{"as_of":"2026-08-17T12:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8d1bf93a8832c627bd098d5970c38b7f1fa520f814724eb61b20f9b254a87dd9","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T00:01:33.927210Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T04:46:12.483085Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-29T19:23:54.271036Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.03238","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.03238","snapshot_observed_at":"2026-06-29T19:23:54.271036Z","title":"RobotxR1: Enabling embodied robotic intelligence on large language models through closed-loop reinforcement learn- ing","venue":null,"work_id":"2938705e-d849-4a63-a7bf-1b90b1acffc6","year":2025},"citing_paper":{"arxiv_id":"2602.03433","last_updated":"2026-02-03T11:56:08Z","snapshot_observed_at":"2026-08-15T04:40:36.784721Z","submitted_at":"2026-02-03T11:56:08Z","title":"When control meets large language models: From words to dynamics","version":1},"reference_index":170,"source":"pdf_text","source_observed_at":"2026-05-21T14:52:44.632671Z"},"links":{"cited_paper":"/paper/2505.03238","citing_paper":"/paper/2602.03433"},"observation_digest":"sha256:85df51ca4eac73fb8eb974942e873cc70856cfe977c7a5491cc76cc5362fcbff","observation_id":"e212aca0-168b-4d19-9caa-328d2a2b083b","resolution":{"observed_at":"2026-05-21T14:54:13.224844Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2505.03238","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.03238","snapshot_observed_at":"2026-06-29T19:23:54.271036Z","title":"RobotxR1: Enabling embodied robotic intelligence on large language models through closed-loop reinforcement learn- ing","venue":null,"work_id":"2938705e-d849-4a63-a7bf-1b90b1acffc6","year":2025},"citing_paper":{"arxiv_id":"2606.27871","last_updated":"2026-06-26T09:11:59Z","snapshot_observed_at":"2026-08-15T10:48:01.103813Z","submitted_at":"2026-06-26T09:11:59Z","title":"LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-29T04:46:12.483085Z"},"links":{"cited_paper":"/paper/2505.03238","citing_paper":"/paper/2606.27871"},"observation_digest":"sha256:08704c4ba258911622cbd6730330f346c5142186c4fd0da0e3e59cdb009d3827","observation_id":"3ddf0e1e-c606-46f1-bda4-ba80fc619d6f","resolution":{"observed_at":"2026-06-29T19:23:54.272291Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.03238/citation-record","integrity":"/paper/2505.03238/integrity","json":"/paper/2505.03238/citation-record.json","paper":"/paper/2505.03238"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.474148Z","title":"Caesar, V","venue":null,"work_id":"ccb69296-cec1-407a-8862-e25ddb87a44b","year":2020},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.774924Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:7b6444146658086aeae221f2ede2fa07b9293a00bb92adc03deee1a7215c374d","observation_id":"cc240c75-dae7-421b-bc51-39acfbce669a","resolution":{"observed_at":"2026-08-16T00:01:34.478666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.461607Z","title":null,"venue":null,"work_id":"c5a0a849-d327-41d8-bd56-86a3e75a05b8","year":2020},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.779005Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:9889ef1154524d6be787951f84a720df67b8cc1ddddf958bd0ab5e2eba9daeba","observation_id":"4932352d-044a-4378-9bdd-7f97152dabc2","resolution":{"observed_at":"2026-08-16T00:01:34.465330Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.450675Z","title":"O’Neill, A","venue":null,"work_id":"0e593fcf-722f-4341-b07b-21d4b15fc331","year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.782663Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:46be7477aa15f5bdb6e40d84b8f6069f763f8d6a13c93ac4d5cdb07779b8d6a9","observation_id":"003d50dd-b702-4162-8b6a-e04b4763d545","resolution":{"observed_at":"2026-08-16T00:01:34.454105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.438590Z","title":null,"venue":null,"work_id":"d5038984-922d-4393-89c9-82c4f5fd9f18","year":2014},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.786080Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:6956beeafac300a0144425c7178857d523e76378ebe503290ed9cdef15f62634","observation_id":"3c98d435-b7a9-487f-bae5-4944da27e349","resolution":{"observed_at":"2026-08-16T00:01:34.443067Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