{"as_of":"2026-08-18T13:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:59b651291efb6af5087f5acbfffb2ca6b96d68abed00feef02d90a53a125840b","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T14:26:30.330510Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.10471/citation-record","integrity":"/paper/2608.10471/integrity","json":"/paper/2608.10471/citation-record.json","paper":"/paper/2608.10471"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.19457","last_updated":"2026-02-14T11:42:30Z","snapshot_observed_at":"2026-08-14T13:34:39.415942Z","submitted_at":"2025-07-25T17:42:32Z","title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.19457","snapshot_observed_at":"2026-08-15T14:26:30.188421Z","title":"Agrawal, O","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.188421Z"},"links":{"cited_paper":"/paper/2507.19457","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:eaa1c71330e1143227f9d9d911dc8721c78ea6c7722f97bda92a330909171c08","observation_id":"638a525f-2864-4c82-b2c9-1c69e093de63","resolution":{"observed_at":"2026-08-15T14:26:30.188421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11695","last_updated":"2024-10-06T17:34:26Z","snapshot_observed_at":"2026-08-18T13:14:20.966153Z","submitted_at":"2024-06-17T16:12:03Z","title":"Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11695","snapshot_observed_at":"2026-08-15T14:26:30.193115Z","title":"Opsahl-Ong et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.193115Z"},"links":{"cited_paper":"/paper/2406.11695","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:c39fe94ed0420e1c207c0185fe1626ce1e2e837b7d1a4a0c53835e62e021eb66","observation_id":"d166e139-46b7-47c1-858c-03dd797f72de","resolution":{"observed_at":"2026-08-15T14:26:30.193115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.03409","last_updated":"2024-04-15T07:50:32Z","snapshot_observed_at":"2026-08-15T09:21:11.223719Z","submitted_at":"2023-09-07T00:07:15Z","title":"Large Language Models as Optimizers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.03409","snapshot_observed_at":"2026-08-15T14:26:30.196997Z","title":"Yang et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.196997Z"},"links":{"cited_paper":"/paper/2309.03409","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:d6cf626a64ebf88419a7a3034b2745088e115bee1a7f68640e805f24519aadf6","observation_id":"cb57501d-d22d-44de-8655-ed96ce006d17","resolution":{"observed_at":"2026-08-15T14:26:30.196997Z","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":"2026-08-15T14:26:30.743266Z","title":null,"venue":null,"work_id":"e6bf6dc7-4a13-492e-a0eb-9e3133b18ba9","year":2023},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.200271Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:14985459e532b2b8ad3b381cd9ca4c2553763c057495aab169c76b9c20e33ebf","observation_id":"cdf0d1ce-eef0-4f7e-b399-4a77fb137fd4","resolution":{"observed_at":"2026-08-15T14:26:30.746741Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07496","last_updated":"2024-06-11T17:32:21Z","snapshot_observed_at":"2026-08-13T02:15:58.634561Z","submitted_at":"2024-06-11T17:32:21Z","title":"TextGrad: Automatic \"Differentiation\" via Text","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07496","snapshot_observed_at":"2026-08-15T14:26:30.203821Z","title":"Differentiation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.203821Z"},"links":{"cited_paper":"/paper/2406.07496","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:a97695ebaa9043e04a8f769d114d55cafc89358533e4755d88e551fcb0691e9d","observation_id":"ed8843cb-c760-417b-8822-748efd971738","resolution":{"observed_at":"2026-08-15T14:26:30.203821Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16797","last_updated":"2023-09-28T19:01:07Z","snapshot_observed_at":"2026-08-14T11:37:32.461743Z","submitted_at":"2023-09-28T19:01:07Z","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16797","snapshot_observed_at":"2026-08-15T14:26:30.207020Z","title":"Fernando, D","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.207020Z"},"links":{"cited_paper":"/paper/2309.16797","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:9d51a3c40371bcb58b5084aaa97407e8991ff45e578669ddc417e66d0d66a31e","observation_id":"de79cd07-8441-4fb4-82bc-0f8b2651735e","resolution":{"observed_at":"2026-08-15T14:26:30.207020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.08532","last_updated":"2025-05-01T11:56:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-15T16:50:09Z","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.08532","snapshot_observed_at":"2026-08-15T14:26:30.210364Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.210364Z"},"links":{