{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3BU76VNGHVGEIWUENLENLL6BYZ","short_pith_number":"pith:3BU76VNG","schema_version":"1.0","canonical_sha256":"d869ff55a63d4c445a846ac8d5afc1c6602fe2aeab343fb783764981ab789cbf","source":{"kind":"arxiv","id":"2606.21470","version":1},"attestation_state":"computed","paper":{"title":"ASCII Art Turns LLMs into VLA Controllers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Brian Plancher, Devin Balkcom, Luyang Zhao, Muhao Chen, Roy Xing, Yitao Jiang","submitted_at":"2026-06-19T14:19:59Z","abstract_excerpt":"Vision--Language--Action (VLA) controllers are often built by extending vision--language models (VLMs) with action supervision, relying on multimodal backbones with large data and compute requirements. We demonstrate that a text-only large language model (LLM) can be adapted into a VLA-style controller when visual observations are rendered into a text input using an ASCII representation. This ASCII-as-vision interface enables existing training and deployment stacks for LLMs to efficiently condition on visual state, follow natural-language instructions, and produce constrained, executable actio"},"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":"2606.21470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-19T14:19:59Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"1679c1e18d700316ac8081496fbb00304d255ff3245e94f1d6320cc5e4505173","abstract_canon_sha256":"bd12d79f284e29f6c582486d586b072e544c14e44550108b8cbcb918a30b356f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:11.480061Z","signature_b64":"t9mn550OM5guC2EXvtOqj999UECrejX8paRX4qxA4cSScTXJO9Y56l6HXO9rjUvB84LND9ddKjNSUnGWLrMLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d869ff55a63d4c445a846ac8d5afc1c6602fe2aeab343fb783764981ab789cbf","last_reissued_at":"2026-06-23T01:13:11.479617Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:11.479617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASCII Art Turns LLMs into VLA Controllers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Brian Plancher, Devin Balkcom, Luyang Zhao, Muhao Chen, Roy Xing, Yitao Jiang","submitted_at":"2026-06-19T14:19:59Z","abstract_excerpt":"Vision--Language--Action (VLA) controllers are often built by extending vision--language models (VLMs) with action supervision, relying on multimodal backbones with large data and compute requirements. We demonstrate that a text-only large language model (LLM) can be adapted into a VLA-style controller when visual observations are rendered into a text input using an ASCII representation. This ASCII-as-vision interface enables existing training and deployment stacks for LLMs to efficiently condition on visual state, follow natural-language instructions, and produce constrained, executable actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21470","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/2606.21470/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":"2606.21470","created_at":"2026-06-23T01:13:11.479684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21470v1","created_at":"2026-06-23T01:13:11.479684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21470","created_at":"2026-06-23T01:13:11.479684+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BU76VNGHVGE","created_at":"2026-06-23T01:13:11.479684+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BU76VNGHVGEIWUE","created_at":"2026-06-23T01:13:11.479684+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BU76VNG","created_at":"2026-06-23T01:13:11.479684+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/3BU76VNGHVGEIWUENLENLL6BYZ","json":"https://pith.science/pith/3BU76VNGHVGEIWUENLENLL6BYZ.json","graph_json":"https://pith.science/api/pith-number/3BU76VNGHVGEIWUENLENLL6BYZ/graph.json","events_json":"https://pith.science/api/pith-number/3BU76VNGHVGEIWUENLENLL6BYZ/events.json","paper":"https://pith.science/paper/3BU76VNG"},"agent_actions":{"view_html":"https://pith.science/pith/3BU76VNGHVGEIWUENLENLL6BYZ","download_json":"https://pith.science/pith/3BU76VNGHVGEIWUENLENLL6BYZ.json","view_paper":"https://pith.science/paper/3BU76VNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21470&json=true","fetch_graph":"https://pith.science/api/pith-number/3BU76VNGHVGEIWUENLENLL6BYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3BU76VNGHVGEIWUENLENLL6BYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BU76VNGHVGEIWUENLENLL6BYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BU76VNGHVGEIWUENLENLL6BYZ/action/storage_attestation","attest_author":"https://pith.science/pith/3BU76VNGHVGEIWUENLENLL6BYZ/action/author_attestation","sign_citation":"https://pith.science/pith/3BU76VNGHVGEIWUENLENLL6BYZ/action/citation_signature","submit_replication":"https://pith.science/pith/3BU76VNGHVGEIWUENLENLL6BYZ/action/replication_record"}},"created_at":"2026-06-23T01:13:11.479684+00:00","updated_at":"2026-06-23T01:13:11.479684+00:00"}