.02114","last_updated":"2021-11-03T10:16:39Z","snapshot_observed_at":"2026-08-02T08:12:49.547570Z","submitted_at":"2021-11-03T10:16:39Z","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.02114","snapshot_observed_at":"2026-08-16T00:01:33.789058Z","title":"Schuhmann, R","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.789058Z"},"links":{"cited_paper":"/paper/2111.02114","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:22b29948736a08ee392cfd3c9fe1ec23986ab7bd69721245aa131fd2cdb75e34","observation_id":"8b721b74-38bf-44cb-bdaa-7e961e4909f5","resolution":{"observed_at":"2026-08-16T00:01:33.789058Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-031-20077-9_","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:33.958704Z","title":null,"venue":null,"work_id":"710a1192-44cc-44f8-87ff-17b1c4c7de34","year":2022},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.792800Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:a966517237dd49ea97d584ded05b257f8409645b104955187a126d1a58454440","observation_id":"16abebf6-ea0d-40fc-8971-e1d4c121c5e6","resolution":{"observed_at":"2026-08-16T00:01:33.963401Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.428110Z","title":null,"venue":null,"work_id":"2ed5c38d-1320-45f9-abd7-bd0b6308fc38","year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.798382Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:c776fb65ade24d06bc80c7ff0bfb55f25987e7a8834ad25b0b03113a6b56e405","observation_id":"6ad8e937-45ef-4765-a484-d9584774ce75","resolution":{"observed_at":"2026-08-16T00:01:34.431604Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.418719Z","title":"Ghosh, H","venue":null,"work_id":"6402ba4b-d5d1-4021-aa47-d81909901061","year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.803099Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:3fdfea2a5e30c7f68a5301e10cf517b37ab3cb0b6a7f934609d47d252550c486","observation_id":"6fc97f29-cd3d-4471-925e-173a1b9c518f","resolution":{"observed_at":"2026-08-16T00:01:34.422084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:33.805879Z","title":"Brohan, N","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.805879Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:64939861e78e9d4e3d8b4b704b17c3f0467d563a2ba0cc125295d2a1feaa69b5","observation_id":"4cdc05f7-c689-4278-a87d-8c4d1821eeeb","resolution":{"observed_at":"2026-08-16T00:01:33.805879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07726","last_updated":"2024-10-10T17:28:23Z","snapshot_observed_at":"2026-08-08T07:16:45.596308Z","submitted_at":"2024-07-10T14:57:46Z","title":"PaliGemma: A versatile 3B VLM for transfer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07726","snapshot_observed_at":"2026-08-16T00:01:33.809206Z","title":"Beyer, A","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.809206Z"},"links":{"cited_paper":"/paper/2407.07726","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:9ccb1a6fb450be7e44cadf9197e787b922532e3440e50ffa76668fbacae4750d","observation_id":"75c23147-84e7-4d79-9428-09e671cd93ee","resolution":{"observed_at":"2026-08-16T00:01:33.809206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.402680Z","title":"Radford, J","venue":null,"work_id":"640bed52-eed3-4d67-9b5b-f51766a99a16","year":2021},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.813972Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:adcd7763f25c18547660da46c3ac8ea1a74c5b94af3d9c242afaebb93329ed15","observation_id":"962d79fb-6b2a-4cec-b65e-200e51422e44","resolution":{"observed_at":"2026-08-16T00:01:34.405736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.391244Z","title":null,"venue":null,"work_id":"cf74c7d0-bd3f-4ee4-944d-4f2c5023d7b3","year":2023},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.817043Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:141d0e38f1715e20929481d1cad0533c41a71f526b4fcf2af366cc3b0a0f9c4c","observation_id":"27f14daf-d0b9-40d1-b38a-8fe79e8285b7","resolution":{"observed_at":"2026-08-16T00:01:34.394763Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18194","last_updated":"2024-12-24T06:03:42Z","snapshot_observed_at":"2026-08-15T19:11:06.150955Z","submitted_at":"2024-12-24T06:03:42Z","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18194","snapshot_observed_at":"2026-08-16T00:01:33.819892Z","title":"Zhang, Z","