"cited_paper":"/paper/2309.08532","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:a3bba33e6af59c27867d6682eaba92f707c434d5a19e6cc79e54de86453acee2","observation_id":"55440776-fc97-4ff5-83e7-7d290f295d9a","resolution":{"observed_at":"2026-08-15T14:26:30.210364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12548","last_updated":"2022-10-22T15:21:46Z","snapshot_observed_at":"2026-08-16T16:57:50.526540Z","submitted_at":"2022-05-25T07:50:31Z","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.12548","snapshot_observed_at":"2026-08-15T14:26:30.213550Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.213550Z"},"links":{"cited_paper":"/paper/2205.12548","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:4725421df768e544b1c63a580ac40acc6c098551a06cf37b7cc86844d0f4f8d1","observation_id":"9babd9a9-c319-4bfb-84ca-aa706b768f2d","resolution":{"observed_at":"2026-08-15T14:26:30.213550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-16T20:01:36.160048Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-15T14:26:30.217121Z","title":"Lester, R","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.217121Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:2db59f58f8b26bd59000cc97e253a6b5c11d303a65e3facc6baf8643922834b0","observation_id":"ad55ee85-c9b7-4f99-ba15-b5c00e5b7c61","resolution":{"observed_at":"2026-08-15T14:26:30.217121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.08435","last_updated":"2025-03-02T05:13:28Z","snapshot_observed_at":"2026-08-06T11:45:45.286982Z","submitted_at":"2024-08-15T21:59:23Z","title":"Automated Design of Agentic Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.08435","snapshot_observed_at":"2026-08-15T14:26:30.220720Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.220720Z"},"links":{"cited_paper":"/paper/2408.08435","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:c2a5cb2369e0df438698db6b2efd959d250a982fe015e65b24222f08ace812a3","observation_id":"0645c6ca-1570-4968-9415-e9e0cc661c9b","resolution":{"observed_at":"2026-08-15T14:26:30.220720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03714","last_updated":"2023-10-05T17:37:25Z","snapshot_observed_at":"2026-08-04T05:21:05.846165Z","submitted_at":"2023-10-05T17:37:25Z","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03714","snapshot_observed_at":"2026-08-15T14:26:30.224219Z","title":"Khattab, A","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.224219Z"},"links":{"cited_paper":"/paper/2310.03714","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:6b6e7e4ef43051a4625549824fe49a909ce1221c63cab2b608556b620b8ea8c3","observation_id":"57182a43-8cfc-4dfd-b863-28dd1a586c82","resolution":{"observed_at":"2026-08-15T14:26:30.224219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.24601","last_updated":"2026-05-11T15:26:31Z","snapshot_observed_at":"2026-08-14T08:15:35.097689Z","submitted_at":"2025-12-31T03:43:41Z","title":"Recursive Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.24601","snapshot_observed_at":"2026-08-15T14:26:30.228045Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.228045Z"},"links":{"cited_paper":"/paper/2512.24601","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:2f481b4e54a5e23f097e04fc610969a4db3fd66c1bc4230642ac1644fac1170c","observation_id":"91559be6-cd38-40ac-af16-2e379081cbc5","resolution":{"observed_at":"2026-08-15T14:26:30.228045Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.23904","last_updated":"2026-05-25T17:58:16Z","snapshot_observed_at":"2026-08-17T09:03:05.421842Z","submitted_at":"2026-05-22T17:59:50Z","title":"SkillOpt: Executive Strategy for Self-Evolving Agent Skills","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.23904","snapshot_observed_at":"2026-08-15T14:26:30.232028Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.232028Z"},"links":{"cited_paper":"/paper/2605.23904","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:ebd21350faf64af0d47e6f48208fb995007a004581ad22b0712f32ae1edc8d2f","observation_id":"b4301cea-f2b9-4c85-87d4-830d2ffd6bbb","resolution":{"observed_at":"2026-08-15T14:26:30.232028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-15T14:26:30.235648Z","title":"Shao