{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NVP5SMCUPH2UMQUOYQZKPX5KRM","short_pith_number":"pith:NVP5SMCU","schema_version":"1.0","canonical_sha256":"6d5fd9305479f546428ec432a7dfaa8b026f9b09719137da269c584c8056189e","source":{"kind":"arxiv","id":"2408.11812","version":1},"attestation_state":"computed","paper":{"title":"Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Homer Walke, Oier Mees, Ria Doshi, Sergey Levine, Sudeep Dasari","submitted_at":"2024-08-21T17:57:51Z","abstract_excerpt":"Modern machine learning systems rely on large datasets to attain broad generalization, and this often poses a challenge in robot learning, where each robotic platform and task might have only a small dataset. By training a single policy across many different kinds of robots, a robot learning method can leverage much broader and more diverse datasets, which in turn can lead to better generalization and robustness. However, training a single policy on multi-robot data is challenging because robots can have widely varying sensors, actuators, and control frequencies. We propose CrossFormer, a scal"},"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":"2408.11812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-21T17:57:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6c640f1ed4c8a13248bfb98f41187bc5c43a938b5a56d5ce5971b20ee7a7277e","abstract_canon_sha256":"fa3c9efe501175e81032ea820e66b9dceec323a25ffc6342ad6b1d39ec0a07aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:49.473719Z","signature_b64":"94aFPPeXY2cMeW6aOlbTBCYidRsiWDo5BAxP6R0GkENAnHoeVKq2kn+CSzDndX33dsJj8DXWYQTlfjtopj+RDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d5fd9305479f546428ec432a7dfaa8b026f9b09719137da269c584c8056189e","last_reissued_at":"2026-07-05T08:57:49.473223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:49.473223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Homer Walke, Oier Mees, Ria Doshi, Sergey Levine, Sudeep Dasari","submitted_at":"2024-08-21T17:57:51Z","abstract_excerpt":"Modern machine learning systems rely on large datasets to attain broad generalization, and this often poses a challenge in robot learning, where each robotic platform and task might have only a small dataset. By training a single policy across many different kinds of robots, a robot learning method can leverage much broader and more diverse datasets, which in turn can lead to better generalization and robustness. However, training a single policy on multi-robot data is challenging because robots can have widely varying sensors, actuators, and control frequencies. We propose CrossFormer, a scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11812","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/2408.11812/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":"2408.11812","created_at":"2026-07-05T08:57:49.473283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11812v1","created_at":"2026-07-05T08:57:49.473283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11812","created_at":"2026-07-05T08:57:49.473283+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVP5SMCUPH2U","created_at":"2026-07-05T08:57:49.473283+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVP5SMCUPH2UMQUO","created_at":"2026-07-05T08:57:49.473283+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVP5SMCU","created_at":"2026-07-05T08:57:49.473283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08751","citing_title":"DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22836","citing_title":"Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLA","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22113","citing_title":"KITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12109","citing_title":"InDex: Empowering VLA Models with Intent-Conditioned Arm-Hand Coordination for Dexterous Manipulation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07999","citing_title":"Efficient Skill Grounding via Code Refactoring with Small Language Models","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29298","citing_title":"MonoDuo: Using One Robot Arm to Learn Bimanual Policies","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20811","citing_title":"Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18780","citing_title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15493","citing_title":"GR-3 Technical Report","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15692","citing_title":"mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21017","citing_title":"Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13645","citing_title":"A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NVP5SMCUPH2UMQUOYQZKPX5KRM","json":"https://pith.science/pith/NVP5SMCUPH2UMQUOYQZKPX5KRM.json","graph_json":"https://pith.science/api/pith-number/NVP5SMCUPH2UMQUOYQZKPX5KRM/graph.json","events_json":"https://pith.science/api/pith-number/NVP5SMCUPH2UMQUOYQZKPX5KRM/events.json","paper":"https://pith.science/paper/NVP5SMCU"},"agent_actions":{"view_html":"https://pith.science/pith/NVP5SMCUPH2UMQUOYQZKPX5KRM","download_json":"https://pith.science/pith/NVP5SMCUPH2UMQUOYQZKPX5KRM.json","view_paper":"https://pith.science/paper/NVP5SMCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11812&json=true","fetch_graph":"https://pith.science/api/pith-number/NVP5SMCUPH2UMQUOYQZKPX5KRM/graph.json","fetch_events":"https://pith.science/api/pith-number/NVP5SMCUPH2UMQUOYQZKPX5KRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVP5SMCUPH2UMQUOYQZKPX5KRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVP5SMCUPH2UMQUOYQZKPX5KRM/action/storage_attestation","attest_author":"https://pith.science/pith/NVP5SMCUPH2UMQUOYQZKPX5KRM/action/author_attestation","sign_citation":"https://pith.science/pith/NVP5SMCUPH2UMQUOYQZKPX5KRM/action/citation_signature","submit_replication":"https://pith.science/pith/NVP5SMCUPH2UMQUOYQZKPX5KRM/action/replication_record"}},"created_at":"2026-07-05T08:57:49.473283+00:00","updated_at":"2026-07-05T08:57:49.473283+00:00"}