{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CX2PNCG343XDGGVXKDL5DY7RV2","short_pith_number":"pith:CX2PNCG3","schema_version":"1.0","canonical_sha256":"15f4f688dbe6ee331ab750d7d1e3f1ae95513ef90f321f2049750b3092cd4da6","source":{"kind":"arxiv","id":"2606.08530","version":1},"attestation_state":"computed","paper":{"title":"GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jiajia Wu, Jiajun Deng, Jianmin Ji, Jia Pan, Shiqi Zhang, Shuai Dong, Xingyi Zhang, Xin Nie, Xin Zhang, Yanyong Zhang, Yedong Shen, Yuan Zhang, Yuxuan Gao, Zhiyuan Cheng","submitted_at":"2026-06-07T09:23:16Z","abstract_excerpt":"Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background shifts, and different robot embodiments. We argue that this stems from the lack of a unified geometry-aware manipulation representation, leaving existing VLAs vulnerable to low-level trajectory supervision, misaligned 3D features, and embodiment differences. To address this, we propose GEAR-VLA, a VLA framework for learning unified geometry-aware action representations for generalizable robotic manipulation. GEAR-VLA adopts coarse-to-fine action l"},"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":"2606.08530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-07T09:23:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"40b146bc5507eac71409e121bd7be6b24d1e3679ef039c215f0e4f98e6517ea2","abstract_canon_sha256":"91b33e61a1a2695f0fd00f000de2323ca38911c5b17652d8ab10d3163a22fb34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:39.204259Z","signature_b64":"cMQyL33VcwrFRKDqdaN7AnJVuPrj44Jh7nsK4Z2M5eJ0uAf4FNXx4SI89+l5Cs6eUaSL6otXxALRWWJmQLEABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15f4f688dbe6ee331ab750d7d1e3f1ae95513ef90f321f2049750b3092cd4da6","last_reissued_at":"2026-06-09T01:05:39.203649Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:39.203649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jiajia Wu, Jiajun Deng, Jianmin Ji, Jia Pan, Shiqi Zhang, Shuai Dong, Xingyi Zhang, Xin Nie, Xin Zhang, Yanyong Zhang, Yedong Shen, Yuan Zhang, Yuxuan Gao, Zhiyuan Cheng","submitted_at":"2026-06-07T09:23:16Z","abstract_excerpt":"Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background shifts, and different robot embodiments. We argue that this stems from the lack of a unified geometry-aware manipulation representation, leaving existing VLAs vulnerable to low-level trajectory supervision, misaligned 3D features, and embodiment differences. To address this, we propose GEAR-VLA, a VLA framework for learning unified geometry-aware action representations for generalizable robotic manipulation. GEAR-VLA adopts coarse-to-fine action l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08530","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/2606.08530/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":"2606.08530","created_at":"2026-06-09T01:05:39.203753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08530v1","created_at":"2026-06-09T01:05:39.203753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08530","created_at":"2026-06-09T01:05:39.203753+00:00"},{"alias_kind":"pith_short_12","alias_value":"CX2PNCG343XD","created_at":"2026-06-09T01:05:39.203753+00:00"},{"alias_kind":"pith_short_16","alias_value":"CX2PNCG343XDGGVX","created_at":"2026-06-09T01:05:39.203753+00:00"},{"alias_kind":"pith_short_8","alias_value":"CX2PNCG3","created_at":"2026-06-09T01:05:39.203753+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/CX2PNCG343XDGGVXKDL5DY7RV2","json":"https://pith.science/pith/CX2PNCG343XDGGVXKDL5DY7RV2.json","graph_json":"https://pith.science/api/pith-number/CX2PNCG343XDGGVXKDL5DY7RV2/graph.json","events_json":"https://pith.science/api/pith-number/CX2PNCG343XDGGVXKDL5DY7RV2/events.json","paper":"https://pith.science/paper/CX2PNCG3"},"agent_actions":{"view_html":"https://pith.science/pith/CX2PNCG343XDGGVXKDL5DY7RV2","download_json":"https://pith.science/pith/CX2PNCG343XDGGVXKDL5DY7RV2.json","view_paper":"https://pith.science/paper/CX2PNCG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08530&json=true","fetch_graph":"https://pith.science/api/pith-number/CX2PNCG343XDGGVXKDL5DY7RV2/graph.json","fetch_events":"https://pith.science/api/pith-number/CX2PNCG343XDGGVXKDL5DY7RV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CX2PNCG343XDGGVXKDL5DY7RV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CX2PNCG343XDGGVXKDL5DY7RV2/action/storage_attestation","attest_author":"https://pith.science/pith/CX2PNCG343XDGGVXKDL5DY7RV2/action/author_attestation","sign_citation":"https://pith.science/pith/CX2PNCG343XDGGVXKDL5DY7RV2/action/citation_signature","submit_replication":"https://pith.science/pith/CX2PNCG343XDGGVXKDL5DY7RV2/action/replication_record"}},"created_at":"2026-06-09T01:05:39.203753+00:00","updated_at":"2026-06-09T01:05:39.203753+00:00"}