{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GXO3356LJOZ2TGJUXRHPRFOSIG","short_pith_number":"pith:GXO3356L","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"},"canonical_sha256":"35ddbdf7cb4bb3a99934bc4ef895d2418f68a22175ff086e3b288f131f9188d5","source":{"kind":"arxiv","id":"2606.02277","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02277","created_at":"2026-06-02T03:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02277v1","created_at":"2026-06-02T03:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02277","created_at":"2026-06-02T03:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"GXO3356LJOZ2","created_at":"2026-06-02T03:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"GXO3356LJOZ2TGJU","created_at":"2026-06-02T03:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"GXO3356L","created_at":"2026-06-02T03:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GXO3356LJOZ2TGJUXRHPRFOSIG","target":"record","payload":{"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"},"canonical_sha256":"35ddbdf7cb4bb3a99934bc4ef895d2418f68a22175ff086e3b288f131f9188d5","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"},"source_kind":"arxiv","source_id":"2606.02277","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T03:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1snUXyrCIJ/pYM+UREsV2NiR1oHOY7qaRD0T5GSK8BU4HhpAkTgGj8du/Okvxw6xnryC2/VDRm3xyRFFt35bBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T12:16:24.742990Z"},"content_sha256":"115bdf22793a4c0a6dbe3e1c604c754ad73331b45e260cd873152247913a18b2","schema_version":"1.0","event_id":"sha256:115bdf22793a4c0a6dbe3e1c604c754ad73331b45e260cd873152247913a18b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GXO3356LJOZ2TGJUXRHPRFOSIG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T03:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h5jZm3LNKKqxEENeVGFGHupRoiPJIWQ8Rnm2klFhgB+jUh+uoDGtIhgYNZeIXEuCVTeJsqTPJfLKLPgaB5ZKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T12:16:24.743768Z"},"content_sha256":"73c730cfec928485c4a22cc82c1a47a45d34d891fc3511582ffa7658161a7de8","schema_version":"1.0","event_id":"sha256:73c730cfec928485c4a22cc82c1a47a45d34d891fc3511582ffa7658161a7de8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/bundle.json","state_url":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-06T12:16:24Z","links":{"resolver":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG","bundle":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/bundle.json","state":"https://pith.science/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GXO3356LJOZ2TGJUXRHPRFOSIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GXO3356LJOZ2TGJUXRHPRFOSIG","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":"c94468b9fe9d033156105b076ecb00654a9da92dd76aa350d6bdd4232f8ac53c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-01T14:02:37Z","title_canon_sha256":"7c4cbe3f68b6e38b5794aba68cbc8faffde6e1d72b9e50ef6a9b3082e5bc21d4"},"schema_version":"1.0","source":{"id":"2606.02277","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02277","created_at":"2026-06-02T03:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02277v1","created_at":"2026-06-02T03:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02277","created_at":"2026-06-02T03:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"GXO3356LJOZ2","created_at":"2026-06-02T03:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"GXO3356LJOZ2TGJU","created_at":"2026-06-02T03:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"GXO3356L","created_at":"2026-06-02T03:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:73c730cfec928485c4a22cc82c1a47a45d34d891fc3511582ffa7658161a7de8","target":"graph","created_at":"2026-06-02T03:04:54Z","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/2606.02277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-01T14:02:37Z","title":"RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02277","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":"sha256:115bdf22793a4c0a6dbe3e1c604c754ad73331b45e260cd873152247913a18b2","target":"record","created_at":"2026-06-02T03:04:54Z","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":"c94468b9fe9d033156105b076ecb00654a9da92dd76aa350d6bdd4232f8ac53c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-01T14:02:37Z","title_canon_sha256":"7c4cbe3f68b6e38b5794aba68cbc8faffde6e1d72b9e50ef6a9b3082e5bc21d4"},"schema_version":"1.0","source":{"id":"2606.02277","kind":"arxiv","version":1}},"canonical_sha256":"35ddbdf7cb4bb3a99934bc4ef895d2418f68a22175ff086e3b288f131f9188d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35ddbdf7cb4bb3a99934bc4ef895d2418f68a22175ff086e3b288f131f9188d5","first_computed_at":"2026-06-02T03:04:54.889134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:04:54.889134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MZlrF5o4BqyJqw4nWJycC1F5I6rPOoDfu/PNrV4zuk98pC5mYbPHNoHbXIS43Rg2qPM3gs7AGux+yR9avzroDA==","signature_status":"signed_v1","signed_at":"2026-06-02T03:04:54.889491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02277","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:115bdf22793a4c0a6dbe3e1c604c754ad73331b45e260cd873152247913a18b2","sha256:73c730cfec928485c4a22cc82c1a47a45d34d891fc3511582ffa7658161a7de8"],"state_sha256":"6c82b85262ccd24872ff5f493474c849bda845661504feaf2aed03895356e6ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y4p1KPrvkkUGFiblihDTG9TUmj9oApklNJCQbKKEhvG6ZW/ZQo1r2oR5bnVVe63hVVxVDFjp+CE3R8ZrADtDAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T12:16:24.747934Z","bundle_sha256":"e5589ce3570e2990679e7d693567f954071d2ac460c32bc366cb8c11dc8e626d"}}