{"as_of":"2026-08-09T21:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:570b4cdadb0385c835add3a4319c1215c6df059240a303dded1d49a9d7a85dca","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":48,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T11:22:28.893446Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T19:50:11.019242Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2406.18665","last_updated":"2025-02-23T08:50:33Z","snapshot_observed_at":"2026-07-30T15:06:18.011623Z","submitted_at":"2024-06-26T18:10:22Z","title":"RouteLLM: Learning to Route LLMs with Preference Data","version":4},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-05-11T23:27:40.397360Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2406.18665"},"observation_digest":"sha256:495e8c593ef6c199e923ddcc6dff3042a9cb8612ad070c0554c457af4ac6ded2","observation_id":"9a2cd744-77f5-4e1d-92ce-a88234198074","resolution":{"observed_at":"2026-05-11T23:27:40.609975Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2407.21787","last_updated":"2024-12-30T19:03:24Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:57:25Z","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-12T04:42:23.297389Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2407.21787"},"observation_digest":"sha256:9ff3453ba5f504f3ecc55afe2991067bc49173e9f4928fb7b2c2c2c304f13dfe","observation_id":"906c4d2c-0195-49fb-8b93-d3d0fdb74bd5","resolution":{"observed_at":"2026-05-12T04:42:23.593082Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2410.18451","last_updated":"2024-10-24T06:06:26Z","snapshot_observed_at":"2026-08-07T05:53:12.643515Z","submitted_at":"2024-10-24T06:06:26Z","title":"Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-17T16:18:01.560780Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2410.18451"},"observation_digest":"sha256:f669b0b39f6289d28be0b9640c74d4d7c8ce0c1cdfab4c05a3bcab245fa3b04f","observation_id":"4e442fa7-fe4f-40bf-9439-cd1ae760b253","resolution":{"observed_at":"2026-05-17T16:18:01.631525Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-09T11:22:28.893446Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02743","last_updated":"2025-02-04T22:09:43Z","snapshot_observed_at":"2026-08-09T16:32:54.357740Z","submitted_at":"2025-02-04T22:09:43Z","title":"LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T11:22:28.893446Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2502.02743"},"observation_digest":"sha256:304a5c33dfdabb91f12ec1786aaefc2bb4f8e6fbecd60d53b74a0d1e534c2906","observation_id":"8caa511e-12f4-4ef1-917a-a22af59ca594","resolution":{"observed_at":"2026-08-09T11:22:28.893446Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-09T10:44:43.531286Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.02908","last_updated":"2025-02-05T06:09:26Z","snapshot_observed_at":"2026-08-09T10:37:13.524355Z","submitted_at":"2025-02-05T06:09:26Z","title":"COSMosFL: Ensemble of Small Language Models for Fault Localisation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T10:44:43.531286Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2502.02908"},"observation_digest":"sha256:aa4212350eebe850426bae7392a327e9d8552b9bcedeb870e063444c7a9e9770","observation_id":"181e6b0a-2277-48fa-a44e-5381194b7130","resolution":{"observed_at":"2026-08-09T10:44:43.531286Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-08T13:08:22.646485Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.07350","last_updated":"2025-09-06T07:54:06Z","snapshot_observed_at":"2026-08-08T12:59:48.269781Z","submitted_at":"2025-02-11T08:22:12Z","title":"KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-08T13:08:22.646485Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2502.07350"},"observation_digest":"sha256:e92dcc8b7e6bc8be295b3cd57733a11595f8eeaa773c92bb17a4579ce2425129","observation_id":"520b2511-708c-4cc1-92ca-65140a3a2d77","resolution":{"observed_at":"2026-08-08T13:08:22.646485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T19:40:07.766237Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10051","last_updated":"2025-02-17T15:30:22Z","snapshot_observed_at":"2026-08-08T15:22:06.356585Z","submitted_at":"2025-02-14T10:00:20Z","title":"ORI: O Routing