{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2AP37RE5P2HQIEGNJD7IMVXKHS","short_pith_number":"pith:2AP37RE5","schema_version":"1.0","canonical_sha256":"d01fbfc49d7e8f0410cd48fe8656ea3c8efdd76ddd0e8d242d8857dce7a30f7c","source":{"kind":"arxiv","id":"2602.16705","version":3},"attestation_state":"computed","paper":{"title":"HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Grasping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Arjun Gupta, Runpei Dong, Saurabh Gupta, Xialin He, Ziyan Li","submitted_at":"2026-02-18T18:55:02Z","abstract_excerpt":"Visual loco-manipulation of arbitrary in-the-wild objects requires accurate end-effector (EE) control and a generalizable understanding of the scene from visual inputs (eg, RGB-D images). Existing imitation and sim2real methods jointly learn both these aspects via monolithic end-to-end learning and are thus hard to scale. In this work, we bring to bear the best tools for each of these problems -- large vision models for generalizable scene understanding and simulated training for accurate EE control -- leading to an overall modular loco-manipulation system that exhibits strong generalization. "},"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":"2602.16705","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-18T18:55:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7333827fdcb74eebfb731cfeba5aa93b335c53b5db404a9176570b189459bd7a","abstract_canon_sha256":"8d6d9d08eac66eb09a67cda77fac74883520e4a4a1c9f1cd18c3588022db3ade"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:35.492356Z","signature_b64":"eZu4rDwH3THROhWRI8w6GWaSfrICTeUcNP7fVFiEU+ECont1awi07YAeyTMKIBaTPqShmS8rvasfI6FkOPZ8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d01fbfc49d7e8f0410cd48fe8656ea3c8efdd76ddd0e8d242d8857dce7a30f7c","last_reissued_at":"2026-06-05T01:14:35.491517Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:35.491517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Grasping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Arjun Gupta, Runpei Dong, Saurabh Gupta, Xialin He, Ziyan Li","submitted_at":"2026-02-18T18:55:02Z","abstract_excerpt":"Visual loco-manipulation of arbitrary in-the-wild objects requires accurate end-effector (EE) control and a generalizable understanding of the scene from visual inputs (eg, RGB-D images). Existing imitation and sim2real methods jointly learn both these aspects via monolithic end-to-end learning and are thus hard to scale. In this work, we bring to bear the best tools for each of these problems -- large vision models for generalizable scene understanding and simulated training for accurate EE control -- leading to an overall modular loco-manipulation system that exhibits strong generalization. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.16705","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/2602.16705/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":"2602.16705","created_at":"2026-06-05T01:14:35.491626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.16705v3","created_at":"2026-06-05T01:14:35.491626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16705","created_at":"2026-06-05T01:14:35.491626+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AP37RE5P2HQ","created_at":"2026-06-05T01:14:35.491626+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AP37RE5P2HQIEGN","created_at":"2026-06-05T01:14:35.491626+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AP37RE5","created_at":"2026-06-05T01:14:35.491626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.19981","citing_title":"CEER: Compliant End-Effector and Root Control as a Unified Interface for Hierarchical Humanoid Loco-Manipulation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2AP37RE5P2HQIEGNJD7IMVXKHS","json":"https://pith.science/pith/2AP37RE5P2HQIEGNJD7IMVXKHS.json","graph_json":"https://pith.science/api/pith-number/2AP37RE5P2HQIEGNJD7IMVXKHS/graph.json","events_json":"https://pith.science/api/pith-number/2AP37RE5P2HQIEGNJD7IMVXKHS/events.json","paper":"https://pith.science/paper/2AP37RE5"},"agent_actions":{"view_html":"https://pith.science/pith/2AP37RE5P2HQIEGNJD7IMVXKHS","download_json":"https://pith.science/pith/2AP37RE5P2HQIEGNJD7IMVXKHS.json","view_paper":"https://pith.science/paper/2AP37RE5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.16705&json=true","fetch_graph":"https://pith.science/api/pith-number/2AP37RE5P2HQIEGNJD7IMVXKHS/graph.json","fetch_events":"https://pith.science/api/pith-number/2AP37RE5P2HQIEGNJD7IMVXKHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AP37RE5P2HQIEGNJD7IMVXKHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AP37RE5P2HQIEGNJD7IMVXKHS/action/storage_attestation","attest_author":"https://pith.science/pith/2AP37RE5P2HQIEGNJD7IMVXKHS/action/author_attestation","sign_citation":"https://pith.science/pith/2AP37RE5P2HQIEGNJD7IMVXKHS/action/citation_signature","submit_replication":"https://pith.science/pith/2AP37RE5P2HQIEGNJD7IMVXKHS/action/replication_record"}},"created_at":"2026-06-05T01:14:35.491626+00:00","updated_at":"2026-06-05T01:14:35.491626+00:00"}