{"as_of":"2026-08-11T17:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0edaa6e44be2d6fbe8bb8755cd92216f8b7ca24f943330ea4ea93c3c40e89160","coverage":[{"denominator":80,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":80,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-19T09:20:12.827871Z","state":"measured"},{"denominator":87,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":87,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":7,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":7,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T11:19:49.639145Z","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":"2026-07-03T17:28:44.173966Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"cited_work":{"arxiv_id":"2506.10060","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.10060","snapshot_observed_at":"2026-07-03T17:28:44.173966Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","venue":"cs.LG","work_id":"556f9937-8f77-4ae1-bdbc-54e8c8cabc52","year":2025},"citing_paper":{"arxiv_id":"2510.04265","last_updated":"2026-05-12T01:55:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-10-05T16:14:03Z","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-18T10:04:39.223895Z"},"links":{"cited_paper":"/paper/2506.10060","citing_paper":"/paper/2510.04265"},"observation_digest":"sha256:d94a7a2752613dd720a024a4507babe50985278dac47ab8b632da93613a3ddb9","observation_id":"ccf5a398-b0d7-42c6-bfad-70a2b02edb2b","resolution":{"observed_at":"2026-05-18T10:06:13.844261Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.10060","snapshot_observed_at":"2026-08-04T11:19:49.639145Z","title":"Textual bayes: Quantifying uncertainty in LLM-based systems, June 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.05709","last_updated":"2026-06-04T12:15:57Z","snapshot_observed_at":"2026-08-07T08:05:26.965055Z","submitted_at":"2025-10-07T09:22:22Z","title":"Correcting Prompt Dependence in LLM Benchmarks: A Bayesian Hierarchical Model with Embedding-Space Clustering","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-04T11:19:49.639145Z"},"links":{"cited_paper":"/paper/2506.10060","citing_paper":"/paper/2510.05709"},"observation_digest":"sha256:7c9ecdb404aea7e225b0e59e0bacc03b11bedf53083169ad8df407f60c8473ad","observation_id":"c486a4f5-dbdd-47f1-912d-fd4e657d1113","resolution":{"observed_at":"2026-08-04T11:19:49.639145Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.10060","snapshot_observed_at":"2026-08-04T11:17:36.735976Z","title":"Textual bayes: Quantifying uncertainty in llm-based systems.arXiv preprint arXiv:2506.10060,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.06096","last_updated":"2026-06-26T18:48:41Z","snapshot_observed_at":"2026-08-09T20:20:11.286361Z","submitted_at":"2025-10-07T16:25:14Z","title":"The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives","version":3},"reference_index":2007,"source":"pdf_text","source_observed_at":"2026-08-04T11:17:36.735976Z"},"links":{"cited_paper":"/paper/2506.10060","citing_paper":"/paper/2510.06096"},"observation_digest":"sha256:85698a064bdb57445abecea633a5086cf78df726032877915bce5e6ca25eb5e1","observation_id":"86eb37f9-d4fa-4adb-8efd-97e1592fb523","resolution":{"observed_at":"2026-08-04T11:17:36.735976Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"cited_work":{"arxiv_id":"2506.10060","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.10060","snapshot_observed_at":"2026-07-03T17:28:44.173966Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","venue":"cs.LG","work_id":"556f9937-8f77-4ae1-bdbc-54e8c8cabc52","year":2025},"citing_paper":{"arxiv_id":"2606.31630","last_updated":"2026-06-30T13:16:39Z","snapshot_observed_at":"2026-08-05T11:04:53.475955Z","submitted_at":"2026-06-30T13:16:39Z","title":"Calibration, Not Compilation: Detecting and Repairing Misspecified Probabilistic Programs Written by Language Models","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-07-01T06:17:08.273981Z"},"links":{"cited_paper":"/paper/2506.10060","citing_paper":"/paper/2606.31630"},"observation_digest":"sha256:3fd05007466d5a861815b1fdb0569a826db8a0ec88e120cf9b58a81a9f91148c","observation_id":"0298b269-e203-44eb-942b-b915a1ddc543","resolution":{"observed_at":"2026-07-01T09:45:39.891578Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"cited_work":{"arxiv_id":"2506.10060","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.10060","snapshot_observed_at":"2026-07-03T17:28:44.173966Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","venue":"cs.LG","work_id":"556f9937-8f77-4ae1-bdbc-54e8c8cabc52","year":2025},"citing_paper":{"arxiv_id":"2607.02104","last_updated":"2026-07-18T10:54:29Z","snapshot_observed_at":"2026-08-02T09:31:38.614567Z","submitted_at":"2026-07-02T12:39:30Z","title":"When Can You Debias an LLM Judge? Identifiability Limits, a Test, and Designs for Top-k Ranking","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-07-03T17:18:44.535428Z"},"links":{"cited_paper":"/paper/2506.10060","citing_paper":"/paper/2607.02104"},"observation_digest":"sha256:12150d0b32aca4c31c3a1d8463d0b2836312791cb7ad41a9c6e4a7f12f0eecd3","observation_id":"66143a1a-69a8-4608-9029-74579fc19f18","resolution":{"observed_at":"2026-07-03T17:28:44.175582Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.10060","snapshot_observed_at":"2026-08-02T09:07:09.534780Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.02104","last_updated":"2026-07-18T10:54:29Z","snapshot_observed_at":"2026-08-02T09:31:38.614567Z","submitted_at":"2026-07-02T12:39:30Z","title":"When Can You Debias an LLM Judge? Identifiability Limits, a Test, and Designs for Top-k Ranking","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-02T09:07:09.534780Z"},"links":{"cited_paper":"/paper/2506.10060","citing_paper":"/paper/2607.02104"},"observation_digest":"sha256:ff3d60553b58bd7b372ec5c798b5ecb2e47837cd5c68182470a427d60fa0a376","observation_id":"47fcfe40-0d87-4f03-a0bc-ee4445b994dd","resolution":{"observed_at":"2026-08-02T09:07:09.534780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.10060","snapshot_observed_at":"2026-07-12T06:24:52.086585Z","title":"Textual bayes: Quantifying uncertainty in llm-based