{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YTIYBM6IWYHBOWGWZFRCHWERSC","short_pith_number":"pith:YTIYBM6I","schema_version":"1.0","canonical_sha256":"c4d180b3c8b60e1758d6c96223d89190b6c74190e8cb4bfdc96bc7c62bdfc28d","source":{"kind":"arxiv","id":"2606.09009","version":1},"attestation_state":"computed","paper":{"title":"Scaling by Diversified Experience for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cewu Lu, Leiyu Wang, Luoyi Fan, Nanyang Ye, Xueqi Li, Zhaofengnian Wang","submitted_at":"2026-06-08T04:13:38Z","abstract_excerpt":"Vision-Language-Action models face significant challenges in real-world deployment due to the entanglement of high-level reasoning with low-level control, and the instability of policy optimization. In this paper, we introduce SyVLA, a robust VLA model trained with diversified experiences. We propose an Intention Decoupling algorithm to isolate control-relevant features from reasoning contexts and a similar-sample guided RL pipeline to stabilize policy updates and mitigate distribution shift. Extensive experiments on real-world robotic tasks and multi-modal benchmarks demonstrate that SyVLA ac"},"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":"2606.09009","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T04:13:38Z","cross_cats_sorted":[],"title_canon_sha256":"896c52cfe935c373aaed8dd4319075eb3d1a4676e7937f98c5ca17e23f60c012","abstract_canon_sha256":"732284030ccb635366cdd0525fcaf8a0c94a49a3563f0b9a83034897b72bdc93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:53.227305Z","signature_b64":"Az/cQxEn2K9YvyNZDoVhaHwnKLcJdO2ZO8I4dlOpiIWRoCXxgruS8Ge1a13a5H5EyYpwPbCEL75JPmMCtKxdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4d180b3c8b60e1758d6c96223d89190b6c74190e8cb4bfdc96bc7c62bdfc28d","last_reissued_at":"2026-06-09T02:07:53.226405Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:53.226405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling by Diversified Experience for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cewu Lu, Leiyu Wang, Luoyi Fan, Nanyang Ye, Xueqi Li, Zhaofengnian Wang","submitted_at":"2026-06-08T04:13:38Z","abstract_excerpt":"Vision-Language-Action models face significant challenges in real-world deployment due to the entanglement of high-level reasoning with low-level control, and the instability of policy optimization. In this paper, we introduce SyVLA, a robust VLA model trained with diversified experiences. We propose an Intention Decoupling algorithm to isolate control-relevant features from reasoning contexts and a similar-sample guided RL pipeline to stabilize policy updates and mitigate distribution shift. Extensive experiments on real-world robotic tasks and multi-modal benchmarks demonstrate that SyVLA ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09009","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/2606.09009/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":"2606.09009","created_at":"2026-06-09T02:07:53.226556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09009v1","created_at":"2026-06-09T02:07:53.226556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09009","created_at":"2026-06-09T02:07:53.226556+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTIYBM6IWYHB","created_at":"2026-06-09T02:07:53.226556+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTIYBM6IWYHBOWGW","created_at":"2026-06-09T02:07:53.226556+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTIYBM6I","created_at":"2026-06-09T02:07:53.226556+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/YTIYBM6IWYHBOWGWZFRCHWERSC","json":"https://pith.science/pith/YTIYBM6IWYHBOWGWZFRCHWERSC.json","graph_json":"https://pith.science/api/pith-number/YTIYBM6IWYHBOWGWZFRCHWERSC/graph.json","events_json":"https://pith.science/api/pith-number/YTIYBM6IWYHBOWGWZFRCHWERSC/events.json","paper":"https://pith.science/paper/YTIYBM6I"},"agent_actions":{"view_html":"https://pith.science/pith/YTIYBM6IWYHBOWGWZFRCHWERSC","download_json":"https://pith.science/pith/YTIYBM6IWYHBOWGWZFRCHWERSC.json","view_paper":"https://pith.science/paper/YTIYBM6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09009&json=true","fetch_graph":"https://pith.science/api/pith-number/YTIYBM6IWYHBOWGWZFRCHWERSC/graph.json","fetch_events":"https://pith.science/api/pith-number/YTIYBM6IWYHBOWGWZFRCHWERSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTIYBM6IWYHBOWGWZFRCHWERSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTIYBM6IWYHBOWGWZFRCHWERSC/action/storage_attestation","attest_author":"https://pith.science/pith/YTIYBM6IWYHBOWGWZFRCHWERSC/action/author_attestation","sign_citation":"https://pith.science/pith/YTIYBM6IWYHBOWGWZFRCHWERSC/action/citation_signature","submit_replication":"https://pith.science/pith/YTIYBM6IWYHBOWGWZFRCHWERSC/action/replication_record"}},"created_at":"2026-06-09T02:07:53.226556+00:00","updated_at":"2026-06-09T02:07:53.226556+00:00"}