{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KJXVMFLLMO7PUXVCAIIL7OPUEX","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":"6ad385c7487663009bc085f5fe141f970cd0a3e56a3c3f1f9537cc7dc72bbdf5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T03:48:10Z","title_canon_sha256":"eb7710d51fded7bc3fba8f9389c5575551ff81753dbf18a4bb59f220b50202f6"},"schema_version":"1.0","source":{"id":"2606.11221","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11221","created_at":"2026-06-11T00:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11221v1","created_at":"2026-06-11T00:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11221","created_at":"2026-06-11T00:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"KJXVMFLLMO7P","created_at":"2026-06-11T00:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"KJXVMFLLMO7PUXVC","created_at":"2026-06-11T00:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"KJXVMFLL","created_at":"2026-06-11T00:08:13Z"}],"graph_snapshots":[{"event_id":"sha256:a447854cc05e7b6afa347529411b58b2c343b081e0126e647366463782efa2bc","target":"graph","created_at":"2026-06-11T00:08:13Z","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/2606.11221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We take a Gromov-Wasserstein perspective on Vision-Language-Action (VLA) learning, where the goal is to make the relational geometry of action representations compatible with the semantic geometry of VL embeddings. However, this alignment is non-trivial due to the mathematical heterogeneity between the domains: the semantic space of vision-language is topologically linear and isotropic, whereas the physical manifold of robotic action is non-Euclidean and anisotropic. Their disjoint metric structures render direct regression ill-posed. To resolve this incompatibility, we introduce LAST (Lie-alg","authors_text":"Changsheng Xu, Chaofan Chen, Huaihai Lyu, Pengwei Wang, Shanghang Zhang, Xiansheng Chen, Yuheng Ji","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T03:48:10Z","title":"LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11221","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:b21e077842819d8b19ed9cb5c8da4d08336a524bad5e963ad82b3494002ccb20","target":"record","created_at":"2026-06-11T00:08:13Z","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":"6ad385c7487663009bc085f5fe141f970cd0a3e56a3c3f1f9537cc7dc72bbdf5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T03:48:10Z","title_canon_sha256":"eb7710d51fded7bc3fba8f9389c5575551ff81753dbf18a4bb59f220b50202f6"},"schema_version":"1.0","source":{"id":"2606.11221","kind":"arxiv","version":1}},"canonical_sha256":"526f56156b63befa5ea20210bfb9f425cef51237ee615a2fad1f0d5b355b2325","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"526f56156b63befa5ea20210bfb9f425cef51237ee615a2fad1f0d5b355b2325","first_computed_at":"2026-06-11T00:08:13.518779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T00:08:13.518779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SNoPKUldlwkvPqlXyf2VaKHOWYta2NwU7OloE1oNjXQ29WB1aTeqKm4EC/Dd8EvJq1QCUHdlcqQDCVuhKd/XBg==","signature_status":"signed_v1","signed_at":"2026-06-11T00:08:13.519620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11221","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b21e077842819d8b19ed9cb5c8da4d08336a524bad5e963ad82b3494002ccb20","sha256:a447854cc05e7b6afa347529411b58b2c343b081e0126e647366463782efa2bc"],"state_sha256":"bb414f6026223c19f4fb0e3f1f9026cf975febb6eeea1a22f3a3113e54d2e7d2"}