systems,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.02882","last_updated":"2026-07-03T02:28:32Z","snapshot_observed_at":"2026-08-01T20:07:04.724562Z","submitted_at":"2026-07-03T02:28:32Z","title":"Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-12T06:24:52.086585Z"},"links":{"cited_paper":"/paper/2506.10060","citing_paper":"/paper/2607.02882"},"observation_digest":"sha256:3b0d0e0796f388a8f20ca117cc8511ed2020d14dd89183b17e756a5bd0c2b4bd","observation_id":"a10ef0c0-2f7f-4650-a7a4-80781eebb611","resolution":{"observed_at":"2026-07-12T06:24:52.086585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.10060/citation-record","integrity":"/paper/2506.10060/integrity","json":"/paper/2506.10060/citation-record.json","paper":"/paper/2506.10060"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":"2303.08774","doi":"10.1002/tea.20265","metadata_source":"pith","pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"GPT-4 Technical Report","venue":"cs.CL","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:db2064e72460829ede313be58b25449b57767d65329c9bc1cffa1b3f13bfdd51","observation_id":"ca79095b-7db6-4fa5-8645-9f4b0bdfb958","resolution":{"observed_at":"2026-05-19T09:22:16.002337Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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 statistical theory of cold posteriors in deep neural networks","venue":null,"work_id":"7003c603-8a15-443a-8d7e-76df33311bb5","year":2021},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:b528e37b7ece192087660827d06e36ee885d58177befcce154f4f6a2099b5aea","observation_id":"b4633ec9-3f79-4658-924a-6a5caba78de2","resolution":{"observed_at":"2026-05-19T09:23:04.223047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.00949","doi":"10.48550/arxiv.2505.00949","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Bie, T., Cao, M., Chen, K., Du, L., Gong, M., Gong, Z., Gu, Y ., Hu, J., Huang, Z., Lan, Z., et al","venue":"ArXiv.org","work_id":"863f4416-1708-46c1-b8f9-c894351db269","year":2025},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:399e459eb7d21099a5049c2e37cea16e57789b4cc78f43018b1bfc539a631b09","observation_id":"0177f880-98d4-47aa-aaa7-704c5c9625f7","resolution":{"observed_at":"2026-05-19T09:22:15.983044Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-05-25T17:53:22.063501+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T17:53:22.063501+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Bayesian Theory, volume 405","venue":null,"work_id":"8e215745-1e91-438d-b3c1-fe5005ca7320","year":2009},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:1c9b8ae1f4780084acd74831901da854453df461ea7a8c1490918c8411128a68","observation_id":"5759095f-d992-405d-ae81-ff60b7003f7e","resolution":{"observed_at":"2026-05-19T09:23:04.219689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Weight uncertainty in neural network","venue":null,"work_id":"9998c0d3-8d3a-43b0-950a-6fddca3ebbc9","year":2015},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:a5411a781807a7c1dcff6e076dfc2e623c45fc6cbe3d4ce969542e53632e2a79","observation_id":"31b3801f-097c-4a99-80b8-80e15536dc5d","resolution":{"observed_at":"2026-05-19T09:23:04.209149Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.05332","last_updated":"2023-04-11T16:50:17Z","snapshot_observed_at":"2026-07-06T15:14:28.574778Z","submitted_at":"2023-04-11T16:50:17Z","title":"Emergent autonomous scientific research capabilities of large language models","version":1},"cited_work":{"arxiv_id":"2304.05332","doi":"10.1038/s41586-023-06792-0;arxiv:2304.05332","metadata_source":"pith","pith_arxiv_id":"2304.05332","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Emergent autonomous scientific research capabilities of large language models","venue":"physics.chem-ph","work_id":"13684544-b165-440c-aceb-3470a18b1133","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2304.05332","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:cb7f2d6b854490f9a95795edfe2e7906a7ccfedc6890e3dd088e592450a9eb79","observation_id":"94dfb5d4-d275-45ef-8c77-6e960a7c2d8f","resolution":{"observed_at":"2026-05-19T21:43:44.843677Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-031-33898-4_3","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Opportunities and Challenges of AI-Driven Customer Service, pages 33–71","venue":null,"work_id":"fa1f6680-350b-482e-88f9-59999584e921","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:5503726659468082b3b93adf1c5c6f4b1133233a4b7829fabd585c08a9957d9e","observation_id":"060fb61c-cf59-4c2a-bca7-eab5b7e9eaa9","resolution":{"observed_at":"2026-05-19T09:22:13.961100Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":"2107.03374","doi":"10.48550/arxiv.2107.03374","metadata_source":"pith","pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Evaluating Large Language Models Trained on Code","venue":"cs.LG","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","year":2021},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:146845f7177b3d30d90ff413257772e412bf232e5f09e245995cede5887c7ae5","observation_id":"55b7900b-ae78-4766-bf76-c4c5b53c6c10","resolution":{"observed_at":"2026-05-19T09:22:16.008496Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-01T08:08:23.404839+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-01T08:08:23.404839+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","venue":null,"work_id":"54dcf128-5209-4978-b5d1-0a8c8d776707","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:641da026d0ec2dbf0ba68afe3d6deb8e2feaa319bf25517ddec01381b1a9aba3","observation_id":"050f1408-c8cf-4ad0-9765-cf2f9441e423","resolution":{"observed_at":"2026-05-19T09:23:04.212916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Aime problems and solutions","venue":null,"work_id":"53aee13b-a7b8-483c-ae06-12b96d0c661f","year":null},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:290630c8d21057335bbd54a6c91ddda92475831d6d160c103c119cfe1f9dbc77","observation_id":"16929d51-2803-410d-a139-55887ebd9db0","resolution":{"observed_at":"2026-05-19T09:23:04.216724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.03011","last_updated":"2021-05-07T00:12:34Z","snapshot_observed_at":"2026-08-11T00:52:16.498491Z","submitted_at":"2021-05-07T00:12:34Z","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","version":1},"cited_work":{"arxiv_id":"2105.03011","doi":"10.48550/arxiv.2105.03011","metadata_source":"arxiv_reference","pith_arxiv_id":"2105.03011","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"A dataset of information-seeking questions and answers anchored in research papers","venue":"arXiv (Cornell