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.819892Z"},"links":{"cited_paper":"/paper/2412.18194","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:0f9569b2a52b03522cc73ce13a4a99cd2458910c95a1f49fb9547ae8486147c3","observation_id":"ce3870ec-e29e-4367-b05b-e6080f75c688","resolution":{"observed_at":"2026-08-16T00:01:33.819892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16292","last_updated":"2024-02-22T03:24:26Z","snapshot_observed_at":"2026-08-16T14:56:54.964327Z","submitted_at":"2023-09-28T09:41:35Z","title":"DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16292","snapshot_observed_at":"2026-08-16T00:01:33.823538Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.823538Z"},"links":{"cited_paper":"/paper/2309.16292","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:7f07cc77a9484004a88dc1e2004e28a1caceebcf5691c43d9822c3f5647f1efe","observation_id":"e61de76f-ddef-4c7c-b946-ecdac31db763","resolution":{"observed_at":"2026-08-16T00:01:33.823538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.381691Z","title":null,"venue":null,"work_id":"75b479f7-405c-4eab-80c7-c347e3993936","year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.826915Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:b43433c3310cc4f3e73402a85db52158e10481c25280513cd3f394ba82736aab","observation_id":"8ea3abd7-8dd8-4504-bba2-57ce91a4e8ae","resolution":{"observed_at":"2026-08-16T00:01:34.384852Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.371666Z","title":null,"venue":null,"work_id":"dd8f18da-c479-40cb-9dd9-aec026858560","year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.830464Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:f24d32d161f184c95206d6aad54919866e7234e5242855598e1ea7cb472726c5","observation_id":"740642b3-d5f6-465e-83b9-c1f99d628911","resolution":{"observed_at":"2026-08-16T00:01:34.375162Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.01691","last_updated":"2022-08-16T16:06:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-04T17:57:11Z","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.01691","snapshot_observed_at":"2026-08-16T00:01:33.833988Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.833988Z"},"links":{"cited_paper":"/paper/2204.01691","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:0761d54073c7692452c6f38ed31eb0a25b782c7ca076148391619460026c06eb","observation_id":"ff03512b-f3a7-437f-bb7b-53622bf6f46f","resolution":{"observed_at":"2026-08-16T00:01:33.833988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-16T00:01:33.837066Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.837066Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:6d53df7221b9a0774b4e560423c2157aeaa2290a74cc52a41eeb57a53502db32","observation_id":"e33c9aec-06d0-4ebe-b1af-a2e9eed69390","resolution":{"observed_at":"2026-08-16T00:01:33.837066Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.12680","last_updated":"2025-04-17T06:16:11Z","snapshot_observed_at":"2026-08-17T00:52:01.999261Z","submitted_at":"2025-04-17T06:16:11Z","title":"Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.12680","snapshot_observed_at":"2026-08-16T00:01:33.840834Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.840834Z"},"links":{"cited_paper":"/paper/2504.12680","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:cdc33d2630dfb80653d1fb52129e360abe06190af736d32291bb699b39d9f92d","observation_id":"0171f8c6-54e7-4295-9353-1520cfa78378","resolution":{"observed_at":"2026-08-16T00:01:33.840834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-16T00:01:33.845187Z","title":"Cobbe, V","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.845187Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:7e1639a207f500d99bd4978c2168cfa6199418c3f8b7a76f53a0943ab3ee5a73","observation_id":"15d57463-8d22-4447-a5db-b86cfc9fa1c1","resolution":{"observed_at":"2026-08-16T00:01:33.845187Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.21934","last_updated":"2025-09-04T19:36:32Z","snapshot_observed_at":"2026-08-16T12:46:09.609350Z","submitted_at":"2025-03-27T19:21:05Z","title":"Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.21934","snapshot_observed_at":"2026-08-16T00:01:33.848663Z","title":"Petrov, J","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.848663Z"},"links":{"cited_paper":"/paper/2503.21934","