{"as_of":"2026-08-13T15:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e60d16286861523d182e67bc5d90b8ad3d4b8f4bf9f039157564aa5bef23a72c","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T21:56:59.041953Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:14:08.203086Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T15:14:16.303537Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"cited_work":{"arxiv_id":"2501.03508","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.03508","snapshot_observed_at":"2026-08-07T15:14:16.303537Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","venue":"cs.CL","work_id":"06f9f983-e1da-420f-9f38-db2e3c6fdfaa","year":2025},"citing_paper":{"arxiv_id":"2505.15741","last_updated":"2025-05-21T16:48:28Z","snapshot_observed_at":"2026-08-13T13:35:00.317948Z","submitted_at":"2025-05-21T16:48:28Z","title":"Evolutionary Computation and Large Language Models: A Survey of Methods, Synergies, and Applications","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T15:14:08.203086Z"},"links":{"cited_paper":"/paper/2501.03508","citing_paper":"/paper/2505.15741"},"observation_digest":"sha256:542245a607e0d28aadffa5f253e65eb1df53f9f97d4c300bb3af45c75a10c772","observation_id":"f246afcf-f705-442f-af5e-dd6c204f4df2","resolution":{"observed_at":"2026-08-07T15:14:16.309596Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.03508/citation-record","integrity":"/paper/2501.03508/integrity","json":"/paper/2501.03508/citation-record.json","paper":"/paper/2501.03508"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:56:59.337064Z","title":"Normalized (pointwise) mutual infor- mation in collocation extraction","venue":null,"work_id":"7b83dc2e-88bb-4616-bd84-930a1d6c12a9","year":2009},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.951237Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:92bfb3e93e491f5cfbee70766fc1551264a5c4d478c006ff32e925c292a199ea","observation_id":"91d8f365-25ac-4ec6-83f4-2ff757b765d4","resolution":{"observed_at":"2026-08-10T21:56:59.339960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.330843Z","title":"Language models are few-shot learners","venue":null,"work_id":"230bd14d-8f5a-404d-836e-5b69c3d6b5ed","year":1901},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.954653Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:2c8b2cc98d060e06a55cc43bf8f74a2ca017fb66744ad9b669185b7a67e954b2","observation_id":"862e55c1-fdad-4045-9f5d-2bc99b998f5e","resolution":{"observed_at":"2026-08-10T21:56:59.333185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.324627Z","title":"Instructzero: Efficient instruc- tion optimization for black-box large language mod- els","venue":null,"work_id":"7fa76d84-362e-41dd-a0ae-a2e3dc50404c","year":2024},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.957596Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:679e953b1c5d9199be394c3a2b2f5deb5ccf085e797242b52152447280b03f67","observation_id":"ef201629-03ba-490e-aa47-af7dfa7ddbc7","resolution":{"observed_at":"2026-08-10T21:56:59.327008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.318439Z","title":"Bayesian ideas and discrete event sim- ulation: why, what and how","venue":null,"work_id":"eb5522f7-aeca-4744-a322-a78a34cdd9a8","year":2006},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.960426Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:16bc2f879a434e93be65b6c9c1b2f069091c2cad1b649a55c17cfff6bcd5f4ed","observation_id":"dbfd15a3-7013-40de-9e47-ef6aaa1957fb","resolution":{"observed_at":"2026-08-10T21:56:59.320852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.312234Z","title":"Sequential sampling to myopically maximize the expected value of information","venue":null,"work_id":"736d569a-be36-4ef7-b0ec-16b8d78412ee","year":2010},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.963361Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:59e74ffacdbb6595ec08adde2737f7fd23e2f9d6dd9febf96fdac6e916cc2674","observation_id":"7ba5d291-01fd-4900-9276-43f2e614376d","resolution":{"observed_at":"2026-08-10T21:56:59.314576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.305711Z","title":"Optimal information blending with measurements in the l 2 sphere","venue":null,"work_id":"5815a0b9-e38d-4e65-b79c-6e8bafb6e7a2","year":2015},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.966262Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:04c2825f3e1b32c41022871dd1dfbf2695481048609c0a805a75a43e604fb781","observation_id":"1d83f6f3-8443-4b3e-9ef0-da9c4b9669f3","resolution":{"observed_at":"2026-08-10T21:56:59.308217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.04205","last_updated":"2024-04-18T23:49:56Z","snapshot_observed_at":"2026-08-13T05:30:22.609300Z","submitted_at":"2023-11-07T18:43:34Z","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.04205","snapshot_observed_at":"2026-08-10T21:56:58.969175Z","title":"Rephrase