et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.235648Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:f10b6643cd060633d185bebee19ed212eeb494009ce3736300d0a9220e816407","observation_id":"8f3b340d-62cc-49ed-928a-1927d446fd6d","resolution":{"observed_at":"2026-08-15T14:26:30.235648Z","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":"2026-08-15T14:26:30.733702Z","title":"Christiano, J","venue":null,"work_id":"e01d723a-b004-4d70-98fe-e8f6455db412","year":2017},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.239224Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:404fbfd457ec33e50bf3ea3248b637d5e84d04bb9b07dcabb9c2e2ebc3f89eac","observation_id":"66f344ff-f5d2-4d9a-83bb-805785fe929d","resolution":{"observed_at":"2026-08-15T14:26:30.737037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.724266Z","title":"Ouyang, J","venue":null,"work_id":"b19870ed-65c3-4cec-b382-24ee07839c3a","year":2022},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.243381Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:645698169d5ddfdff9da743f5b35e21208a71a5b40209be9fdc2238111296f41","observation_id":"94c2c675-e94e-4988-b5a0-13e64ec83ac9","resolution":{"observed_at":"2026-08-15T14:26:30.727714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.11366","last_updated":"2023-10-10T05:21:45Z","snapshot_observed_at":"2026-08-17T19:15:32.679249Z","submitted_at":"2023-03-20T18:08:50Z","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.11366","snapshot_observed_at":"2026-08-15T14:26:30.247223Z","title":"Shinn, F","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.247223Z"},"links":{"cited_paper":"/paper/2303.11366","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:ac8ece87024cbcc816abafdfb08b61d4138d4f6af295b8fa9165e5576b630f36","observation_id":"9bc6aec3-0590-4fc0-9cc7-3c37e609f118","resolution":{"observed_at":"2026-08-15T14:26:30.247223Z","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":"2026-08-15T14:26:30.715500Z","title":null,"venue":null,"work_id":"9fde7f84-8f8a-4ccc-be7e-d5873d2f6d59","year":2023},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.251553Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:1e693bea7c6ce02a64e1cf426a10f1c85a26a034d1661658a4cd0d15323c74f9","observation_id":"66a2986d-ef64-41df-8be3-c6a24eaaa7e3","resolution":{"observed_at":"2026-08-15T14:26:30.718509Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16291","last_updated":"2023-10-19T16:27:03Z","snapshot_observed_at":"2026-08-13T16:55:46.498156Z","submitted_at":"2023-05-25T17:46:38Z","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.16291","snapshot_observed_at":"2026-08-15T14:26:30.254943Z","title":"Wang et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.254943Z"},"links":{"cited_paper":"/paper/2305.16291","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:4e23a7b622c7b5c41117dd757dfc46e997736c086474e54bea9bf57b72095be2","observation_id":"870da879-4de2-4409-90c0-f0f9f0e17dd4","resolution":{"observed_at":"2026-08-15T14:26:30.254943Z","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":"2026-08-15T14:26:30.707136Z","title":null,"venue":null,"work_id":"823b96e7-2d0f-4cf5-b3fb-0cd3545a5e11","year":2024},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.257778Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:627b67c1fb1de9916c731da4a7dcecb6844d3a0c1923372d7ec91e614f75073e","observation_id":"239440e6-f545-4ce9-94cf-357bf160c06f","resolution":{"observed_at":"2026-08-15T14:26:30.710174Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.697892Z","title":"Zheng, W.-L","venue":null,"work_id":"e3247c6d-0f58-43ad-8fb0-89b966813b00","year":2023},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.260971Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:0f3d1c786a72c909083701da9d873c45446bb34d915f5a6fd277a53adfa526f2","observation_id":"5099acf5-6e07-4b3f-b60a-a8ecea7a7896","resolution":{"observed_at":"2026-08-15T14:26:30.701774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.689284Z","title":null,"venue":null,"work_id":"60af6a32-86c6-4b9a-8867-02f6b4a3c53d","year":2018},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.263889Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:2438616a155e5a7bd76f5b6c3e940ffa573a24c8ca9b64f98a7b3234f864877a","observation_id":"f09585e0-219b-4402-938e-29f3e567814d","resolution":{"observed_at":"2026-08-15T14:26:30.692528Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07911","last_updated":"2023-11-14T05:13:55Z","snapshot_observed_at":"2026-07-06T16:47:08.877195Z","submitted_at":"2023-11-14T05:13:55Z","title":"Instruction-Following Evaluation for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07911","snapshot_observed_at":"2026-08-15T14:26:30.266740Z","title":"Zhou