{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZAXTO6RHH5TJ2XYMW46ZWVEA4I","short_pith_number":"pith:ZAXTO6RH","schema_version":"1.0","canonical_sha256":"c82f377a273f669d5f0cb73d9b5480e21aa5da9d083efaf6bc575d407b04afc8","source":{"kind":"arxiv","id":"2507.05331","version":1},"attestation_state":"computed","paper":{"title":"A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aditya Bhat, Aimee Goncalves, Alejandro Castro, Alex Alspach, Allison Henry, Andrew Beaulieu, Aykut Onol, Basile Van Hoorick, Benjamin Burchfiel, Blake Wulfe, Brendan Hathaway, Calder Phillips-Grafflin, Charles Richter, Chen Xu, Ching-Hsin Fang, Christopher Rodriguez, Dale McConachie, Damrong Guoy, David Tago, Derick Seale, Dian Chen, Donovon Jackson, Emma Dixon, Eric Cousineau, Eric Dusel, Gordon Richardson, Grant Gould, Hadas Kress-Gazit, Haruki Nishimura, Hillel Hochsztein, Hongkai Dai, Ian McMahon, Igor Vasiljevic, Jean Mercat, Jeremy Nimmer, Jose Barreiros, Joseph Masterjohn, Katherine Liu, Kerri Fetzer-Borelli, Krishnan Srinivasan, Kuan-Hui Lee, Kunimatsu Hashimoto, Kushal Arora, Kyle Hatch, Leticia Priebe Mendes Rocha, Mariah Smith-Jones, Mark Zolotas, Masha Itkina, Matthew Ferreira, Matthew Tran, Maya Angeles, Mengchao Zhang, Michael Sherman, Muhammad Zubair Irshad, Naveen Kuppuswamy, Owen Pfannenstiehl, Paarth Shah, Patrick Miller, Paul Mitiguy, Pavel Tokmakov, Phoebe Horgan, Rares Ambrus, Reko Ong, Richard Denitto, Richard Poyner, Rick Cory, Russ Tedrake, Sam Creasey, Sean Curtis, Sedrick Keh, Sergey Zakharov, Shun Iwase, Siddharth Karamcheti, Siyuan Feng, Stacie Ford, Swati Gupta, Ting-Sheng Chu, Tony Nguyen, TRI LBM Team, Vitor Campagnolo Guizilini, Xuchen Han, Yuki Noguchi","submitted_at":"2025-07-07T17:56:01Z","abstract_excerpt":"Robot manipulation has seen tremendous progress in recent years, with imitation learning policies enabling successful performance of dexterous and hard-to-model tasks. Concurrently, scaling data and model size has led to the development of capable language and vision foundation models, motivating large-scale efforts to create general-purpose robot foundation models. While these models have garnered significant enthusiasm and investment, meaningful evaluation of real-world performance remains a challenge, limiting both the pace of development and inhibiting a nuanced understanding of current ca"},"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":"2507.05331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T17:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"835d89185be89b0cca3b1f3e87d3d7c20c96fcc6d930a23b279678f6c9e5c749","abstract_canon_sha256":"a7c1b30f81bf5f2aed74e1adc439ba508409dea0a1bc779548e320ebb301863f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T04:28:55.670169Z","signature_b64":"3WrcV82Td2vQjnHbQDG5DaCUyF2/8VFcZ1+P6lCGIO3xV4/fvfYevWREK0ncVQ9/TmqVXT854RKpk92eOgUGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c82f377a273f669d5f0cb73d9b5480e21aa5da9d083efaf6bc575d407b04afc8","last_reissued_at":"2026-05-25T04:28:55.666628Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T04:28:55.666628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aditya Bhat, Aimee Goncalves, Alejandro Castro, Alex Alspach, Allison Henry, Andrew Beaulieu, Aykut Onol, Basile Van Hoorick, Benjamin Burchfiel, Blake Wulfe, Brendan Hathaway, Calder Phillips-Grafflin, Charles Richter, Chen Xu, Ching-Hsin Fang, Christopher Rodriguez, Dale McConachie, Damrong Guoy, David Tago, Derick Seale, Dian Chen, Donovon Jackson, Emma Dixon, Eric Cousineau, Eric Dusel, Gordon Richardson, Grant Gould, Hadas Kress-Gazit, Haruki Nishimura, Hillel Hochsztein, Hongkai Dai, Ian McMahon, Igor Vasiljevic, Jean Mercat, Jeremy Nimmer, Jose Barreiros, Joseph Masterjohn, Katherine Liu, Kerri Fetzer-Borelli, Krishnan Srinivasan, Kuan-Hui Lee, Kunimatsu Hashimoto, Kushal Arora, Kyle Hatch, Leticia Priebe Mendes Rocha, Mariah Smith-Jones, Mark Zolotas, Masha Itkina, Matthew Ferreira, Matthew Tran, Maya Angeles, Mengchao Zhang, Michael Sherman, Muhammad Zubair Irshad, Naveen Kuppuswamy, Owen Pfannenstiehl, Paarth Shah, Patrick Miller, Paul Mitiguy, Pavel Tokmakov, Phoebe Horgan, Rares Ambrus, Reko Ong, Richard Denitto, Richard Poyner, Rick Cory, Russ Tedrake, Sam Creasey, Sean Curtis, Sedrick Keh, Sergey Zakharov, Shun Iwase, Siddharth Karamcheti, Siyuan Feng, Stacie Ford, Swati Gupta, Ting-Sheng Chu, Tony Nguyen, TRI LBM Team, Vitor Campagnolo Guizilini, Xuchen Han, Yuki Noguchi","submitted_at":"2025-07-07T17:56:01Z","abstract_excerpt":"Robot manipulation has seen tremendous progress in recent years, with imitation learning policies enabling successful performance of dexterous and hard-to-model tasks. Concurrently, scaling data and model size has led to the development of capable language and vision foundation models, motivating large-scale efforts to create general-purpose robot foundation models. While these models have garnered significant enthusiasm and investment, meaningful evaluation of real-world performance remains a challenge, limiting both the pace of development