{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2NNFWYX65DUXL5R47Y3LF2UHED","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2dbbfdce5afb40861d3f02ffb0aea9f16b8d63c77872e1b5e18708b24268a5f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-10T17:34:25Z","title_canon_sha256":"70ba40be0aa750eb4d33fbb55dc5da529c13a4c82fbe356a06c638158ee4d4b8"},"schema_version":"1.0","source":{"id":"2606.12366","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12366","created_at":"2026-06-11T02:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12366v1","created_at":"2026-06-11T02:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12366","created_at":"2026-06-11T02:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"2NNFWYX65DUX","created_at":"2026-06-11T02:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"2NNFWYX65DUXL5R4","created_at":"2026-06-11T02:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"2NNFWYX6","created_at":"2026-06-11T02:09:48Z"}],"graph_snapshots":[{"event_id":"sha256:85be19183e6f331b7f424bc7f6e0da63e7d6f91a04fcbc3a584195fa753ccaf7","target":"graph","created_at":"2026-06-11T02:09:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.12366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models that couple pretrained Vision-Language Models (VLMs) with continuous action experts have achieved strong manipulation performance, yet generalization to out-of-distribution (OOD) language instructions remains poor. A known challenge is the structural imbalance in VLA data, where language is far less diverse than visual and action content, making policies prone to visual shortcuts. While discrete-action methods mitigate this through vision-language co-training, continuous action experts lack such protection: they start from random initialization and learn ent","authors_text":"Anzhe Chen, Kechun Xu, Rong Xiong, Yue Wang, Zhenjie Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-10T17:34:25Z","title":"APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12366","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a36b0990847f38ad0cafc6e8c13a1968a046adcdc77d4c1fd56fb17030b18df4","target":"record","created_at":"2026-06-11T02:09:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2dbbfdce5afb40861d3f02ffb0aea9f16b8d63c77872e1b5e18708b24268a5f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-10T17:34:25Z","title_canon_sha256":"70ba40be0aa750eb4d33fbb55dc5da529c13a4c82fbe356a06c638158ee4d4b8"},"schema_version":"1.0","source":{"id":"2606.12366","kind":"arxiv","version":1}},"canonical_sha256":"d35a5b62fee8e975f63cfe36b2ea8720fef91b4ab16190fbbb23917562ed2d8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d35a5b62fee8e975f63cfe36b2ea8720fef91b4ab16190fbbb23917562ed2d8a","first_computed_at":"2026-06-11T02:09:48.623262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T02:09:48.623262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TOGoSNt4mJMyludmFzbkg0KwK/4IakRMrzMbkmKVn3rycsKkP/Bal9btFP7k1Ndz9YTFOH4c/sMDxCiIP1zkCA==","signature_status":"signed_v1","signed_at":"2026-06-11T02:09:48.623874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12366","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a36b0990847f38ad0cafc6e8c13a1968a046adcdc77d4c1fd56fb17030b18df4","sha256:85be19183e6f331b7f424bc7f6e0da63e7d6f91a04fcbc3a584195fa753ccaf7"],"state_sha256":"ccd816b56a468683a42a206e1e166be15568616f41bdc203717a9f90032c147b"}