University)","work_id":"a52f872a-7afa-4ac3-9a74-74f8fb148aa9","year":2021},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2105.03011","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:5d6eec77580f30af1e118dd71994fb4950024ae2fd9932272f1cc2e0f37236ec","observation_id":"8ac89577-5801-4448-867b-2d49801cdbd8","resolution":{"observed_at":"2026-05-19T09:22:15.989908Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Laplace redux-effortless Bayesian deep learning","venue":null,"work_id":"e5c08ab1-73d3-4e70-8ee4-9475dc0a4ea5","year":2021},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:0841071b7a189ad72bf368a821a3f9855584e42f5ac5c428d6bece1edb7db17e","observation_id":"f588d314-aae5-4716-8866-40ac5626582c","resolution":{"observed_at":"2026-05-19T09:23:04.176336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"e49a2a55-fcb3-4885-a900-7ff9106796ca","year":1987},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:6982ca009c1574fb8f75b88a00d70fb2a649995af853ee420b819712add2ee0e","observation_id":"4900f99c-3a11-4147-8209-31963695a0cd","resolution":{"observed_at":"2026-05-19T09:23:04.039328Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2504.03790","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T01:17:30.672032Z","title":"Sample, don’t search: Rethinking test-time alignment for language models","venue":null,"work_id":"8367320c-bafd-4736-b916-9edf9d0baa6e","year":2025},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:059643ac8829c1fd3a5f00137fc710806f1138149613ffe33565786ac0dd3661","observation_id":"ec6e8b08-7af4-4103-91eb-30e6ea14034c","resolution":{"observed_at":"2026-05-19T09:22:15.941560Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"QUEST: Quality-aware metropolis-hastings sampling for machine translation","venue":null,"work_id":"063e35ae-71f3-4d49-ad23-e35f506e7d2b","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:398203a30bf4ee223c4db11b8317576cd589db4825b2e8e73f1d3bdc3e669eb2","observation_id":"a8a2e341-43ae-406f-a9b2-9d303f68eba1","resolution":{"observed_at":"2026-05-19T09:23:04.043506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Ober, Florian Wenzel, Gunnar Ratsch, Richard E Turner, Mark van der Wilk, and Laurence Aitchison","venue":null,"work_id":"8a0ee12f-39ea-4627-b6d5-ad6a4cee0a19","year":2022},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:331124d4e4387a6386e401655b73285347e45527970e699a531cdd8e11ed994f","observation_id":"18c24100-24eb-4c7d-9ceb-d7a6d4b35828","resolution":{"observed_at":"2026-05-19T09:23:04.192889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02509","last_updated":"2024-03-04T21:55:22Z","snapshot_observed_at":"2026-08-10T13:48:37.085067Z","submitted_at":"2024-03-04T21:55:22Z","title":"SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models","version":1},"cited_work":{"arxiv_id":"2403.02509","doi":"10.48550/arxiv.2403.02509","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02509","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Spuq: Perturbation-based uncertainty quantification for large language models.arXiv preprint arXiv:2403.02509","venue":"arXiv (Cornell University)","work_id":"d9a2845d-0008-4141-94fc-dddb7b8842e0","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2403.02509","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:eaf66805c184f53aa329035664ccc3af0c9baa077cdbfb5caf8c0f844a68a3e0","observation_id":"b2f2e1e4-4ddd-4826-9dfa-24101cdcdbb6","resolution":{"observed_at":"2026-05-19T09:22:15.976487Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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 Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing","venue":null,"work_id":"0814feeb-0e2e-4503-a0a9-37ce63f4024e","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:0c0dc8f9d7103119cb42ac79ee3f6d2db6cf1b4f7dba884f02d4793568e0a316","observation_id":"6014652a-e57f-4e8f-97b4-2596947c5c0e","resolution":{"observed_at":"2026-05-19T09:23:04.061622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.22685","last_updated":"2024-10-30T04:41:46Z","snapshot_observed_at":"2026-07-06T19:41:59.246720Z","submitted_at":"2024-10-30T04:41:46Z","title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","version":1},"cited_work":{"arxiv_id":"2410.22685","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.22685","snapshot_observed_at":"2026-07-04T03:39:30.634270Z","title":"InAdvances in Neural Information Processing Systems (NeurIPS) Datasets and Bench- marks Track","venue":null,"work_id":"22695d55-13ba-4502-8b7a-ddad5b28183f","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2410.22685","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:af2a53f9471a9f1efbcf0b7019003181d0dbe94bdf43b6c01a54fb2708f5193b","observation_id":"3bdee7e4-02c4-4283-8e99-6d1b6eb55e39","resolution":{"observed_at":"2026-05-19T09:22:15.886714Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Weinberger","venue":null,"work_id":"c8fd3d54-dc1f-435e-8a87-07b16572b717","year":2017},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:8fc12a584113ba0e40e717e39040ba89795850dae90bc66a13c5bd4de268740e","observation_id":"ac4635bf-1ea3-4daa-9703-a2a8b5d77a06","resolution":{"observed_at":"2026-05-19T09:23:04.026745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"De- composing uncertainty for large language models through input clarification ensembling","venue":null,"work_id":"272e8165-1808-4605-8ac5-65b92152ca76","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:bfcacf1383131cf1ae91a0f64ccc1b06fa54cad5090776c56ff87456c32553e0","observation_id":"d305396e-4de8-4a9a-86e2-2468f634da81","resolution":{"observed_at":"2026-05-19T09:23:04.002668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.08435","last_updated":"2025-03-02T05:13:28Z","snapshot_observed_at":"2026-08-06T11:45:45.286982Z","submitted_at":"2024-08-15T21:59:23Z","title":"Automated Design of Agentic Systems","version":2},"cited_work":{"arxiv_id":"2408.08435","doi":"10.48550/arxiv.2408.08435","metadata_source":"pith","pith_arxiv_id":"2408.08435","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Automated Design of Agentic Systems","venue":"cs.AI","work_id":"100d6cbf-e729-4ef1-828a-0bb6cb04b7d5","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2408.08435","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:91df7e6dcb89eb71dd6a13b372469ac208f5e7fd10a3be73164b8c89abc817c3","observation_id":"95b8370f-d732-4fa9-99d2-8b5f4c0d4d73","resolution":{"observed_at":"2026-05-19T09:22:15.955244Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-07-14T18:20:19.852993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T18:20:19.852993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"What