{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JJXKTJXRRMQIC5AQ4IZS3HBBKD","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":"6cca88c431048806221c38935eff2cd299ddec4da22a52456814b6b8083ee4cf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-23T12:02:36Z","title_canon_sha256":"6a76a667a9f14fa5f1cadad55f4b8095461098f5580a91a7a615b20f8165097e"},"schema_version":"1.0","source":{"id":"2606.24472","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24472","created_at":"2026-06-24T01:15:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24472v1","created_at":"2026-06-24T01:15:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24472","created_at":"2026-06-24T01:15:31Z"},{"alias_kind":"pith_short_12","alias_value":"JJXKTJXRRMQI","created_at":"2026-06-24T01:15:31Z"},{"alias_kind":"pith_short_16","alias_value":"JJXKTJXRRMQIC5AQ","created_at":"2026-06-24T01:15:31Z"},{"alias_kind":"pith_short_8","alias_value":"JJXKTJXR","created_at":"2026-06-24T01:15:31Z"}],"graph_snapshots":[{"event_id":"sha256:19ecdfaeaebf3f63c46f5cb59c90dfc1c642d821c2cba8ecb51f79b36e29bcbe","target":"graph","created_at":"2026-06-24T01:15:31Z","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/2606.24472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language-action (VLA) models have made rapid progress in generalist robot manipulation by harnessing semantic knowledge from pretrained vision-language backbones, but their visual tokens remain grounded in 2D image coordinates rather than the calibrated geometry of the robot's cameras -- a mismatch especially pronounced in multi-camera setups, where views are coupled by known intrinsics and extrinsics yet processed as independent images. We propose G$^3$VLA, a camera-aware geometric module that injects calibrated structure into the visual-token stream of a pretrained VLA without alterin","authors_text":"Artur Habuda, Fares Abu-Dakka, Khuyen Pham, Li Guo, Tran Nguyen Le, Yanheng Zhu, Yongzhe Zhao, Yue Peng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-23T12:02:36Z","title":"G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24472","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":"sha256:0e5520b55f5682dcacaf2dd4a28aafb6d2d42784eee747ba9a22c32668120883","target":"record","created_at":"2026-06-24T01:15:31Z","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":"6cca88c431048806221c38935eff2cd299ddec4da22a52456814b6b8083ee4cf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-23T12:02:36Z","title_canon_sha256":"6a76a667a9f14fa5f1cadad55f4b8095461098f5580a91a7a615b20f8165097e"},"schema_version":"1.0","source":{"id":"2606.24472","kind":"arxiv","version":1}},"canonical_sha256":"4a6ea9a6f18b20817410e2332d9c2150e10fcd0fa0c9f7046d479b4173979dc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a6ea9a6f18b20817410e2332d9c2150e10fcd0fa0c9f7046d479b4173979dc2","first_computed_at":"2026-06-24T01:15:31.389490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:31.389490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZY69UCxrdw021LSBUQHFK+/ZiKobM4jS5SXdV4nmi2BizF8fFd8kAmThcZdiWB8ulXlHSuV307pdBF+FdEcUDw==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:31.389855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24472","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e5520b55f5682dcacaf2dd4a28aafb6d2d42784eee747ba9a22c32668120883","sha256:19ecdfaeaebf3f63c46f5cb59c90dfc1c642d821c2cba8ecb51f79b36e29bcbe"],"state_sha256":"cb64ea1d9d5888f8b80ed4a18a3ab66d463c00808c836d222a5f4b739026731e"}