{"as_of":"2026-08-10T19:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:14bea7fc10548f7c9b12425adb00cf6f2e5ff52bade1bec454b0cc4b9e06f4fa","coverage":[{"denominator":70,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":70,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:10:06.295584Z","state":"measured"},{"denominator":70,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":70,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2505.23844/citation-record","integrity":"/paper/2505.23844/integrity","json":"/paper/2505.23844/citation-record.json","paper":"/paper/2505.23844"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:17.927183Z","title":"Evolutionary optimization of model merging recipes.Nature Machine Intelligence, pages 1–10, 2025","venue":null,"work_id":"4ec32765-ae15-4d09-84a6-653b43dac166","year":2025},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:56.422431Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:7b54747a9f3d4e38dd7d1815f392838f09ef9a55c93ad26d67245e2a8f151f82","observation_id":"f1578d50-e2d8-4351-a0f7-f5097e109591","resolution":{"observed_at":"2026-08-07T13:10:18.097799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:17.693273Z","title":"Ensemble of averages: Improv- ing model selection and boosting performance in domain generalization.Advances in Neural Information Processing Systems, 35:8265–8277, 2022","venue":null,"work_id":"dd410259-2c64-4d5f-8e6e-3710ab0c9cfa","year":2022},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:56.555840Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:e1af1082c5170f42595e803f0d698160c735cb54affc98388e689e927a02a295","observation_id":"e2b4ece2-9003-4a42-9a85-32a8d8790ce6","resolution":{"observed_at":"2026-08-07T13:10:17.792206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:09:56.730191Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models.Transactions on Machine Learning Research, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:56.730191Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:e42b72a20f1c395dd2bf304e6e310ad3126922d54db8c532d574d8639203ccfb","observation_id":"08e1875d-3fe7-4091-92dc-0f633f600b80","resolution":{"observed_at":"2026-08-07T13:09:56.730191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:09:56.864219Z","title":"Pythia: A suite for analyzing large language models across training and scaling","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:56.864219Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:03a0375e5c240fb0600acfef31a4abe9042455e8261a24b2f7fa237a098e592c","observation_id":"4bf9b854-4bb7-4a29-b1f1-b3508a0917a8","resolution":{"observed_at":"2026-08-07T13:09:56.864219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:17.312550Z","title":"GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow, March 2021","venue":null,"work_id":"b57f60d0-9706-43e1-9b3f-8bceef624224","year":2021},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:56.998560Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:fbadc2a30155a406708f2f6a1d09b8647bf672f99922e7c177878deb6cf35d7c","observation_id":"3c35beef-cb74-4aa2-8e10-0e6c261f5d7e","resolution":{"observed_at":"2026-08-07T13:10:17.527249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:16.974001Z","title":"Multipl- e: a scalable and polyglot approach to benchmarking neural code generation.IEEE Transactions on Software Engineering, 2023","venue":null,"work_id":"875bde83-b2a0-4588-9676-6cf42f94018b","year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:57.108926Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:e706a40baf902e24a5fd801db8a1f0ff6bce27683e9ef32f480d2b9c67d9327f","observation_id":"b8b5c40a-9274-4dc7-bd8d-f03170c71195","resolution":{"observed_at":"2026-08-07T13:10:17.166917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:16.651788Z","title":"Meditron- 70b: Scaling medical pretraining for large language models, 2023","venue":null,"work_id":"528e0fb0-7968-4c56-acf0-cb777e919e69","year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:57.308540Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:66a3e880f4f25550ff8311c2107c30f40949e3a641ec6b5527722b7bd8f6c09f","observation_id":"5dcbbc6b-8e1a-4f92-a4dd-640a5cae4524","resolution":{"observed_at":"2026-08-07T13:10:16.794583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:16.327460Z","title":"Chinese-vicuna: A chinese instruction-following llama-based