{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5SHS3NJVTKESIPDTNBK3GHYHGJ","short_pith_number":"pith:5SHS3NJV","schema_version":"1.0","canonical_sha256":"ec8f2db5359a89243c736855b31f073254ef7f64cd1141c107e708be94096cec","source":{"kind":"arxiv","id":"2403.03174","version":3},"attestation_state":"computed","paper":{"title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Fangchen Liu, Kuan Fang, Pieter Abbeel, Sergey Levine","submitted_at":"2024-03-05T18:08:45Z","abstract_excerpt":"Open-world generalization requires robotic systems to have a profound understanding of the physical world and the user command to solve diverse and complex tasks. While the recent advancement in vision-language models (VLMs) has offered unprecedented opportunities to solve open-world problems, how to leverage their capabilities to control robots remains a grand challenge. In this paper, we introduce Marking Open-world Keypoint Affordances (MOKA), an approach that employs VLMs to solve robotic manipulation tasks specified by free-form language instructions. Central to our approach is a compact "},"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":"2403.03174","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-05T18:08:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ee4d20adbe5c2b80318b52718ef83f568b1bf2ad9216beef990d62f6cb9c29d9","abstract_canon_sha256":"141d3e44f06d0f166e4617771ccb6d70d108846f21fadbbdf495a467e63cce45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:40.384247Z","signature_b64":"6JtdvVL1wdcSiYgTbn3zQvHXaF78nK+E13pYIvolnWN+NBymyeqhWvfck9KbnljIzbB8MZM+aB93ce+Iaon7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec8f2db5359a89243c736855b31f073254ef7f64cd1141c107e708be94096cec","last_reissued_at":"2026-07-05T09:02:40.383772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:40.383772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Fangchen Liu, Kuan Fang, Pieter Abbeel, Sergey Levine","submitted_at":"2024-03-05T18:08:45Z","abstract_excerpt":"Open-world generalization requires robotic systems to have a profound understanding of the physical world and the user command to solve diverse and complex tasks. While the recent advancement in vision-language models (VLMs) has offered unprecedented opportunities to solve open-world problems, how to leverage their capabilities to control robots remains a grand challenge. In this paper, we introduce Marking Open-world Keypoint Affordances (MOKA), an approach that employs VLMs to solve robotic manipulation tasks specified by free-form language instructions. Central to our approach is a compact "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03174","kind":"arxiv","version":3},"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/2403.03174/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":"2403.03174","created_at":"2026-07-05T09:02:40.383830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03174v3","created_at":"2026-07-05T09:02:40.383830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03174","created_at":"2026-07-05T09:02:40.383830+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SHS3NJVTKES","created_at":"2026-07-05T09:02:40.383830+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SHS3NJVTKESIPDT","created_at":"2026-07-05T09:02:40.383830+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SHS3NJV","created_at":"2026-07-05T09:02:40.383830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25880","citing_title":"USS: Unified Spatial-Semantic Prompts for Embodied Visual Tracking with Latent Dynamics Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27036","citing_title":"RelAfford6D: Relational 6D Affordance Graphs for Constraint-Driven Robotic Manipulation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19340","citing_title":"ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13515","citing_title":"MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24203","citing_title":"Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30613","citing_title":"Sequential Planning via Anchored Robotic Keypoints","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23856","citing_title":"Point Tracking Improves World Action Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13998","citing_title":"Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2409.01652","citing_title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13833","citing_title":"Semantic-Contact Fields for Category-Level Generalizable Tactile Tool Manipulation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10345","citing_title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11114","citing_title":"SEVO: Semantic-Enhanced Virtual Observation for Robust VLA Manipulation via Active Illumination and Data-Centric Collection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05714","citing_title":"TriRelVLA: Triadic Relational Structure for Generalizable Embodied Manipulation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09036","citing_title":"V-CAGE: Vision-Closed-Loop Agentic Generation Engine for Robotic Manipulation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07034","citing_title":"KITE: Keyframe-Indexed Tokenized Evidence for VLM-Based Robot Failure Analysis","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SHS3NJVTKESIPDTNBK3GHYHGJ","json":"https://pith.science/pith/5SHS3NJVTKESIPDTNBK3GHYHGJ.json","graph_json":"https://pith.science/api/pith-number/5SHS3NJVTKESIPDTNBK3GHYHGJ/graph.json","events_json":"https://pith.science/api/pith-number/5SHS3NJVTKESIPDTNBK3GHYHGJ/events.json","paper":"https://pith.science/paper/5SHS3NJV"},"agent_actions":{"view_html":"https://pith.science/pith/5SHS3NJVTKESIPDTNBK3GHYHGJ","download_json":"https://pith.science/pith/5SHS3NJVTKESIPDTNBK3GHYHGJ.json","view_paper":"https://pith.science/paper/5SHS3NJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03174&json=true","fetch_graph":"https://pith.science/api/pith-number/5SHS3NJVTKESIPDTNBK3GHYHGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5SHS3NJVTKESIPDTNBK3GHYHGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SHS3NJVTKESIPDTNBK3GHYHGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SHS3NJVTKESIPDTNBK3GHYHGJ/action/storage_attestation","attest_author":"https://pith.science/pith/5SHS3NJVTKESIPDTNBK3GHYHGJ/action/author_attestation","sign_citation":"https://pith.science/pith/5SHS3NJVTKESIPDTNBK3GHYHGJ/action/citation_signature","submit_replication":"https://pith.science/pith/5SHS3NJVTKESIPDTNBK3GHYHGJ/action/replication_record"}},"created_at":"2026-07-05T09:02:40.383830+00:00","updated_at":"2026-07-05T09:02:40.383830+00:00"}