{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T5VLBTENAOCNHHJEJ5R5MY563G","short_pith_number":"pith:T5VLBTEN","schema_version":"1.0","canonical_sha256":"9f6ab0cc8d0384d39d244f63d663bed99d251a25178bdce38e39064843074c72","source":{"kind":"arxiv","id":"2505.03238","version":2},"attestation_state":"computed","paper":{"title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Liam Boyle, Luca Benini, Michele Magno, Nicolas Baumann, Paviththiren Sivasothilingam","submitted_at":"2025-05-06T07:07:28Z","abstract_excerpt":"Future robotic systems operating in real-world environments will require on-board embodied intelligence without continuous cloud connection, balancing capabilities with constraints on computational power and memory. This work presents an extension of the R1-zero approach, which enables the usage of low parameter-count Large Language Models (LLMs) in the robotic domain. The R1-Zero approach was originally developed to enable mathematical reasoning in LLMs using static datasets. We extend it to the robotics domain through integration in a closed-loop Reinforcement Learning (RL) framework. This e"},"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":"2505.03238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-06T07:07:28Z","cross_cats_sorted":[],"title_canon_sha256":"c2abcaaa19665a11cc3c983bb13aa56ee28203e421ea37fc83877a2be58f9779","abstract_canon_sha256":"8f6fc94edff097041e697a5f2acc3bdde7ca5aeb9ba8ced7f820a948d68e8e72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:01.151163Z","signature_b64":"eixavsnx3tc/Gh4Sl4IotrOFLaWba0H+BTWUIl7u/7gY5AJBHLdcHhEbLoXbKiGBN7JTl1Mnf5g7nmV7Jjz9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f6ab0cc8d0384d39d244f63d663bed99d251a25178bdce38e39064843074c72","last_reissued_at":"2026-07-05T12:02:01.150685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:01.150685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Liam Boyle, Luca Benini, Michele Magno, Nicolas Baumann, Paviththiren Sivasothilingam","submitted_at":"2025-05-06T07:07:28Z","abstract_excerpt":"Future robotic systems operating in real-world environments will require on-board embodied intelligence without continuous cloud connection, balancing capabilities with constraints on computational power and memory. This work presents an extension of the R1-zero approach, which enables the usage of low parameter-count Large Language Models (LLMs) in the robotic domain. The R1-Zero approach was originally developed to enable mathematical reasoning in LLMs using static datasets. We extend it to the robotics domain through integration in a closed-loop Reinforcement Learning (RL) framework. This e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03238","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/2505.03238/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":"2505.03238","created_at":"2026-07-05T12:02:01.150749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03238v2","created_at":"2026-07-05T12:02:01.150749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03238","created_at":"2026-07-05T12:02:01.150749+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5VLBTENAOCN","created_at":"2026-07-05T12:02:01.150749+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5VLBTENAOCNHHJE","created_at":"2026-07-05T12:02:01.150749+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5VLBTEN","created_at":"2026-07-05T12:02:01.150749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27871","citing_title":"LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":170,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5VLBTENAOCNHHJEJ5R5MY563G","json":"https://pith.science/pith/T5VLBTENAOCNHHJEJ5R5MY563G.json","graph_json":"https://pith.science/api/pith-number/T5VLBTENAOCNHHJEJ5R5MY563G/graph.json","events_json":"https://pith.science/api/pith-number/T5VLBTENAOCNHHJEJ5R5MY563G/events.json","paper":"https://pith.science/paper/T5VLBTEN"},"agent_actions":{"view_html":"https://pith.science/pith/T5VLBTENAOCNHHJEJ5R5MY563G","download_json":"https://pith.science/pith/T5VLBTENAOCNHHJEJ5R5MY563G.json","view_paper":"https://pith.science/paper/T5VLBTEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03238&json=true","fetch_graph":"https://pith.science/api/pith-number/T5VLBTENAOCNHHJEJ5R5MY563G/graph.json","fetch_events":"https://pith.science/api/pith-number/T5VLBTENAOCNHHJEJ5R5MY563G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5VLBTENAOCNHHJEJ5R5MY563G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5VLBTENAOCNHHJEJ5R5MY563G/action/storage_attestation","attest_author":"https://pith.science/pith/T5VLBTENAOCNHHJEJ5R5MY563G/action/author_attestation","sign_citation":"https://pith.science/pith/T5VLBTENAOCNHHJEJ5R5MY563G/action/citation_signature","submit_replication":"https://pith.science/pith/T5VLBTENAOCNHHJEJ5R5MY563G/action/replication_record"}},"created_at":"2026-07-05T12:02:01.150749+00:00","updated_at":"2026-07-05T12:02:01.150749+00:00"}