model","venue":null,"work_id":"08e12c6a-e0ee-4e2e-b413-22e24ee52212","year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:57.435120Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:67b8f058016ea58e4c237a6fed424c05753d28c3af9a304e2e03651d7ff58919","observation_id":"bf753216-0e61-427c-9428-199457ffa8a7","resolution":{"observed_at":"2026-08-07T13:10:16.443819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:16.050564Z","title":"Med42 – evaluating fine-tuning strategies for medical llms: Full-parameter vs","venue":null,"work_id":"0bfb7ae7-cee9-4627-b16c-75b9da14d21d","year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:57.568617Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:8260af1fbb6ca86868038d3784d5878e10fbf71595c1eb7a2b60e5f9a3c7658a","observation_id":"fdab5838-4552-4155-bbfb-4d88a5ca2608","resolution":{"observed_at":"2026-08-07T13:10:16.179125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-08-07T13:09:57.727544Z","title":"Think you have solved question answering? try arc, the ai2 reasoning challenge.arXiv preprint arXiv:1803.05457, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:57.727544Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:50a220b944e9cd97d0123fe48df0d2840211089ae3b90850a245260fd1327980","observation_id":"bed2ea84-00f8-4eef-993e-d54e8829629b","resolution":{"observed_at":"2026-08-07T13:09:57.727544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:09:57.917599Z","title":"Glam: Efficient scaling of language models with mixture-of-experts","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:57.917599Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:267e9852ca8372dd1785be34b5b9bcabcbedb3616bf3b09a61525969f3fe8695","observation_id":"6c4cba97-8bf1-499e-be4c-bca65eac2190","resolution":{"observed_at":"2026-08-07T13:09:57.917599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:09:57.983013Z","title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23(120):1–39, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:57.983013Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:79260012872255bf37cb77e58468875c8656a9ba90240a207303cc2fcd8f690c","observation_id":"4e98753a-603a-4abd-8d15-a901f7bac1f3","resolution":{"observed_at":"2026-08-07T13:09:57.983013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:09:58.106644Z","title":"A framework for few-shot language model evaluation, 12 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:58.106644Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:f9d4ba86c3d360476d7ceac33d5aafa6ba66ebf8c0fd2b2c20bcebfb21311c4f","observation_id":"e8d8b5a1-87fe-4385-9eaf-43fd883e4d28","resolution":{"observed_at":"2026-08-07T13:09:58.106644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:09:58.251949Z","title":"Koala: A dialogue model for academic research","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:58.251949Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:eacd0f894674d0808fff2a58b2b27020e1594a55f2e4ade5b9b00be5fafb0be9","observation_id":"788e244e-44cc-4b0f-acd0-286baae9d2e6","resolution":{"observed_at":"2026-08-07T13:09:58.251949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:15.720290Z","title":"Openllama: An open reproduction of llama, May 2023","venue":null,"work_id":"52cd4f23-0dca-4403-b548-540fe1998ed0","year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:58.361274Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:9391696c86b03ba20a47ff83a6b9a109cee9df02ae915a0d0893470897ece718","observation_id":"5866328c-3c01-4f1c-8b28-6a1751721f86","resolution":{"observed_at":"2026-08-07T13:10:15.794220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13257","last_updated":"2025-01-09T22:21:56Z","snapshot_observed_at":"2026-08-09T03:38:22.081528Z","submitted_at":"2024-03-20T02:38:01Z","title":"Arcee's MergeKit: A Toolkit for Merging Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13257","snapshot_observed_at":"2026-08-07T13:09:58.537084Z","title":"Arcee’s mergekit: A toolkit for merging large language models.arXiv preprint arXiv:2403.13257, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:58.537084Z"},"links":{"cited_paper":"/paper/2403.13257","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:3d2d7a3293c02eb38388ab8b644147057e854d23bbcc460e3e26f087770b4070","observation_id":"ca392154-0900-4fe7-88ef-4e7ace0f4cb8","resolution":{"observed_at":"2026-08-07T13:09:58.537084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-10T16:40:37.411115Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T13:09:58.783438Z","title":"The llama 3 