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:34b25111bb39a60d915e2d6e8715718c8a35a89ce7ec7718534f9a9bc9ea02e8","observation_id":"f382a607-15ab-48e0-9e2e-f82ce66fe699","resolution":{"observed_at":"2026-08-16T00:01:33.848663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:33.852193Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.852193Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:b9d4b49e1afe8dd1c4d72862ba314863b8b914ebc5ffb6cf526a173b88c55e1b","observation_id":"14b2d62d-69c5-4085-ade0-2a6d647029a2","resolution":{"observed_at":"2026-08-16T00:01:33.852193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.361399Z","title":null,"venue":null,"work_id":"2902638c-bc01-4e76-8bdd-0af232e05997","year":null},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.855190Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:c4572abb989b7b22c6e49a5933162353bb180eea9a27674e1d70c36d790ff969","observation_id":"713403b7-e1ff-4f69-8705-ef82e4641fae","resolution":{"observed_at":"2026-08-16T00:01:34.365217Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.343624Z","title":null,"venue":null,"work_id":"390df061-5f23-4c9f-96dc-3b0b8ef12e7f","year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.862557Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:4e0aa0116c852ba83ae19c119a7aed0a17a0a2d65a621e66ec7cc7824ef9c273","observation_id":"14387f21-4f23-402c-aee0-8ddcc50d37ab","resolution":{"observed_at":"2026-08-16T00:01:34.346889Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.17749","last_updated":"2024-06-25T17:34:52Z","snapshot_observed_at":"2026-08-16T13:39:40.804646Z","submitted_at":"2024-06-25T17:34:52Z","title":"Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical Investigation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.17749","snapshot_observed_at":"2026-08-16T00:01:33.866260Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.866260Z"},"links":{"cited_paper":"/paper/2406.17749","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:14190f1558d8f124ad19a55907f51cc74dbd8ac078a59ca2e5300e80977441da","observation_id":"285bb1d6-6642-49c0-a3d4-fd5fef8e0e45","resolution":{"observed_at":"2026-08-16T00:01:33.866260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:33.869586Z","title":"Chen and X","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.869586Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:f42371fd97df6facfde37dfaa4272f752f0d8e5987e66d591aa0c164297455f5","observation_id":"3ce36d9e-38d5-4889-97a7-1c94968016e0","resolution":{"observed_at":"2026-08-16T00:01:33.869586Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.15790","last_updated":"2025-02-26T06:34:55Z","snapshot_observed_at":"2026-08-16T13:15:59.066127Z","submitted_at":"2024-09-24T06:36:56Z","title":"Small Language Models: Survey, Measurements, and Insights","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.15790","snapshot_observed_at":"2026-08-16T00:01:33.874062Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.874062Z"},"links":{"cited_paper":"/paper/2409.15790","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:9ccf0cad8f9cb84a765134ae5e6acdae4fd8dcc6536c749763c3638b1f30d673","observation_id":"2662bc64-8916-49f0-b10b-dcf588fa1635","resolution":{"observed_at":"2026-08-16T00:01:33.874062Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.331406Z","title":"Silver and R","venue":null,"work_id":"b6a49723-e426-4e54-9af0-def82af5a076","year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.877534Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:0b96ae4bc681cca273f6afa1624c3bf3fffef1ee41e6978ffbc813a91ee6411d","observation_id":"94c70752-d1ef-4de4-a726-197d65d7fbf9","resolution":{"observed_at":"2026-08-16T00:01:34.335059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-16T00:01:33.880507Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.880507Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:87102073c01648fa01d335f3f50c6c0371ecabce9dabe900f8e4a8556abbae04","observation_id":"806e0de7-3dcd-40cd-8c6e-dcf38b7f5914","resolution":{"observed_at":"2026-08-16T00:01:33.880507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.321196Z","title":"Rudin, D","venue":null,"work_id":"e8ef7a4c-945b-4b48-a6f5-b0598af99849","year":2022},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.883952Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