{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IZW7ZTGIZTAAZ2J6MAJTK2C5Q3","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":"b2f39331098eff6aaab3e7e8d2f0b31104052613619ce3d75547af74778853d5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T08:52:47Z","title_canon_sha256":"9cfae2ad0cb5360cacc4e26eb2ea546e8bcb67509bd4300811eb3d9027dcdf9c"},"schema_version":"1.0","source":{"id":"2605.22183","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22183","created_at":"2026-05-22T01:04:30Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22183v1","created_at":"2026-05-22T01:04:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22183","created_at":"2026-05-22T01:04:30Z"},{"alias_kind":"pith_short_12","alias_value":"IZW7ZTGIZTAA","created_at":"2026-05-22T01:04:30Z"},{"alias_kind":"pith_short_16","alias_value":"IZW7ZTGIZTAAZ2J6","created_at":"2026-05-22T01:04:30Z"},{"alias_kind":"pith_short_8","alias_value":"IZW7ZTGI","created_at":"2026-05-22T01:04:30Z"}],"graph_snapshots":[{"event_id":"sha256:d6684242cadd653361f3dab636fc69cd92f28fd2189e69334701b1f697e153f1","target":"graph","created_at":"2026-05-22T01:04:30Z","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/2605.22183/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures maps language instructions and visual observations to actions in a single forward pass. While conceptually simple, this formulation entangles instruction comprehension, spatial scene understanding, and motor control within a single learning objective. As a result, the action expert must implicitly relearn cognitive and perceptual capabilities already present in the pretrained VLM, which can limit both learning efficiency and generalization. We i","authors_text":"Gao Huang, Renping Zhou, Rui Fang, Weilong Guo, Wenda Xu, Yuan He, Yuchen Wang, Yue Meng, Yunfeng Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T08:52:47Z","title":"Action with Visual Primitives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22183","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:c7c32ddba842a12bcfdff1aef85e0cd1b476b25ee239509f96e1b7ec4e65666d","target":"record","created_at":"2026-05-22T01:04:30Z","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":"b2f39331098eff6aaab3e7e8d2f0b31104052613619ce3d75547af74778853d5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-21T08:52:47Z","title_canon_sha256":"9cfae2ad0cb5360cacc4e26eb2ea546e8bcb67509bd4300811eb3d9027dcdf9c"},"schema_version":"1.0","source":{"id":"2605.22183","kind":"arxiv","version":1}},"canonical_sha256":"466dfcccc8ccc00ce93e601335685d86ee9e93d2516048629c35837ae0ba4855","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"466dfcccc8ccc00ce93e601335685d86ee9e93d2516048629c35837ae0ba4855","first_computed_at":"2026-05-22T01:04:30.717925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:30.717925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ke8UEE4YNQA/irKS5KY/RmIlmUCmg7KkQwok/h1NcMq/dYJa27IVwowivcnBu7FR7ux2H6DDEMUi1S1iifXBw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:30.718756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22183","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7c32ddba842a12bcfdff1aef85e0cd1b476b25ee239509f96e1b7ec4e65666d","sha256:d6684242cadd653361f3dab636fc69cd92f28fd2189e69334701b1f697e153f1"],"state_sha256":"f6a211b253eaf16219e6a6304c9ac2722d3fafbd09934a336e19130c68386f57"}