{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NXIRZ2MARPXWQIETZZYOVDTQG7","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":"1d2351a04b59a90e932247e0d2d982eee3d4556d8779c92096eee3c6c391b90c","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T18:59:20Z","title_canon_sha256":"f39356bf6e3747bf7dd276257c08a5249f673ebb056b3f7664f0ee3f6f0a4638"},"schema_version":"1.0","source":{"id":"2602.17659","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17659","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17659v2","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17659","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"pith_short_12","alias_value":"NXIRZ2MARPXW","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"pith_short_16","alias_value":"NXIRZ2MARPXWQIET","created_at":"2026-07-16T01:22:35Z"},{"alias_kind":"pith_short_8","alias_value":"NXIRZ2MA","created_at":"2026-07-16T01:22:35Z"}],"graph_snapshots":[{"event_id":"sha256:ec0831b48a08e10d964a06da79b0dd89ad136219a0e7ee8484c605902be1ab5a","target":"graph","created_at":"2026-07-16T01:22:35Z","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/2602.17659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action models (VLAs) promise to ground language instructions in robot control, yet in practice often fail to faithfully follow language. When presented with instructions that lack strong scene-specific supervision, VLAs suffer from counterfactual failures: they act based on vision shortcuts induced by dataset biases, repeatedly executing well-learned behaviors and selecting objects frequently seen during training regardless of language intent. To systematically study it, we introduce LIBERO-CF, the first counterfactual benchmark for VLAs that evaluates language following capabi","authors_text":"Daniel Szafir, Dong Jing, Jiaqi Liu, Mingyu Ding, Yuchun Feng, Yue Yang, Yu Fang, Zhenyu Wei","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T18:59:20Z","title":"When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17659","kind":"arxiv","version":2},"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":"sha256:0719f8f707cefbe9b553d5a95dc45a21149a7af421aa704bc447cdab14eccca4","target":"record","created_at":"2026-07-16T01:22:35Z","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":"1d2351a04b59a90e932247e0d2d982eee3d4556d8779c92096eee3c6c391b90c","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T18:59:20Z","title_canon_sha256":"f39356bf6e3747bf7dd276257c08a5249f673ebb056b3f7664f0ee3f6f0a4638"},"schema_version":"1.0","source":{"id":"2602.17659","kind":"arxiv","version":2}},"canonical_sha256":"6dd11ce9808bef682093ce70ea8e7037cfb93b4675739478477f7360f23f70b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dd11ce9808bef682093ce70ea8e7037cfb93b4675739478477f7360f23f70b8","first_computed_at":"2026-07-16T01:22:35.107340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:22:35.107340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DMXcpt4EHvdZ5XEldBvAlr65V/iGF5Tqhhm7xTeS1sYabna74CWanwBnNGBujrY4GvhEW99LlRPIAYjWtL8KCA==","signature_status":"signed_v1","signed_at":"2026-07-16T01:22:35.108339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.17659","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0719f8f707cefbe9b553d5a95dc45a21149a7af421aa704bc447cdab14eccca4","sha256:ec0831b48a08e10d964a06da79b0dd89ad136219a0e7ee8484c605902be1ab5a"],"state_sha256":"bab41d7a0fa3617a28bff408f4e8b1f1b6e9e71600f9dad6309b16124c73c1e5"}