:0389d95578ddb20510faa037753f3752611cc602775c82f0303070f1d702e04f","observation_id":"ce365763-589a-41df-9b66-556f5896b28e","resolution":{"observed_at":"2026-08-16T00:01:34.324085Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.311105Z","title":null,"venue":null,"work_id":"d7dea1fe-4e4e-4af2-a5d3-de4ef4d3fee3","year":2022},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.886962Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:b1b4fc13bba0250b9562f32f36967ef0965e8aaba365b9ea7cfb24a4b9ade749","observation_id":"40cd18db-bdc1-4a17-8e99-f949b9c9d165","resolution":{"observed_at":"2026-08-16T00:01:34.314840Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.11514","last_updated":"2025-04-15T13:49:17Z","snapshot_observed_at":"2026-08-16T12:40:53.497050Z","submitted_at":"2025-04-15T13:49:17Z","title":"Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.11514","snapshot_observed_at":"2026-08-16T00:01:33.889809Z","title":"Baumann, C","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.889809Z"},"links":{"cited_paper":"/paper/2504.11514","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:2ae4e736dfa8afa08f1a0fdeda6698116a0fb49bfa744c1cfbd7d959863fc86b","observation_id":"a2516f92-ce54-4fe1-beec-ce23fcc6b10b","resolution":{"observed_at":"2026-08-16T00:01:33.889809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08647","last_updated":"2023-06-16T23:02:21Z","snapshot_observed_at":"2026-08-16T15:23:54.319293Z","submitted_at":"2023-06-14T17:27:10Z","title":"Language to Rewards for Robotic Skill Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08647","snapshot_observed_at":"2026-08-16T00:01:33.893211Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.893211Z"},"links":{"cited_paper":"/paper/2306.08647","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:0669dd9e238faf2c7e5a8573ebd2d4766395a69a7159d9122f2d7bac13cd26fe","observation_id":"ae1adfe9-f324-4f75-ada1-2db330993a1a","resolution":{"observed_at":"2026-08-16T00:01:33.893211Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.10762","last_updated":"2024-03-16T01:57:35Z","snapshot_observed_at":"2026-08-16T14:09:16.986640Z","submitted_at":"2024-03-16T01:57:35Z","title":"NARRATE: Versatile Language Architecture for Optimal Control in Robotics","version":1},"cited_work":{"arxiv_id":"2403.10762","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.10762","snapshot_observed_at":"2026-08-16T00:01:34.010607Z","title":"NARRATE: Versatile Language Architecture for Optimal Control in Robotics","venue":"cs.RO","work_id":"00f182ec-0f32-4dc1-81cd-eabcdb4cfbb2","year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.896503Z"},"links":{"cited_paper":"/paper/2403.10762","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:9239e392914472cb1a93abd1728001f71434a2b53dc7304b76cd2d7ad5246dd3","observation_id":"827bfe6e-d587-4934-9960-47655eaa3b4d","resolution":{"observed_at":"2026-08-16T00:01:34.015133Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.12931","last_updated":"2024-04-30T21:35:53Z","snapshot_observed_at":"2026-08-02T10:40:03.816188Z","submitted_at":"2023-10-19T17:31:01Z","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.12931","snapshot_observed_at":"2026-08-16T00:01:33.900292Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.900292Z"},"links":{"cited_paper":"/paper/2310.12931","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:b78dfbf0e5c276da64414e90a609f4f78b2b36495681b25bdb221b547b106d9a","observation_id":"92f7430f-e55d-404d-9516-172b830b3e33","resolution":{"observed_at":"2026-08-16T00:01:33.900292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14669","last_updated":"2025-02-25T08:56:11Z","snapshot_observed_at":"2026-08-16T12:56:37.850837Z","submitted_at":"2025-02-20T16:05:18Z","title":"AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.14669","snapshot_observed_at":"2026-08-16T00:01:33.903602Z","title":"Dao and