herd of models.arXiv preprint arXiv:2407.21783, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:58.783438Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:681f44539325edb4b049878104eb54fdd3f366a933153c674b5092e510d43578","observation_id":"0eec150c-0161-4c43-ac7a-32dec477a60e","resolution":{"observed_at":"2026-08-07T13:09:58.783438Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:09:58.880826Z","title":"Measuring massive multitask language understanding, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:58.880826Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:ddd7a6888b816bf3204625ff044a36abecd9d572ff1405eb7ade3358399f0361","observation_id":"0eb772e3-2ac6-41bd-8ce1-a0d6765b38ee","resolution":{"observed_at":"2026-08-07T13:09:58.880826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:15.346308Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":"0ea568d3-0dd6-42ea-a71d-a754d7a97efe","year":2015},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:58.976616Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:ef11d374e38c6b24afd84604b9b2adfa13aa1df5b72859110dc80ff7d0967c82","observation_id":"e2ea96e6-4ef4-4053-88f8-1c858d0b8d56","resolution":{"observed_at":"2026-08-07T13:10:15.524109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01144","last_updated":"2017-08-05T22:45:19Z","snapshot_observed_at":"2026-08-01T18:34:23.156273Z","submitted_at":"2016-11-03T19:48:08Z","title":"Categorical Reparameterization with Gumbel-Softmax","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01144","snapshot_observed_at":"2026-08-07T13:09:59.102320Z","title":"Categorical reparameterization with gumbel-softmax","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:59.102320Z"},"links":{"cited_paper":"/paper/1611.01144","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:4184eade078d68dd7d72baa88df19b8f119c538c6720ee5e003c738c926beb74","observation_id":"0f5499e0-e775-46c6-9550-6292f21b06d0","resolution":{"observed_at":"2026-08-07T13:09:59.102320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04088","last_updated":"2024-01-08T18:47:34Z","snapshot_observed_at":"2026-08-08T06:16:25.839566Z","submitted_at":"2024-01-08T18:47:34Z","title":"Mixtral of Experts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.04088","snapshot_observed_at":"2026-08-07T13:09:59.182648Z","title":"Mixtral of experts.arXiv preprint arXiv:2401.04088, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:59.182648Z"},"links":{"cited_paper":"/paper/2401.04088","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:c7242051517913cdb96b932dc6d550a55e1a67e34f9b17b91a4e81a26496e6bf","observation_id":"8d87cc3c-273d-4143-8c20-74e98a660717","resolution":{"observed_at":"2026-08-07T13:09:59.182648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:09:59.348625Z","title":"Llm-blender: Ensembling large language models with pairwise ranking and generative fusion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:59.348625Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:b49e202380dcde1afbe60c11650ed0b30a89d00625c6d839c5da72ef8cd5b4d7","observation_id":"2714b9f5-c1cb-4aab-9c0c-d4ec2a3786df","resolution":{"observed_at":"2026-08-07T13:09:59.348625Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:14.984325Z","title":"Dataless knowledge fusion by merging weights of language models","venue":null,"work_id":"dd50c8c6-ef61-4648-b365-b3d35839199d","year":2022},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:59.441842Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:9cb5882a4382237cde1f8d23eb39ec2d26dea5471110e409c1104790b36c1250","observation_id":"d0a4d0b5-b1b3-4c82-83ed-0a2f9eac31be","resolution":{"observed_at":"2026-08-07T13:10:15.137953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.08442","last_updated":"2023-04-17T17:03:56Z","snapshot_observed_at":"2026-08-09T20:42:25.574104Z","submitted_at":"2023-04-17T17:03:56Z","title":"The MiniPile Challenge for Data-Efficient Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.08442","snapshot_observed_at":"2026-08-07T13:09:59.498544Z","title":"The minipile challenge for data-efficient language models.arXiv preprint arXiv:2304.08442, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:59.498544Z"},"links":{"cited_paper":"/paper/2304.08442","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:d7607f9bfd3ce47728f70677907b0e940a1522a4a7dfbb9e736d89d1dedc831e","observation_id":"05fcb154-0386-485f-ba5a-f8a97e565261","resolution":{"observed_at":"2026-08-07T13:09:59.498544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:14.639059Z","title":"Token