{"as_of":"2026-08-04T23:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2568da3436dec0aeb4debca01b7e6d4bdb2a9dccc285cffad205a44c5e3d2b2f","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T16:34:11.393056Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2604.11141/citation-record","integrity":"/paper/2604.11141/integrity","json":"/paper/2604.11141/citation-record.json","paper":"/paper/2604.11141"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.17311","last_updated":"2023-11-29T02:07:09Z","snapshot_observed_at":"2026-07-06T16:54:10.590804Z","submitted_at":"2023-11-29T02:07:09Z","title":"Universal Self-Consistency for Large Language Model Generation","version":1},"cited_work":{"arxiv_id":"2311.17311","doi":"10.48550/arxiv.2311.17311","metadata_source":"pith","pith_arxiv_id":"2311.17311","snapshot_observed_at":"2026-07-10T21:57:37.889334Z","title":"ACM Transactions on Intelligent Systems and Technology, 15(3)","venue":"cs.CL","work_id":"9d1484c2-6ca2-4421-8b90-995b3adbc93c","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2311.17311","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:02ff9a6ea88ae8da1aa88ad4ff286de67bd8be74e6e76888cbcefb67f298d176","observation_id":"1209a7d1-5f90-44b9-a6e1-8cdb2385d884","resolution":{"observed_at":"2026-05-11T08:40:58.898152Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-05-23T16:25:44.09333+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T16:25:44.09333+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.03883","last_updated":"2024-03-11T02:01:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-07T17:45:31Z","title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models","version":2},"cited_work":{"arxiv_id":"2309.03883","doi":"10.48550/arxiv.2309.03883","metadata_source":"pith","pith_arxiv_id":"2309.03883","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models","venue":"cs.CL","work_id":"0f1b9a7a-0623-4efc-bed3-6dd997054681","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2309.03883","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:4a18e17a281997c9ab83723d9b0e4d4a7e9c7b17097896e4102c3a8422ff049b","observation_id":"26114c27-56ef-476e-8d02-36f738d5381d","resolution":{"observed_at":"2026-05-16T13:21:24.577996Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-04T15:46:25.710484Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":"2110.14168","doi":"10.1002/j.1545-","metadata_source":"pith","pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Training Verifiers to Solve Math Word Problems","venue":"cs.LG","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","year":2021},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:2ac01cb23668fd3175959092e265c31b06921af2cb41c0a2f927327bc303067c","observation_id":"9dba6d25-f4fb-4464-aa26-66286638a9fb","resolution":{"observed_at":"2026-05-11T08:40:58.890322Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.11495","last_updated":"2023-09-25T15:25:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-20T17:50:55Z","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","version":2},"cited_work":{"arxiv_id":"2309.11495","doi":"10.48550/arxiv.2309.11495","metadata_source":"pith","pith_arxiv_id":"2309.11495","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","venue":"cs.CL","work_id":"e9e9983c-a72a-4864-9005-cd09bbd7876c","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2309.11495","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:69e2508b352cc9f9c5f01db9bb3d1aee7598016e2d3891b787f532f34fc3b6f2","observation_id":"d40ff8ae-38ae-4fad-bcf3-668ea42ed403","resolution":{"observed_at":"2026-05-18T01:06:50.701847Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14325","last_updated":"2023-05-23T17:55:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-23T17:55:11Z","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","version":1},"cited_work":{"arxiv_id":"2305.14325","doi":"10.48550/arxiv.2305.14325","metadata_source":"pith","pith_arxiv_id":"2305.14325","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","venue":"cs.CL","work_id":"a543e65c-1cf8-4182-b03b-33c0cd2c65d5","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2305.14325","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:bdb15bdb8dc79e483c7b65fbca7304eba46c4397aff300ebc077f54ee6e8ca15","observation_id":"18fdde62-5829-4d8b-8729-c0557b91f5eb","resolution":{"observed_at":"2026-05-12T03:01:45.301651Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.10283","last_updated":"2020-10-28T11:29:52Z","snapshot_observed_at":"2026-07-06T09:22:05.728894Z","submitted_at":"2020-05-20T18:05:51Z","title":"Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation","version":2},"cited_work":{"arxiv_id":"2005.10283","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