{"as_of":"2026-08-05T08:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4b00ab0b5a547c53ac5d7499a5a3d6e247f8630f67991de2a74ef387342881fd","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-15T01:50:21.013336Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2605.14553/citation-record","integrity":"/paper/2605.14553/integrity","json":"/paper/2605.14553/citation-record.json","paper":"/paper/2605.14553"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gepa: Reflective prompt evolution can outperform reinforcement learning","venue":null,"work_id":"3de5a529-96e4-4800-82cd-546562b68f98","year":2025},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:45743eb18e81615b2a4e120173d45ce8b7f14b04770b790eb5a13902ead03698","observation_id":"ac2abbae-81f9-4468-b204-7ae3267a5c5c","resolution":{"observed_at":"2026-05-15T08:30:17.972667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Best arm identification in multi-armed bandits","venue":null,"work_id":"8c40c1c5-f69c-4f4d-966c-e335bdb85b4e","year":2010},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:0758117e7860b19c7c4712b02cec4b4ff26ba62f2fdb21ab842afd775e646b08","observation_id":"a265d99e-d00a-457f-8b14-d1dc890e5e40","resolution":{"observed_at":"2026-05-15T08:30:17.967761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-10T14:57:14.742120Z","title":"Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901","venue":null,"work_id":"84780adb-76cf-44ac-a8b7-e24d4fa5c592","year":1901},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:10f2f85277ca36583901ab5c28aac39b83c0a2138ca7ebee53df8fb8e25320b2","observation_id":"aba489c4-eb97-4df5-b038-695a82017d5d","resolution":{"observed_at":"2026-05-15T08:30:17.970396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01097","last_updated":"2019-12-09T20:02:37Z","snapshot_observed_at":"2026-08-04T05:41:15.966625Z","submitted_at":"2018-12-03T21:59:41Z","title":"LEAF: A Benchmark for Federated Settings","version":3},"cited_work":{"arxiv_id":"1812.01097","doi":"10.48550/arxiv.1812.01097","metadata_source":"pith","pith_arxiv_id":"1812.01097","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Leaf: A benchmark for federated settings","venue":"cs.LG","work_id":"94ec8be1-6cf1-4962-994c-e762a0b9c3ee","year":2018},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"cited_paper":"/paper/1812.01097","citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:bdc4cdfdd006a8190223fa03210f2d3bec383d6931eacfb0c66a80045c03e3af","observation_id":"c84e5a03-b9fe-4b33-b5e9-03701ad70099","resolution":{"observed_at":"2026-05-15T01:53:29.078725Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Discrete prompt optimization via constrained generation for zero-shot re-ranker","venue":null,"work_id":"0c01ab93-25b2-4bca-b51b-919144ac6c2c","year":2023},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:57f75dad3091e313fa11086c1a5b8eacb0af74731a658dd90770c662d9f739bc","observation_id":"014dea16-a4dd-4af2-b065-487116c14bf0","resolution":{"observed_at":"2026-05-15T08:30:17.921458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Rlprompt: Optimizing discrete text prompts with reinforcement learning","venue":null,"work_id":"55768685-ff40-4557-b6f5-bb42c6c98974","year":2022},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:e854a1f854059e243782ef10bda236e6a66e8ed39fe6fded02cd2fe1df83e26a","observation_id":"5daa4583-fcb2-4a20-bedf-d20d139d0ccb","resolution":{"observed_at":"2026-05-15T08:30:17.957041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.14768","last_updated":"2022-11-27T08:58:16Z","snapshot_observed_at":"2026-08-03T21:32:54.693371Z","submitted_at":"2022-11-27T08:58:16Z","title":"Constrained Pure Exploration Multi-Armed Bandits with a Fixed Budget","version":1},"cited_work":{"arxiv_id":"2211.14768","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2211.14768","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Constrained pure exploration multi-armed bandits with a fixed budget.arXiv preprint arXiv:2211.14768","venue":null,"work_id":"773f154e-c4e4-414a-a6ac-beed8fa22567","year":2022},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"cited_paper":"/paper/2211.14768","citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:6a2f124407ed2ad14a2a927b50c5457bbb2b5b8e6c19a8a6313018d437b7ca03","observation_id":"880ef7b5-42d0-4a98-8cf7-9a99fa300174","resolution":{"observed_at":"2026-05-15T01:53:29.088035Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Connecting large language models with evolutionary algorithms yields powerful prompt