{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BXDLH6SB4KDUTBTULG3ASL3SGA","short_pith_number":"pith:BXDLH6SB","schema_version":"1.0","canonical_sha256":"0dc6b3fa41e28749867459b6092f723025d5d452653c443c057bf7f0d764d639","source":{"kind":"arxiv","id":"2510.03896","version":2},"attestation_state":"computed","paper":{"title":"GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Canyu Zhao, Chunhua Shen, Hao Chen, Haoyi Zhu, Mingyu Liu, Muzhi Zhu, Xiaoyi Lin, Yating Wang, Zheng Huang","submitted_at":"2025-10-04T18:33:27Z","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"},"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":"2510.03896","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-04T18:33:27Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"d1ce5ce64c9ac89646734e8b3a494cde0724e83d6dbc48471fef0f7c5bf94384","abstract_canon_sha256":"632b6d79249e4d0ee1f314bdd9d5b2def700e3321420f46302201f7deaed2c9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:16.270460Z","signature_b64":"xjdQ+rIz+P8LxzTAz/mttEpaZpsCi9ETgRC/9H6EfO/AEklKMl7dznkZxANaoropkl37ElCY1citmQaMBWATBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dc6b3fa41e28749867459b6092f723025d5d452653c443c057bf7f0d764d639","last_reissued_at":"2026-06-12T01:08:16.269541Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:16.269541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Canyu Zhao, Chunhua Shen, Hao Chen, Haoyi Zhu, Mingyu Liu, Muzhi Zhu, Xiaoyi Lin, Yating Wang, Zheng Huang","submitted_at":"2025-10-04T18:33:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03896","kind":"arxiv","version":2},"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/2510.03896/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":"2510.03896","created_at":"2026-06-12T01:08:16.269693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.03896v2","created_at":"2026-06-12T01:08:16.269693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03896","created_at":"2026-06-12T01:08:16.269693+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXDLH6SB4KDU","created_at":"2026-06-12T01:08:16.269693+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXDLH6SB4KDUTBTU","created_at":"2026-06-12T01:08:16.269693+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXDLH6SB","created_at":"2026-06-12T01:08:16.269693+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/BXDLH6SB4KDUTBTULG3ASL3SGA","json":"https://pith.science/pith/BXDLH6SB4KDUTBTULG3ASL3SGA.json","graph_json":"https://pith.science/api/pith-number/BXDLH6SB4KDUTBTULG3ASL3SGA/graph.json","events_json":"https://pith.science/api/pith-number/BXDLH6SB4KDUTBTULG3ASL3SGA/events.json","paper":"https://pith.science/paper/BXDLH6SB"},"agent_actions":{"view_html":"https://pith.science/pith/BXDLH6SB4KDUTBTULG3ASL3SGA","download_json":"https://pith.science/pith/BXDLH6SB4KDUTBTULG3ASL3SGA.json","view_paper":"https://pith.science/paper/BXDLH6SB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.03896&json=true","fetch_graph":"https://pith.science/api/pith-number/BXDLH6SB4KDUTBTULG3ASL3SGA/graph.json","fetch_events":"https://pith.science/api/pith-number/BXDLH6SB4KDUTBTULG3ASL3SGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXDLH6SB4KDUTBTULG3ASL3SGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXDLH6SB4KDUTBTULG3ASL3SGA/action/storage_attestation","attest_author":"https://pith.science/pith/BXDLH6SB4KDUTBTULG3ASL3SGA/action/author_attestation","sign_citation":"https://pith.science/pith/BXDLH6SB4KDUTBTULG3ASL3SGA/action/citation_signature","submit_replication":"https://pith.science/pith/BXDLH6SB4KDUTBTULG3ASL3SGA/action/replication_record"}},"created_at":"2026-06-12T01:08:16.269693+00:00","updated_at":"2026-06-12T01:08:16.269693+00:00"}