{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NNLAQP4ISPC5S4XTEUQPMALA2O","short_pith_number":"pith:NNLAQP4I","schema_version":"1.0","canonical_sha256":"6b56083f8893c5d972f32520f60160d395fc7c1bb94473a10057e0e33897b8e8","source":{"kind":"arxiv","id":"2504.04191","version":2},"attestation_state":"computed","paper":{"title":"GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Jiale Yu, Jieming Cui, Ran Song, Siyuan Huang, Tengyu Liu, Wei Zhang, Yixin Zhu, Ziyu Meng","submitted_at":"2025-04-05T14:44:47Z","abstract_excerpt":"Learning open-vocabulary physical skills for simulated agents presents a significant challenge in artificial intelligence. Current reinforcement learning approaches face critical limitations: manually designed rewards lack scalability across diverse tasks, while demonstration-based methods struggle to generalize beyond their training distribution. We introduce GROVE, a generalized reward framework that enables open-vocabulary physical skill learning without manual engineering or task-specific demonstrations. Our key insight is that Large Language Models(LLMs) and Vision Language Models(VLMs) p"},"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":"2504.04191","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-05T14:44:47Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"ba555ecc246c5181f4059b7c7911bd0f947a08e951ed17de4c36895793008bf9","abstract_canon_sha256":"4aa9456492cdcd938560059bd27d669c520f6ce64b1d846e07c197ba230d0388"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:10:56.898139Z","signature_b64":"lkUL5T+/6ng1gJnWMKR9GPcOp4BtGjGy+d+uV3wOntktNP9jtHOOpweFRZrlKV16wjnSbfC7J9+RwFEVtNgCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b56083f8893c5d972f32520f60160d395fc7c1bb94473a10057e0e33897b8e8","last_reissued_at":"2026-07-05T12:10:56.897647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:10:56.897647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Jiale Yu, Jieming Cui, Ran Song, Siyuan Huang, Tengyu Liu, Wei Zhang, Yixin Zhu, Ziyu Meng","submitted_at":"2025-04-05T14:44:47Z","abstract_excerpt":"Learning open-vocabulary physical skills for simulated agents presents a significant challenge in artificial intelligence. Current reinforcement learning approaches face critical limitations: manually designed rewards lack scalability across diverse tasks, while demonstration-based methods struggle to generalize beyond their training distribution. We introduce GROVE, a generalized reward framework that enables open-vocabulary physical skill learning without manual engineering or task-specific demonstrations. Our key insight is that Large Language Models(LLMs) and Vision Language Models(VLMs) p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04191","kind":"arxiv","version":2},"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/2504.04191/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":"2504.04191","created_at":"2026-07-05T12:10:56.897710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04191v2","created_at":"2026-07-05T12:10:56.897710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04191","created_at":"2026-07-05T12:10:56.897710+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNLAQP4ISPC5","created_at":"2026-07-05T12:10:56.897710+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNLAQP4ISPC5S4XT","created_at":"2026-07-05T12:10:56.897710+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNLAQP4I","created_at":"2026-07-05T12:10:56.897710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00276","citing_title":"RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Reward","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNLAQP4ISPC5S4XTEUQPMALA2O","json":"https://pith.science/pith/NNLAQP4ISPC5S4XTEUQPMALA2O.json","graph_json":"https://pith.science/api/pith-number/NNLAQP4ISPC5S4XTEUQPMALA2O/graph.json","events_json":"https://pith.science/api/pith-number/NNLAQP4ISPC5S4XTEUQPMALA2O/events.json","paper":"https://pith.science/paper/NNLAQP4I"},"agent_actions":{"view_html":"https://pith.science/pith/NNLAQP4ISPC5S4XTEUQPMALA2O","download_json":"https://pith.science/pith/NNLAQP4ISPC5S4XTEUQPMALA2O.json","view_paper":"https://pith.science/paper/NNLAQP4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04191&json=true","fetch_graph":"https://pith.science/api/pith-number/NNLAQP4ISPC5S4XTEUQPMALA2O/graph.json","fetch_events":"https://pith.science/api/pith-number/NNLAQP4ISPC5S4XTEUQPMALA2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNLAQP4ISPC5S4XTEUQPMALA2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNLAQP4ISPC5S4XTEUQPMALA2O/action/storage_attestation","attest_author":"https://pith.science/pith/NNLAQP4ISPC5S4XTEUQPMALA2O/action/author_attestation","sign_citation":"https://pith.science/pith/NNLAQP4ISPC5S4XTEUQPMALA2O/action/citation_signature","submit_replication":"https://pith.science/pith/NNLAQP4ISPC5S4XTEUQPMALA2O/action/replication_record"}},"created_at":"2026-07-05T12:10:56.897710+00:00","updated_at":"2026-07-05T12:10:56.897710+00:00"}