Are Bayesian Neural Network Posteriors Really Like? In Proceedings of the 38th International Conference on Machine Learning, volume 139, pages 4629–4640","venue":null,"work_id":"e924ca83-be27-408d-9b76-31290e1580bf","year":2021},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:c47d600789c577c2a07cb6bb00c898951d63438657a422b4c49f3a4cb2850dda","observation_id":"9ca38320-2bcf-426b-bc3d-a65e3065ba90","resolution":{"observed_at":"2026-05-19T09:23:04.164184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Estimating the hallucination rate of generative AI","venue":null,"work_id":"66adb625-bfc4-4ff9-a22c-0d8a3359d67f","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:a0503a9813bfc90edb90af405ef39f7611fcf39cbdfed077c48471deae7d3f1c","observation_id":"c786b5d3-0b7c-4b05-b88c-9ee9047f0e03","resolution":{"observed_at":"2026-05-19T09:23:04.017993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05221","last_updated":"2022-11-21T16:38:35Z","snapshot_observed_at":"2026-08-06T08:34:11.887259Z","submitted_at":"2022-07-11T22:59:39Z","title":"Language Models (Mostly) Know What They Know","version":4},"cited_work":{"arxiv_id":"2207.05221","doi":"10.1145/3618260.3649777","metadata_source":"pith","pith_arxiv_id":"2207.05221","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Language Models (Mostly) Know What They Know","venue":"cs.CL","work_id":"8ca58a10-da41-4f70-baae-7e449512e345","year":2022},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2207.05221","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:0e63db397c24ee02a5ee0c648815799f8b8ba9de456abd081edadc0111544f97","observation_id":"9d13bc5e-01d9-4045-8d86-ef9b05cd5323","resolution":{"observed_at":"2026-05-19T09:22:15.880422Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-05-21T07:53:13.382372+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T07:53:13.382372+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"On uncertainty, tempering, and data augmentation in bayesian classification","venue":null,"work_id":"a41b5531-2fa3-45c9-a4d7-105d687f37df","year":2022},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:e13e6c7c08a3e6e37aebb4b254e8d26f9c908c065984c3fd754a36cc9096b4e7","observation_id":"08079ea4-7d55-4c3d-b985-7106b723e84e","resolution":{"observed_at":"2026-05-19T09:23:04.010295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts","venue":null,"work_id":"8cb6c6fc-030c-4734-aaae-fb60f23efd44","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:d2a5450c709a09b8648a5965dfb6464a0f8df7c132dd8c6856cbdea2aff79264","observation_id":"f98672d8-ad49-4ae9-ac9e-6c019bbc69e1","resolution":{"observed_at":"2026-05-19T09:23:04.006484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Auto-encoding variational Bayes","venue":null,"work_id":"bb2e918d-aa5e-4d73-b910-9a00a123b368","year":2014},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:be1f7d65cacf63dbbb3c149fcbbf3c93bbd778244bfc5ca7d829ae92b466d3ec","observation_id":"6b011272-54fc-4811-bd82-08dfb6b7bdfc","resolution":{"observed_at":"2026-05-19T09:23:04.172728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Being Bayesian, even just a bit, fixes overconfidence in relu networks","venue":null,"work_id":"313e4a07-2fee-4aba-88bd-6e8889446662","year":2020},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:f30ee8fc5d697c8abeb2bbf4a81c694c527b39aa773198e20dc66ad4be3cb58b","observation_id":"9c355347-0fea-4f98-a7be-029a4abbbf8e","resolution":{"observed_at":"2026-05-19T09:23:04.058016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation","venue":null,"work_id":"eb40794f-a5f9-4da2-8951-b8e3881e3cee","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:fad9aa4b95b6969e55379801380ae570000de22a2d974d42b687cd59e8312292","observation_id":"505203e2-8062-42f1-a473-469478595d0d","resolution":{"observed_at":"2026-05-19T09:23:04.140376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-07-09T04:05:56.007610Z","title":"Simple and scalable predictive uncertainty estimation using deep ensembles","venue":null,"work_id":"c046e351-ce97-4be2-a0b1-55ef82f86068","year":2017},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:5b30cd3781a3cb1c50e1609d91256edd32c949cd542eafea80e378890cccdaa4","observation_id":"9df5bcbf-12ec-487b-8c23-e7acaa3bc192","resolution":{"observed_at":"2026-05-19T09:23:04.047214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","venue":null,"work_id":"d630ee2b-7da9-4173-8faf-e2a4c1791778","year":2020},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:4d48849c49d3bd4e47ea844a17a2167830af01e5df099e3789ebafa41131c9f8","observation_id":"9be4b414-fa7b-4849-85ac-50029033bac9","resolution":{"observed_at":"2026-05-19T09:23:04.051016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Generating with confidence: Uncertainty quantification for black-box large language models","venue":null,"work_id":"ec00ebad-4b3f-4869-9f89-4168444eddea","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:759bef62230bc5460bf5a2cb6b9777e92954b356e6aa6e152cc193bf82bfa9e0","observation_id":"bce37f25-debb-4b99-867f-f6f969aec8bc","resolution":{"observed_at":"2026-05-19T09:23:03.999022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10189","last_updated":"2024-03-28T19:41:34Z","snapshot_observed_at":"2026-08-11T12:42:30.529321Z","submitted_at":"2024-02-15T18:46:24Z","title":"Uncertainty Quantification for In-Context Learning of Large Language Models","version":2},"cited_work":{"arxiv_id":"2402.10189","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.10189","snapshot_observed_at":"2026-07-01T19:16:00.104174Z","title":"Uncertainty quantification for in-context learning of large language models.arXiv preprint arXiv:2402.10189","venue":null,"work_id":"38288ae0-71b6-414f-a233-a3dc3f542e46","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2402.10189","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:dc6d50035b4848f96fefb30c3f611dc4378c8257ef9ba1becb910c761fd08f6e","observation_id":"fbc47071-af24-43e3-9562-03ab0db3c823","resolution":{"observed_at":"2026-05-19T09:22:15.916798Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Information Theory, Inference and Learning