Intelligence","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T19:40:07.766237Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2502.10051"},"observation_digest":"sha256:a95b6412f462c7d70eae6dd7103bb3614ceb5ddf578b60143a1ad72fd227595b","observation_id":"cca31f8b-28f7-4787-952c-a5dcb5af890a","resolution":{"observed_at":"2026-08-07T19:40:07.766237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2505.12601","last_updated":"2026-05-14T18:08:42Z","snapshot_observed_at":"2026-08-02T11:09:30.375825Z","submitted_at":"2025-05-19T01:33:41Z","title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-22T15:13:28.927880Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2505.12601"},"observation_digest":"sha256:eb77111befe0b21d5b13916e9f67b5b13b5e06c058db41794b768045089376d3","observation_id":"46f4965b-a0fd-4222-977b-7393c212c9cf","resolution":{"observed_at":"2026-05-22T15:14:57.453781Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T15:11:17.439648Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion.arXiv preprint arXiv:2306.02561,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.16221","last_updated":"2025-05-22T04:46:04Z","snapshot_observed_at":"2026-08-08T05:31:07.480386Z","submitted_at":"2025-05-22T04:46:04Z","title":"LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:11:17.439648Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2505.16221"},"observation_digest":"sha256:8380c432c709e46a49855cfd329dfa86bde1161ee6f07e96579f8afaaf01792f","observation_id":"49450460-5ef7-4d2f-872b-e5b496c3bb6f","resolution":{"observed_at":"2026-08-07T15:11:17.439648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T15:02:26.329866Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.17151","last_updated":"2025-05-22T10:16:56Z","snapshot_observed_at":"2026-08-08T11:14:11.223688Z","submitted_at":"2025-05-22T10:16:56Z","title":"Bayesian Optimization for Enhanced Language Models: Optimizing Acquisition Functions","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:02:26.329866Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2505.17151"},"observation_digest":"sha256:c76ea8ffdc26ef0d5ab9b1a40cd928273c7cdb270f6e338468285e528eb46032","observation_id":"d6597a11-85a1-48dc-8b7c-a64ae0802d7d","resolution":{"observed_at":"2026-08-07T15:02:26.329866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T14:48:08.836617Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.17552","last_updated":"2025-05-30T09:21:07Z","snapshot_observed_at":"2026-08-07T15:39:44.592768Z","submitted_at":"2025-05-23T06:56:55Z","title":"Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T14:48:08.836617Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2505.17552"},"observation_digest":"sha256:fdd9f9a8dca1491b69c3b8d47ccd307078442e9517fbfa84c3badf53edd8af7c","observation_id":"69ef58c9-a619-4f44-aec4-2f4dc4773214","resolution":{"observed_at":"2026-08-07T14:48:08.836617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T12:32:21.788871Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24273","last_updated":"2025-05-30T06:49:00Z","snapshot_observed_at":"2026-08-07T18:34:20.398845Z","submitted_at":"2025-05-30T06:49:00Z","title":"How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T12:32:21.788871Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2505.24273"},"observation_digest":"sha256:e3bc6bf03b903be62b49f73c53252c1b7b109e5aa8fdff04809ccab1216804c7","observation_id":"3bc6cbd6-ce91-4ebe-b662-afd965667325","resolution":{"observed_at":"2026-08-07T12:32:21.788871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T11:04:07.031741Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03637","last_updated":"2025-07-07T09:53:22Z","snapshot_observed_at":"2026-08-08T03:23:19.289933Z","submitted_at":"2025-06-04T07:30:16Z","title":"RewardAnything: Generalizable Principle-Following Reward Models","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T11:04:07.031741Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2506.03637"},"observation_digest":"sha256:157cf2aadce5fd5aa8014ea9e97b601a913ac39501b90f5032511b7d44749ce4","observation_id":"83ab8c1a-22ac-4a8f-9eac-3cb3de3b8b80","resolution":{"observed_at":"2026-08-07T11:04:07.031741Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T05:56:56.989615Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06579","last_updated":"2025-06-06T23:13:08Z","snapshot_observed_at":"2026-08-07T05:51:34.237166Z","submitted_at":"2025-06-06T23:13:08Z","title":"Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T05:56:56.989615Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2506.06579"},"observation_digest":"sha256:8f0cd14c842eed2fce4274f14930ee8483e1a251667278db0d176c461fb7e68a","observation_id":"b897ca20-8400-4e57-94b6-ba9e268f6016","resolution":{"observed_at":"2026-08-07T05:56:56.989615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T05:42:38.707387Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07440","last_updated":"2025-06-09T05:33:28Z","snapshot_observed_at":"2026-08-07T21:40:46.271523Z","submitted_at":"2025-06-09T05:33:28Z","title":"Federated In-Context Learning: Iterative Refinement for Improved Answer Quality","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T05:42:38.707387Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2506.07440"},"observation_digest":"sha256:c46195ccb1d1542a34a3bafb2c22903175f714e1e557d2eabe6206d5cdf78239","observation_id":"a5d7070e-ea2d-45b0-9f0f-1f8dc7e67019","resolution":{"observed_at":"2026-08-07T05:42:38.707387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T05:11:38.299577Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.08626","last_updated":"2025-06-11T03:47:20Z","snapshot_observed_at":"2026-08-08T02:59:03.014761Z","submitted_at":"2025-06-10T09:44:03Z","title":"Leveraging LLMs to Evaluate Usefulness of Document","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:38.299577Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2506.08626"},"observation_digest":"sha256:036f881f3e37f0bf4c0e9ba8aa996a021f142ada4fe7b2c7a34a08ee0a111e51","observation_id":"7793a646-d39c-4b91-93d5-06c8be2ec339","resolution":{"observed_at":"2026-08-07T05:11:38.299577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T05:10:47.699915Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion.arXiv preprint arXiv:2306.02561, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.08643","last_updated":"2025-06-10T09:55:53Z","snapshot_observed_at":"2026-08-07T22:00:08.822941Z","submitted_at":"2025-06-10T09:55:53Z","title":"MEMETRON: Metaheuristic Mechanisms for Test-time Response Optimization of Large Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:10:47.699915Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2506.08643"},"observation_digest":"sha256:f0b3b14c36ea5a7ae4bee8aa9bd676560aff0989c2b8479489834d0839e11938","observation_id":"6b271064-6b92-40f7-b857-bd7ba9331e1c","resolution":{"observed_at":"2026-08-07T05:10:47.699915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-07T04:30:43.639675Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.10525","last_updated":"2025-06-12T09:43:48Z","snapshot_observed_at":"2026-08-08T21:26:08.789047Z","submitted_at":"2025-06-12T09:43:48Z","title":"AdaptiveLLM: A Framework for Selecting Optimal Cost-Efficient LLM for Code-Generation Based on CoT Length","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T04:30:43.639675Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2506.10525"},"observation_digest":"sha256:e0bef07f5abba48f8cca58fedd1199cf08a91f852845e9ad77432244b157fa25","observation_id":"38c27a63-7aab-4904-91fd-52fa2f6f72cc","resolution":{"observed_at":"2026-08-07T04:30:43.639675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-06T22:05:27.625864Z","title":"Jiang, X","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22716","last_updated":"2025-06-28T01:52:50Z","snapshot_observed_at":"2026-08-06T21:57:22.791105Z","submitted_at":"2025-06-28T01:52:50Z","title":"BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T22:05:27.625864Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2506.22716"},"observation_digest":"sha256:bc8df9a8e26632081e52029cecb43cb3efe183e3f79380b150214f7c50f38af6","observation_id":"483fd1da-e1d9-4aa9-9052-affc7e5e6bf2","resolution":{"observed_at":"2026-08-06T22:05:27.625864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-06T18:12:58.673023Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion.arXiv preprint