{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FTGAKXJRHTXA2RBN2I2G5VWRC4","short_pith_number":"pith:FTGAKXJR","schema_version":"1.0","canonical_sha256":"2ccc055d313cee0d442dd2346ed6d11712125ceaafaa1078fa2891f224361134","source":{"kind":"arxiv","id":"2607.27180","version":1},"attestation_state":"computed","paper":{"title":"HumanCLAW: Can Vision-Language Models Act Through a Body?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Abhay Mittal, Amy Zhao, Chengcheng Tang, Chuan Guo, Ivan Shugurov, Jiawei Gu, Kairui Hu, Lingni Ma, Linjie Li, Manling Li, Michael Zollhoefer, Po-Chen Wu, Ranjay Krishna, Shuai Liu, Siyao Li, Sizhe An, Zekun Li, Ziwei Liu","submitted_at":"2026-07-29T17:51:36Z","abstract_excerpt":"Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task fails, it is hard to tell whether the VLM made a bad choice or the motor controller simply failed to execute it, e.g., losing balance and falling. In this work, we introduce HumanCLAW, an evaluation framework that decouples action decision-making from low-level execution. At every step, a harnessed, off-the-shelf VLM issues an atomic skill command, and the command is translated into a sub-second chunk of continuous "},"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":"2607.27180","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T17:51:36Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"7b66f3baf4c301a5e0d3b0a8ae5e3d646df21f15cbd9dc786e0cfdab8f47cd60","abstract_canon_sha256":"9c134c688a4ead8123cd4e5280b257a30140b357c2873dc0bb5c4db1ee5adeef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ccc055d313cee0d442dd2346ed6d11712125ceaafaa1078fa2891f224361134","last_reissued_at":"2026-07-30T01:23:58.762716Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:23:58.762716Z"},"graph_snapshot":{"paper":{"title":"HumanCLAW: Can Vision-Language Models Act Through a Body?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Abhay Mittal, Amy Zhao, Chengcheng Tang, Chuan Guo, Ivan Shugurov, Jiawei Gu, Kairui Hu, Lingni Ma, Linjie Li, Manling Li, Michael Zollhoefer, Po-Chen Wu, Ranjay Krishna, Shuai Liu, Siyao Li, Sizhe An, Zekun Li, Ziwei Liu","submitted_at":"2026-07-29T17:51:36Z","abstract_excerpt":"Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task fails, it is hard to tell whether the VLM made a bad choice or the motor controller simply failed to execute it, e.g., losing balance and falling. In this work, we introduce HumanCLAW, an evaluation framework that decouples action decision-making from low-level execution. At every step, a harnessed, off-the-shelf VLM issues an atomic skill command, and the command is translated into a sub-second chunk of continuous "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27180","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/2607.27180/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":"2607.27180","created_at":"2026-07-30T01:23:58.767656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27180v1","created_at":"2026-07-30T01:23:58.767656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27180","created_at":"2026-07-30T01:23:58.767656+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTGAKXJRHTXA","created_at":"2026-07-30T01:23:58.767656+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTGAKXJRHTXA2RBN","created_at":"2026-07-30T01:23:58.767656+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTGAKXJR","created_at":"2026-07-30T01:23:58.767656+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/FTGAKXJRHTXA2RBN2I2G5VWRC4","json":"https://pith.science/pith/FTGAKXJRHTXA2RBN2I2G5VWRC4.json","graph_json":"https://pith.science/api/pith-number/FTGAKXJRHTXA2RBN2I2G5VWRC4/graph.json","events_json":"https://pith.science/api/pith-number/FTGAKXJRHTXA2RBN2I2G5VWRC4/events.json","paper":"https://pith.science/paper/FTGAKXJR"},"agent_actions":{"view_html":"https://pith.science/pith/FTGAKXJRHTXA2RBN2I2G5VWRC4","download_json":"https://pith.science/pith/FTGAKXJRHTXA2RBN2I2G5VWRC4.json","view_paper":"https://pith.science/paper/FTGAKXJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27180&json=true","fetch_graph":"https://pith.science/api/pith-number/FTGAKXJRHTXA2RBN2I2G5VWRC4/graph.json","fetch_events":"https://pith.science/api/pith-number/FTGAKXJRHTXA2RBN2I2G5VWRC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTGAKXJRHTXA2RBN2I2G5VWRC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTGAKXJRHTXA2RBN2I2G5VWRC4/action/storage_attestation","attest_author":"https://pith.science/pith/FTGAKXJRHTXA2RBN2I2G5VWRC4/action/author_attestation","sign_citation":"https://pith.science/pith/FTGAKXJRHTXA2RBN2I2G5VWRC4/action/citation_signature","submit_replication":"https://pith.science/pith/FTGAKXJRHTXA2RBN2I2G5VWRC4/action/replication_record"}},"created_at":"2026-07-30T01:23:58.767656+00:00","updated_at":"2026-07-30T01:23:58.767656+00:00"}