optimizers","venue":null,"work_id":"998628a3-a1db-4c82-8be7-37e0c80ea111","year":2024},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:99e6d30e8b8193d2301dfd17e3c3a25c8d50870be135a860692c727384e6c141","observation_id":"36fa0f86-9814-47a1-bbcf-4aec30e08724","resolution":{"observed_at":"2026-05-15T08:30:17.923973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Morl-prompt: An em- pirical analysis of multi-objective reinforcement learning for discrete prompt optimization","venue":null,"work_id":"56f1d201-3b3a-4ffc-a2f1-81c41d887513","year":2024},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:5a482db0211d7864debfb363d5840291ce3bee72385be81f473040f1d4e8e7c2","observation_id":"a5d8aa67-73ed-487b-a436-2a04af6ec472","resolution":{"observed_at":"2026-05-15T08:30:17.926195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.11246","last_updated":"2024-01-20T14:59:43Z","snapshot_observed_at":"2026-07-06T17:18:16.042313Z","submitted_at":"2024-01-20T14:59:43Z","title":"Prompt-RAG: Pioneering Vector Embedding-Free Retrieval-Augmented Generation in Niche Domains, Exemplified by Korean Medicine","version":1},"cited_work":{"arxiv_id":"2401.11246","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.11246","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Prompt-rag: Pioneering vector embedding- free retrieval-augmented generation in niche domains, exemplified by korean medicine","venue":null,"work_id":"a34c0c30-8fd7-4f14-bd0a-162c07c66aa4","year":2024},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"cited_paper":"/paper/2401.11246","citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:35152331a30e0689907d9e26b78e0dde375f1f9f9bac1d781454086db7ccaf34","observation_id":"becde7a7-e613-4c92-90a6-30cc8297ccad","resolution":{"observed_at":"2026-05-15T01:53:29.097534Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Bounded archiving using the lebesgue measure","venue":null,"work_id":"ce1e6bc5-9848-4f6f-9fdb-11dc6de9df78","year":2003},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:c61be7fe5e48601666333bcb3042f3682f2fa5d422674411a5aec502660918b2","observation_id":"9b6b264f-bb7e-48f8-a1fa-90d1ca9744f5","resolution":{"observed_at":"2026-05-15T08:30:17.945945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Bandit Pareto set identification in a multi- output linear model","venue":null,"work_id":"6a8b2f9d-791d-46bc-85c0-3a34147dbda2","year":2025},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:fe944515264fb5dc2777c8c09a15b38ecabca51aa7deb9c9f5199391a6d4ae6b","observation_id":"a04f48bb-bf70-4602-a6f2-e75af73d9438","resolution":{"observed_at":"2026-05-15T08:30:17.952727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Meta-prompt optimization for LLM- based sequential decision making","venue":null,"work_id":"cf6e3882-b9b5-4952-91e8-bcfa7143ca06","year":2025},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:2b835611a6f16c3c2b4b2e39d4d8c64e92a5396b2409952717033aeda4c359d5","observation_id":"35148e7c-5146-41f1-b58a-41da6c34345f","resolution":{"observed_at":"2026-05-15T08:30:17.928324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Prompt optimization with human feedback","venue":null,"work_id":"8906cdad-34ce-4ce5-aaae-a9c12ae2db5f","year":2024},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:d463a10f4b75e0f908b5d96b0317b247e5a2fd032e5c9f4057291a276f7ef460","observation_id":"95b29c6a-b6e5-4728-b23d-e76ea094ccd0","resolution":{"observed_at":"2026-05-15T08:30:17.959147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1808.08745","last_updated":"2018-08-27T09:08:18Z","snapshot_observed_at":"2026-07-06T06:57:36.335954Z","submitted_at":"2018-08-27T09:08:18Z","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","version":1},"cited_work":{"arxiv_id":"1808.08745","doi":"10.48550/arxiv.1808.08745","metadata_source":"pith","pith_arxiv_id":"1808.08745","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","venue":"cs.CL","work_id":"83dfe48d-b12e-425e-a8c9-d62ac86d1373","year":2018},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"cited_paper":"/paper/1808.08745","citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:533a4a6848fa33619c8ffa71e490771cdde6bf9bdd860ba0d4aa23f3ab6d71db","observation_id":"f07e2739-d4d6-4929-a33b-8df2188e29c0","resolution":{"observed_at":"2026-05-15T01:53:29.075357Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"gradient