reduction should go beyond efficiency in generative models – from vision, language to multimodality, 2025","venue":null,"work_id":"06ada5a3-9b61-4be1-b142-7cae90abe48b","year":2025},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:59.554338Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:d7feb0b653099f4445b52e134784f599da51392cdca32d597ef956d780ce2595","observation_id":"a981b260-2dfd-4837-a9d7-b3e95dc7d085","resolution":{"observed_at":"2026-08-07T13:10:14.820907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.16668","last_updated":"2020-06-30T10:42:02Z","snapshot_observed_at":"2026-08-07T09:27:36.420559Z","submitted_at":"2020-06-30T10:42:02Z","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.16668","snapshot_observed_at":"2026-08-07T13:09:59.649722Z","title":"Gshard: Scaling giant models with condi- tional computation and automatic sharding.arXiv preprint arXiv:2006.16668, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:59.649722Z"},"links":{"cited_paper":"/paper/2006.16668","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:50029c391a0cb0baf1800b609bf304ea9d575cbbe8608732eccc8466b6c4e573","observation_id":"d0709e28-f384-44b2-8ef3-96744b32eed2","resolution":{"observed_at":"2026-08-07T13:09:59.649722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:14.315374Z","title":"Distinct but correct: generating diversified and entity-revised medical response","venue":null,"work_id":"6a158403-8c2a-4567-bb4a-0ceab24a366f","year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:59.764394Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:1ae2b1418b69641188b8ba4ebde67f4fd41f71d35fbe486b39aa3d54cd786418","observation_id":"dda5e345-2044-4379-9165-e9160762d313","resolution":{"observed_at":"2026-08-07T13:10:14.441124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:14.038009Z","title":"Towards better chinese-centric neural machine translation for low-resource languages.Computer Speech & Language, 84:101566, 2024","venue":null,"work_id":"a7ce17aa-ceea-4ca3-8fa0-11d457e97a44","year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:09:59.891120Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:ef30eaecd90d8eaee13e06272927291b8073e0a2979d00aeefd34a89055de856","observation_id":"31f5659d-e056-41ed-8d5f-f5e28f1a32ba","resolution":{"observed_at":"2026-08-07T13:10:14.153107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:13.742064Z","title":"Efficient transformer-based large scale language representations using hardware-friendly block structured pruning","venue":null,"work_id":"5f4c9f6f-c328-47cd-9c62-c20ec33a6304","year":2020},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:00.019051Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:289aefeb0e7966ab2edb120aa89604fda81394bf5e1febb5e7b97601f75fd6d0","observation_id":"bca2a8fe-c0cf-485f-a443-b93c4b5eec39","resolution":{"observed_at":"2026-08-07T13:10:13.847334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.06161","last_updated":"2023-12-13T14:44:10Z","snapshot_observed_at":"2026-07-06T15:25:35.930688Z","submitted_at":"2023-05-09T08:16:42Z","title":"StarCoder: may the source be with you!","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.06161","snapshot_observed_at":"2026-08-07T13:10:00.245138Z","title":"Starcoder: may the source be with you!arXiv preprint arXiv:2305.06161, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:00.245138Z"},"links":{"cited_paper":"/paper/2305.06161","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:df93c2a9264c28ddfe0c9e75fc251f9e48ac25cb087893e2a0b5d60f7bd20a24","observation_id":"aba8bafd-912c-4917-a338-5a81cff12fe8","resolution":{"observed_at":"2026-08-07T13:10:00.245138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:13.414899Z","title":"A comprehensive review of multi-agent reinforcement learning in video games.Authorea Preprints, 