{"as_of":"2026-08-15T17:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:10cf1c348bf8771afaa63235f5446094dd70a8f2b8a01cd829959c22151ad092","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T18:00:22.243698Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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":"2026-08-02T19:22:25.370012Z","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":"2026-05-20T19:08:53.951599Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.00728","snapshot_observed_at":"2026-08-02T19:22:25.370012Z","title":"Meta-prompt optimization for llm-based sequential decision making","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.02630","last_updated":"2026-05-29T15:37:29Z","snapshot_observed_at":"2026-08-02T19:22:22.341348Z","submitted_at":"2026-03-03T05:59:05Z","title":"MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-02T19:22:25.370012Z"},"links":{"cited_paper":"/paper/2502.00728","citing_paper":"/paper/2603.02630"},"observation_digest":"sha256:5051b0d58757928e2dfb6bed4bb80155cc0a270ce063dfd675893e7d61da9b2f","observation_id":"217ebc3a-46c6-4f14-ba92-3dc281c7eb16","resolution":{"observed_at":"2026-08-02T19:22:25.370012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"cited_work":{"arxiv_id":"2502.00728","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.00728","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"acl-long.607/","venue":null,"work_id":"39779d62-3794-4f54-aa9e-4070a66f7f87","year":2025},"citing_paper":{"arxiv_id":"2605.15768","last_updated":"2026-05-19T06:16:22Z","snapshot_observed_at":"2026-08-13T04:31:54.902839Z","submitted_at":"2026-05-15T09:25:15Z","title":"ALSO: Adversarial Online Strategy Optimization for Social Agents","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-20T19:08:46.636811Z"},"links":{"cited_paper":"/paper/2502.00728","citing_paper":"/paper/2605.15768"},"observation_digest":"sha256:5e80cc128b94ef85091c5ad79e74ea67090dcabe22a0a6a3935d9f572ab3c943","observation_id":"3f2cfcd6-14b5-451b-b840-9da92574f633","resolution":{"observed_at":"2026-05-20T19:08:53.953119Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.00728/citation-record","integrity":"/paper/2502.00728/integrity","json":"/paper/2502.00728/citation-record.json","paper":"/paper/2502.00728"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.16827","last_updated":"2024-08-02T17:59:31Z","snapshot_observed_at":"2026-08-15T10:00:03.235901Z","submitted_at":"2024-02-26T18:54:35Z","title":"A Survey on Data Selection for Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16827","snapshot_observed_at":"2026-08-09T18:00:22.119847Z","title":"M., Longpre, S., Lambert, N., Wang, X., Muennighoff, N., Hou, B., Pan, L., Jeong, H., Raffel, C., Chang, S., Hashimoto, T., and Wang, W","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.119847Z"},"links":{"cited_paper":"/paper/2402.16827","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:984b9c67e8fe4392a85650d05687d3bc9bf1df1171fec6a072d25f992a7429c7","observation_id":"af21dd5b-02d6-43f6-8c9d-181a57701e23","resolution":{"observed_at":"2026-08-09T18:00:22.119847Z","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":"2026-08-09T18:00:23.348836Z","title":"3.2, there are two major differences compared to the way in which our EXPO algorithm optimizes the task description and meta-instruction (Algo","venue":null,"work_id":"963f8c2e-96ae-47bc-9701-1827245b4ebd","year":2024},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.224840Z"},"links":{"citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:7fb911dbd612b2316e97d94082d992d1d8180c0736dca7d688b06db32a85c4ef","observation_id":"462f690f-de3f-43a1-971b-d5307930b9d7","resolution":{"observed_at":"2026-08-09T18:00:23.353314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.03428","last_updated":"2024-01-07T09:08:24Z","snapshot_observed_at":"2026-08-13T04:47:51.274788Z","submitted_at":"2024-01-07T09:08:24Z","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.03428","snapshot_observed_at":"2026-08-09T18:00:22.135311Z","title":"Ex- ploring large language model based intelligent agents: Definitions, methods, and