{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LPTEL3U6TUJAYXEP76CWQDFI7G","short_pith_number":"pith:LPTEL3U6","schema_version":"1.0","canonical_sha256":"5be645ee9e9d120c5c8fff85680ca8f98b3ef513008d38abf8e6d7f4dcf9a41a","source":{"kind":"arxiv","id":"2606.12299","version":1},"attestation_state":"computed","paper":{"title":"Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrea Bajcsy, Gokul Swamy, Hyun Joe Jeong","submitted_at":"2026-06-10T16:34:49Z","abstract_excerpt":"Vision-Language-Action (VLA) models provide a natural language interface to robot control, but the mapping from language to behavior is often brittle and unintuitive: semantically similar instructions can induce drastically different behaviors, while some capabilities may not be elicitable through prompting alone. As a result, both human instructions and zero-shot language models can fail to reliably steer VLAs toward successful task execution. In this work, we propose a framework that interactively searches for language sequences that improve closed-loop VLA task performance, distills these s"},"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":"2606.12299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-10T16:34:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04ea1cb5706f95b7a592765e1cb2c0cb7ab612d0c67f2f709d985a17cb381371","abstract_canon_sha256":"0eb99def9496b67f773e018acebcaa931b991909b4d76674000939d9e76b3077"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:11:00.626354Z","signature_b64":"XD0TgErPEAuxCnPy1ageOD3zotY8Be6nC6GL8xIEqb1toukyS55wbsKozhj/SOnFteBchHH9ISQe1uddjPqbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5be645ee9e9d120c5c8fff85680ca8f98b3ef513008d38abf8e6d7f4dcf9a41a","last_reissued_at":"2026-06-11T01:11:00.625466Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:11:00.625466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrea Bajcsy, Gokul Swamy, Hyun Joe Jeong","submitted_at":"2026-06-10T16:34:49Z","abstract_excerpt":"Vision-Language-Action (VLA) models provide a natural language interface to robot control, but the mapping from language to behavior is often brittle and unintuitive: semantically similar instructions can induce drastically different behaviors, while some capabilities may not be elicitable through prompting alone. As a result, both human instructions and zero-shot language models can fail to reliably steer VLAs toward successful task execution. In this work, we propose a framework that interactively searches for language sequences that improve closed-loop VLA task performance, distills these s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12299","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/2606.12299/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":"2606.12299","created_at":"2026-06-11T01:11:00.625611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12299v1","created_at":"2026-06-11T01:11:00.625611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12299","created_at":"2026-06-11T01:11:00.625611+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPTEL3U6TUJA","created_at":"2026-06-11T01:11:00.625611+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPTEL3U6TUJAYXEP","created_at":"2026-06-11T01:11:00.625611+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPTEL3U6","created_at":"2026-06-11T01:11:00.625611+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/LPTEL3U6TUJAYXEP76CWQDFI7G","json":"https://pith.science/pith/LPTEL3U6TUJAYXEP76CWQDFI7G.json","graph_json":"https://pith.science/api/pith-number/LPTEL3U6TUJAYXEP76CWQDFI7G/graph.json","events_json":"https://pith.science/api/pith-number/LPTEL3U6TUJAYXEP76CWQDFI7G/events.json","paper":"https://pith.science/paper/LPTEL3U6"},"agent_actions":{"view_html":"https://pith.science/pith/LPTEL3U6TUJAYXEP76CWQDFI7G","download_json":"https://pith.science/pith/LPTEL3U6TUJAYXEP76CWQDFI7G.json","view_paper":"https://pith.science/paper/LPTEL3U6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12299&json=true","fetch_graph":"https://pith.science/api/pith-number/LPTEL3U6TUJAYXEP76CWQDFI7G/graph.json","fetch_events":"https://pith.science/api/pith-number/LPTEL3U6TUJAYXEP76CWQDFI7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPTEL3U6TUJAYXEP76CWQDFI7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPTEL3U6TUJAYXEP76CWQDFI7G/action/storage_attestation","attest_author":"https://pith.science/pith/LPTEL3U6TUJAYXEP76CWQDFI7G/action/author_attestation","sign_citation":"https://pith.science/pith/LPTEL3U6TUJAYXEP76CWQDFI7G/action/citation_signature","submit_replication":"https://pith.science/pith/LPTEL3U6TUJAYXEP76CWQDFI7G/action/replication_record"}},"created_at":"2026-06-11T01:11:00.625611+00:00","updated_at":"2026-06-11T01:11:00.625611+00:00"}