{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F7EOSE4RRRSCTJGW5R5TDMGGQ7","short_pith_number":"pith:F7EOSE4R","schema_version":"1.0","canonical_sha256":"2fc8e913918c6429a4d6ec7b31b0c687d4f0be1e1348988983239c1ba03fb890","source":{"kind":"arxiv","id":"2606.10180","version":1},"attestation_state":"computed","paper":{"title":"Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.RO","authors_text":"Andy Wang, Jason Chan, Jonathan C. Kao","submitted_at":"2026-06-08T21:16:37Z","abstract_excerpt":"We introduce flow control of vision-language-action (VLA) models, a simple and effective way to steer VLA actions in real-time through generic inputs, such as a keyboard. This method can be used out-of-the-box and does not require retraining or fine-tuning VLAs. It enables relatively crude user inputs to steer a VLA to align with user intent. The VLA transforms these inputs into action samples drawn from the VLA expert action distribution learned during training, so that the generated actions are high quality (conformity to the action expert distribution) and high fidelity (reflecting the user"},"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":"2606.10180","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-08T21:16:37Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"ed184755e92f0f58476481d3d60833a0494df60fda2ee2a12d0bcd0c9d74e11c","abstract_canon_sha256":"ca7175b207d7435d725edf8d67506d4e00cc12a368a3132ef144618e534513d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:08:58.370953Z","signature_b64":"zI54m0497MDkB2hC56procfnm+tt7bfYcJbXcFiwpTieqOpAYHQojX4GmybrClfGWJKvXPg3B1+GwDeWMCk6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fc8e913918c6429a4d6ec7b31b0c687d4f0be1e1348988983239c1ba03fb890","last_reissued_at":"2026-06-10T01:08:58.370209Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:08:58.370209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.RO","authors_text":"Andy Wang, Jason Chan, Jonathan C. Kao","submitted_at":"2026-06-08T21:16:37Z","abstract_excerpt":"We introduce flow control of vision-language-action (VLA) models, a simple and effective way to steer VLA actions in real-time through generic inputs, such as a keyboard. This method can be used out-of-the-box and does not require retraining or fine-tuning VLAs. It enables relatively crude user inputs to steer a VLA to align with user intent. The VLA transforms these inputs into action samples drawn from the VLA expert action distribution learned during training, so that the generated actions are high quality (conformity to the action expert distribution) and high fidelity (reflecting the user"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10180","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/2606.10180/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":"2606.10180","created_at":"2026-06-10T01:08:58.370336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10180v1","created_at":"2026-06-10T01:08:58.370336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10180","created_at":"2026-06-10T01:08:58.370336+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7EOSE4RRRSC","created_at":"2026-06-10T01:08:58.370336+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7EOSE4RRRSCTJGW","created_at":"2026-06-10T01:08:58.370336+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7EOSE4R","created_at":"2026-06-10T01:08:58.370336+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/F7EOSE4RRRSCTJGW5R5TDMGGQ7","json":"https://pith.science/pith/F7EOSE4RRRSCTJGW5R5TDMGGQ7.json","graph_json":"https://pith.science/api/pith-number/F7EOSE4RRRSCTJGW5R5TDMGGQ7/graph.json","events_json":"https://pith.science/api/pith-number/F7EOSE4RRRSCTJGW5R5TDMGGQ7/events.json","paper":"https://pith.science/paper/F7EOSE4R"},"agent_actions":{"view_html":"https://pith.science/pith/F7EOSE4RRRSCTJGW5R5TDMGGQ7","download_json":"https://pith.science/pith/F7EOSE4RRRSCTJGW5R5TDMGGQ7.json","view_paper":"https://pith.science/paper/F7EOSE4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10180&json=true","fetch_graph":"https://pith.science/api/pith-number/F7EOSE4RRRSCTJGW5R5TDMGGQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/F7EOSE4RRRSCTJGW5R5TDMGGQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7EOSE4RRRSCTJGW5R5TDMGGQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7EOSE4RRRSCTJGW5R5TDMGGQ7/action/storage_attestation","attest_author":"https://pith.science/pith/F7EOSE4RRRSCTJGW5R5TDMGGQ7/action/author_attestation","sign_citation":"https://pith.science/pith/F7EOSE4RRRSCTJGW5R5TDMGGQ7/action/citation_signature","submit_replication":"https://pith.science/pith/F7EOSE4RRRSCTJGW5R5TDMGGQ7/action/replication_record"}},"created_at":"2026-06-10T01:08:58.370336+00:00","updated_at":"2026-06-10T01:08:58.370336+00:00"}