Algorithms","venue":null,"work_id":"fe789fe3-fc70-4904-8ca0-f1f776c0ebda","year":2003},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:80ff1fb52eb22d87f3ced2cb5829f9672fd0ebb7ceb6c3bcafe68089fa3dbb3a","observation_id":"6a770bee-a331-480f-afe3-49ebf647d628","resolution":{"observed_at":"2026-05-19T09:23:04.168909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Self- Refine: Iterative Refinement with Self-Feedback","venue":null,"work_id":"0d86ea05-74b1-4296-b524-f916ea944e74","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:bbfc73b1ebcc8f0bd9888faa18d00b80596e8f29118780dab26b473ae013e53e","observation_id":"c87913a9-c1b6-4e3c-862b-2fd6070a4d68","resolution":{"observed_at":"2026-05-19T09:23:04.022394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.emnlp-main.557","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T13:16:57.985321Z","title":"Manakul, A","venue":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","work_id":"668c2115-8eeb-420f-8e23-0c5315e216c3","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:d2704c0c16b60b36e0f88e034dae2848cec90fba4071973e2bc60a6d1a03a7f8","observation_id":"8c69d0f6-ab60-48a6-aedf-81ed2adab8f9","resolution":{"observed_at":"2026-05-19T09:22:13.936748Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-08T01:38:04.946388+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-08T01:38:04.946388+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"On faithfulness and factuality in abstractive summarization","venue":null,"work_id":"fe2a13e8-3a58-4e16-b413-79a023e8ba01","year":1906},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:b5479f845852f83bb0456a7ce9bb8c776a588757d2e1588ea4e5d19b8bbfc3d3","observation_id":"d3fa9b46-c592-4ce4-ac8e-122679a23aa9","resolution":{"observed_at":"2026-05-19T09:23:04.029722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","venue":null,"work_id":"c74a26f1-aebb-43e5-a60e-4ff8a98a7db5","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:0ceb34a8e9f16fe607bd8c90e392ec5be8063459b434641019d14c945ab713e0","observation_id":"9f148d29-8d71-47e1-9675-32d963161384","resolution":{"observed_at":"2026-05-19T09:23:04.035964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.emnlp-main.741","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T13:37:06.726417Z","title":"Proceedings of the 2023","venue":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","work_id":"f952e39f-7d85-4a4f-9dd7-9da09cf2c1d8","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:40794d3996d12aa22c635eff642e9e828ab789882733f897805daf7187dcb6a7","observation_id":"37ad64c5-5ec1-47d0-82b8-881b2ee3c7bf","resolution":{"observed_at":"2026-05-19T09:22:13.942490Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-07-11T21:20:13.984389+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T21:20:13.984389+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Language models with conformal factuality guarantees","venue":null,"work_id":"cd94b694-ea9e-4bf5-8ace-4a8e47c52535","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:570e7c39cadf1630cb683c1471db845ec272824150ea5ff2d4343db05f4675da","observation_id":"04752fa0-26b7-46f0-99d6-a025daeec8e6","resolution":{"observed_at":"2026-05-19T09:23:04.155853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Data augmentation in Bayesian neural networks and the cold posterior effect","venue":null,"work_id":"0e239f66-00df-481e-8b63-ed4ad583c8c3","year":2022},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:15989ffdb2a52c526e87eec059eb51c50e4e3e00ac0a12f2de4eca3f890c171b","observation_id":"4da31421-c03d-439c-9b44-e63776e5105e","resolution":{"observed_at":"2026-05-19T09:23:04.133164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-1-4612-0745-0","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Neal.Bayesian Learning for Neural Networks, volume 118 ofLecture Notes in Statistics","venue":"Lecture notes in statistics","work_id":"32c87cce-b632-4b9f-a374-66d5756bc675","year":1996},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:5c65ae571ff43a3439f1428f360c40e924424a67c29a616fbc8ecd64c81511fa","observation_id":"6a36ab45-06b4-49d6-9542-459ffec0a768","resolution":{"observed_at":"2026-05-19T09:22:13.954491Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-01T12:38:07.076447+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-01T12:38:07.076447+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Kernel language entropy: Fine-grained uncertainty quantification for LLMs from semantic similarities","venue":null,"work_id":"da4151bf-86c7-4e0b-8f36-51fae7eeb77d","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:2d88a670b7876a65e4756c68be9f25109d1ee1fdb767777967395576465396af","observation_id":"aa35143e-a04e-4eac-948a-fcba815229df","resolution":{"observed_at":"2026-05-19T09:23:04.184966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Disentangling the roles of curation, data-augmentation and the prior in the cold posterior effect","venue":null,"work_id":"029e732d-23ca-419f-a9db-b304979b62be","year":2021},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:4241ca88a37c8d449daad9be26783f59e6c32b642a7f5c6dbc571a0486fcd097","observation_id":"c7209b4b-7238-4efd-8395-72c337fee669","resolution":{"observed_at":"2026-05-19T09:23:04.189362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1609/aaai.v29i1.9602","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Obtaining well calibrated probabilities using bayesian binning","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","work_id":"34281328-717c-4789-a36e-f9fcd05b7e2e","year":2015},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:4c80d78c8000cfd55d8641e7eba3d6723c725889f0b964ce26014c8485756c66","observation_id":"9729a636-9bf0-486f-a4df-abd29f06e0f5","resolution":{"observed_at":"2026-05-19T09:22:13.948196Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Semantic density: Uncertainty quantification for large language models through confidence measurement in semantic space","venue":null,"work_id":"c952315a-2d1e-4650-b68e-46a52bd3f480","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:cc167c8bbb0c27dd73689001ebdd861815ead4cf0e90ff5612f68603435df299","observation_id":"59ab5b03-ba62-4a62-9e57-4113a9b891c5","resolution":{"observed_at":"2026-05-19T09:23:04.110634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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 Scalable Laplace Approximation for Neural