{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJXKTJXRRMQIC5AQ4IZS3HBBKD","short_pith_number":"pith:JJXKTJXR","schema_version":"1.0","canonical_sha256":"4a6ea9a6f18b20817410e2332d9c2150e10fcd0fa0c9f7046d479b4173979dc2","source":{"kind":"arxiv","id":"2606.24472","version":1},"attestation_state":"computed","paper":{"title":"G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Artur Habuda, Fares Abu-Dakka, Khuyen Pham, Li Guo, Tran Nguyen Le, Yanheng Zhu, Yongzhe Zhao, Yue Peng","submitted_at":"2026-06-23T12:02:36Z","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"},"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":"2606.24472","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-23T12:02:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a76a667a9f14fa5f1cadad55f4b8095461098f5580a91a7a615b20f8165097e","abstract_canon_sha256":"6cca88c431048806221c38935eff2cd299ddec4da22a52456814b6b8083ee4cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:31.389855Z","signature_b64":"ZY69UCxrdw021LSBUQHFK+/ZiKobM4jS5SXdV4nmi2BizF8fFd8kAmThcZdiWB8ulXlHSuV307pdBF+FdEcUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a6ea9a6f18b20817410e2332d9c2150e10fcd0fa0c9f7046d479b4173979dc2","last_reissued_at":"2026-06-24T01:15:31.389490Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:31.389490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Artur Habuda, Fares Abu-Dakka, Khuyen Pham, Li Guo, Tran Nguyen Le, Yanheng Zhu, Yongzhe Zhao, Yue Peng","submitted_at":"2026-06-23T12:02:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24472","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/2606.24472/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":"2606.24472","created_at":"2026-06-24T01:15:31.389553+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24472v1","created_at":"2026-06-24T01:15:31.389553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24472","created_at":"2026-06-24T01:15:31.389553+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJXKTJXRRMQI","created_at":"2026-06-24T01:15:31.389553+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJXKTJXRRMQIC5AQ","created_at":"2026-06-24T01:15:31.389553+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJXKTJXR","created_at":"2026-06-24T01:15:31.389553+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/JJXKTJXRRMQIC5AQ4IZS3HBBKD","json":"https://pith.science/pith/JJXKTJXRRMQIC5AQ4IZS3HBBKD.json","graph_json":"https://pith.science/api/pith-number/JJXKTJXRRMQIC5AQ4IZS3HBBKD/graph.json","events_json":"https://pith.science/api/pith-number/JJXKTJXRRMQIC5AQ4IZS3HBBKD/events.json","paper":"https://pith.science/paper/JJXKTJXR"},"agent_actions":{"view_html":"https://pith.science/pith/JJXKTJXRRMQIC5AQ4IZS3HBBKD","download_json":"https://pith.science/pith/JJXKTJXRRMQIC5AQ4IZS3HBBKD.json","view_paper":"https://pith.science/paper/JJXKTJXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24472&json=true","fetch_graph":"https://pith.science/api/pith-number/JJXKTJXRRMQIC5AQ4IZS3HBBKD/graph.json","fetch_events":"https://pith.science/api/pith-number/JJXKTJXRRMQIC5AQ4IZS3HBBKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJXKTJXRRMQIC5AQ4IZS3HBBKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJXKTJXRRMQIC5AQ4IZS3HBBKD/action/storage_attestation","attest_author":"https://pith.science/pith/JJXKTJXRRMQIC5AQ4IZS3HBBKD/action/author_attestation","sign_citation":"https://pith.science/pith/JJXKTJXRRMQIC5AQ4IZS3HBBKD/action/citation_signature","submit_replication":"https://pith.science/pith/JJXKTJXRRMQIC5AQ4IZS3HBBKD/action/replication_record"}},"created_at":"2026-06-24T01:15:31.389553+00:00","updated_at":"2026-06-24T01:15:31.389553+00:00"}