{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CTRL3GTMDLFFIP54MN462FTANX","short_pith_number":"pith:CTRL3GTM","schema_version":"1.0","canonical_sha256":"14e2bd9a6c1aca543fbc6379ed16606defdc82e7259697f69740ac59e741fc32","source":{"kind":"arxiv","id":"2307.00595","version":2},"attestation_state":"computed","paper":{"title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Cewu Lu, Chenxi Wang, Hao-Shu Fang, Haoyi Zhu, Hongjie Fang, Jirong Liu, Junbo Wang, Zhenyu Tang","submitted_at":"2023-07-02T15:33:31Z","abstract_excerpt":"A key challenge in robotic manipulation in open domains is how to acquire diverse and generalizable skills for robots. Recent research in one-shot imitation learning has shown promise in transferring trained policies to new tasks based on demonstrations. This feature is attractive for enabling robots to acquire new skills and improving task and motion planning. However, due to limitations in the training dataset, the current focus of the community has mainly been on simple cases, such as push or pick-place tasks, relying solely on visual guidance. In reality, there are many complex skills, som"},"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":"2307.00595","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-02T15:33:31Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"a5294fa7e225fafa977852d3767e423924e96a3944eb1ba6c82f6b6a02f9cc4f","abstract_canon_sha256":"fdaa6f42ca89f97d9263f00045e247204af9a5f68054d362b4ac88d44d2499ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:19.793766Z","signature_b64":"n3+l6QlgMP7VKwSBd3DiF1wU23AHQ/seVvTmOD/vf1nzgKuxBzyx+Vpaj91EVJu6GmFd6PbIVFVx5tVFcEhdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14e2bd9a6c1aca543fbc6379ed16606defdc82e7259697f69740ac59e741fc32","last_reissued_at":"2026-07-05T06:54:19.793273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:19.793273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Cewu Lu, Chenxi Wang, Hao-Shu Fang, Haoyi Zhu, Hongjie Fang, Jirong Liu, Junbo Wang, Zhenyu Tang","submitted_at":"2023-07-02T15:33:31Z","abstract_excerpt":"A key challenge in robotic manipulation in open domains is how to acquire diverse and generalizable skills for robots. Recent research in one-shot imitation learning has shown promise in transferring trained policies to new tasks based on demonstrations. This feature is attractive for enabling robots to acquire new skills and improving task and motion planning. However, due to limitations in the training dataset, the current focus of the community has mainly been on simple cases, such as push or pick-place tasks, relying solely on visual guidance. In reality, there are many complex skills, som"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00595","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/2307.00595/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":"2307.00595","created_at":"2026-07-05T06:54:19.793334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00595v2","created_at":"2026-07-05T06:54:19.793334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00595","created_at":"2026-07-05T06:54:19.793334+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTRL3GTMDLFF","created_at":"2026-07-05T06:54:19.793334+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTRL3GTMDLFFIP54","created_at":"2026-07-05T06:54:19.793334+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTRL3GTM","created_at":"2026-07-05T06:54:19.793334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26801","citing_title":"Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19914","citing_title":"Co-policy: Responsive Human-Robot Co-Creation for Musical Performances","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13102","citing_title":"FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07100","citing_title":"LARA: Latent Action Representation Alignment for Vision-Language-Action Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06194","citing_title":"ActiveMimic: Egocentric Video Pretraining with Active Perception","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02551","citing_title":"AFUN: Towards an Affordance Foundation Model for Functionality Understanding","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31234","citing_title":"HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07100","citing_title":"LARA: Latent Action Representation Alignment for Vision-Language-Action Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01799","citing_title":"Embody4D: A Generalist Data Engine for Embodied 4D World Modeling","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00054","citing_title":"From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27284","citing_title":"FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20433","citing_title":"Spacetime Optimal-Transport Attention for Visuo-Haptic Imitation Learning of Contact-Rich Manipulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19328","citing_title":"RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17441","citing_title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01773","citing_title":"IGen: Scalable Data Generation for Robot Learning from Open-World Images","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02115","citing_title":"Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09631","citing_title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","ref_index":17,"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":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09441","citing_title":"Beyond Isolation: A Unified Benchmark for General-Purpose Navigation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08774","citing_title":"ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02881","citing_title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00078","citing_title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21914","citing_title":"VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTRL3GTMDLFFIP54MN462FTANX","json":"https://pith.science/pith/CTRL3GTMDLFFIP54MN462FTANX.json","graph_json":"https://pith.science/api/pith-number/CTRL3GTMDLFFIP54MN462FTANX/graph.json","events_json":"https://pith.science/api/pith-number/CTRL3GTMDLFFIP54MN462FTANX/events.json","paper":"https://pith.science/paper/CTRL3GTM"},"agent_actions":{"view_html":"https://pith.science/pith/CTRL3GTMDLFFIP54MN462FTANX","download_json":"https://pith.science/pith/CTRL3GTMDLFFIP54MN462FTANX.json","view_paper":"https://pith.science/paper/CTRL3GTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00595&json=true","fetch_graph":"https://pith.science/api/pith-number/CTRL3GTMDLFFIP54MN462FTANX/graph.json","fetch_events":"https://pith.science/api/pith-number/CTRL3GTMDLFFIP54MN462FTANX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTRL3GTMDLFFIP54MN462FTANX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTRL3GTMDLFFIP54MN462FTANX/action/storage_attestation","attest_author":"https://pith.science/pith/CTRL3GTMDLFFIP54MN462FTANX/action/author_attestation","sign_citation":"https://pith.science/pith/CTRL3GTMDLFFIP54MN462FTANX/action/citation_signature","submit_replication":"https://pith.science/pith/CTRL3GTMDLFFIP54MN462FTANX/action/replication_record"}},"created_at":"2026-07-05T06:54:19.793334+00:00","updated_at":"2026-07-05T06:54:19.793334+00:00"}