et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.266740Z"},"links":{"cited_paper":"/paper/2311.07911","citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:30c1bf6e2b11393906ce497a4e5b5204a6edd371c017bd56ca8ac253e1257793","observation_id":"f09da6e0-ed0d-4b74-b2e5-ed9779256aa5","resolution":{"observed_at":"2026-08-15T14:26:30.266740Z","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":"2026-08-15T14:26:30.679035Z","title":null,"venue":null,"work_id":"e125a4c6-1ef5-4d77-a1c4-2616b798496c","year":2020},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.270711Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:98abe1896aea1e5bbf6ad4cb679cb77f008572e5bac21543ceef8124bf3d62b6","observation_id":"cb3a5adc-ba8a-473c-8f42-21d3ee46d9b7","resolution":{"observed_at":"2026-08-15T14:26:30.683569Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.669650Z","title":"Benchmark suite (58-verifier registry), 2025","venue":null,"work_id":"24ba07da-9f7e-47e4-8b2a-0ab4ce0c8d81","year":2025},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.274626Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:09fd2b216b13f24c0d4833ebabb2476933d7f344049e44693432e2efe851b6c1","observation_id":"93096b78-c4de-4e2a-a587-fe21f920b0b5","resolution":{"observed_at":"2026-08-15T14:26:30.673140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.660166Z","title":"Call describe_task() + dataset_overview() + peek_examples() a single time each, then STOP – they are static","venue":null,"work_id":"e958638b-0f50-4a4b-a498-a4715b9f5664","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.279244Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:ddbfb6cfb59737d0303b114f31f5e5c8825faafcfaf106ee5647b142673fc275","observation_id":"b62bb3cf-abb8-4e09-bf43-fe04315aa228","resolution":{"observed_at":"2026-08-15T14:26:30.663295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.651016Z","title":"Read describe_task()[’known_rules’] (rules promoted from earlier runs of THIS task) AND scratchpad_read(...)","venue":null,"work_id":"8a57d590-8882-48fc-b7bf-5803800b2877","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.282679Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:f65484117b4947652abd3bb0bd60b929a469a66a30e2c637977ec415a8024c32","observation_id":"139082b5-9720-4ff7-aaa7-1370f79fd9ad","resolution":{"observed_at":"2026-08-15T14:26:30.654360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.641507Z","title":null,"venue":null,"work_id":"85de9359-c566-41f1-a498-2cb34439ff55","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.286324Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:daff73dfe59c3585521420a949a07899f395ba34ff1ab1a43ee668ce3ebe1306","observation_id":"e112e896-bfcf-4a0f-9976-7edf638b9ae4","resolution":{"observed_at":"2026-08-15T14:26:30.644738Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.631315Z","title":"Make ONE targeted change, then run_candidate(prompt) WITHOUT example_ids (the host’s representative minibatch)","venue":null,"work_id":"e748e22f-057b-4b30-81b6-f47ebe4c012f","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.290018Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:b78a61c8fa0b7f99e50e930da3dda6ee9e6fe98a3c8e609518464c16d2df60e0","observation_id":"64ef524a-16bb-401c-a52e-577907bc2ba2","resolution":{"observed_at":"2026-08-15T14:26:30.635395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.620451Z","title":"Build only on REAL_GAIN","venue":null,"work_id":"cb6316ba-0772-4c16-92d7-01553660c84c","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.293493Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:c293ac215441c45a2edc87d2ac968e22493c2bedcb260eb93703a3e9685bfe64","observation_id":"b7a11e0c-84bb-42e8-84b3-bb6eb9b7159c","resolution":{"observed_at":"2026-08-15T14:26:30.624834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.609639Z","title":"When a change earns a REAL_GAIN, record the durable, transferable rule via scratchpad_add(kind=\"rule\", ...) – it is promoted to the cross-run library so future runs start ahead","venue":null,"work_id":"17486789-6a4c-43b5-9122-d835e7f93d9c","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.296831Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:819e4f55647e18c98927bf5de28bb98247c1ea25b15d068eceb13c35578ca6f4","observation_id":"88e0c93d-d85b-4b5a-b1cd-20c358e1424a","resolution":{"observed_at":"2026-08-15T14:26:30.613571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.599404Z","title":"You are a helpful assistant","venue":null,"work_id":"be99c3f8-b896-45bd-9547-fed55e21674f","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.300858Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:e2c3aee3f52f329e11da02b2266aa1079554bab7ebeb5b542a837d0e1e3bbb0e","observation_id":"8eb9daa4-7f92-45f8-969b-774a79f553fa","resolution":{"observed_at":"2026-08-15T14:26:30.603128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.589124Z","title":null,"venue":null,"work_id":"707b91e3-0dbf-4c48-9e93-0061b6fb6b8e","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.304307Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:50f5632ced3d98b68587652df7aad97ed57df17ba3b5f036b72281669805ae89","observation_id":"576fdc2b-0765-4525-8011-7e8a1526554f","resolution":{"observed_at":"2026-08-15T14:26:30.592321Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.579975Z","title":"bigger