and inhibiting a nuanced understanding of current ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05331","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/2507.05331/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":"2507.05331","created_at":"2026-05-25T04:28:55.667214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05331v1","created_at":"2026-05-25T04:28:55.667214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05331","created_at":"2026-05-25T04:28:55.667214+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAXTO6RHH5TJ","created_at":"2026-05-25T04:28:55.667214+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAXTO6RHH5TJ2XYM","created_at":"2026-05-25T04:28:55.667214+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAXTO6RH","created_at":"2026-05-25T04:28:55.667214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2605.23477","citing_title":"Semantically Structured Mixture-of-Experts for Compositional Robotic Manipulation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23847","citing_title":"Instrumentation for Imitation Learning: Enhancing Training Datasets for Clothes Hanger Insertion","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21811","citing_title":"Safe and Steerable Geometric Motion Policies for Robotic Dexterous Manipulation","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2602.12978","citing_title":"Learning Native Continuation for Action Chunking Flow Policies","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2603.03243","citing_title":"HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17601","citing_title":"From a Single Demonstration to a General Policy for Contact-Rich Manipulation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19029","citing_title":"Distributionally Robust Control via Stein Variational Inference for Contact-Rich Manipulation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19919","citing_title":"Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17411","citing_title":"SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17774","citing_title":"Contact-Rich Robotic Assembly in Construction via Diffusion Policy Learning","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2507.15493","citing_title":"GR-3 Technical Report","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2512.06571","citing_title":"Learning Agile Striker Skills for Humanoid Soccer Robots from Noisy Sensory Input","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2512.15840","citing_title":"Large Video Planner Enables Generalizable Robot Control","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2508.00795","citing_title":"Video Generators are Robot Policies","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2603.12510","citing_title":"Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13959","citing_title":"WarmPrior: Straightening Flow-Matching Policies with Temporal Priors","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21998","citing_title":"Causal World Modeling for Robot Control","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2602.15922","citing_title":"World Action Models are Zero-shot Policies","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21924","citing_title":"Long-Horizon Manipulation via Trace-Conditioned VLA Planning","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21017","citing_title":"Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19728","citing_title":"VLA Foundry: A Unified Framework for Training Vision-Language-Action Models","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13645","citing_title":"A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15483","citing_title":"${\\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZAXTO6RHH5TJ2XYMW46ZWVEA4I","json":"https://pith.science/pith/ZAXTO6RHH5TJ2XYMW46ZWVEA4I.json","graph_json":"https://pith.science/api/pith-number/ZAXTO6RHH5TJ2XYMW46ZWVEA4I/graph.json","events_json":"https://pith.science/api/pith-number/ZAXTO6RHH5TJ2XYMW46ZWVEA4I/events.json","paper":"https://pith.science/paper/ZAXTO6RH"},"agent_actions":{"view_html":"https://pith.science/pith/ZAXTO6RHH5TJ2XYMW46ZWVEA4I","download_json":"https://pith.science/pith/ZAXTO6RHH5TJ2XYMW46ZWVEA4I.json","view_paper":"https://pith.science/paper/ZAXTO6RH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05331&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAXTO6RHH5TJ2XYMW46ZWVEA4I/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAXTO6RHH5TJ2XYMW46ZWVEA4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAXTO6RHH5TJ2XYMW46ZWVEA4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAXTO6RHH5TJ2XYMW46ZWVEA4I/action/storage_attestation","attest_author":"https://pith.science/pith/ZAXTO6RHH5TJ2XYMW46ZWVEA4I/action/author_attestation","sign_citation":"https://pith.science/pith/ZAXTO6RHH5TJ2XYMW46ZWVEA4I/action/citation_signature","submit_replication":"https://pith.science/pith/ZAXTO6RHH5TJ2XYMW46ZWVEA4I/action/replication_record"}},"created_at":"2026-05-25T04:28:55.667214+00:00","updated_at":"2026-05-25T04:28:55.667214+00:00"}