{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2AP37RE5P2HQIEGNJD7IMVXKHS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8d6d9d08eac66eb09a67cda77fac74883520e4a4a1c9f1cd18c3588022db3ade","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-18T18:55:02Z","title_canon_sha256":"7333827fdcb74eebfb731cfeba5aa93b335c53b5db404a9176570b189459bd7a"},"schema_version":"1.0","source":{"id":"2602.16705","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.16705","created_at":"2026-06-05T01:14:35Z"},{"alias_kind":"arxiv_version","alias_value":"2602.16705v3","created_at":"2026-06-05T01:14:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16705","created_at":"2026-06-05T01:14:35Z"},{"alias_kind":"pith_short_12","alias_value":"2AP37RE5P2HQ","created_at":"2026-06-05T01:14:35Z"},{"alias_kind":"pith_short_16","alias_value":"2AP37RE5P2HQIEGN","created_at":"2026-06-05T01:14:35Z"},{"alias_kind":"pith_short_8","alias_value":"2AP37RE5","created_at":"2026-06-05T01:14:35Z"}],"graph_snapshots":[{"event_id":"sha256:3d4be9b8d7dc53bd734f696dc0cd60fcf4912f417eb16fc19957f9862f9d10ec","target":"graph","created_at":"2026-06-05T01:14:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.16705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","authors_text":"Arjun Gupta, Runpei Dong, Saurabh Gupta, Xialin He, Ziyan Li","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-18T18:55:02Z","title":"HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Grasping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.16705","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f8f638940cd57c69c579fc7e143f2ca4e1464d9434aef0e1aeeef49cc69f4815","target":"record","created_at":"2026-06-05T01:14:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8d6d9d08eac66eb09a67cda77fac74883520e4a4a1c9f1cd18c3588022db3ade","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-18T18:55:02Z","title_canon_sha256":"7333827fdcb74eebfb731cfeba5aa93b335c53b5db404a9176570b189459bd7a"},"schema_version":"1.0","source":{"id":"2602.16705","kind":"arxiv","version":3}},"canonical_sha256":"d01fbfc49d7e8f0410cd48fe8656ea3c8efdd76ddd0e8d242d8857dce7a30f7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d01fbfc49d7e8f0410cd48fe8656ea3c8efdd76ddd0e8d242d8857dce7a30f7c","first_computed_at":"2026-06-05T01:14:35.491517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:35.491517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eZu4rDwH3THROhWRI8w6GWaSfrICTeUcNP7fVFiEU+ECont1awi07YAeyTMKIBaTPqShmS8rvasfI6FkOPZ8Dg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:35.492356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.16705","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8f638940cd57c69c579fc7e143f2ca4e1464d9434aef0e1aeeef49cc69f4815","sha256:3d4be9b8d7dc53bd734f696dc0cd60fcf4912f417eb16fc19957f9862f9d10ec"],"state_sha256":"045cad9a606dbcf17930cc4dc6d444fb253f1bdb16d9326fb329e6efae72a552"}