{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WAZOF3EGUEM56GZTTTVJ5OFYPO","short_pith_number":"pith:WAZOF3EG","schema_version":"1.0","canonical_sha256":"b032e2ec86a119df1b339cea9eb8b87b90b01c5a6c0bf6632f1ffe0b4d4f1d62","source":{"kind":"arxiv","id":"2503.04280","version":4},"attestation_state":"computed","paper":{"title":"Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alberto Dalla Libera, Aris Synodinos, Matteo Iovino, Niccol\\`o Turcato, Pietro Falco, Ruggero Carli","submitted_at":"2025-03-06T10:08:44Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) and Visual Language Models (VLMs) have significantly impacted robotics, enabling high-level semantic motion planning applications. Reinforcement Learning (RL), a complementary paradigm, enables agents to autonomously optimize complex behaviors through interaction and reward signals. However, designing effective reward functions for RL remains challenging, especially in real-world tasks where sparse rewards are insufficient and dense rewards require elaborate design. In this work, we propose Autonomous Reinforcement learning for Complex Human-"},"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":"2503.04280","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-06T10:08:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6c059e350e8c965c958be58ca3ed086fce96dfe9a0e8f25a971a5cfe6597162c","abstract_canon_sha256":"bc600b880cf2cb76cd3ac3ac2de95a1107ce75b4271b08f6a37047e4becf3c1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:04.166251Z","signature_b64":"H4ZKAcvwdsuCb0mMytp3LFA1ofclYlIM3dMjyikwgo27QVUXcVhPmbFteEEHa6ISOf+FT1ipE6XTPtke1hhMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b032e2ec86a119df1b339cea9eb8b87b90b01c5a6c0bf6632f1ffe0b4d4f1d62","last_reissued_at":"2026-07-05T11:19:04.165802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:04.165802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alberto Dalla Libera, Aris Synodinos, Matteo Iovino, Niccol\\`o Turcato, Pietro Falco, Ruggero Carli","submitted_at":"2025-03-06T10:08:44Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) and Visual Language Models (VLMs) have significantly impacted robotics, enabling high-level semantic motion planning applications. Reinforcement Learning (RL), a complementary paradigm, enables agents to autonomously optimize complex behaviors through interaction and reward signals. However, designing effective reward functions for RL remains challenging, especially in real-world tasks where sparse rewards are insufficient and dense rewards require elaborate design. In this work, we propose Autonomous Reinforcement learning for Complex Human-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04280","kind":"arxiv","version":4},"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/2503.04280/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":"2503.04280","created_at":"2026-07-05T11:19:04.165850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04280v4","created_at":"2026-07-05T11:19:04.165850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04280","created_at":"2026-07-05T11:19:04.165850+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAZOF3EGUEM5","created_at":"2026-07-05T11:19:04.165850+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAZOF3EGUEM56GZT","created_at":"2026-07-05T11:19:04.165850+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAZOF3EG","created_at":"2026-07-05T11:19:04.165850+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/WAZOF3EGUEM56GZTTTVJ5OFYPO","json":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO.json","graph_json":"https://pith.science/api/pith-number/WAZOF3EGUEM56GZTTTVJ5OFYPO/graph.json","events_json":"https://pith.science/api/pith-number/WAZOF3EGUEM56GZTTTVJ5OFYPO/events.json","paper":"https://pith.science/paper/WAZOF3EG"},"agent_actions":{"view_html":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO","download_json":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO.json","view_paper":"https://pith.science/paper/WAZOF3EG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04280&json=true","fetch_graph":"https://pith.science/api/pith-number/WAZOF3EGUEM56GZTTTVJ5OFYPO/graph.json","fetch_events":"https://pith.science/api/pith-number/WAZOF3EGUEM56GZTTTVJ5OFYPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/action/storage_attestation","attest_author":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/action/author_attestation","sign_citation":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/action/citation_signature","submit_replication":"https://pith.science/pith/WAZOF3EGUEM56GZTTTVJ5OFYPO/action/replication_record"}},"created_at":"2026-07-05T11:19:04.165850+00:00","updated_at":"2026-07-05T11:19:04.165850+00:00"}