arXiv:2306.02561, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08960","last_updated":"2025-07-11T18:34:07Z","snapshot_observed_at":"2026-08-06T18:05:47.861506Z","submitted_at":"2025-07-11T18:34:07Z","title":"How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:58.673023Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2507.08960"},"observation_digest":"sha256:983a9f5bd3d1db0ed3b6fb8f8d98e1fae01e37821315b628a3aeb00d05224682","observation_id":"908b419e-cb3d-45e8-b949-634ed9bfb66c","resolution":{"observed_at":"2026-08-06T18:12:58.673023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2507.14200","last_updated":"2026-05-15T13:08:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-14T16:17:11Z","title":"A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-05-21T23:26:38.457193Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2507.14200"},"observation_digest":"sha256:640602d4b6236a0c1f4692270529885b5ab8fe9fec325029178c2337d929ccf6","observation_id":"36a2f02c-f215-46ad-bd40-b0da709f528f","resolution":{"observed_at":"2026-05-21T23:30:46.055962Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-05T17:15:15.279206Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16757","last_updated":"2025-08-22T19:30:04Z","snapshot_observed_at":"2026-08-08T21:45:21.487237Z","submitted_at":"2025-08-22T19:30:04Z","title":"How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-05T17:15:15.279206Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2508.16757"},"observation_digest":"sha256:352543d6120c57c136711b04d9210fad1fbcb12263aa2a8a2b9f728d1230bee1","observation_id":"a88aacd8-5d3b-4c5d-b1d6-7c35231fde31","resolution":{"observed_at":"2026-08-05T17:15:15.279206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-05T16:18:45.844235Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18763","last_updated":"2025-08-26T07:41:33Z","snapshot_observed_at":"2026-08-08T03:30:31.091934Z","submitted_at":"2025-08-26T07:41:33Z","title":"Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-05T16:18:45.844235Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2508.18763"},"observation_digest":"sha256:e45a53a41f05c1c12a48d4c6d4221f280dee92b704c18cf1b5052d0068c38567","observation_id":"7c622c49-da51-4300-b926-d025b53eb3b7","resolution":{"observed_at":"2026-08-05T16:18:45.844235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-05T05:04:52.686656Z","title":"arXiv preprint arXiv:2306.02561 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.05764","last_updated":"2025-09-06T16:29:42Z","snapshot_observed_at":"2026-08-05T05:04:52.222364Z","submitted_at":"2025-09-06T16:29:42Z","title":"DRF: LLM-AGENT Dynamic Reputation Filtering Framework","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T05:04:52.686656Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2509.05764"},"observation_digest":"sha256:a71b9ce0e35255a9323b169da7364f7e4dadb05a279505f02faa5129be68af88","observation_id":"aae3b31e-57a4-4630-97df-095af7344139","resolution":{"observed_at":"2026-08-05T05:04:52.686656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-04T22:03:01.998475Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion.arXiv preprint arXiv:2306.02561,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.07571","last_updated":"2025-09-11T02:09:54Z","snapshot_observed_at":"2026-08-09T10:55:33.372063Z","submitted_at":"2025-09-09T10:15:42Z","title":"Towards Generalized Routing: Model and Agent Orchestration for Adaptive and Efficient Inference","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T22:03:01.998475Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2509.07571"},"observation_digest":"sha256:16d773f3baa99e99d91508b6fc6dcaebdd80d27de805e1984f086ea1d3b3a572","observation_id":"9747c1c0-3807-410f-bf75-e47dc570bee1","resolution":{"observed_at":"2026-08-04T22:03:01.998475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-04T10:36:23.672689Z","title":"Ren, and B","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.09517","last_updated":"2026-07-02T09:56:45Z","snapshot_observed_at":"2026-08-08T00:15:14.362197Z","submitted_at":"2025-10-10T16:28:43Z","title":"StatEval: A Comprehensive Benchmark for Large Language Models in Statistics","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T10:36:23.672689Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2510.09517"},"observation_digest":"sha256:24b095442a0519cf51523724ff37522edf0bb532daaf9ea2062ab12b6deda745","observation_id":"7791bab7-543f-4490-9da7-f376ccb0d767","resolution":{"observed_at":"2026-08-04T10:36:23.672689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2512.23213","last_updated":"2026-04-25T15:41:44Z","snapshot_observed_at":"2026-08-02T22:41:07.172721Z","submitted_at":"2025-12-29T05:25:49Z","title":"Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-05-16T19:57:03.999154Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2512.23213"},"observation_digest":"sha256:320fed01f4b736ecc6073caf785dbd13e10174a95e8d31ea7fd9be32ab847d39","observation_id":"5529df80-0829-4460-bc9d-24cbda953884","resolution":{"observed_at":"2026-05-16T19:58:22.743646Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2602.02350","last_updated":"2026-05-13T02:31:43Z","snapshot_observed_at":"2026-08-06T12:45:12.155521Z","submitted_at":"2026-02-02T17:15:17Z","title":"Context