prospects","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.135311Z"},"links":{"cited_paper":"/paper/2401.03428","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:3e169af447063757ceec759e474e1cb1d11104c1f324610ad068a2d9c1368930","observation_id":"9359591a-19dd-43a1-b28f-42ead42bd4af","resolution":{"observed_at":"2026-08-09T18:00:22.135311Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.06826","last_updated":"2024-03-11T15:43:14Z","snapshot_observed_at":"2026-08-13T08:35:32.401211Z","submitted_at":"2024-03-11T15:43:14Z","title":"In-context Exploration-Exploitation for Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.06826","snapshot_observed_at":"2026-08-09T18:00:22.140133Z","title":"In-context exploration- exploitation for reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.140133Z"},"links":{"cited_paper":"/paper/2403.06826","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:ac4d41ec3b3f1a7afd01b02df29a270acef89ab9e73de1e345d3226f6b77a731","observation_id":"cd1a4c34-747c-4588-85a7-88626223d23c","resolution":{"observed_at":"2026-08-09T18:00:22.140133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.07900","last_updated":"2024-01-30T18:26:03Z","snapshot_observed_at":"2026-08-14T02:35:53.220024Z","submitted_at":"2023-09-14T17:48:34Z","title":"Ambiguity-Aware In-Context Learning with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.07900","snapshot_observed_at":"2026-08-09T18:00:22.150366Z","title":"Ambiguity-aware in-context learning with large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.150366Z"},"links":{"cited_paper":"/paper/2309.07900","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:559f2afe1fa413a4513ef01649e512bdcffe992ba78697cdb6507998d6fe41ef","observation_id":"654bebc2-e3da-48c5-a748-d3d4e50ee02e","resolution":{"observed_at":"2026-08-09T18:00:22.150366Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10504","last_updated":"2025-05-19T06:17:42Z","snapshot_observed_at":"2026-08-13T14:36:00.514769Z","submitted_at":"2024-06-15T04:54:26Z","title":"Task Facet Learning: A Structured Approach to Prompt Optimization","version":2},"cited_work":{"arxiv_id":"2406.10504","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.10504","snapshot_observed_at":"2026-08-09T18:00:23.175985Z","title":"Task Facet Learning: A Structured Approach to Prompt Optimization","venue":"cs.AI","work_id":"e1af5708-c9e3-40a6-8e0c-34f5681300b1","year":2024},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.154795Z"},"links":{"cited_paper":"/paper/2406.10504","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:20741020ba42c1a620d8b6dcdc3c70d747d53cbbff5bb96055c812f453ba0309","observation_id":"4eceadef-b432-4c94-af6d-1a2370874ca4","resolution":{"observed_at":"2026-08-09T18:00:23.182415Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T18:00:23.334730Z","title":null,"venue":null,"work_id":"0050bf8f-f503-4d29-a41d-2a2e1a95c3e9","year":2024},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.229519Z"},"links":{"citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:507b2eed6eb2d710ad7942d1d4661886c9959ee4e7af8004e76b3e7151341078","observation_id":"c285bda6-aaf2-44ec-b807-bf17045ea1ae","resolution":{"observed_at":"2026-08-09T18:00:23.339018Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.15371","last_updated":"2024-10-28T19:55:46Z","snapshot_observed_at":"2026-08-13T08:34:54.250401Z","submitted_at":"2024-03-22T17:50:43Z","title":"Can large language models explore in-context?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.15371","snapshot_observed_at":"2026-08-09T18:00:22.163766Z","title":"J., Zhang, C., and Slivkins, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.163766Z"},"links":{"cited_paper":"/paper/2403.15371","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:e0b8500b5b415c44056cdbabee8703e5cb3d997190c17e83ef631092f9065823","observation_id":"ff14cd29-9328-44eb-87b2-62ad0667ac1a","resolution":{"observed_at":"2026-08-09T18:00:22.163766Z","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":"2026-08-09T18:00:23.320606Z","title":"The texts we have modified are highlighted in red","venue":null,"work_id":"31cf7bda-01c3-40f5-9b08-c5bb2d928648","year":2024},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.233951Z"},"links":{"citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:fdc6c9a4d316b2d338134042bbd8144bfb7ff7698d132d37aede44278e64eb8a","observation_id":"fb9eb3b4-3c5e-4249-ae6f-3d199b64e5bb","resolution":{"observed_at":"2026-08-09T18:00:23.324953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03688","last_updated":"2025-10-04T03:54:18Z","snapshot_observed_at":"2026-08-13T14:09:17.964744Z","submitted_at":"2023-08-07T16:08:11Z","title":"AgentBench: Evaluating LLMs as Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03688","snapshot_observed_at":"2026-08-09T18:00:22.173010Z","title":"Agentbench: Evalu- ating llms as agents","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.173010Z"},"links":{"cited_paper":"/paper/2308.03688","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:c69722e0b0100c8619b97953120b0d083387d436edabdeecb3ade28d978ecfbd","observation_id":"9b2461c9-9827-4a92-aa5a-38452fb26acb","resolution":{"observed_at":"2026-08-09T18:00:22.173010Z","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":"2026-08-09T18:00:22.177654Z","title":"P., Xie, Q., and Nowak, R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.177654Z"},"links":{"citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:b9c5ac0bf0a36f6712f5f475dae97d2b69447d0f7518a1a953ac5bfd9be6add3","observation_id":"6cc5a2ef-5aef-4f63-92dd-903ee2cf5cfc","resolution":{"observed_at":"2026-08-09T18:00:22.177654Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11042","last_updated":"2023-06-05T17:49:58Z","snapshot_observed_at":"2026-08-13T14:19:51.901049Z","submitted_at":"2023-02-21T22:47:45Z","title":"In-context Example Selection with Influences","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11042","snapshot_observed_at":"2026-08-09T18:00:22.181850Z","title":"and Wong, E","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.181850Z"},"links":{"cited_paper":"/paper/2302.11042","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:f95441c7262796e65926b2213d9f7387975996cde65103dfd280ed823900a28d","observation_id":"2fb9a376-1f31-46f4-8570-bf2bd42546a8","resolution":{"observed_at":"2026-08-09T18:00:22.181850Z","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":"2026-08-12T23:40:55.018358Z","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":"2026-08-09T18:00:22.186149Z","title":"J., Purtell, J., Broman, D., Potts, C., Zaharia, M., and Khattab, O","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.186149Z"},"links":{"cited_paper":"/paper/2406.11695","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:b68ee29767e755e539c7d1ad83f8de9c78075e40188424a2b1cd3e89488154de","observation_id":"5f5dde57-31f6-4e41-bdf7-e4b1d6d36c36","resolution":{"observed_at":"2026-08-09T18:00:22.186149Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.07820","last_updated":"2025-06-03T09:59:18Z","snapshot_observed_at":"2026-08-14T06:52:51.902022Z","submitted_at":"2024-12-10T14:42:51Z","title":"Hyperband-based Bayesian Optimization for Black-box Prompt Selection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.07820","snapshot_observed_at":"2026-08-09T18:00:22.190454Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.190454Z"},"links":{"cited_paper":"/paper/2412.07820","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:3aac8afd24c5f83e2ff9b7b26032b9e54d21477fe613c75c8a9e5eff36f2b6b2","observation_id":"784bf2ce-e540-4eed-957f-ceb6b1fe9cba","resolution":{"observed_at":"2026-08-09T18:00:22.190454Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09723","last_updated":"2024-05-30T19:40:21Z","snapshot_observed_at":"2026-08-13T04:18:36.339733Z","submitted_at":"2024-02-15T05:31:13Z","title":"Efficient Prompt Optimization Through the Lens of Best Arm Identification","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09723","snapshot_observed_at":"2026-08-09T18:00:22.194703Z","title":"Best arm identifi- cation for prompt learning under a limited budget","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.194703Z"},"links":{"cited_paper":"/paper/2402.09723","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:afb93be182282c8c3e6829b8ea415ee43a18460a9ca1f30e47923d9f7c576eac","observation_id":"00c6afe2-3a42-4875-a0c0-26ca0322022e","resolution":{"observed_at":"2026-08-09T18:00:22.194703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.13861","last_updated":"2025-02-24T20:47:35Z","snapshot_observed_at":"2026-08-13T00:01:57.584352Z","submitted_at":"2024-05-22T17:38:16Z","title":"Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.13861","snapshot_observed_at":"2026-08-09T18:00:22.203334Z","title":"Trans- formers learn temporal difference methods for in-context reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.203334Z"},"links":{"cited_paper":"/paper/2405.13861","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:f151d98b96058d385f80e6abc1261b98fe835b993206798dd5dc8706fac511dc","observation_id":"c0a90b81-627e-42c7-b363-c5761d2ae73b","resolution":{"observed_at":"2026-08-09T18:00:22.203334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.07864","last_updated":"2023-09-19T08:29:18Z","snapshot_observed_at":"2026-08-09T18:54:02.679174Z","submitted_at":"2023-09-14T17:12:03Z","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.07864","snapshot_observed_at":"2026-08-09T18:00:22.207860Z","title":"The rise and potential of large language model based agents: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.207860Z"},"links":{"cited_paper":"/paper/2309.07864","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:4b13d26447fd5c3121d270f254d19839dec6c9adbd8ca51f92f32ad2f0613666","observation_id":"ee64b18d-af2c-4530-8083-d969a5375018","resolution":{"observed_at":"2026-08-09T18:00:22.207860Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04151","last_updated":"2024-06-06T15:15:41Z","snapshot_observed_at":"2026-08-12T23:48:41.258216Z","submitted_at":"2024-06-06T15:15:41Z","title":"AgentGym: Evolving Large Language Model-based Agents across Diverse Environments","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04151","snapshot_observed_at":"2026-08-09T18:00:22.211991Z","title":"Agentgym: Evolving large language model-based agents across di- verse environments","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.211991Z"},"links":{"cited_paper":"/paper/2406.04151","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:8879a9860193bd7ee3c6439d34dd0a407b377331cce340d4c76239b4a0c5b7d6","observation_id":"eed582d5-f821-472c-ad03-5c6ff4c80787","resolution":{"observed_at":"2026-08-09T18:00:22.211991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01887","last_updated":"2025-06-09T14:56:27Z","snapshot_observed_at":"2026-08-12T23:30:48.488727Z","submitted_at":"2024-07-02T02:18:14Z","title":"Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01887","snapshot_observed_at":"2026-08-09T18:00:22.216200Z","title":"Beyond numeric awards: In-context dueling bandits with llm agents.arXiv preprint arXiv:2407.01887,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.216200Z"},"links":{"cited_paper":"/paper/2407.01887","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:f01147b8868593d4cf87ae9b909eb68358f3535e66688b9efae44ef3c5bc506d","observation_id":"da3d5e68-d7d4-4ad2-89cb-67ae10560aa3","resolution":{"observed_at":"2026-08-09T18:00:22.216200Z","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":"2026-08-09T18:00:23.363844Z","title":"Unlock- ing black-box prompt tuning efficiency via zeroth-order optimization","venue":null,"work_id":"e9077898-5c76-4b69-b785-188d94425b4e","year":2024},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.220502Z"},"links":{"citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:e8968817164e38eb89cad1254e71d6767a2c7681dff90b88747886f14cf3c778","observation_id":"7242a53b-f5cf-48fb-99d8-336053bdde34","resolution":{"observed_at":"2026-08-09T18:00:23.368742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T18:00:23.306199Z","title":"The different components in the prompt are explained in detail in App","venue":null,"work_id":"4fb42d88-01c4-445f-87b1-5d8557e9c90a","year":2024},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.238843Z"},"links":{"citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:910d439df993fa5bddb0053ff310f7c8ee4dd900375c37bc7821abf9a1ec8f54","observation_id":"7b5e3e55-8000-4d4f-8427-1f81d90481f0","resolution":{"observed_at":"2026-08-09T18:00:23.310890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T18:00:23.291718Z","title":null,"venue":null,"work_id":"d8514896-e6c8-4b68-ac93-2b41d4a72333","year":2024},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.243698Z"},"links":{"citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:779f9d3105110a142e40b322b437710ba3d13e06d95bd04a8aeeabbdce3cdb67","observation_id":"754201a6-4ff8-495f-818b-5b3206d925dd","resolution":{"observed_at":"2026-08-09T18:00:23.296169Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08189","last_updated":"2024-06-10T13:46:22Z","snapshot_observed_at":"2026-08-13T04:42:13.955562Z","submitted_at":"2024-01-16T08:04:50Z","title":"PRewrite: Prompt Rewriting with Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08189","snapshot_observed_at":"2026-08-09T18:00:22.159425Z","title":"A., Zhang, M., Mei, Q., and Ben- dersky, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":1995,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.159425Z"},"links":{"cited_paper":"/paper/2401.08189","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:03f3248fd4de4fafeca444330a4cf1fd03e439f5b841b1ab7341ed8dd510d5b0","observation_id":"80a28cc4-8303-444d-b549-dfc0310ba3c0","resolution":{"observed_at":"2026-08-09T18:00:22.159425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15708","last_updated":"2024-11-06T22:07:17Z","snapshot_observed_at":"2026-08-15T00:01:39.580084Z","submitted_at":"2024-06-22T02:07:10Z","title":"Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15708","snapshot_observed_at":"2026-08-09T18:00:22.199016Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.199016Z"},"links":{"cited_paper":"/paper/2406.15708","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:97b94634a03eed6ab335e2684c2dfffc453899dd34495e2e07bfb7f9f1644c62","observation_id":"352d58f4-4954-4d01-9453-d9f5a2d16eba","resolution":{"observed_at":"2026-08-09T18:00:22.199016Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17346","last_updated":"2024-05-27T16:49:29Z","snapshot_observed_at":"2026-08-12T23:56:56.305103Z","submitted_at":"2024-05-27T16:49:29Z","title":"Prompt Optimization with Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17346","snapshot_observed_at":"2026-08-09T18:00:22.168152Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.168152Z"},"links":{"cited_paper":"/paper/2405.17346","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:be56a0edff638e23f07f29e95f44c5b2e531587d1b3593bc7a150d7209549e90","observation_id":"a0f5423e-9fe3-47f0-8768-6d997c86d5ad","resolution":{"observed_at":"2026-08-09T18:00:22.168152Z","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":"2026-08-09T18:00:22.145044Z","title":"Promptbreeder: Self-referential self- improvement via prompt evolution","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.145044Z"},"links":{"cited_paper":"/paper/2309.16797","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:82c3b37a42e7b1ba114cef79ed73790c5801068d32910bd0b9e07b53548d9d4b","observation_id":"2d270bcf-542e-4ff5-92df-397c10ffe41f","resolution":{"observed_at":"2026-08-09T18:00:22.145044Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.12125","last_updated":"2025-06-15T04:49:56Z","snapshot_observed_at":"2026-08-12T23:40:35.154262Z","submitted_at":"2024-06-17T22:13:22Z","title":"Efficient Sequential Decision Making with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.12125","snapshot_observed_at":"2026-08-09T18:00:22.125335Z","title":"Efficient sequential deci- sion making with large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.125335Z"},"links":{"cited_paper":"/paper/2406.12125","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:9224db9dd48cebceaa97a15ec50d754c1cdeb59a760528bb2f72cb0d7e971eda","observation_id":"b52bdfb2-11c0-46d3-b3f9-7803b343a3a7","resolution":{"observed_at":"2026-08-09T18:00:22.125335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03082","last_updated":"2023-08-08T17:33:54Z","snapshot_observed_at":"2026-08-14T07:14:20.129195Z","submitted_at":"2023-06-05T17:55:22Z","title":"InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.03082","snapshot_observed_at":"2026-08-09T18:00:22.130184Z","title":"InstructZero: Efficient instruction optimization for black- box large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-09T18:00:22.130184Z"},"links":{"cited_paper":"/paper/2306.03082","citing_paper":"/paper/2502.00728"},"observation_digest":"sha256:e99066e4ed8e6fad6cf7fa2402900bb4d507da5c9276d1a94b1c3dd9a31d573f","observation_id":"75df76e5-3748-4981-8f55-a211fb62f66d","resolution":{"observed_at":"2026-08-09T18:00:22.130184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.00728","last_updated":"2025-02-02T09:22:39Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T02:20:08.368283Z","submitted_at":"2025-02-02T09:22:39Z","title":"Meta-Prompt Optimization for LLM-Based Sequential Decision Making"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":1,"verified_fuzzy":4},"total_outbound_references":28},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 2 inbound Pith citation observations for arXiv:2502.00728."}