2025","venue":null,"work_id":"b0908c94-c18f-45ad-a9dd-620564891775","year":2025},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:00.437364Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:c51df5f306e825b304595a0b477b4df90cfc1d58cddc7ddf156f1bbe3a70653b","observation_id":"444c3af3-a6a0-4260-a4a6-e9bda4bcf59e","resolution":{"observed_at":"2026-08-07T13:10:13.575740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04315","last_updated":"2025-01-11T18:17:46Z","snapshot_observed_at":"2026-08-07T02:18:25.227072Z","submitted_at":"2025-01-08T07:13:52Z","title":"RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation","version":2},"cited_work":{"arxiv_id":"2501.04315","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.04315","snapshot_observed_at":"2026-08-07T13:10:07.924290Z","title":"RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation","venue":"cs.LG","work_id":"c16a97ef-2323-4b89-a15d-21bacb5fba4d","year":2025},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:00.615053Z"},"links":{"cited_paper":"/paper/2501.04315","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:269b4f29abad392afa6684609fa77b92a1cda17642871f62cf8c4cefca522c95","observation_id":"eeeceb25-dbae-490c-b39b-c84c34924aa4","resolution":{"observed_at":"2026-08-07T13:10:07.976715Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2403.10799","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:07.597260Z","title":"Toward adaptive large language models structured pruning via hybrid-grained weight importance assessment.arXiv preprint arXiv:2403.10799, 2024","venue":null,"work_id":"e8f05b5c-a068-4539-8166-cf88a9deb2c3","year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:00.813379Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:26f65580ee0bdc8f789ddca470bcf93d3cb723354624f27ddb20dbf7faaf2bad","observation_id":"2ddeb21d-e696-4e97-a593-72ce135308c4","resolution":{"observed_at":"2026-08-07T13:10:07.752783Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:01.038628Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:01.038628Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:5e43ebdd95d2853c2c86c236b6d444c7944140e4273d2009c4e1aa22a3ad0843","observation_id":"20620199-7571-4b80-8455-38d889743294","resolution":{"observed_at":"2026-08-07T13:10:01.038628Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.08692","last_updated":"2023-11-15T04:40:43Z","snapshot_observed_at":"2026-07-06T16:47:45.504109Z","submitted_at":"2023-11-15T04:40:43Z","title":"Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.08692","snapshot_observed_at":"2026-08-07T13:10:01.189304Z","title":"Routing to the expert: Efficient reward-guided ensemble of large language models.arXiv preprint arXiv:2311.08692, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:01.189304Z"},"links":{"cited_paper":"/paper/2311.08692","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:320e1609cf506e9e36dbf9c8b6647efa807e9b7d297ff503d9839fe45e3ed7a6","observation_id":"f2c06686-1f11-4f30-95ad-ab6ad3ccc422","resolution":{"observed_at":"2026-08-07T13:10:01.189304Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11531","last_updated":"2024-04-17T16:24:07Z","snapshot_observed_at":"2026-07-06T18:01:40.563108Z","submitted_at":"2024-04-17T16:24:07Z","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11531","snapshot_observed_at":"2026-08-07T13:10:01.465919Z","title":"Pack of llms: Model fusion at test-time via perplexity optimization.arXiv preprint arXiv:2404.11531, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:01.465919Z"},"links":{"cited_paper":"/paper/2404.11531","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:8ec89320fbe639fcb5727d1389cf998ed772047e7c2a0f7b53d4b3231ac4a465","observation_id":"49b28ee2-90d6-4fed-aa48-c5fb91a26915","resolution":{"observed_at":"2026-08-07T13:10:01.465919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:13.030579Z","title":"Specinfer: Accelerating generative llm serving with speculative inference and token tree verification, 2023","venue":null,"work_id":"4b2c6b7a-01f6-4f01-a35c-35da5ac13a2d","year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:01.585593Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:2a2f54cece7160ecf0ae4a50ebe609d7bad8f194e9d8fd84d667477d50ff9ce4","observation_id":"53b65bbd-6c68-4866-a08f-a5b6fe289013","resolution":{"observed_at":"2026-08-07T13:10:13.223824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.02789","last_updated":"2018-09-08T11:47:16Z","snapshot_observed_at":"2026-08-08T02:19:52.596062Z","submitted_at":"2018-09-08T11:47:16Z","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.02789","snapshot_observed_at":"2026-08-07T13:10:01.696431Z","title":"Can a suit of armor conduct electricity? a new dataset for open book question answering.arXiv preprint