{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KJXVMFLLMO7PUXVCAIIL7OPUEX","short_pith_number":"pith:KJXVMFLL","schema_version":"1.0","canonical_sha256":"526f56156b63befa5ea20210bfb9f425cef51237ee615a2fad1f0d5b355b2325","source":{"kind":"arxiv","id":"2606.11221","version":1},"attestation_state":"computed","paper":{"title":"LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Chaofan Chen, Huaihai Lyu, Pengwei Wang, Shanghang Zhang, Xiansheng Chen, Yuheng Ji","submitted_at":"2026-05-27T03:48:10Z","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"},"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":"2606.11221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T03:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"eb7710d51fded7bc3fba8f9389c5575551ff81753dbf18a4bb59f220b50202f6","abstract_canon_sha256":"6ad385c7487663009bc085f5fe141f970cd0a3e56a3c3f1f9537cc7dc72bbdf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T00:08:13.519620Z","signature_b64":"SNoPKUldlwkvPqlXyf2VaKHOWYta2NwU7OloE1oNjXQ29WB1aTeqKm4EC/Dd8EvJq1QCUHdlcqQDCVuhKd/XBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"526f56156b63befa5ea20210bfb9f425cef51237ee615a2fad1f0d5b355b2325","last_reissued_at":"2026-06-11T00:08:13.518779Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T00:08:13.518779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Chaofan Chen, Huaihai Lyu, Pengwei Wang, Shanghang Zhang, Xiansheng Chen, Yuheng Ji","submitted_at":"2026-05-27T03:48:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11221","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/2606.11221/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":"2606.11221","created_at":"2026-06-11T00:08:13.518919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11221v1","created_at":"2026-06-11T00:08:13.518919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11221","created_at":"2026-06-11T00:08:13.518919+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJXVMFLLMO7P","created_at":"2026-06-11T00:08:13.518919+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJXVMFLLMO7PUXVC","created_at":"2026-06-11T00:08:13.518919+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJXVMFLL","created_at":"2026-06-11T00:08:13.518919+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/KJXVMFLLMO7PUXVCAIIL7OPUEX","json":"https://pith.science/pith/KJXVMFLLMO7PUXVCAIIL7OPUEX.json","graph_json":"https://pith.science/api/pith-number/KJXVMFLLMO7PUXVCAIIL7OPUEX/graph.json","events_json":"https://pith.science/api/pith-number/KJXVMFLLMO7PUXVCAIIL7OPUEX/events.json","paper":"https://pith.science/paper/KJXVMFLL"},"agent_actions":{"view_html":"https://pith.science/pith/KJXVMFLLMO7PUXVCAIIL7OPUEX","download_json":"https://pith.science/pith/KJXVMFLLMO7PUXVCAIIL7OPUEX.json","view_paper":"https://pith.science/paper/KJXVMFLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11221&json=true","fetch_graph":"https://pith.science/api/pith-number/KJXVMFLLMO7PUXVCAIIL7OPUEX/graph.json","fetch_events":"https://pith.science/api/pith-number/KJXVMFLLMO7PUXVCAIIL7OPUEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJXVMFLLMO7PUXVCAIIL7OPUEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJXVMFLLMO7PUXVCAIIL7OPUEX/action/storage_attestation","attest_author":"https://pith.science/pith/KJXVMFLLMO7PUXVCAIIL7OPUEX/action/author_attestation","sign_citation":"https://pith.science/pith/KJXVMFLLMO7PUXVCAIIL7OPUEX/action/citation_signature","submit_replication":"https://pith.science/pith/KJXVMFLLMO7PUXVCAIIL7OPUEX/action/replication_record"}},"created_at":"2026-06-11T00:08:13.518919+00:00","updated_at":"2026-06-11T00:08:13.518919+00:00"}