{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BXDLH6SB4KDUTBTULG3ASL3SGA","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":"632b6d79249e4d0ee1f314bdd9d5b2def700e3321420f46302201f7deaed2c9a","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-04T18:33:27Z","title_canon_sha256":"d1ce5ce64c9ac89646734e8b3a494cde0724e83d6dbc48471fef0f7c5bf94384"},"schema_version":"1.0","source":{"id":"2510.03896","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.03896","created_at":"2026-06-12T01:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"2510.03896v2","created_at":"2026-06-12T01:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03896","created_at":"2026-06-12T01:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"BXDLH6SB4KDU","created_at":"2026-06-12T01:08:16Z"},{"alias_kind":"pith_short_16","alias_value":"BXDLH6SB4KDUTBTU","created_at":"2026-06-12T01:08:16Z"},{"alias_kind":"pith_short_8","alias_value":"BXDLH6SB","created_at":"2026-06-12T01:08:16Z"}],"graph_snapshots":[{"event_id":"sha256:1b7168636a0de6668515c6fe77c7df043d68b46b5de8ec1f538f0bb14dafe291","target":"graph","created_at":"2026-06-12T01:08:16Z","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/2510.03896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models demonstrate strong reasoning and planning abilities, yet grounding these predictions into precise robot actions remains a central challenge. Existing Vision-Language-Action methods typically entangle reasoning and action generation, leading to limited generalization. We propose Generalizable Action Expert (GAE), a task-agnostic model that converts sparse geometric plans into dense robot actions. Our approach introduces a sparse geometric interface: the VLM predicts sparse 3D waypoints representing high-level intention, while GAE maps these waypoints together with real-ti","authors_text":"Canyu Zhao, Chunhua Shen, Hao Chen, Haoyi Zhu, Mingyu Liu, Muzhi Zhu, Xiaoyi Lin, Yating Wang, Zheng Huang","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-04T18:33:27Z","title":"GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03896","kind":"arxiv","version":2},"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":"sha256:850a3791f473335e49fdde8bf4c5814669a9dcd2d9bfd0714d92327c1813f960","target":"record","created_at":"2026-06-12T01:08:16Z","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":"632b6d79249e4d0ee1f314bdd9d5b2def700e3321420f46302201f7deaed2c9a","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-04T18:33:27Z","title_canon_sha256":"d1ce5ce64c9ac89646734e8b3a494cde0724e83d6dbc48471fef0f7c5bf94384"},"schema_version":"1.0","source":{"id":"2510.03896","kind":"arxiv","version":2}},"canonical_sha256":"0dc6b3fa41e28749867459b6092f723025d5d452653c443c057bf7f0d764d639","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dc6b3fa41e28749867459b6092f723025d5d452653c443c057bf7f0d764d639","first_computed_at":"2026-06-12T01:08:16.269541Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:08:16.269541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xjdQ+rIz+P8LxzTAz/mttEpaZpsCi9ETgRC/9H6EfO/AEklKMl7dznkZxANaoropkl37ElCY1citmQaMBWATBw==","signature_status":"signed_v1","signed_at":"2026-06-12T01:08:16.270460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.03896","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:850a3791f473335e49fdde8bf4c5814669a9dcd2d9bfd0714d92327c1813f960","sha256:1b7168636a0de6668515c6fe77c7df043d68b46b5de8ec1f538f0bb14dafe291"],"state_sha256":"4a1384cf0515727b28e9927584f89af723b876c2507cae4e94e75a56af1cb31a"}