Learning for Multi-Agent Discussion","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-16T08:08:39.182921Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2602.02350"},"observation_digest":"sha256:c79dd5f5be8f8be70f656171a237e6556a9b364a3bc36f9034c55845d24b046b","observation_id":"34049d38-ef2b-4938-bc4e-59cb377bcd12","resolution":{"observed_at":"2026-05-16T08:10:45.520815Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-02T17:52:54.761095Z","title":"LLM- Blender: Ensembling large language models with pair- wise ranking and generative fusion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.20324","last_updated":"2026-07-21T00:19:03Z","snapshot_observed_at":"2026-08-07T10:38:46.914990Z","submitted_at":"2026-03-20T00:50:53Z","title":"When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T17:52:54.761095Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2603.20324"},"observation_digest":"sha256:23d2690a36a08ebadfa215b02daefea44cecfca90671db002904c14e953f62e0","observation_id":"4c94298c-68e7-4207-a626-7e755e893ae6","resolution":{"observed_at":"2026-08-02T17:52:54.761095Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2604.10023","last_updated":"2026-04-11T04:32:59Z","snapshot_observed_at":"2026-07-06T22:58:43.155246Z","submitted_at":"2026-04-11T04:32:59Z","title":"FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-10T15:55:16.158145Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2604.10023"},"observation_digest":"sha256:d73efc1d8984560d63f98a0c1f6d13aec4927f17158f1539763557e0497e1eb5","observation_id":"d8504df3-7680-4447-b66e-8e1d4ba037ec","resolution":{"observed_at":"2026-05-11T09:36:07.060071Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"sha256:9e1881c4e11c9f95ac8beae6afd50eaf5f02ef30b7b52eefb796cb24df540542","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 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2604.15728","last_updated":"2026-04-17T06:02:27Z","snapshot_observed_at":"2026-07-06T23:03:12.000381Z","submitted_at":"2026-04-17T06:02:27Z","title":"Privacy-Preserving LLMs Routing","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T08:32:43.015370Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2604.15728"},"observation_digest":"sha256:4a7871f3dc26954e894da7c8918c35bcf4244eec67c44146f87d8ddc0f5705ad","observation_id":"6d191fb7-be81-4ebc-a3f4-4b1be9cc4839","resolution":{"observed_at":"2026-05-10T08:32:51.612098Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2604.17950","last_updated":"2026-04-20T08:30:28Z","snapshot_observed_at":"2026-08-02T22:39:47.888438Z","submitted_at":"2026-04-20T08:30:28Z","title":"CADMAS-CTX: Contextual Capability Calibration for Multi-Agent Delegation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-10T05:31:27.700576Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2604.17950"},"observation_digest":"sha256:7306ffc10c7a05aba4d10565825e6ea35dc82689aaa68ff478bebaf877c0b56e","observation_id":"814a8f01-eb21-4054-8780-a411504833ac","resolution":{"observed_at":"2026-05-10T05:36:02.123951Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2605.06987","last_updated":"2026-05-07T22:05:23Z","snapshot_observed_at":"2026-07-31T05:30:22.249144Z","submitted_at":"2026-05-07T22:05:23Z","title":"Response Time Enhances Alignment with Heterogeneous Preferences","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-05-11T01:04:26.288913Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2605.06987"},"observation_digest":"sha256:236d27558cfbfe636c4da40bbf64302d8a547da02300a8347d3c2e94dada4262","observation_id":"74e8d109-16ab-402f-8277-8a449cbbda41","resolution":{"observed_at":"2026-05-11T04:46:00.166854Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2605.15207","last_updated":"2026-07-08T14:36:15Z","snapshot_observed_at":"2026-07-12T17:52:34.996306Z","submitted_at":"2026-05-01T23:42:57Z","title":"TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-05-19T18:01:06.649723Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2605.15207"},"observation_digest":"sha256:07d8189780dbbff483acec3fe3d893aaf3894ce6e7d0c664ac227ad44c939032","observation_id":"4e4b216f-ee15-44a4-9083-a507888d1e62","resolution":{"observed_at":"2026-05-19T18:02:42.355523Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2605.27810","last_updated":"2026-05-27T01:04:36Z","snapshot_observed_at":"2026-08-02T00:44:01.035863Z","submitted_at":"2026-05-27T01:04:36Z","title":"LRanker: LLM Ranker for Massive Candidates","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-29T10:30:39.472561Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2605.27810"},"observation_digest":"sha256:de053c0a1757a5c727cff28e16e7f4e0125159ad42605425ad66d11fadb140c8","observation_id":"7e315b3f-ef97-41f6-936b-b235ca51369c","resolution":{"observed_at":"2026-06-29T10:33:18.835695Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2606.07392","last_updated":"2026-06-05T15:29:17Z","snapshot_observed_at":"2026-07-06T23:47:00.425715Z","submitted_at":"2026-06-05T15:29:17Z","title":"Online Pandora's Box for Contextual LLM Cascading","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-06-27T21:59:43.429931Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2606.07392"},"observation_digest":"sha256:46a47c999dc646165abebc572ce36234917b73e6eeaf0528834266330dff1bab","observation_id":"1aaf0e39-0fb3-47c8-9a66-7389d7fc0356","resolution":{"observed_at":"2026-07-02T17:37:14.307640Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2606.18774","last_updated":"2026-06-19T09:33:33Z","snapshot_observed_at":"2026-08-06T18:36:21.111914Z","submitted_at":"2026-06-17T07:35:10Z","title":"RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-26T21:17:29.543901Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2606.18774"},"observation_digest":"sha256:58e37b71c9edf572e7ffafe58d619adeb3304d9b682169313c2eb83c9a018875","observation_id":"c35e507b-9b72-4fa9-9768-bb6a55d13dea","resolution":{"observed_at":"2026-07-04T00:19:13.486216Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2606.25476","last_updated":"2026-07-21T11:09:35Z","snapshot_observed_at":"2026-08-06T23:05:07.064301Z","submitted_at":"2026-06-24T07:00:53Z","title":"A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-06-25T20:58:53.119386Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2606.25476"},"observation_digest":"sha256:8cdc643b4f169d98ed3b50c7ab98ef77586629210d39aa1be6477a7b79794324","observation_id":"cfa73881-c34d-4d1d-a5f2-845c3898e66e","resolution":{"observed_at":"2026-07-04T19:50:11.020770Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-02T10:16:44.905476Z","title":"arXiv preprint arXiv:2306.02561 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25476","last_updated":"2026-07-21T11:09:35Z","snapshot_observed_at":"2026-08-06T23:05:07.064301Z","submitted_at":"2026-06-24T07:00:53Z","title":"A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-02T10:16:44.905476Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2606.25476"},"observation_digest":"sha256:d28e0d75465d4f5539e79c63fe85ac79bf1cdb2fee7575e404419a5623c2dfed","observation_id":"62b80367-163c-4fcd-bba9-360fedd7756d","resolution":{"observed_at":"2026-08-02T10:16:44.905476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2606.27288","last_updated":"2026-06-25T17:06:06Z","snapshot_observed_at":"2026-08-06T18:40:51.405864Z","submitted_at":"2026-06-25T17:06:06Z","title":"When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-26T04:20:02.722108Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2606.27288"},"observation_digest":"sha256:91b58034becbcb49ed671b4a3715d8fb0b62ec7eab49688261272ba1dbb80ebb","observation_id":"e46e67cd-140b-4bef-8264-3858b6cb8fa1","resolution":{"observed_at":"2026-07-04T14:19:53.623152Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":"2607.00053","last_updated":"2026-06-30T01:46:26Z","snapshot_observed_at":"2026-07-07T00:05:41.920778Z","submitted_at":"2026-06-30T01:46:26Z","title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-07-02T18:19:43.146102Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2607.00053"},"observation_digest":"sha256:1118297f99650af5f782276223080f3b282d647b6ddaba8154d41f134dc85f7b","observation_id":"292be8c5-a6da-402a-8463-7f6c9041b839","resolution":{"observed_at":"2026-07-02T18:37:16.509464Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-07-11T13:53:36.775836Z","title":"arXiv preprint arXiv:2306.02561 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04763","last_updated":"2026-07-26T14:17:18Z","snapshot_observed_at":"2026-08-02T10:24:43.977557Z","submitted_at":"2026-07-06T07:56:53Z","title":"Multi-Turn