{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N73JMEGDBQRGFRKEYQ3NHVWMGF","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":"085b7b2ac78fff77bd81bc0df28cdbecc8b274ef5d47c27c9cf2bce47bfd4081","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-06T15:21:42Z","title_canon_sha256":"35dd7ba0c46647281a24b70b0b30ea7f3f0633c0a118a1188232554477735a6c"},"schema_version":"1.0","source":{"id":"2608.06154","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06154","created_at":"2026-08-07T01:40:49Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06154v1","created_at":"2026-08-07T01:40:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06154","created_at":"2026-08-07T01:40:49Z"},{"alias_kind":"pith_short_12","alias_value":"N73JMEGDBQRG","created_at":"2026-08-07T01:40:49Z"},{"alias_kind":"pith_short_16","alias_value":"N73JMEGDBQRGFRKE","created_at":"2026-08-07T01:40:49Z"},{"alias_kind":"pith_short_8","alias_value":"N73JMEGD","created_at":"2026-08-07T01:40:49Z"}],"graph_snapshots":[{"event_id":"sha256:da3c33a4c01b44c11ffb71184223f1b241db7e21032f9bc2971b894515d87f3f","target":"graph","created_at":"2026-08-07T01:40:49Z","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/2608.06154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are increasingly used as zero-shot controllers, but successful trajectories do not necessarily show that decisions are grounded in visual input: simulator dynamics and conservative action priors can produce favourable scores without meaningful perception. We investigate this with an input-ablation battery: blind-image controls, repeated identical inputs, lane-axis reflection, non-visual baselines, and pipeline-integrity checks. Across nine direct-action models, six structured local VLMs, and an exploratory VLM-MPC hierarchy, we analyse 32,874 scored calls over two","authors_text":"Dayani Plasencia, Diego S\\'anchez, I. de Zarz\\`a, J. de Curt\\`o","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-06T15:21:42Z","title":"Visual Grounding in Zero-Shot Vision-Language Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06154","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":"sha256:28df5dd1bad3aef1638b5a5a8f4ed125c1c51157846b2ca85a06a72fe47578e2","target":"record","created_at":"2026-08-07T01:40:49Z","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":"085b7b2ac78fff77bd81bc0df28cdbecc8b274ef5d47c27c9cf2bce47bfd4081","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-06T15:21:42Z","title_canon_sha256":"35dd7ba0c46647281a24b70b0b30ea7f3f0633c0a118a1188232554477735a6c"},"schema_version":"1.0","source":{"id":"2608.06154","kind":"arxiv","version":1}},"canonical_sha256":"6ff69610c30c2262c544c436d3d6cc3146c3da9ef1ec400853d35163970d1541","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ff69610c30c2262c544c436d3d6cc3146c3da9ef1ec400853d35163970d1541","first_computed_at":"2026-08-07T01:40:49.948706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T01:40:49.948706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xo7BHuCO+Kvofj/V54URwLdeHiB2uhR0R3+DqzDNywMhERdMefJyid9Cenx04kzTC37B/7e5zSdEieFxk3/oBw==","signature_status":"signed_v1","signed_at":"2026-08-07T01:40:49.950322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06154","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28df5dd1bad3aef1638b5a5a8f4ed125c1c51157846b2ca85a06a72fe47578e2","sha256:da3c33a4c01b44c11ffb71184223f1b241db7e21032f9bc2971b894515d87f3f"],"state_sha256":"56aebe89ff5f98442fd090b528ea81e5ef18170a8e0ae90c66c32c567ac5a5c8"}