2005.10283","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"6173d670-c824-4c2d-b17c-d051e8c1f192","year":2020},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2005.10283","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:770ae9c4dfefa170b3281eb81c272eecddfb47da4931fb194242ab66f945587d","observation_id":"4f6fdc3d-72ee-471d-be0e-157d87299cd9","resolution":{"observed_at":"2026-05-11T08:40:58.886264Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02825","last_updated":"2024-10-11T18:37:37Z","snapshot_observed_at":"2026-08-03T23:37:44.574635Z","submitted_at":"2024-09-30T20:32:29Z","title":"Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG","version":2},"cited_work":{"arxiv_id":"2410.02825","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.02825","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ab7aab19-cfde-43bd-a7f7-3541eb1978b2","year":2024},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2410.02825","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:9c4f289bf020c22aac16b6dc373e783dbae3baded295800283720350c641f274","observation_id":"951a5000-0b56-4db0-b7e4-b654371a8b18","resolution":{"observed_at":"2026-05-11T08:40:58.867875Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.00863","last_updated":"2024-06-20T07:10:28Z","snapshot_observed_at":"2026-08-04T19:07:00.648791Z","submitted_at":"2024-02-29T23:03:19Z","title":"LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction","version":2},"cited_work":{"arxiv_id":"2403.00863","doi":"10.48550/arxiv.2403.00863","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.00863","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"arXiv:2403.00863","venue":null,"work_id":"99226e30-6797-4797-bc0a-229a305abbd4","year":2024},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2403.00863","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:729addccee1da6d03031cd8073ae77d5f90fc37d32532d04cba3d74ae9b5a7e5","observation_id":"3c55da1e-5047-4bbc-b115-d3707dba3c7e","resolution":{"observed_at":"2026-05-11T08:40:58.862990Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.21142","last_updated":"2025-07-23T08:00:20Z","snapshot_observed_at":"2026-08-03T06:29:00.469623Z","submitted_at":"2025-07-23T08:00:20Z","title":"Privacy Artifact ConnecTor (PACT): Embedding Enterprise Artifacts for Compliance AI Agents","version":1},"cited_work":{"arxiv_id":"2507.21142","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.21142","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"f4773041-ed63-449a-a99d-041d13db0307","year":2025},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2507.21142","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:5e504d7c74620b06ee21015ad8616d333867e4e2612270505f9362328638244e","observation_id":"1998b2f0-95fd-4d53-be0d-f3ad3ee94b3b","resolution":{"observed_at":"2026-05-11T08:40:58.924552Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.findings-emnlp.617","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T07:43:13.115547Z","title":"Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum B ayes Risk Decoding for Machine Translation","venue":null,"work_id":"18ed798c-89e7-4a4f-9ab6-bbc1808b4856","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:46915a1a65a5b61580e016e23d8f8dd456e51105af4b7ad2fa571178f68d0729","observation_id":"eb940c7d-7934-4c13-a389-57ea4b616558","resolution":{"observed_at":"2026-05-10T16:35:35.489919Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"0e848551-f633-491f-940b-a36926102319","year":2002},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:3476884231061b3d5742e706a067ecdb447cf99dce6b9687196c48224fde388a","observation_id":"86cdcae7-4237-4f31-a5ef-0bd8753338d7","resolution":{"observed_at":"2026-05-17T14:41:53.192580Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1145/3571730","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T13:37:06.800059Z","title":"Survey of Hallucination in Natural Language Generation","venue":"ACM Computing Surveys","work_id":"aa2fb99f-beb8-463c-8cd4-c575e96e2512","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:d8c1d3051f418d20297e5044da17c2cc018c20113d3778e2b062ff6b48998e59","observation_id":"d42fb58c-0b33-4cfc-bef0-a9e9403479ca","resolution":{"observed_at":"2026-05-10T16:35:35.488339Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T01:08:06.897682+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-04T01:08:06.897682+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-07-06T15:37:54.747810Z","submitted_at":"2023-06-05T03:32:26Z","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","version":3},"cited_work":{"arxiv_id":"2306.02561","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-07-04T19:50:11.019242Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion","venue":null,"work_id":"1accd5f4-8546-41b7-a132-6f6dde8df864","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:137d65371336bc2b4d17926f273f92882be12a0faf1b42af6467ed925d23e296","observation_id":"c0b067d5-8037-41d9-9a46-d834587c9638","resolution":{"observed_at":"2026-05-11T08:40:58.908052Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.09664","last_updated":"2023-04-15T12:55:45Z","snapshot_observed_at":"2026-07-06T14:53:27.667483Z","submitted_at":"2023-02-19T20:10:07Z","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","version":3},"cited_work":{"arxiv_id":"2302.09664","doi":"10.48550/arxiv.2302.09664","metadata_source":"pith","pith_arxiv_id":"2302.09664","snapshot_observed_at":"2026-07-11T03:07:50.343232Z","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","venue":"cs.CL","work_id":"d66d411b-c2c1-4cd6-8a6b-9fac872fa257","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2302.09664","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:d7a150910c0ad378c027caa9a8e409d453000b53b113f74898f9d5bf6d317499","observation_id":"0bfc0619-0d38-434b-8f29-c2d28a04bb1d","resolution":{"observed_at":"2026-05-12T18:00:05.468379Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.11401","last_updated":"2021-04-12T15:42:18Z","snapshot_observed_at":"2026-08-04T13:06:14.768886Z","submitted_at":"2020-05-22T21:34:34Z","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","version":4},"cited_work":{"arxiv_id":"2005.11401","doi":"10.1145/3626772.3657717","metadata_source":"pith","pith_arxiv_id":"2005.11401","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","venue":"cs.CL","work_id":"27eaec54-c105-4969-8188-da5f0fca3688","year":2020},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2005.11401","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:4cfed96ba7149dd73e93bd492e8768d82dc6ad8fbaa81ce353351ccc4a83ee33","observation_id":"4b4b5c54-0f23-418b-b191-86f01c8b2a8c","resolution":{"observed_at":"2026-05-11T08:40:58.842107Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03341","last_updated":"2024-06-26T14:11:53Z","snapshot_observed_at":"2026-07-06T15:38:58.578200Z","submitted_at":"2023-06-06T01:26:53Z","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","version":6},"cited_work":{"arxiv_id":"2306.03341","doi":"10.1109/tcds.2021.3071170","metadata_source":"pith","pith_arxiv_id":"2306.03341","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","venue":"cs.LG","work_id":"cea287bd-7a03-4e95-8b27-f9db5f278697","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2306.03341","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:594db78926a128733ce45773fe5a4901dbe3ccf6bbf0ca8ab8ee16ca3e8ce7b7","observation_id":"545510d7-6e10-4542-83c6-c5c5245d22bf","resolution":{"observed_at":"2026-05-15T09:21:59.414933Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19118","last_updated":"2024-10-09T02:41:21Z","snapshot_observed_at":"2026-08-01T16:20:31.337598Z","submitted_at":"2023-05-30T15:25:45Z","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","version":4},"cited_work":{"arxiv_id":"2305.19118","doi":"10.48550/arxiv.2305.19118","metadata_source":"pith","pith_arxiv_id":"2305.19118","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","venue":"cs.CL","work_id":"920bbf2b-e5b9-4d6e-a597-b82621d19ef9","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2305.19118","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:2f4cf0d2449c7ac9e27b8bbb411c68c6700ee8f67f993ccc42dfd88df9a3d3aa","observation_id":"2b68723f-206e-4d23-b8ac-819c637aff68","resolution":{"observed_at":"2026-05-14T00:00:16.565169Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03172","last_updated":"2023-11-20T23:09:34Z","snapshot_observed_at":"2026-07-06T15:51:12.179086Z","submitted_at":"2023-07-06T17:54:11Z","title":"Lost in the Middle: How Language Models Use Long Contexts","version":3},"cited_work":{"arxiv_id":"2307.03172","doi":"10.1162/tacl","metadata_source":"pith","pith_arxiv_id":"2307.03172","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Lost in the Middle: How Language Models Use Long