descent","venue":null,"work_id":"5dbdaef5-e612-479b-b01f-e3cae33f2b0d","year":2023},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:7fd6e47784ba1cd176321f35204e27c70e74065ca34cb3a51a5c853ac197f55a","observation_id":"b9b3b0d5-5cd2-41e6-959e-b70e9e98e73f","resolution":{"observed_at":"2026-05-15T08:30:17.963431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07927","last_updated":"2025-03-16T06:23:34Z","snapshot_observed_at":"2026-08-04T23:13:14.416173Z","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":"2402.07927","doi":"10.1145/3658644.3670388","metadata_source":"pith","pith_arxiv_id":"2402.07927","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","venue":"cs.AI","work_id":"83d5f1d1-b40d-49c8-9770-6c57bed8a8b8","year":2024},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"cited_paper":"/paper/2402.07927","citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:8527db3f0f39e3d12158d4c50d120a310dbb86af4768ea25b03b009269624dfe","observation_id":"63bc68b5-5084-431e-bd1f-3c6034b3f7a7","resolution":{"observed_at":"2026-05-15T01:53:29.094523Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06608","last_updated":"2025-02-26T18:59:01Z","snapshot_observed_at":"2026-07-06T18:28:24.821865Z","submitted_at":"2024-06-06T18:10:11Z","title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","version":6},"cited_work":{"arxiv_id":"2406.06608","doi":"10.1007/s00146-025-02667-2","metadata_source":"pith","pith_arxiv_id":"2406.06608","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","venue":"cs.CL","work_id":"089548ef-9ae9-4016-a6d9-b951128416c7","year":2024},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"cited_paper":"/paper/2406.06608","citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:41ebf693eec43a9dfb56fe8e759f359e87f98b445e36147d4907d2dd3a2a073f","observation_id":"39016120-146d-4124-b252-106ab70d1ad1","resolution":{"observed_at":"2026-05-15T02:16:17.988307Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-05-30T14:25:31.500281+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-30T14:25:31.500281+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Autoprompt: Eliciting knowledge from language models with automatically generated prompts","venue":null,"work_id":"e49ce667-4132-42bd-bbe5-5e5f29c1c669","year":2020},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:e87173225113dc8e0b2cefee8ad112edb3b78f4a0031029beffad40c46bd7a64","observation_id":"93a0d0bd-11be-4306-a0ee-4b674f827caf","resolution":{"observed_at":"2026-05-15T08:30:17.930461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08295","last_updated":"2024-04-16T12:52:47Z","snapshot_observed_at":"2026-08-03T03:29:01.959523Z","submitted_at":"2024-03-13T06:59:16Z","title":"Gemma: Open Models Based on Gemini Research and Technology","version":4},"cited_work":{"arxiv_id":"2403.08295","doi":"10.48550/arxiv.2403.08295","metadata_source":"pith","pith_arxiv_id":"2403.08295","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Gemma: Open Models Based on Gemini Research and Technology","venue":"cs.CL","work_id":"a9ea2870-df28-40b8-a9e0-a7e9a116f793","year":2024},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"cited_paper":"/paper/2403.08295","citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:363bf48aafae2e98767c6cd048585d1c63bed0a7c9fda0c8d1151140ce7b1312","observation_id":"1db96bb4-3e6a-44cf-9890-249e41f1e3a3","resolution":{"observed_at":"2026-05-15T01:53:29.084605Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837","venue":null,"work_id":"85e9d0a3-0329-402c-a185-9b084fdbf57a","year":2026},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:a2f182c7024fd5b56bde3c78f7bdff49c4e528525b149671253f0bcd077f0bfd","observation_id":"aa5b0daf-b655-42da-845d-f676fd58d717","resolution":{"observed_at":"2026-05-15T08:30:17.943446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.12567","last_updated":"2025-05-18T22:55:16Z","snapshot_observed_at":"2026-07-06T21:25:56.796553Z","submitted_at":"2025-05-18T22:55:16Z","title":"A Survey of Attacks on Large Language Models","version":1},"cited_work":{"arxiv_id":"2505.12567","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.12567","snapshot_observed_at":"2026-07-01T11:05:42.376291Z","title":"arXiv preprint arXiv:2505.12567 , year=","venue":null,"work_id":"9f7dbf1c-be92-4e5d-a654-39f8259e2768","year":2025},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"cited_paper":"/paper/2505.12567","citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:c78be95c961c0c58b21520930481bf9dd59c5703bc8f21b39ddf644cd21df898","observation_id":"c2da5128-f804-4b81-bdbd-f4f90322c51e","resolution":{"observed_at":"2026-05-15T01:53:29.081821Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Backdooring instruction-tuned large language models with virtual prompt injection","venue":null,"work_id":"68644d98-3b51-4f61-bb21-f59e841d546d","year":2024},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:5bdd7e00b8c8886df8eea0c36c992bcde2baac2ad184ff5c81dedc50dca0c6bd","observation_id":"a246509f-ab48-4110-ba97-433d37d9ad27","resolution":{"observed_at":"2026-05-15T08:30:17.948169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Instoptima: Evolutionary multi-objective instruction optimization via large language model-based instruction operators","venue":null,"work_id":"65d63811-72c4-42f6-addc-781c6ab829db","year":2023},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:e1ab91377d468af6d7a7c181dced4f98be79698834750a3b4c09cd6a55ab8712","observation_id":"e6837e30-c243-4867-8e4c-29ba5cf861d2","resolution":{"observed_at":"2026-05-15T08:30:17.954982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"c5a42064-64a6-4f6a-b763-a7a7e859fed9","year":2026},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:7d4ed9b19be9ae98f94448802b1c4f9d1dab426626116d2ef6f3657f61375f7c","observation_id":"7a44ea58-731e-42d2-bfbb-88e3fe1c03ea","resolution":{"observed_at":"2026-05-15T08:30:17.965452Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"For the multi-objective bandit setting, we have the prompt or arm setXwith|X |=K, and the expected performance or reward vector µ(x), x∈ X","venue":null,"work_id":"71fd89a5-fe5a-4c2b-8852-c84d0cee1338","year":2022},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:1f0078cb0a785cdc21aab12917e0c494dd8282465261d7d8194437c4c205189a","observation_id":"51433411-0d5a-4712-b4c0-de7041ed367f","resolution":{"observed_at":"2026-05-15T08:30:17.961233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"c0e9dabe-fed7-4936-a549-c2a799a8cef5","year":2026},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:6af9bb2dd07ecb252db0e9e6eab7dcb3d74c413bb9a6190c04743876243c2426","observation_id":"cbb164f1-72f8-4122-b299-d9ae0ac31d6d","resolution":{"observed_at":"2026-05-15T08:30:17.938962Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"In roundr, given the active arm setA r−1, the arm pulled at steptsatisfiesx (t) ∈A r−1 and yields the observed outcomef (t)","venue":null,"work_id":"1fd525ca-1303-4ff7-a519-ff81f956e93d","year":2026},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:ee1c7dcaa3ed0a13e4759419a5f7ac31580655a57ff35d3cb746e97dc072f5be","observation_id":"7124e729-03d6-41ed-9978-e177f21a5b44","resolution":{"observed_at":"2026-05-15T08:30:17.950582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"bf4ab137-aca4-4b66-9833-4537b7697ab4","year":2026},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:31da128c34fb56bc785249b67a3e56a0c65e9826c72e8543dd8913f32bd6fef6","observation_id":"5ab7226a-e076-4e30-9c6c-1cd3a0f53580","resolution":{"observed_at":"2026-05-15T08:30:17.936717Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"5fafc07a-c017-47f2-ac02-9d8833283fcf","year":2016},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:73827d9851f8e347e22455e68bc5e90527de73520f3256af535303f1934be1f6","observation_id":"0244d1b1-39db-403f-812f-ef9e74a90a67","resolution":{"observed_at":"2026-05-15T08:30:17.941158Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"For the instruction models, we adopt the recommended system template as Figure","venue":null,"work_id":"0c3bc3a2-6de7-4722-91b7-c872bcf7fd2c","year":2024},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:3f777ffb577a642b4361e058364036caaa718b55784381801e625282e8c6309d","observation_id":"59fe84ed-ea82-41b9-821a-d6c74c5f8ab0","resolution":{"observed_at":"2026-05-15T08:30:17.934653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"It captures the token-wise similarity between two texts","venue":null,"work_id":"6c95f988-155c-484f-8ef6-b0b8439bcf5d","year":2026},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:445688d1026ab971e53860ea0cb563bdb5adc069bb36ac3aa1e3f78060d61b76","observation_id":"d37313f5-2a9c-43eb-aa83-664c4bbe4646","resolution":{"observed_at":"2026-05-15T08:30:17.919239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"(a) Constraint = 0.6 (b) Constraint = 0.5 (c) Constraint = 0.4 Figure 9: Feasible average reward vs","venue":null,"work_id":"ffac73a3-22ec-41ea-a287-8d3f8384dd35","year":2026},"citing_paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-15T01:50:21.013336Z"},"links":{"citing_paper":"/paper/2605.14553"},"observation_digest":"sha256:b6cdb6b8826681652d41aa3893a82c8d0ce7fe21e900e9afecf9668d162465c9","observation_id":"49cb6f07-521a-4f28-9742-0031623c6118","resolution":{"observed_at":"2026-05-15T08:30:17.932535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.14553","last_updated":"2026-05-14T08:31:17Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T23:25:58.895612Z","submitted_at":"2026-05-14T08:31:17Z","title":"Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":4,"verified_exact":6,"verified_fuzzy":21},"total_outbound_references":33},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2605.14553."}