrF5o4BqyJqw4nWJycC1F5I6rPOoDfu/PNrV4zuk98pC5mYbPHNoHbXIS43Rg2qPM3gs7AGux+yR9avzroDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35ddbdf7cb4bb3a99934bc4ef895d2418f68a22175ff086e3b288f131f9188d5","last_reissued_at":"2026-06-02T03:04:54.889134Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:54.889134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bailing Wang, Bin Yu, Changti Wu, Cong Huang, Haishan Liu, Kai Chen, Ruina Hu, Shijie Lian, Xiaopeng Lin, Yao Zhang, Yuliang Wei, Zhaolong Shen","submitted_at":"2026-06-01T14:02:37Z","abstract_excerpt":"Vision-language-action (VLA) models are built on the premise that semantic understanding from pretrained language or vision-language backbones should guide robot action prediction. Yet robot fine-tuning is optimized as imitation over task-specific action distributions, and many evaluations can be solved through visual or instruction-action shortcuts. We introduce RoboSemanticBench (RSB), an embodied benchmark for diagnosing semantic grounding in action prediction: whether post-trained VLA models can use complex instruction semantics to select and manipulate the correct physical target. In each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02277","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/2606.02277/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":"2606.02277","created_at":"2026-06-02T03:04:54.889192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02277v1","created_at":"2026-06-02T03:04:54.889192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02277","created_at":"2026-06-02T03:04:54.889192+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXO3356LJOZ2","created_at":"2026-06-02T03:04:54.889192+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXO3356LJOZ2TGJU","created_at":"2026-06-02T03:04:54.889192+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXO3356L","created_at":"2026-06-02T03:04:54.889192+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/GXO3356LJOZ2TGJUXRHPRFOSIG","json":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG.json","graph_json":"https://pith.science/api/pith-number/GXO3356LJOZ2TGJUXRHPRFOSIG/graph.json","events_json":"https://pith.science/api/pith-number/GXO3356LJOZ2TGJUXRHPRFOSIG/events.json","paper":"https://pith.science/paper/GXO3356L"},"agent_actions":{"view_html":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG","download_json":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG.json","view_paper":"https://pith.science/paper/GXO3356L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02277&json=true","fetch_graph":"https://pith.science/api/pith-number/GXO3356LJOZ2TGJUXRHPRFOSIG/graph.json","fetch_events":"https://pith.science/api/pith-number/GXO3356LJOZ2TGJUXRHPRFOSIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/action/storage_attestation","attest_author":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/action/author_attestation","sign_citation":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/action/citation_signature","submit_replication":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/action/replication_record"}},"created_at":"2026-06-02T03:04:54.889192+00:00","updated_at":"2026-06-02T03:04:54.889192+00:00"}