arXiv:1809.02789, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:01.696431Z"},"links":{"cited_paper":"/paper/1809.02789","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:7bab2fee1c4b240783699959a2168a219161543fa3399a5467596527ef3426ff","observation_id":"fc2d92e0-84fe-4f78-81ad-5790fb046402","resolution":{"observed_at":"2026-08-07T13:10:01.696431Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:12.632526Z","title":"Diverse weight averaging for out-of-distribution generalization","venue":null,"work_id":"c611951d-f14a-4640-ab72-7741185e33f1","year":2022},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:01.787035Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:e63d0ba172baa2a9f589b1817b4564434d2cc87af9ecd0c231120d15d7cc59e9","observation_id":"c6af0390-c849-4bdc-9823-f2d60d948275","resolution":{"observed_at":"2026-08-07T13:10:12.807940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1701.06538","last_updated":"2017-01-23T18:10:00Z","snapshot_observed_at":"2026-07-06T05:27:13.416519Z","submitted_at":"2017-01-23T18:10:00Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.06538","snapshot_observed_at":"2026-08-07T13:10:01.916221Z","title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer.arXiv preprint arXiv:1701.06538, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:01.916221Z"},"links":{"cited_paper":"/paper/1701.06538","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:851f32057a87dad733679871572670d9f5604f954ec10dd563d7257dce96fabd","observation_id":"6854ab9f-3fdf-4064-9d31-5097fb950b6b","resolution":{"observed_at":"2026-08-07T13:10:01.916221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:12.342213Z","title":"Agile-quant: Activation-guided quantization for faster inference of llms on the edge","venue":null,"work_id":"23d65f98-c990-4533-b9cc-94c13cc5f930","year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:02.047319Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:c44bf725eec12e0d480bcae2dfeb31d7ca2adedcb870f1dcfd6c35364c022f24","observation_id":"000ce4b0-4adc-4bc5-8af0-e03af2c058ff","resolution":{"observed_at":"2026-08-07T13:10:12.492333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10787","last_updated":"2025-07-01T19:43:45Z","snapshot_observed_at":"2026-07-06T17:31:13.010759Z","submitted_at":"2024-02-16T16:10:38Z","title":"Squat: Quant Small Language Models on the Edge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.10787","snapshot_observed_at":"2026-08-07T13:10:02.240857Z","title":"Edgeqat: Entropy and distribution guided quantization-aware training for the acceleration of lightweight llms on the edge.arXiv preprint arXiv:2402.10787, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:02.240857Z"},"links":{"cited_paper":"/paper/2402.10787","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:5f1b7faaa46d6c0dcd4ad3ec44d7f92574b0eeab401e3635d56eaaf15acb5d11","observation_id":"a01b7968-acfe-478b-b56e-6bd28019bab2","resolution":{"observed_at":"2026-08-07T13:10:02.240857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15766","last_updated":"2023-12-08T01:23:56Z","snapshot_observed_at":"2026-08-06T05:33:02.351414Z","submitted_at":"2023-11-27T12:37:51Z","title":"Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.15766","snapshot_observed_at":"2026-08-07T13:10:02.359079Z","title":"Knowledge unlearning for llms: Tasks, methods, and challenges.arXiv preprint arXiv:2311.15766, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:02.359079Z"},"links":{"cited_paper":"/paper/2311.15766","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:b85c49b90945eab362bc8613326d993cbb612457502a88daf9682988023f57ad","observation_id":"f386f2c1-1dcf-4883-b847-5cfdcc60e9ec","resolution":{"observed_at":"2026-08-07T13:10:02.359079Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:11.959875Z","title":"Zipit! merging models from different tasks without training","venue":null,"work_id":"a5db9a4b-7184-4a08-8a05-8c5c684f0077","year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:02.513876Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:e790769954f489edfc1bb81c2f0f84387c624746c926b4fbdc4fb9e568778a7d","observation_id":"3cc1738c-f6b6-4d61-90d9-824fd9a88fd9","resolution":{"observed_at":"2026-08-07T13:10:12.139790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.09261","last_updated":"2022-10-17T17:08:26Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-10-17T17:08:26Z","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.09261","snapshot_observed_at":"2026-08-07T13:10:02.652468Z","title":"Challenging big-bench tasks and whether chain-of-thought can solve them.arXiv preprint arXiv:2210.09261, 