and respond: Let large language models ask better questions for themselves","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.969175Z"},"links":{"cited_paper":"/paper/2311.04205","citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:54f2ae64119e6ae453251113f66830dd87c629a707aea6c179d8a65db56538ae","observation_id":"098f41bb-72db-401e-aa05-f5ca817f90c2","resolution":{"observed_at":"2026-08-10T21:56:58.969175Z","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":"2026-08-10T21:56:59.299252Z","title":"Promptbreeder: Self-referential self-improvement via prompt evolution","venue":null,"work_id":"177d7a3c-fb41-4943-a5fe-10161bac4927","year":2024},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.971710Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:ea2dfe0894133062e8259fe4ff949814276c1225391da01684874fb7a7c54237","observation_id":"5f629928-a52c-4d58-a11a-48b7d21cd1fe","resolution":{"observed_at":"2026-08-10T21:56:59.301767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.293261Z","title":"The knowledge-gradient policy for correlated normal be- liefs","venue":null,"work_id":"1d63bb9f-4222-424c-beef-b97da2198987","year":2009},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.973834Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:0cf755f84b74df2565fb671955792b77d1af9f7c4494e66bba1f0ee5d65de020","observation_id":"b07ce3e7-948f-4c62-a0b7-cf9d4665c525","resolution":{"observed_at":"2026-08-10T21:56:59.295485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.287088Z","title":"Consistency of sequential bayesian sampling policies","venue":null,"work_id":"bfacedda-8921-4b23-85b8-d037f4319242","year":2011},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.975870Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:41789fa741e20a86310bfd72a5777d7a7b3505f047096ce56a1b1a12424cc90b","observation_id":"a360d647-9503-4709-8948-4046d24caeef","resolution":{"observed_at":"2026-08-10T21:56:59.289251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.280593Z","title":"A knowledge-gradient policy for sequential information collection","venue":null,"work_id":"2a73e52e-c076-4268-953b-c7fae07dfcb6","year":2008},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.977886Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:b00861d7d8a06c2d9583f5b01226d607e4e186d1871a9041063a880ca2b3bcb5","observation_id":"fa9b26a8-1eba-4237-aa71-d5b065e6cc84","resolution":{"observed_at":"2026-08-10T21:56:59.283413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.272814Z","title":"Connecting large language models with evolu- tionary algorithms yields powerful prompt optimizers","venue":null,"work_id":"6cae9bdc-374b-4dd4-85a9-748d567d7c95","year":2024},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.980049Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:3b7c51983d5fa143f922cd7f96536dfae0121c58b3ea282da492492fe1ab7add","observation_id":"f829ea99-75d0-49da-a9f0-4ed0d7a666da","resolution":{"observed_at":"2026-08-10T21:56:59.275837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.266306Z","title":"Bayesian look ahead one-stage sampling allocations for selection of the best population","venue":null,"work_id":"c359562f-a882-44ba-a33b-9e39c0ebef7e","year":1996},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.982033Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:365473236cc889c4bc2a8066fd35b6d101452e3a745eea76f232423d3dbf6c28","observation_id":"f27561b7-f6ed-466f-b43f-6fa72716babc","resolution":{"observed_at":"2026-08-10T21:56:59.268561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.260272Z","title":"Op- timal learning in linear regression with combinatorial feature selection","venue":null,"work_id":"49d419cc-39af-45d5-aa3b-f9d8c2e2085f","year":2016},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.983992Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:dc12c83539c8efda8fde0dd1b8de365e105e3070a8b3cabea94be73353df3941","observation_id":"af95272d-cedf-4c00-accd-b430c0f9f910","resolution":{"observed_at":"2026-08-10T21:56:59.262578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.10782","last_updated":"2022-05-22T09:22:37Z","snapshot_observed_at":"2026-08-09T09:06:16.150258Z","submitted_at":"2022-05-22T09:22:37Z","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.10782","snapshot_observed_at":"2026-08-10T21:56:58.985933Z","title":"Instruction induction: From few examples to natural language task descriptions","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.985933Z"},"links":{"cited_paper":"/paper/2205.10782","citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:870b1caa717aa182b5f80a02da03b3c6526b49276641f116e1fd838eb10f254a","observation_id":"f6fb3c21-8c3d-4131-91c2-b3da15f3f714","resolution":{"observed_at":"2026-08-10T21:56:58.985933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14449","last_updated":"2025-05-20T02:36:54Z","snapshot_observed_at":"2026-08-12T23:38:14.287347Z","submitted_at":"2024-06-20T16:11:45Z","title":"APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14449","snapshot_observed_at":"2026-08-10T21:56:58.988324Z","title":"Apeer: Automatic prompt engineering en- hances large language model reranking","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.988324Z"},"links":{"cited_paper":"/paper/2406.14449","citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:86580e1e5a90aff7646a749b47563925b6321721f87fe0d38185310de514d27e","observation_id":"62212b30-e288-4640-bb37-096312f77534","resolution":{"observed_at":"2026-08-10T21:56:58.988324Z","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":"2026-08-10T21:56:59.254060Z","title":"Better zero-shot reasoning with role- play prompting","venue":null,"work_id":"c497dc0b-964f-4d89-b41a-50529d2cbc7f","year":2024},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.990712Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:9ef48cc1b8c2e2bba042b4cdc09c62ff96624d2929ea0281ef0282fc6b8c12ac","observation_id":"5b683cb7-9018-4bf6-8893-9a6ea531fac9","resolution":{"observed_at":"2026-08-10T21:56:59.256369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.11760","last_updated":"2023-11-12T12:35:41Z","snapshot_observed_at":"2026-08-13T10:55:47.155817Z","submitted_at":"2023-07-14T00:57:12Z","title":"Large Language Models Understand and Can be Enhanced by Emotional Stimuli","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.11760","snapshot_observed_at":"2026-08-10T21:56:58.992852Z","title":"Large language models understand and can be enhanced by emotional stimuli","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.992852Z"},"links":{"cited_paper":"/paper/2307.11760","citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:5fae2c87367a7f86ad8b9132a8c0ae90d8f83b8e9b5541133faaa6d25c0c1752","observation_id":"06e4d18d-dc61-4c6c-8215-71eccb3aabf9","resolution":{"observed_at":"2026-08-10T21:56:58.992852Z","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":"2026-08-10T21:56:59.247476Z","title":"Use your INSTINCT: IN- STruction optimization for LLMs using neural bandits 11 coupled with transformers","venue":null,"work_id":"80359401-080c-4d68-a174-220c88f1caad","year":2024},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.995192Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:6c286d903b60210d45eef56808fbb13032f5ac4ac16e1a55f681807ba08bd4c0","observation_id":"d1985576-0516-495c-8e00-8d23ab611cd4","resolution":{"observed_at":"2026-08-10T21:56:59.250118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.240864Z","title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","venue":null,"work_id":"3c7bf0ff-a144-4ecc-8a35-88ca07b10044","year":2023},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.997259Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:4e4eccd403cc5266e0217ccecfd840da20f37625c962b09421a7c90df3b37c16","observation_id":"cbbfcfb2-0983-47d0-949a-f94fe417edc0","resolution":{"observed_at":"2026-08-10T21:56:59.243285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.234563Z","title":"Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity","venue":null,"work_id":"4856aaff-fb5b-484c-953d-f3e6ef0457d6","year":2022},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:58.999447Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:d8a5ce9a8d67998cb13b42d2c5225a4169059d5d6250ec3939530fecfa4ee8d9","observation_id":"e9228df1-5a75-44f2-b0f0-040cccb1bea2","resolution":{"observed_at":"2026-08-10T21:56:59.236973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14201","last_updated":"2023-11-03T11:59:45Z","snapshot_observed_at":"2026-08-13T05:43:54.008878Z","submitted_at":"2023-10-22T06:34:09Z","title":"Prompt Engineering Through the Lens of Optimal Control","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14201","snapshot_observed_at":"2026-08-10T21:56:59.001475Z","title":"Prompt engineering through the lens of optimal control","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.001475Z"},"links":{"cited_paper":"/paper/2310.14201","citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:0c8c8e45afa5f7ab0774283b6a278ea8389d93f52105e20b0cee389c254e6766","observation_id":"34dd0c31-5ff7-4150-a5a7-7c9132dea439","resolution":{"observed_at":"2026-08-10T21:56:59.001475Z","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":"2026-08-10T21:56:59.228328Z","title":"Rlprompt: Optimiz- ing discrete text prompts with reinforcement learning","venue":null,"work_id":"a3bda34a-56f3-4e58-a793-2a2ef0b5673e","year":2022},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.003973Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:de882de80f4b119ce672592f71d3315b1555e0394b241313bdc58b5c6f18c8ff","observation_id":"77bfbd05-7f11-445a-baa8-61e4cc3acc69","resolution":{"observed_at":"2026-08-10T21:56:59.230735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.222116Z","title":"Sequential