is not better","venue":null,"work_id":"ceeee20d-e29f-4b04-a83a-7591bd8cfd2f","year":2003},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.307963Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:efe1afbd0394ea78c471200e43bccc0dd476c4187dc74f23758b736fae7387a1","observation_id":"df5eee8d-41a8-4148-af5a-fc3d1474875c","resolution":{"observed_at":"2026-08-15T14:26:30.582865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.571211Z","title":"output nothing","venue":null,"work_id":"7c32a0bf-4e87-4412-a71e-857f55c013fc","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.311964Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:26c6865bfa7106c6fe6e79d6513bbbfd11bc436a1a1f983fa2ae25cfa4021891","observation_id":"78a18ea2-7f34-42ba-a43b-921af3bd756e","resolution":{"observed_at":"2026-08-15T14:26:30.574374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.561741Z","title":"output nothing","venue":null,"work_id":"37f6779d-98be-4bf0-9586-bfdf053cb2f1","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.315204Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:f8ea4b05f67e1f0db6b4d21699e8b7d112d93da230caeb0b024bd3fb9617fce1","observation_id":"18ded130-f873-40c4-8e99-4087f7040915","resolution":{"observed_at":"2026-08-15T14:26:30.564336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.552704Z","title":"start with","venue":null,"work_id":"2788ce78-b19f-415f-b9e5-ba88c81a321e","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.318124Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:fd51db9c35f5db51ba189b0ffcc8c88bbaec605a1655e79c7faa8cee74e49222","observation_id":"925f9d06-2ed7-41eb-8066-53834c2396b5","resolution":{"observed_at":"2026-08-15T14:26:30.555841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.542417Z","title":"- Include every required keyword or phrase verbatim and exclude every forbidden keyword or phrase, respecting case sensitivity when specified","venue":null,"work_id":"1b9842c4-0877-4179-851e-b953de5b110c","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.320954Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:4132b62bd0b46d5fa6dc0deeb04cfaf80023dd65d86dacf22afaf34a90ae1b54","observation_id":"268d599d-6e3d-4035-a802-fcda101b167f","resolution":{"observed_at":"2026-08-15T14:26:30.546384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.529983Z","title":"- Do NOT define concepts, explain laws, or provide background information unless the instruction explicitly asks for an explanation","venue":null,"work_id":"8396b0f9-8939-44cb-96c7-dde99ce887a4","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.323656Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:d4820f901a61c0659289597a975ff47f4ae52a7eef822ff3eff026a4e7a10344","observation_id":"f7c23747-3600-44da-9621-56fe6f99841e","resolution":{"observed_at":"2026-08-15T14:26:30.533822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.516107Z","title":"- Do not relax or ignore any stated constraint; choose the interpretation that best satisfies all explicit requirements without adding new assumptions","venue":null,"work_id":"11d44d6b-b09f-41b7-9d0c-5d30a1311079","year":null},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.327205Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:89e4eff4a0ec0ce048736583df9d2f7a52ac7ca541a411e3761e304a27cf7f52","observation_id":"232318da-8970-4179-be3c-df5a6421f7a9","resolution":{"observed_at":"2026-08-15T14:26:30.521580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T14:26:30.501065Z","title":"no explanation","venue":null,"work_id":"04c81a82-3d14-435e-9baa-aa19f7b233c1","year":2025},"citing_paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:30.330510Z"},"links":{"citing_paper":"/paper/2608.10471"},"observation_digest":"sha256:c24e909a6c6f52756873d3ef433a4251a80d7bf4801524134ed26268f477349a","observation_id":"151b8418-0b20-4c2a-939c-5124391b4990","resolution":{"observed_at":"2026-08-15T14:26:30.505934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.10471","last_updated":"2026-08-11T04:35:05Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-17T08:44:43.078086Z","submitted_at":"2026-08-11T04:35:05Z","title":"RLMOpt: Adaptive Prompt Optimization via Recursive Language Models"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":0,"verified_fuzzy":18},"total_outbound_references":41},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2608.10471."}