2022","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:02.652468Z"},"links":{"cited_paper":"/paper/2210.09261","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:74683db96622be65eb775c6f2a56ac13ef41f68e5b78e507493d1409bdf82049","observation_id":"3a3986b5-53d9-41b0-8920-612fa13b20d8","resolution":{"observed_at":"2026-08-07T13:10:02.652468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.00937","last_updated":"2019-03-15T18:02:58Z","snapshot_observed_at":"2026-08-10T07:37:55.457401Z","submitted_at":"2018-11-02T15:34:29Z","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.00937","snapshot_observed_at":"2026-08-07T13:10:02.856087Z","title":"Commonsenseqa: A ques- tion answering challenge targeting commonsense knowledge.arXiv preprint arXiv:1811.00937, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:02.856087Z"},"links":{"cited_paper":"/paper/1811.00937","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:f46d8b69f9b4dbb62b1f778036a5a17b38a54750b7eb8e1561f82963a5d4b9e6","observation_id":"76174996-1246-4c65-8350-bd97055d00c6","resolution":{"observed_at":"2026-08-07T13:10:02.856087Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:11.733484Z","title":"Introducing mpt-7b: A new standard for open-source, commercially usable llms, 2023","venue":null,"work_id":"f699df4a-f601-4c35-9380-c78231a5d6cf","year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:03.019913Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:b13e90126a350cdef13791922cbf1184b06b583c4fa16a5f1ef6e5244e4741c3","observation_id":"4ccac0ef-63f5-43a5-a3b7-9280be9b4c07","resolution":{"observed_at":"2026-08-07T13:10:11.804778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T13:10:03.131945Z","title":"Llama: Open and efficient foundation language models.arXiv preprint arXiv:2302.13971, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:03.131945Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:6de42cb3ed10a4e6c58fb69649b314fe7c1bba63beb229a31117020c6e361b59","observation_id":"1319e17b-6e2b-4d8f-a259-3c459bcaa690","resolution":{"observed_at":"2026-08-07T13:10:03.131945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:11.165689Z","title":"Knowl- edge fusion of large language models","venue":null,"work_id":"b6203d89-bc49-4f3c-a009-7fef27693df0","year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:03.230237Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:65c2e4c7153f915cdbea59e46a5bbe1e8379a825d3a28e0ccf5fa339d9489aeb","observation_id":"ea9a9365-7b3e-448a-b76b-314d8581334a","resolution":{"observed_at":"2026-08-07T13:10:11.350396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16107","last_updated":"2024-05-29T03:58:10Z","snapshot_observed_at":"2026-07-06T17:35:10.248760Z","submitted_at":"2024-02-25T15:11:58Z","title":"Knowledge Fusion of Chat LLMs: A Preliminary Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16107","snapshot_observed_at":"2026-08-07T13:10:03.421397Z","title":"Fusechat: Knowledge fusion of chat models.arXiv preprint arXiv:2402.16107, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:03.421397Z"},"links":{"cited_paper":"/paper/2402.16107","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:0d6956c50ca56df5337846ec40fc48750570e1c40cd3c1573ff6dc2762998172","observation_id":"6ecaa61b-5a7f-4679-ad98-1ae7c87abd27","resolution":{"observed_at":"2026-08-07T13:10:03.421397Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01542","last_updated":"2024-05-09T16:04:20Z","snapshot_observed_at":"2026-07-06T16:26:46.131908Z","submitted_at":"2023-10-02T18:31:35Z","title":"Fusing Models with Complementary Expertise","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01542","snapshot_observed_at":"2026-08-07T13:10:03.549476Z","title":"Fusing models with complementary expertise.arXiv preprint arXiv:2310.01542, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:03.549476Z"},"links":{"cited_paper":"/paper/2310.01542","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:bb603fceeb7ad2ea99395df45c89febf3c30617ba5c6a28ec5c7ffe25ba74360","observation_id":"4b273336-b154-4158-beb0-5e54dfe11d01","resolution":{"observed_at":"2026-08-07T13:10:03.549476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:10.821984Z","title":"Learn it or leave it: Module composition and pruning for continual learning","venue":null,"work_id":"e78bd465-8128-45ab-89c1-9f2ec7343063","year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:03.717960Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:730c09dbd42497827badd201ffa9998d7aad0b3e3cbcfa17d9fd1d8fafb57444","observation_id":"0237101a-f371-49dd-8d22-b7a7ac54e62c","resolution":{"observed_at":"2026-08-07T13:10:10.989181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:10.436036Z","title":"Rehearsal- free