Networks","venue":null,"work_id":"fe77c191-ef00-4fd0-af8e-683f276020a0","year":2018},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:eb32c32e7a4d9cbad92ee1fa7d01dbf67ef311959cbfc72ee8cdc700ba9b58a9","observation_id":"544a7b3e-ce32-4b1c-bb3a-d59c3f55800d","resolution":{"observed_at":"2026-05-19T09:23:04.180218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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 scalable Laplace approximation for neural networks","venue":null,"work_id":"e798e945-18aa-4aa8-98be-4ed3c8091b7d","year":2018},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:29ab8b83f62bc3db5be44ac4a1bec3154528117ae8b647a516b17911e23493cf","observation_id":"50aff046-de85-4c9c-9b05-a0dc68c46226","resolution":{"observed_at":"2026-05-19T09:23:04.127856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1504.01896","last_updated":"2016-01-27T13:21:39Z","snapshot_observed_at":"2026-08-05T00:45:24.627950Z","submitted_at":"2015-04-08T10:13:16Z","title":"The Metropolis-Hastings algorithm","version":3},"cited_work":{"arxiv_id":"1504.01896","doi":null,"metadata_source":"pith","pith_arxiv_id":"1504.01896","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The Metropolis-Hastings algorithm","venue":"stat.CO","work_id":"26a3b67b-30d3-41aa-b5e0-18591531abc6","year":2015},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/1504.01896","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:71737f1a458492b47c450ea3a2cb72eebef6594e40df5983abe0f5e4f341949b","observation_id":"86c375ff-7960-4924-9fee-dad39ef8db32","resolution":{"observed_at":"2026-05-19T09:22:15.874698Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Optimal proposal distributions and adaptive MCMC","venue":null,"work_id":"f3b4aa3f-8cf7-481b-a970-cdd2742f05c0","year":2011},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:44d2b35a0c3764d162cb11c3ad6242038a843db0b6c559ad0bdc4ee284fc5c5f","observation_id":"2341d4b7-c1f2-400a-9b21-f2302a619bff","resolution":{"observed_at":"2026-05-19T09:23:04.086382Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Mean field theory for sigmoid belief networks","venue":null,"work_id":"1a744d6e-2a2b-427d-ac91-467739934142","year":1996},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:6da18a10fd4049fec7519c886ef550524cf8fc54e8988d18157a9253ffcf30b9","observation_id":"69afdeeb-94b7-462d-b6da-03dee8178503","resolution":{"observed_at":"2026-05-19T09:23:04.077957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04227","last_updated":"2025-06-17T16:19:14Z","snapshot_observed_at":"2026-08-03T03:40:06.947021Z","submitted_at":"2025-01-08T01:58:42Z","title":"Agent Laboratory: Using LLM Agents as Research Assistants","version":2},"cited_work":{"arxiv_id":"2501.04227","doi":"10.48550/arxiv.2501.04227","metadata_source":"pith","pith_arxiv_id":"2501.04227","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Agent Laboratory: Using LLM Agents as Research Assistants","venue":"cs.HC","work_id":"cb6e0bd7-2f2d-4052-875a-985ba5600340","year":2025},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2501.04227","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:0d9e7cf737b08fbf361cdc6400160f3ea97ed7321bd60452191773115d0748e6","observation_id":"3ba2d168-a5e2-4cf8-ad61-6a812bc28c86","resolution":{"observed_at":"2026-05-19T09:22:15.892515Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-05-25T19:23:20.272963+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T19:23:20.272963+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"An efficient minibatch acceptance test for metropolis-hastings","venue":null,"work_id":"74d2546e-7076-4bab-8901-4ab1344506e8","year":2018},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:5d969a3c62c1268849fd88af8c25d35abbaf57e33c7dc7cedb4b765cf86496a6","observation_id":"60bf237a-e8a8-47b5-bdb2-a08fe6a443ee","resolution":{"observed_at":"2026-05-19T09:23:04.082170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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 tutorial on conformal prediction","venue":null,"work_id":"b0c78c72-5e07-4f18-b3f3-633add37afd4","year":2008},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:fb224bed13cabef2f028425a3c464902b32a94a2904e16959b3f63a3c4476732","observation_id":"2f89e590-441f-4ddb-a651-847e14f0cd0b","resolution":{"observed_at":"2026-05-19T09:23:04.114291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Springer","venue":null,"work_id":"d21ff993-175a-4778-aa81-7ff6f8607491","year":2005},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:33bae54b5cd16d883292378357c6ca87db6414c71088c7004a96fd5f29017e5c","observation_id":"12d866f7-a449-45b9-ab52-9d4e81c55757","resolution":{"observed_at":"2026-05-19T09:23:04.159971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00035","last_updated":"2023-10-04T19:13:35Z","snapshot_observed_at":"2026-07-06T16:25:42.545425Z","submitted_at":"2023-09-29T16:38:38Z","title":"LoRA ensembles for large language model fine-tuning","version":2},"cited_work":{"arxiv_id":"2310.00035","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.00035","snapshot_observed_at":"2026-07-04T10:09:45.341936Z","title":"Lora ensembles for large language model fine-tuning.arXiv preprint arXiv:2310.00035","venue":null,"work_id":"95c627f4-8c06-4f58-90e7-d4241160b0f4","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2310.00035","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:a960fd575e3b038f14de9cbeb90267b1b662e85812440e71043e255465dad3d4","observation_id":"dd0f5501-d24f-4e05-a506-e637fcf20386","resolution":{"observed_at":"2026-05-19T09:22:15.948220Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou","venue":null,"work_id":"8592edb8-fe19-4b4b-8bf3-992f8143c03e","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:d8212e2fd2435c649f4095f1784d83f7efed5be81675080a098434aebf85db0e","observation_id":"d9b0ff3f-35a2-454d-8992-12cb02019d90","resolution":{"observed_at":"2026-05-19T09:23:04.201604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation","venue":null,"work_id":"63e54a3c-2e7c-4aa1-8875-f72203a19280","year":2021},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:68b92981a4f1172f1e4d892734b992c43e688ee661185b539ea3bfd3f4b0fe7c","observation_id":"7304ac50-3bbf-4e6f-bd22-4b0975c2e187","resolution":{"observed_at":"2026-05-19T09:23:04.118599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01257","last_updated":"2025-03-06T12:13:14Z","snapshot_observed_at":"2026-07-06T19:25:42.156795Z","submitted_at":"2024-10-02T06:05:52Z","title":"HelpSteer2-Preference: Complementing Ratings with