{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V67IAPT5RHEP2MCGI46KS2BWGZ","short_pith_number":"pith:V67IAPT5","schema_version":"1.0","canonical_sha256":"afbe803e7d89c8fd3046473ca96836367c069b7f1538dcf28cc530005c4ae871","source":{"kind":"arxiv","id":"2606.12403","version":1},"attestation_state":"computed","paper":{"title":"World Pilot: Steering Vision-Language-Action Models with World-Action Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Junjia Xu, Lue Fan, Rongxu Cui, Wenling Li, Xiaojuan Jin, Zefu Lin, Zhaoxiang Zhang","submitted_at":"2026-06-10T17:59:08Z","abstract_excerpt":"Vision-Language-Action (VLA) models inherit semantic grounding from large-scale pretraining and perform competently across in-distribution manipulation tasks. This grounding, however, is built on static image-text pairs, whereas manipulation is a continuous, contact-rich process whose dynamics this pretraining cannot capture. We present World Pilot, a VLA framework that augments the policy with priors from a World-Action Model (WAM), routed into the decision chain through two complementary pathways. Latent Steering conditions the perception layer on a scene-evolution latent, and Action Steerin"},"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":"2606.12403","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-10T17:59:08Z","cross_cats_sorted":[],"title_canon_sha256":"8c4b17c94089dd9651d04bb64821371a2511391fcd4959a8cad9bde30f306a39","abstract_canon_sha256":"fb7b9ad40385659a4e6b019f10b57c594a13f63cc22f6c2df598c66ed57a29a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T02:09:49.924214Z","signature_b64":"UYA8GYjE04sS6J4Me/LZfYQC8/bxkFlA4pdIyHb0rmJiHzwYGA+EuZ3a+qUPDhF/o7HZ34I28dRJQvFJbRjLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afbe803e7d89c8fd3046473ca96836367c069b7f1538dcf28cc530005c4ae871","last_reissued_at":"2026-06-11T02:09:49.923790Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T02:09:49.923790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"World Pilot: Steering Vision-Language-Action Models with World-Action Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Junjia Xu, Lue Fan, Rongxu Cui, Wenling Li, Xiaojuan Jin, Zefu Lin, Zhaoxiang Zhang","submitted_at":"2026-06-10T17:59:08Z","abstract_excerpt":"Vision-Language-Action (VLA) models inherit semantic grounding from large-scale pretraining and perform competently across in-distribution manipulation tasks. This grounding, however, is built on static image-text pairs, whereas manipulation is a continuous, contact-rich process whose dynamics this pretraining cannot capture. We present World Pilot, a VLA framework that augments the policy with priors from a World-Action Model (WAM), routed into the decision chain through two complementary pathways. Latent Steering conditions the perception layer on a scene-evolution latent, and Action Steerin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12403","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/2606.12403/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":"2606.12403","created_at":"2026-06-11T02:09:49.923853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12403v1","created_at":"2026-06-11T02:09:49.923853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12403","created_at":"2026-06-11T02:09:49.923853+00:00"},{"alias_kind":"pith_short_12","alias_value":"V67IAPT5RHEP","created_at":"2026-06-11T02:09:49.923853+00:00"},{"alias_kind":"pith_short_16","alias_value":"V67IAPT5RHEP2MCG","created_at":"2026-06-11T02:09:49.923853+00:00"},{"alias_kind":"pith_short_8","alias_value":"V67IAPT5","created_at":"2026-06-11T02:09:49.923853+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/V67IAPT5RHEP2MCGI46KS2BWGZ","json":"https://pith.science/pith/V67IAPT5RHEP2MCGI46KS2BWGZ.json","graph_json":"https://pith.science/api/pith-number/V67IAPT5RHEP2MCGI46KS2BWGZ/graph.json","events_json":"https://pith.science/api/pith-number/V67IAPT5RHEP2MCGI46KS2BWGZ/events.json","paper":"https://pith.science/paper/V67IAPT5"},"agent_actions":{"view_html":"https://pith.science/pith/V67IAPT5RHEP2MCGI46KS2BWGZ","download_json":"https://pith.science/pith/V67IAPT5RHEP2MCGI46KS2BWGZ.json","view_paper":"https://pith.science/paper/V67IAPT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12403&json=true","fetch_graph":"https://pith.science/api/pith-number/V67IAPT5RHEP2MCGI46KS2BWGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/V67IAPT5RHEP2MCGI46KS2BWGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V67IAPT5RHEP2MCGI46KS2BWGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V67IAPT5RHEP2MCGI46KS2BWGZ/action/storage_attestation","attest_author":"https://pith.science/pith/V67IAPT5RHEP2MCGI46KS2BWGZ/action/author_attestation","sign_citation":"https://pith.science/pith/V67IAPT5RHEP2MCGI46KS2BWGZ/action/citation_signature","submit_replication":"https://pith.science/pith/V67IAPT5RHEP2MCGI46KS2BWGZ/action/replication_record"}},"created_at":"2026-06-11T02:09:49.923853+00:00","updated_at":"2026-06-11T02:09:49.923853+00:00"}