Contexts","venue":"cs.CL","work_id":"37c05e13-4a24-44f8-a1c4-da1bbe7223aa","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2307.03172","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:637ec3b708b84115ef9b2e67a95513012fcfd87656c737dbd0b8587ca6c74b2f","observation_id":"e1826237-3635-4c8e-9a79-e3e29f4c8023","resolution":{"observed_at":"2026-05-11T08:40:58.752120Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18460","last_updated":"2025-06-03T17:47:36Z","snapshot_observed_at":"2026-07-06T20:42:33.518153Z","submitted_at":"2025-02-25T18:59:07Z","title":"DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers","version":2},"cited_work":{"arxiv_id":"2502.18460","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.18460","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"816148b9-385e-4093-aca3-556180286d6c","year":2025},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2502.18460","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:c0ae93781c17fca189a028449329f8126fdfe7c04d0d10efb373f23892bd1f5d","observation_id":"57cb6d5d-c8a6-46b7-99ad-124aa69b98d6","resolution":{"observed_at":"2026-05-11T08:40:58.855396Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08896","last_updated":"2023-10-11T17:43:28Z","snapshot_observed_at":"2026-07-06T15:03:55.982628Z","submitted_at":"2023-03-15T19:31:21Z","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","version":3},"cited_work":{"arxiv_id":"2303.08896","doi":"10.48550/arxiv.2303.08896","metadata_source":"pith","pith_arxiv_id":"2303.08896","snapshot_observed_at":"2026-07-10T18:27:31.339843Z","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","venue":"cs.CL","work_id":"90efebf6-4006-4176-9bf1-21a876571751","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2303.08896","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:f281990d49cde24dd0d3322fd12fa53a6766609fb1d66d508ea5462d23946727","observation_id":"56eae473-0c09-43b0-9297-4b014e2ac82c","resolution":{"observed_at":"2026-05-15T15:11:22.649439Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06872","last_updated":"2025-02-08T06:50:47Z","snapshot_observed_at":"2026-08-04T05:57:06.226812Z","submitted_at":"2025-02-08T06:50:47Z","title":"Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey","version":1},"cited_work":{"arxiv_id":"2502.06872","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.06872","snapshot_observed_at":"2026-07-11T00:47:43.085343Z","title":"Towards trustworthy re- trieval augmented generation for large language models: A survey","venue":"cs.CL","work_id":"5ceafaa3-5f79-4c22-aa54-7d513b44ba8a","year":2025},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2502.06872","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:58eb5c72fab43479a20250fb539d292935a122d2e712b86aad629b85cf61d906","observation_id":"ad48257c-2bbc-438a-ac56-79b694408a86","resolution":{"observed_at":"2026-05-11T08:40:58.802969Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.02155","last_updated":"2022-03-04T07:04:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-03-04T07:04:42Z","title":"Training language models to follow instructions with human feedback","version":1},"cited_work":{"arxiv_id":"2203.02155","doi":"10.1007/s00354-022-00198-8","metadata_source":"pith","pith_arxiv_id":"2203.02155","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Training language models to follow instructions with human feedback","venue":"cs.CL","work_id":"52aff42f-4fa9-4fcf-bdb3-1459b9bebf65","year":2022},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2203.02155","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:0c6b88d871fbad1c8d27b6e0c5e2b5a3d121c1c7f7fe1f2ed37a77c415ccbece","observation_id":"c4a254bf-c574-44ed-bd40-b882402eb2b1","resolution":{"observed_at":"2026-05-11T08:40:58.808221Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14739","last_updated":"2023-05-24T05:19:15Z","snapshot_observed_at":"2026-07-06T15:32:14.701994Z","submitted_at":"2023-05-24T05:19:15Z","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","version":1},"cited_work":{"arxiv_id":"2305.14739","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.14739","snapshot_observed_at":"2026-07-04T06:49:37.587344Z","title":"arXiv preprint arXiv:2305.14739 (2023)","venue":null,"work_id":"b6d64925-d075-46ce-ab1a-72500a3b4457","year":2024},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2305.14739","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:5caffc02517cac407ae15e289fa4b136048f3399de20f60c3c8241e7f61fc20e","observation_id":"c7802480-b33d-4cff-862d-33aad4bd998a","resolution":{"observed_at":"2026-05-11T08:40:58.821870Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"ba8c3f63-1687-46c1-a39b-d4de72178899","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:dcd5d316b0dff291a02ba21de7299313c6da9487aa772efabab4dbcb29999ba3","observation_id":"bbabe434-605c-4aa9-8f82-2cf5d744d459","resolution":{"observed_at":"2026-05-17T14:41:53.202441Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.04388","last_updated":"2023-12-09T21:25:02Z","snapshot_observed_at":"2026-08-02T07:12:38.105035Z","submitted_at":"2023-05-07T22:44:25Z","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","version":2},"cited_work":{"arxiv_id":"2305.04388","doi":"10.1109/cdics61497.2023.00014","metadata_source":"pith","pith_arxiv_id":"2305.04388","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","venue":"cs.CL","work_id":"6ed38946-7275-41a4-91b9-b9f7fa043250","