Preferences","version":2},"cited_work":{"arxiv_id":"2410.01257","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.01257","snapshot_observed_at":"2026-07-03T01:37:30.542430Z","title":"Helpsteer2-preference: Complementing ratings with prefer- ences","venue":null,"work_id":"7c1f79f6-a9a9-41cc-9bfb-524bf82cc24a","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2410.01257","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:cd9a4d19f4b90e34c288f084fde6ad72e4509a4f667f9e3400089f44fd1b9276","observation_id":"755f426c-4980-4b25-9170-c6be89aa72b4","resolution":{"observed_at":"2026-05-19T09:22:15.929822Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05213","last_updated":"2024-10-18T02:55:27Z","snapshot_observed_at":"2026-08-07T14:13:54.280561Z","submitted_at":"2024-06-07T18:54:40Z","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","version":2},"cited_work":{"arxiv_id":"2406.05213","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.05213","snapshot_observed_at":"2026-07-03T18:08:46.925070Z","title":"On subjective uncertainty quantification and calibration in natural language generation","venue":null,"work_id":"e64175ac-bc80-4826-9666-c06c7653fd2c","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2406.05213","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:4085f8eb67f1c7c3ade188cdb11c2394537b4aa56557096ca645b0c667e4045c","observation_id":"4626bf7d-b2aa-48d6-ae42-45bc1ec3761c","resolution":{"observed_at":"2026-05-19T09:22:15.962131Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Jailbroken: How does LLM safety training fail? Advances in Neural Information Processing Systems, 36:80079–80110","venue":null,"work_id":"54a46e4b-91dd-4d14-be08-ae09020bc3e6","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:8917786661a43778353c3a4f927cbfed4c138a3272afa203812f42674ddbc6cb","observation_id":"446b6891-c756-41bc-bf9a-f3ab1f12e427","resolution":{"observed_at":"2026-05-19T09:23:04.032674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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","venue":null,"work_id":"503b2fdc-d9f2-42e4-a04c-8794ef47bef8","year":2022},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:2643a35cc1b535b0a3dedb1f9c65a9fd5e846a1f36e030ad49baba4573aa5339","observation_id":"a5afbbc3-760e-4c3c-90d1-efff001a7b65","resolution":{"observed_at":"2026-05-19T09:23:04.197239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.04368","last_updated":"2024-11-07T01:58:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-11-07T01:58:42Z","title":"Measuring short-form factuality in large language models","version":1},"cited_work":{"arxiv_id":"2411.04368","doi":"10.48550/arxiv.2411.04368","metadata_source":"pith","pith_arxiv_id":"2411.04368","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Measuring short-form factuality in large language models","venue":"cs.CL","work_id":"f8e490ab-7057-43fb-8c6d-06fc603836c7","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2411.04368","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:2867db4047c4a703977847a9f17b28f4507027894a84f7aa8d81067467657452","observation_id":"62e5ed4e-0cb3-4a94-a314-773e22ff5983","resolution":{"observed_at":"2026-05-19T09:22:15.910547Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Bayesian Learning via Stochastic Gradient Langevin Dynam- ics","venue":null,"work_id":"c3f453b1-82e8-48f8-8df1-b7a59645762f","year":null},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:75333d7036c6d98e166531286563445f8c71683b4de50b2c7d04ad2623bc4364","observation_id":"ce614dda-63b9-44ea-b1c0-a8c945f3d5ba","resolution":{"observed_at":"2026-05-19T09:23:04.013938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"e45abc7a-7f06-421e-82a9-3ee2fe5fa4eb","year":null},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:0fe2758a17705c17e28faeabc1453a1475339d528b440eee8f72a3ab14fbca27","observation_id":"d38f3e0a-d6ad-46aa-bb8b-4b9398231f86","resolution":{"observed_at":"2026-05-19T09:23:04.054378Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.12452","last_updated":"2024-10-06T05:55:28Z","snapshot_observed_at":"2026-08-09T22:45:15.337634Z","submitted_at":"2024-04-18T18:26:43Z","title":"Characterizing LLM Abstention Behavior in Science QA with Context Perturbations","version":2},"cited_work":{"arxiv_id":"2404.12452","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.12452","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Characterizing llm abstention behavior in science qa with context perturbations.arXiv preprint arXiv:2404.12452","venue":null,"work_id":"0969b73f-0200-488c-a94b-d3eb81b5e68d","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2404.12452","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:a238c52276c20f141a4460ec1ab2f7e3bc97231ccb1ee4f0cb1928cc2f2ee214","observation_id":"bc96b930-01b1-424a-aeab-af980a2f4932","resolution":{"observed_at":"2026-05-19T09:22:15.899014Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"How good is the Bayes posterior in deep neural networks really? In Proceedings of the 37th International Conference on Machine Learning, volume 119, pages 10248–10259","venue":null,"work_id":"9afc6e48-7eee-491d-995b-565b98aa5f22","year":2020},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:85a4cdde1c3281b126fb465587266a8d0f3ba4ec60c30084595655e995e55cde","observation_id":"493ff05b-d8fe-4134-846d-c23f24178f2d","resolution":{"observed_at":"2026-05-19T09:23:04.122860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Intelligent agents: Theory and practice","venue":null,"work_id":"42a2fca9-def6-468d-a703-46b47a2516e5","year":1995},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:6be5c4de0cc0134e51412ea10963c47a3e6f03fe313f8b4ba153d7d63f4b2ace","observation_id":"9a445467-46c1-44e1-aaab-1e39b2b4771c","resolution":{"observed_at":"2026-05-19T09:23:04.104947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"The rise and potential of large language model based agents: A