{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7R5FNZ4LDT6ERBJBFT3RFOQZ6J","short_pith_number":"pith:7R5FNZ4L","schema_version":"1.0","canonical_sha256":"fc7a56e78b1cfc4885212cf712ba19f24f7f40836d48038664cadc30436a42df","source":{"kind":"arxiv","id":"2606.03127","version":1},"attestation_state":"computed","paper":{"title":"TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiajun Liu, Jianxiong Li, Lingqiao Liu, Shuai Yang, Sijin Chen, Wenbo Zhang, Xiao Ma","submitted_at":"2026-06-02T04:10:39Z","abstract_excerpt":"Vision-Language-Action (VLA) models trained on large-scale data have made remarkable progress, but they remain vulnerable to distribution shifts at deployment time. Recent VLA models suggest that prompts can serve as an efficient interface for steering policy behavior, but existing prompt-based steering typically relies on external guidance. This raises a natural question: can test-time training (TTT) for VLA be achieved by optimizing a prompt, so that the steering interface itself can be learned and adapted from interaction? We address this question with TTT-VLA, a test-time training framewor"},"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":"2606.03127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T04:10:39Z","cross_cats_sorted":[],"title_canon_sha256":"a06ef0dff936f38907e6a728b11b43dcda7a4eccb37d8dde9ef9dcc563038575","abstract_canon_sha256":"b67bd743bd2a65c00288d488a5e124c55c5a7a3b069c17cb4d63d4945249c9d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:32.425051Z","signature_b64":"GKeX2mRGUOUF+YlRYLG1oF37QWtQ1CKiTQtBhBDU0mfVojd9Ipwpp8HIH2BuyQ9aU0sFRF2L4rp8nAO4Ag0VCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc7a56e78b1cfc4885212cf712ba19f24f7f40836d48038664cadc30436a42df","last_reissued_at":"2026-06-03T01:05:32.424694Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:32.424694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiajun Liu, Jianxiong Li, Lingqiao Liu, Shuai Yang, Sijin Chen, Wenbo Zhang, Xiao Ma","submitted_at":"2026-06-02T04:10:39Z","abstract_excerpt":"Vision-Language-Action (VLA) models trained on large-scale data have made remarkable progress, but they remain vulnerable to distribution shifts at deployment time. Recent VLA models suggest that prompts can serve as an efficient interface for steering policy behavior, but existing prompt-based steering typically relies on external guidance. This raises a natural question: can test-time training (TTT) for VLA be achieved by optimizing a prompt, so that the steering interface itself can be learned and adapted from interaction? We address this question with TTT-VLA, a test-time training framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03127","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/2606.03127/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":"2606.03127","created_at":"2026-06-03T01:05:32.424749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03127v1","created_at":"2026-06-03T01:05:32.424749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03127","created_at":"2026-06-03T01:05:32.424749+00:00"},{"alias_kind":"pith_short_12","alias_value":"7R5FNZ4LDT6E","created_at":"2026-06-03T01:05:32.424749+00:00"},{"alias_kind":"pith_short_16","alias_value":"7R5FNZ4LDT6ERBJB","created_at":"2026-06-03T01:05:32.424749+00:00"},{"alias_kind":"pith_short_8","alias_value":"7R5FNZ4L","created_at":"2026-06-03T01:05:32.424749+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/7R5FNZ4LDT6ERBJBFT3RFOQZ6J","json":"https://pith.science/pith/7R5FNZ4LDT6ERBJBFT3RFOQZ6J.json","graph_json":"https://pith.science/api/pith-number/7R5FNZ4LDT6ERBJBFT3RFOQZ6J/graph.json","events_json":"https://pith.science/api/pith-number/7R5FNZ4LDT6ERBJBFT3RFOQZ6J/events.json","paper":"https://pith.science/paper/7R5FNZ4L"},"agent_actions":{"view_html":"https://pith.science/pith/7R5FNZ4LDT6ERBJBFT3RFOQZ6J","download_json":"https://pith.science/pith/7R5FNZ4LDT6ERBJBFT3RFOQZ6J.json","view_paper":"https://pith.science/paper/7R5FNZ4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03127&json=true","fetch_graph":"https://pith.science/api/pith-number/7R5FNZ4LDT6ERBJBFT3RFOQZ6J/graph.json","fetch_events":"https://pith.science/api/pith-number/7R5FNZ4LDT6ERBJBFT3RFOQZ6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7R5FNZ4LDT6ERBJBFT3RFOQZ6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7R5FNZ4LDT6ERBJBFT3RFOQZ6J/action/storage_attestation","attest_author":"https://pith.science/pith/7R5FNZ4LDT6ERBJBFT3RFOQZ6J/action/author_attestation","sign_citation":"https://pith.science/pith/7R5FNZ4LDT6ERBJBFT3RFOQZ6J/action/citation_signature","submit_replication":"https://pith.science/pith/7R5FNZ4LDT6ERBJBFT3RFOQZ6J/action/replication_record"}},"created_at":"2026-06-03T01:05:32.424749+00:00","updated_at":"2026-06-03T01:05:32.424749+00:00"}