{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TSCLCPTFGQK5E7VBFU4W4LMDL6","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":"6c14e3b9afee905cb95d1947c4891338e5f1a3be330d04377ed98a9de4cd7129","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-17T14:55:32Z","title_canon_sha256":"2e47016f230408c458f636c43293b175ce3ccd4170050f06a4d9ebfab5433de7"},"schema_version":"1.0","source":{"id":"2605.17486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17486","created_at":"2026-05-20T00:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17486v1","created_at":"2026-05-20T00:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17486","created_at":"2026-05-20T00:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"TSCLCPTFGQK5","created_at":"2026-05-20T00:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"TSCLCPTFGQK5E7VB","created_at":"2026-05-20T00:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"TSCLCPTF","created_at":"2026-05-20T00:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:e6b5ace577049d4ee1fbb6ede74d7deaf035c70c84dbb24ceced49617f981a9a","target":"graph","created_at":"2026-05-20T00:04:41Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.685034Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.645226Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17486/integrity.json","findings":[],"snapshot_sha256":"536a529078826a8b788d5e33bc1fc21e529c64f217a91ba98808947ba8da5808","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in Reinforcement Learning (RL) provides a principled approach to optimizing Vision-Language-Action (VLA) models, facilitating a shift from trajectory imitation to active learning in the task environment. Despite improvements in control precision, most RL optimizers remain task-specific, which reduces VLA models from generalist controllers to policies that overfit to a narrow set of tasks. In this study, we conduct an in-depth analysis of this phenomenon and highlight the importance of cross-task feature representations for improving the generalizability of VLA models. Motivated","authors_text":"Guiliang Liu, Litao Liu, Ming Zhou, Ruixing Jin, Sixu Lin, Xiaoyi Fan, Yunpeng Qing","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-17T14:55:32Z","title":"DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17486","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":"sha256:69f57224e7d1c9477356f2cb505b22b04d1b3013645d0b0e41bb80b5285ec2ad","target":"record","created_at":"2026-05-20T00:04:41Z","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":"6c14e3b9afee905cb95d1947c4891338e5f1a3be330d04377ed98a9de4cd7129","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-17T14:55:32Z","title_canon_sha256":"2e47016f230408c458f636c43293b175ce3ccd4170050f06a4d9ebfab5433de7"},"schema_version":"1.0","source":{"id":"2605.17486","kind":"arxiv","version":1}},"canonical_sha256":"9c84b13e653415d27ea12d396e2d835f9547db1df62c10634480ef64a4dcf1d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c84b13e653415d27ea12d396e2d835f9547db1df62c10634480ef64a4dcf1d6","first_computed_at":"2026-05-20T00:04:41.509536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:41.509536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H3FkhLV8HVnGDsnuc6Fof4nyktEiaStw2kjGFKGnzD8bU8A7aB1i26I68OeVD+Hj4eVc7kEPOKNjmtTy+r1ZAg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:41.510374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69f57224e7d1c9477356f2cb505b22b04d1b3013645d0b0e41bb80b5285ec2ad","sha256:e6b5ace577049d4ee1fbb6ede74d7deaf035c70c84dbb24ceced49617f981a9a"],"state_sha256":"255a3c1c44c52e11334f7482845636ddb570906061a501c282036968ba3d9c69"}