learning in designing marketing campaigns for market entry","venue":null,"work_id":"1e1225fc-142a-4e46-a9f1-61613606f0da","year":2020},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.006042Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:b91e99f49c44ecd4408b6a05588e0a7848057af9c5fc767ef80b16043b31f8f7","observation_id":"ba20e96d-2dcc-4b92-865f-e2259dfdb451","resolution":{"observed_at":"2026-08-10T21:56:59.224568Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.215336Z","title":"Reinforcement Learning and Stochas- tic Optimization: A Unified Framework for Sequential Decisions","venue":null,"work_id":"bce1b110-9bf2-438f-b449-b92e57486266","year":2022},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.008085Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:6388da29ee3fdef6d0add589ccd0350668c42540bae174623bfed132856e7758","observation_id":"e06c41a3-c73b-4463-8521-2e7ce05f55cc","resolution":{"observed_at":"2026-08-10T21:56:59.218172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.207829Z","title":"Optimal learning, volume 841","venue":null,"work_id":"46fefd5f-3fd1-4039-b75e-6ded1627e22c","year":2012},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.010109Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:715488edc507a3775f173965588e2f4d572e16c5f4d31de0b11fdae8bf886b92","observation_id":"cd6fab6d-6325-4764-80e3-39c741f77d2f","resolution":{"observed_at":"2026-08-10T21:56:59.210546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.07281","last_updated":"2023-04-26T19:20:57Z","snapshot_observed_at":"2026-08-09T17:47:25.069526Z","submitted_at":"2022-03-14T16:54:46Z","title":"GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.07281","snapshot_observed_at":"2026-08-10T21:56:59.012110Z","title":"Grips: Gradient-free, edit-based instruction search for prompting large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.012110Z"},"links":{"cited_paper":"/paper/2203.07281","citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:ab4e21a1a52d09a9dbfb1eeb6904111886e3ab8b7df1b6183c36a3b017f541f8","observation_id":"43263a24-ff46-4e41-a922-05fe1be2f1da","resolution":{"observed_at":"2026-08-10T21:56:59.012110Z","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":"2026-08-10T21:56:59.200083Z","title":"Automatic prompt op- timization with ”gradient descent” and beam search","venue":null,"work_id":"5c3eb8bf-2bf9-4feb-84a2-8dc4a23e8d4d","year":2023},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.014476Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:133932fdf062cfa50bcb002addbfb3ebd969384a66069859fd1a385334a64ea7","observation_id":"189f5e9c-d1f0-4a2d-b60a-5291d7f526a2","resolution":{"observed_at":"2026-08-10T21:56:59.202959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.192998Z","title":"Markov decision processes: dis- crete stochastic dynamic programming","venue":null,"work_id":"2233e621-41f7-4726-a7a6-8529cecaae2b","year":2014},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.016865Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:98d26996e9c96f062bb448dcffddbd8b01b5a14abcbb5889fb6859fc6075602c","observation_id":"86943dd7-7bbb-49b0-8eb3-4b07d162f45f","resolution":{"observed_at":"2026-08-10T21:56:59.195476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.186430Z","title":"Language mod- els are unsupervised multitask learners","venue":null,"work_id":"6c38d67a-b481-482f-b7c4-396f2eddf35e","year":2019},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.018757Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:0ea1966e050a6c3c3bc2714258eebd987f6bb92308e70e31e6fbe970fa3da118","observation_id":"50ccc1f6-6101-440e-84b2-c9c276e4249e","resolution":{"observed_at":"2026-08-10T21:56:59.188842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07927","last_updated":"2025-03-16T06:23:34Z","snapshot_observed_at":"2026-08-05T17:55:26.008016Z","submitted_at":"2024-02-05T19:49:13Z","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07927","snapshot_observed_at":"2026-08-10T21:56:59.020953Z","title":"A sys- tematic survey of prompt engineering in large language models: Techniques and applications","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.020953Z"},"links":{"cited_paper":"/paper/2402.07927","citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:4f3569cce0817835dd4d1382bbb3798f6d9c684d926f235f504a7e88667a3062","observation_id":"60e5f92d-0b15-4022-8df0-8f15fa76c40d","resolution":{"observed_at":"2026-08-10T21:56:59.020953Z","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":"2026-08-10T21:56:59.179238Z","title":"Quantifying language models’ sensitivity to