D","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.903602Z"},"links":{"cited_paper":"/paper/2502.14669","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:42c9bc1e66174b42738f40e20669c05e6bb6f8132c1eac3e635844bf5f83fd32","observation_id":"166eb0ce-85c0-43c7-9e41-f20cdf2223b5","resolution":{"observed_at":"2026-08-16T00:01:33.903602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.15558","last_updated":"2025-05-19T17:59:19Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-18T22:06:58Z","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.15558","snapshot_observed_at":"2026-08-16T00:01:33.906665Z","title":"Azzolini, H","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.906665Z"},"links":{"cited_paper":"/paper/2503.15558","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:7b163fd3e9891a4c4d1375f7f63f8e684bd0dfc76b451939ed778fd66223f07f","observation_id":"8d3660e1-215f-4787-b053-469382c35ce6","resolution":{"observed_at":"2026-08-16T00:01:33.906665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16609","last_updated":"2023-09-28T17:07:49Z","snapshot_observed_at":"2026-08-09T21:25:20.369782Z","submitted_at":"2023-09-28T17:07:49Z","title":"Qwen Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16609","snapshot_observed_at":"2026-08-16T00:01:33.910737Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.910737Z"},"links":{"cited_paper":"/paper/2309.16609","citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:5894ed165ad4c3b9600c7356a064aae0c776b25f64cef953b35111f20f3f82ee","observation_id":"2ac23d6e-d281-4e00-bfe5-663471eb0c89","resolution":{"observed_at":"2026-08-16T00:01:33.910737Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.300352Z","title":"Baumann, E","venue":null,"work_id":"df2f65e9-17d5-410e-a8c3-79d5f5560c26","year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.914224Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:b2c04aca36b3be3a536aaeef94099a3521506232ba8c1551a594c6d87072920b","observation_id":"0b16eebe-42b5-4c6e-87a6-0473b4b7e143","resolution":{"observed_at":"2026-08-16T00:01:34.303824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.288583Z","title":null,"venue":null,"work_id":"eb90d789-fda5-4962-bc33-eed9205713cc","year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.917072Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:a1b349a1af449da4f68ff0b5c30b15f3e84c61cc4b496de79e3eaba1c1e9528e","observation_id":"797cf812-b404-42e8-a336-39ce249a080b","resolution":{"observed_at":"2026-08-16T00:01:34.292123Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.278380Z","title":null,"venue":null,"work_id":"d82410dd-1288-4fa0-9406-dd077c354a1e","year":2024},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.920575Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:de6b3d0bc9a55ea6ec8d01e2f8c0b79997cd0340d73f48a9b837a3e15ec7e4aa","observation_id":"1d137424-4e6c-48b7-a57f-4d97f7e3e052","resolution":{"observed_at":"2026-08-16T00:01:34.281895Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.267534Z","title":null,"venue":null,"work_id":"d79e6825-e7ec-4b37-8976-58e963b8968a","year":2020},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.924398Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:3ca46b3aac66bef60600cf60250a7fd56fefbd8dbf23d825ee9d5b91f5cda9e4","observation_id":"5c5e4ec1-db11-4b1a-a7b7-25385688f5b3","resolution":{"observed_at":"2026-08-16T00:01:34.271490Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:34.257350Z","title":"Gerganov and O.-S","venue":null,"work_id":"ea6805af-2c4f-415e-be70-8d5f0b2e025b","year":2023},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.927210Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:4fad01d434335a09038cc7d419dd559a914df3156f51b6c612089cfee9fc1b52","observation_id":"abf9a3f8-876f-4fc3-9100-01fdd6d07b18","resolution":{"observed_at":"2026-08-16T00:01:34.260686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:01:33.858858Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:33.858858Z"},"links":{"citing_paper":"/paper/2505.03238"},"observation_digest":"sha256:cc1ee83be5a06d918ecb6bf2d0c517474a5a9b0d46ad9597300d8574e6f88155","observation_id":"b054846e-e150-492a-83c6-fba50273b813","resolution":{"observed_at":"2026-08-16T00:01:33.858858Z","resolver_source":null,"status":"parse_uncertain"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.03238","last_updated":"2025-08-30T14:28:36Z","latest_version":2,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-17T00:52:50.974346Z","submitted_at":"2025-05-06T07:07:28Z","title":"RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":33,"verified_exact":2,"verified_fuzzy":8},"total_outbound_references":44},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2505.03238."}