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2305.04388","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:2d3a158c6ef5134f3ad4ff217038a64a62ef392000316633d8682a5a2d2c8498","observation_id":"e7125d8a-ca50-43c0-ade5-6893fb102cff","resolution":{"observed_at":"2026-05-15T12:01:19.882845Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11171","last_updated":"2023-03-07T17:57:37Z","snapshot_observed_at":"2026-07-06T12:50:22.773056Z","submitted_at":"2022-03-21T17:48:52Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","version":4},"cited_work":{"arxiv_id":"2203.11171","doi":"10.1101/2025.04.03.646459","metadata_source":"pith","pith_arxiv_id":"2203.11171","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","venue":"cs.CL","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","year":2022},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2203.11171","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:6db9a3af47f726804c30d53241353f44010b649fac0f37ed12e8c254904fb4a6","observation_id":"ef48c5eb-805c-4ac0-9b45-744023dfb7d7","resolution":{"observed_at":"2026-05-11T08:40:58.782395Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-05-21T18:52:42.88633+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T18:52:42.88633+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01219","last_updated":"2025-09-14T09:34:46Z","snapshot_observed_at":"2026-07-06T16:13:46.112815Z","submitted_at":"2023-09-03T16:56:48Z","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","version":3},"cited_work":{"arxiv_id":"2309.01219","doi":"10.48550/arxiv.2309.01219","metadata_source":"pith","pith_arxiv_id":"2309.01219","snapshot_observed_at":"2026-07-10T08:06:57.486498Z","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","venue":"cs.CL","work_id":"1f8027cc-877a-494d-b9e5-a01d32d3d76f","year":2023},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2309.01219","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:ae53ca7f435d67d4009a1936a3f78b513ae6c7cb2a075f2da9ad9fc4571dde38","observation_id":"d47e2458-c31f-4df1-bcec-0ddc3e397a01","resolution":{"observed_at":"2026-05-12T14:21:16.592379Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-18T08:21:11.191936+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-18T08:21:11.191936+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.17289","last_updated":"2025-07-26T21:24:32Z","snapshot_observed_at":"2026-07-06T22:01:30.654331Z","submitted_at":"2025-07-23T07:51:10Z","title":"Compliance Brain Assistant: Conversational Agentic AI for Assisting Compliance Tasks in Enterprise Environments","version":3},"cited_work":{"arxiv_id":"2507.17289","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.17289","snapshot_observed_at":"2026-06-29T21:13:59.515681Z","title":"sparse hallucination","venue":null,"work_id":"9ddfed49-5b6d-46ee-a639-cb418836f586","year":2025},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"cited_paper":"/paper/2507.17289","citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:190baa7259738cbf8504a45a67ee7e5ab60e7cd2ce1bbe2f57d4b5cf290b2ac9","observation_id":"3fd10f9a-dc04-4649-b328-d243c928a74b","resolution":{"observed_at":"2026-05-11T08:40:58.774960Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"c3f3f416-23c4-4faf-82f6-4f3c0cd52029","year":null},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:e316eab4e506f55f19b9d59c960722326eb0cf0a469c6ea6931ee07ab250d6d0","observation_id":"7412d43b-858a-43bb-b75b-db9a13ae1caf","resolution":{"observed_at":"2026-05-17T14:41:53.199312Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"I don't know","venue":null,"work_id":"3df14742-c844-45ca-8269-b512ac63113d","year":null},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:a45bba4d4dbfe7d71938c5be909d3d7aadd23f66a4e8da6862c0c8c20a21e656","observation_id":"7024adf6-75d6-413d-a656-4232c79aa06d","resolution":{"observed_at":"2026-05-17T14:41:53.195940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"truthful","venue":null,"work_id":"f0f2fe4f-f88b-44a7-99ba-856abe06cec5","year":2026},"citing_paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T16:34:11.393056Z"},"links":{"citing_paper":"/paper/2604.11141"},"observation_digest":"sha256:2de2660da15f4db270e2791ffb6581690f7b1d7af491f14748f6d4f8e757d211","observation_id":"836c5594-9a69-4d57-8648-5bdc85986f51","resolution":{"observed_at":"2026-05-17T14:41:53.189326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.11141","last_updated":"2026-04-13T07:57:48Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T22:59:36.571641Z","submitted_at":"2026-04-13T07:57:48Z","title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":3,"verified_exact":24,"verified_fuzzy":2},"total_outbound_references":31},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2604.11141."}