spu- rious features in prompt design or: How i learned to start worrying about prompt formatting","venue":null,"work_id":"d01a1dcf-063b-4182-937c-f99e48ca3714","year":2024},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.023599Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:5d18c96d4cac99475c1c7042413611e7d91e64f02b1f88f307313643196ea63e","observation_id":"215c0e6f-b769-4c85-863d-4ea2280ec94d","resolution":{"observed_at":"2026-08-10T21:56:59.181966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-10T21:56:59.026152Z","title":"Best arm identification for prompt learning under a lim- ited budget","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.026152Z"},"links":{"cited_paper":"/paper/2402.09723","citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:22dc1f4e1dde17c5ab511943a035bf395f1c5c170e587fd3e95b31e04144bcba","observation_id":"b5a37a9c-27ba-4c0f-a295-cf2efd6c3ee9","resolution":{"observed_at":"2026-08-10T21:56:59.026152Z","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":"2026-08-10T21:56:59.171681Z","title":"Toward human readable prompt tuning: Kubrick’s the shining is a good movie, and a good prompt too? In The 2023 Conference on Empirical Methods in Natural Language Processing, 2023","venue":null,"work_id":"e42b52ad-f7c5-4771-95cf-320fc2b490af","year":2023},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.028925Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:29bf360157a3710a1d6954f926caa03ba3296a76eeb94997e83162d3bef06c98","observation_id":"790e5a9f-22c5-4599-8cbf-6daceda40e07","resolution":{"observed_at":"2026-08-10T21:56:59.174598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.15980","last_updated":"2020-11-07T05:33:35Z","snapshot_observed_at":"2026-08-05T14:17:34.026911Z","submitted_at":"2020-10-29T22:54:00Z","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.15980","snapshot_observed_at":"2026-08-10T21:56:59.031520Z","title":"Autoprompt: Eliciting knowledge from language models with automatically generated prompts","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.031520Z"},"links":{"cited_paper":"/paper/2010.15980","citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:b9b5dc53137d6f6564ce340dcb33ba05b2d812952c293bac8b32b70c259b4105","observation_id":"c38e902d-f9b7-4fe0-b7e9-059f82a79338","resolution":{"observed_at":"2026-08-10T21:56:59.031520Z","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":"2026-08-10T21:56:59.164268Z","title":"Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery","venue":null,"work_id":"249284dd-d441-4308-b1d0-1cbe3fc0be78","year":2024},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.034398Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:82e4591d464e2f697894060135a102601c862d79250251fc0c0ab67273c06b17","observation_id":"7e2e11fa-4ac8-48e1-a79f-c507a75362b3","resolution":{"observed_at":"2026-08-10T21:56:59.167145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.157567Z","title":"Large language models are diverse role- players for summarization evaluation","venue":null,"work_id":"80122d03-d711-4b86-98f3-ade5b64e14bf","year":2023},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.037019Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:085ec80ab25d061c1a1087b42fecbd3a7d52ab11cbeb91974dfb5ddd2347a6ea","observation_id":"df378670-86d8-4c1d-b488-0881e3716239","resolution":{"observed_at":"2026-08-10T21:56:59.159960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.150647Z","title":"Calibrate before use: Improving few- shot performance of language models","venue":null,"work_id":"92c369d3-57a2-46b0-941b-5b0148b83c03","year":2021},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.039548Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:0b65710e971c70d2f8a87f82b50a71a58cefcde9a50696ceecaabc8bc9562851","observation_id":"847dd0e3-e9de-44b9-8ade-4eaca59c4392","resolution":{"observed_at":"2026-08-10T21:56:59.153131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-10T21:56:59.141784Z","title":"Large language models are human-level prompt engi- neers","venue":null,"work_id":"0c4b9552-0932-4320-8a93-4a930d73c360","year":2023},"citing_paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T21:56:59.041953Z"},"links":{"citing_paper":"/paper/2501.03508"},"observation_digest":"sha256:7db56fd7076ecbbb1341cd74a1130dba6e237a8626ea6e2016d3483b731172fe","observation_id":"4a152f67-929c-485d-87ef-a0b5d7e4756a","resolution":{"observed_at":"2026-08-10T21:56:59.145828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.03508","last_updated":"2025-01-07T03:51:10Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-11T11:29:50.068367Z","submitted_at":"2025-01-07T03:51:10Z","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":30},"total_outbound_references":39},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2501.03508."}