On-Policy Distillation with Prefix Replay","version":1},"reference_index":277,"source":"arxiv_source","source_observed_at":"2026-07-11T13:53:36.775836Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2607.04763"},"observation_digest":"sha256:2703466d66d469ab86d41e0c1861055a8c9fcab4402465062927dd31501785ed","observation_id":"a2c8d4ee-c42e-4dd3-a3ac-3723e7ed33ac","resolution":{"observed_at":"2026-07-11T13:53:36.775836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-02T08:41:04.832285Z","title":"arXiv preprint arXiv:2306.02561 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.04763","last_updated":"2026-07-26T14:17:18Z","snapshot_observed_at":"2026-08-02T10:24:43.977557Z","submitted_at":"2026-07-06T07:56:53Z","title":"Multi-Turn On-Policy Distillation with Prefix Replay","version":3},"reference_index":278,"source":"arxiv_source","source_observed_at":"2026-08-02T08:41:04.832285Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2607.04763"},"observation_digest":"sha256:363de6f38a35a6fa4a44beb20d2e2971c71b9764b68c64c6e07c309b7382e6e5","observation_id":"aabd426a-27ae-4397-b967-f579a7284acf","resolution":{"observed_at":"2026-08-02T08:41:04.832285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-01T09:29:44.637481Z","title":"2023 , address =","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20768","last_updated":"2026-07-22T22:34:57Z","snapshot_observed_at":"2026-08-07T08:12:23.947409Z","submitted_at":"2026-07-22T22:34:57Z","title":"Are Diversity Metrics Measuring Diversity? A Capability-Controlled Audit of Majority-Vote Gain in LLM Ensembles","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-01T09:29:44.637481Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2607.20768"},"observation_digest":"sha256:476c0d3b42062c646d6e9ff836abba2ccbb0b4498850ab85df2f872079c3166f","observation_id":"e8787761-f6cc-4b33-866b-02215d92ab96","resolution":{"observed_at":"2026-08-01T09:29:44.637481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-01T05:09:54.163495Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion.arXiv preprint arXiv:2306.02561, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22334","last_updated":"2026-07-24T14:12:54Z","snapshot_observed_at":"2026-08-06T13:13:09.326315Z","submitted_at":"2026-07-24T14:12:54Z","title":"Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T05:09:54.163495Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2607.22334"},"observation_digest":"sha256:6e798402dc215f2d6135376548503b89b0d166f02e3330b1d5ab6c2f5265bdbb","observation_id":"0adee1f2-c634-4bcc-936b-efa9db5f12d7","resolution":{"observed_at":"2026-08-01T05:09:54.163495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-02T11:01:29.440785Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22621","last_updated":"2026-06-17T02:43:58Z","snapshot_observed_at":"2026-08-08T07:34:03.579917Z","submitted_at":"2026-06-17T02:43:58Z","title":"Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T11:01:29.440785Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2607.22621"},"observation_digest":"sha256:0e34b204fc5d937c3091e35ac1ad5a5064f5110f4594d8e8d508072384e40865","observation_id":"42958fc3-d9e3-4267-a06b-abbfc2a90ab8","resolution":{"observed_at":"2026-08-02T11:01:29.440785Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-04T07:49:39.975819Z","title":"arXiv preprint arXiv:2306.02561 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02415","last_updated":"2026-08-03T15:53:49Z","snapshot_observed_at":"2026-08-08T15:56:39.139618Z","submitted_at":"2026-08-03T15:53:49Z","title":"Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes","version":1},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-08-04T07:49:39.975819Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2608.02415"},"observation_digest":"sha256:adee2731b63fd067043b2b1edb2efdf03a11cf5d865fb72795d4bef8120c0b9a","observation_id":"7957c398-a41b-47a6-8971-22d0b63af353","resolution":{"observed_at":"2026-08-04T07:49:39.975819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2306.02561/citation-record","integrity":"/paper/2306.02561/integrity","json":"/paper/2306.02561/citation-record.json","paper":"/paper/2306.02561"},"outbound":[],"paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T15:27:19.717152Z","submitted_at":"2023-06-05T03:32:26Z","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 48 inbound Pith citation observations for arXiv:2306.02561."}