{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RB3E4MGT57LG5HPHXSRLTAHLGY","short_pith_number":"pith:RB3E4MGT","schema_version":"1.0","canonical_sha256":"88764e30d3efd66e9de7bca2b980eb361589117fddf87ea31679baf5200d2e18","source":{"kind":"arxiv","id":"2605.21061","version":1},"attestation_state":"computed","paper":{"title":"Grounding Driving VLA via Inverse Kinematics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hyunjung Shim, Junsung Park","submitted_at":"2026-05-20T11:45:32Z","abstract_excerpt":"Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a structurally ill-posed task formulation. We show that trajectory recovery, when viewed through the lens of inverse kinematics, requires both a current and a future visual state as boundary conditions; existing VLAs supply only the former, which encourages the model to shortcut through ego status and text commands alone. To address this, we re-design Driving VLA in the style of an inverse kinematics solver. First, a next visual state prediction obj"},"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":"2605.21061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T11:45:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"94cf81b34a42bd3b82fafae012df3d75b8bb782c81e14e5d42a3130882086914","abstract_canon_sha256":"bb457026a168bd30b5414afd96a8692caa6c52126a4ee0b5934a8378deac4812"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:34.642447Z","signature_b64":"1DvWelQSbTqLIXX3yZ9IbtOt4HQ+SSpdQUQFSR53D9Bc9scChd5D4GhcTGcnOzI0dPRTD6+ZhJ6+B8nxweObCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88764e30d3efd66e9de7bca2b980eb361589117fddf87ea31679baf5200d2e18","last_reissued_at":"2026-05-21T01:05:34.641732Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:34.641732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Driving VLA via Inverse Kinematics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hyunjung Shim, Junsung Park","submitted_at":"2026-05-20T11:45:32Z","abstract_excerpt":"Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a structurally ill-posed task formulation. We show that trajectory recovery, when viewed through the lens of inverse kinematics, requires both a current and a future visual state as boundary conditions; existing VLAs supply only the former, which encourages the model to shortcut through ego status and text commands alone. To address this, we re-design Driving VLA in the style of an inverse kinematics solver. First, a next visual state prediction obj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21061","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/2605.21061/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":"2605.21061","created_at":"2026-05-21T01:05:34.641840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21061v1","created_at":"2026-05-21T01:05:34.641840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21061","created_at":"2026-05-21T01:05:34.641840+00:00"},{"alias_kind":"pith_short_12","alias_value":"RB3E4MGT57LG","created_at":"2026-05-21T01:05:34.641840+00:00"},{"alias_kind":"pith_short_16","alias_value":"RB3E4MGT57LG5HPH","created_at":"2026-05-21T01:05:34.641840+00:00"},{"alias_kind":"pith_short_8","alias_value":"RB3E4MGT","created_at":"2026-05-21T01:05:34.641840+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/RB3E4MGT57LG5HPHXSRLTAHLGY","json":"https://pith.science/pith/RB3E4MGT57LG5HPHXSRLTAHLGY.json","graph_json":"https://pith.science/api/pith-number/RB3E4MGT57LG5HPHXSRLTAHLGY/graph.json","events_json":"https://pith.science/api/pith-number/RB3E4MGT57LG5HPHXSRLTAHLGY/events.json","paper":"https://pith.science/paper/RB3E4MGT"},"agent_actions":{"view_html":"https://pith.science/pith/RB3E4MGT57LG5HPHXSRLTAHLGY","download_json":"https://pith.science/pith/RB3E4MGT57LG5HPHXSRLTAHLGY.json","view_paper":"https://pith.science/paper/RB3E4MGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21061&json=true","fetch_graph":"https://pith.science/api/pith-number/RB3E4MGT57LG5HPHXSRLTAHLGY/graph.json","fetch_events":"https://pith.science/api/pith-number/RB3E4MGT57LG5HPHXSRLTAHLGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RB3E4MGT57LG5HPHXSRLTAHLGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RB3E4MGT57LG5HPHXSRLTAHLGY/action/storage_attestation","attest_author":"https://pith.science/pith/RB3E4MGT57LG5HPHXSRLTAHLGY/action/author_attestation","sign_citation":"https://pith.science/pith/RB3E4MGT57LG5HPHXSRLTAHLGY/action/citation_signature","submit_replication":"https://pith.science/pith/RB3E4MGT57LG5HPHXSRLTAHLGY/action/replication_record"}},"created_at":"2026-05-21T01:05:34.641840+00:00","updated_at":"2026-05-21T01:05:34.641840+00:00"}