survey","venue":null,"work_id":"bc7545e0-e551-452b-9c5c-3b5634876cde","year":2025},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:e0e11074976bda8d63e512e42a96c26f2e1de321d6deb06e740abb00db8b9be4","observation_id":"7f38c75f-1bf9-4403-aa9a-620fbde87dae","resolution":{"observed_at":"2026-05-19T09:23:04.205661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.11817","last_updated":"2025-02-13T08:11:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-22T10:26:14Z","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","version":2},"cited_work":{"arxiv_id":"2401.11817","doi":"10.48550/arxiv.2401.11817","metadata_source":"pith","pith_arxiv_id":"2401.11817","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","venue":"cs.CL","work_id":"9297385f-b00c-4c3e-b65b-204d2fdbbfe3","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2401.11817","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:75a5184f4e69469af4346a5e5888170fad9c8aebd9d3805e590f4ba6bf4729a4","observation_id":"e45dea1c-1134-4581-b733-e018da8ee24b","resolution":{"observed_at":"2026-05-19T09:22:15.904746Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.08066","last_updated":"2025-04-10T18:44:41Z","snapshot_observed_at":"2026-08-10T03:18:36.275195Z","submitted_at":"2025-04-10T18:44:41Z","title":"The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search","version":1},"cited_work":{"arxiv_id":"2504.08066","doi":"10.48550/arxiv.2504.08066","metadata_source":"pith","pith_arxiv_id":"2504.08066","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search","venue":"cs.AI","work_id":"fa04f346-ee20-4e9d-bf04-3ad3569a8ed1","year":2025},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2504.08066","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:fd1f2fbf04501585437be1c5c3f20a017e94f8da819ef051741a87658fa71fe0","observation_id":"4cdb6333-c0fc-4bf0-9c6d-519ff1024b60","resolution":{"observed_at":"2026-05-19T09:22:15.923759Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-05-25T19:23:27.206897+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T19:23:27.206897+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+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":"4c47b463-d1ad-4f02-9207-d6b4dd85b0b9","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:bb26eec658f61b8611be302e69056e92465a62bc5b477b61d3cfdd33ecdcd756","observation_id":"16615df9-30f0-48bc-9709-f89e8b97cdec","resolution":{"observed_at":"2026-05-19T09:23:04.136597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Bayesian low-rank adaptation for large language models","venue":null,"work_id":"85cbfdf0-b97f-4b46-89c0-7125916c4b2f","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:371a3550933864ad29fe489e8b98b9e2e58cf7d2fb00a5777db65917b0a0269b","observation_id":"d5e47119-4219-458e-b88e-e4a903e671a7","resolution":{"observed_at":"2026-05-19T09:23:04.145103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.14737","last_updated":"2026-05-05T09:22:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T11:10:36Z","title":"On Verbalized Confidence Scores for LLMs","version":2},"cited_work":{"arxiv_id":"2412.14737","doi":"10.48550/arxiv.2412.14737","metadata_source":"pith","pith_arxiv_id":"2412.14737","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"On Verbalized Confidence Scores for LLMs","venue":"cs.CL","work_id":"2f06055e-cb87-48e6-b737-6a084329edd5","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2412.14737","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:1e884e0a0e49668245d9fa7ab408c2e7094d8d8cb02016e7e6ac4cd7ef62797d","observation_id":"9a405a36-f65a-4f9c-b2eb-a3ca666d9f7d","resolution":{"observed_at":"2026-05-19T09:22:15.968495Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Optimizing generative AI by backpropagating language model feedback","venue":null,"work_id":"b9f7b82a-b94f-4bc7-bf7d-889760036758","year":2025},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:a90d1351a08d03a0c2847eb2c1539ee4149dd00d0579294d217a6ef89cea0e00","observation_id":"3a2ba4ba-9de4-4ff9-8a0b-e7ff477c1c44","resolution":{"observed_at":"2026-05-19T09:23:04.150493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Judging llm-as-a-judge with mt-bench and chatbot arena","venue":null,"work_id":"e2f91466-a8ba-4238-8142-7801e553fa10","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:69248ca02b841622248d16fb493cf16290374db4bdf231fe5a2798aa646d68cd","observation_id":"3b662838-bed4-4d6d-9015-dc9ca1e16686","resolution":{"observed_at":"2026-05-19T09:23:04.070877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"Large language models are human-level prompt engineers","venue":null,"work_id":"8ca9e3a0-e347-4849-b98b-b19cdcf3927a","year":2022},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:5b5e6f28ead30df54838ae104fcfbbb64f6f8d2c78f948c8df3642249c6e44a8","observation_id":"2117e68a-675e-4e40-81a0-3062ca3dc168","resolution":{"observed_at":"2026-05-19T09:23:04.074284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"GPTSwarm: Language Agents as Optimizable Graphs","venue":null,"work_id":"0578bf35-203e-440a-9308-16c945b87342","year":2024},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:a826302ddf91a8fb645b727b6fcd49683a9fbeb8a5d85a3f42cf13f0ab440438","observation_id":"ee4d3ecd-3374-4091-ad78-27ed8f69d6a0","resolution":{"observed_at":"2026-05-19T09:23:04.065584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.15043","last_updated":"2023-12-20T20:48:57Z","snapshot_observed_at":"2026-07-06T15:59:23.019044Z","submitted_at":"2023-07-27T17:49:12Z","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","version":2},"cited_work":{"arxiv_id":"2307.15043","doi":"10.48550/arxiv.2307.15043","metadata_source":"pith","pith_arxiv_id":"2307.15043","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","venue":"cs.CL","work_id":"3322fa86-1768-4677-8425-dd326b45e078","year":2023},"citing_paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-05-19T09:20:12.827871Z"},"links":{"cited_paper":"/paper/2307.15043","citing_paper":"/paper/2506.10060"},"observation_digest":"sha256:a4950db5c677fc811744b0c53e2aef058260e370ab7113315f0bab443aaf7288","observation_id":"80df81ac-fe22-4c21-b861-2c9cf89ea567","resolution":{"observed_at":"2026-05-19T09:22:15.935221Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-07-15T23:50:40.271168+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T23:50:40.271168+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.10060","last_updated":"2026-04-17T19:21:30Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T18:00:00Z","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems"},"reference_resolution":{"displayed":80,"state_counts":{"malformed_identifier":1,"metadata_mismatch":5,"parse_uncertain":1,"unresolved":1,"verified_exact":22,"verified_fuzzy":50},"total_outbound_references":80},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 80 of 80 outbound references and 7 inbound Pith citation observations for arXiv:2506.10060."}