modular and compositional continual learning for language models","venue":null,"work_id":"b4217769-5821-4a36-b970-fba6e56550b3","year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:03.929066Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:1c62f56818b30036f254239844003eb41aceeb84e7659936fdeae4977d39ebd3","observation_id":"0b831a7e-9d42-4dd1-a803-2d805c3b92c1","resolution":{"observed_at":"2026-08-07T13:10:10.616997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:10.189549Z","title":"A systematic review of machine learning applications in infectious disease prediction, diagnosis, and outbreak forecasting","venue":null,"work_id":"692adb5b-f47f-4ed3-ab37-c45f45b87c65","year":2025},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:04.076238Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:ae5c1c540a40017688176a6aae8a792be6f18766782c228db2c80ed93ca6d513","observation_id":"f90f0a5c-cb5b-41e1-82b4-eafa93a9d560","resolution":{"observed_at":"2026-08-07T13:10:10.317579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:04.259210Z","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:04.259210Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:31da5f23c9f40939442167a407800d8226d9b363fe6c09954e4e6aaf3431cea7","observation_id":"4fb50154-2521-400f-bdb2-9c102cc3f8a9","resolution":{"observed_at":"2026-08-07T13:10:04.259210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:09.888265Z","title":"Ties-merging: Resolving interference when merging models.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"7edc6c24-b1f1-4482-8a84-73f9ccc1d8cc","year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:04.455535Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:4404d08820a0752737991d1ae84b54d1d595465f5455b057390c760ad7dfe1b9","observation_id":"43cb4c9e-3b6c-4052-88d8-27fe28dfbbff","resolution":{"observed_at":"2026-08-07T13:10:10.025304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02575","last_updated":"2024-05-28T06:42:31Z","snapshot_observed_at":"2026-08-10T08:38:34.106077Z","submitted_at":"2023-10-04T04:26:33Z","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02575","snapshot_observed_at":"2026-08-07T13:10:04.588295Z","title":"Adamerging: Adaptive model merging for multi-task learning.arXiv preprint arXiv:2310.02575, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:04.588295Z"},"links":{"cited_paper":"/paper/2310.02575","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:5d77210836e000f51e2f90b470d3271c69e0e982df6dff0a25fa66c3ea5e866d","observation_id":"a995a56d-4a8a-48fe-82d9-f905834e75e5","resolution":{"observed_at":"2026-08-07T13:10:04.588295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.04652","last_updated":"2025-01-21T10:12:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-03-07T16:52:49Z","title":"Yi: Open Foundation Models by 01.AI","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.04652","snapshot_observed_at":"2026-08-07T13:10:04.720488Z","title":"Yi: Open foundation models by 01","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:04.720488Z"},"links":{"cited_paper":"/paper/2403.04652","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:ed25d514eef6277f60f9fdc8aa45db717d9575ac9627d422ab6c9ce2aedfa90f","observation_id":"1894a646-95e7-4bba-91ca-c2b1584c5f2c","resolution":{"observed_at":"2026-08-07T13:10:04.720488Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.07830","last_updated":"2019-05-19T23:57:23Z","snapshot_observed_at":"2026-08-10T16:18:23.994244Z","submitted_at":"2019-05-19T23:57:23Z","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.07830","snapshot_observed_at":"2026-08-07T13:10:04.899531Z","title":"Hellaswag: Can a machine really finish your sentence?arXiv preprint arXiv:1905.07830, 2019","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:04.899531Z"},"links":{"cited_paper":"/paper/1905.07830","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:465694e1780e4d2b90320899d8f2f246a073e9fe78036ce1fae45395b3d8d010","observation_id":"7707b560-55b5-438a-952c-7efc9d7972d8","resolution":{"observed_at":"2026-08-07T13:10:04.899531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.14725","last_updated":"2024-10-16T00:06:13Z","snapshot_observed_at":"2026-08-10T12:42:04.522958Z","submitted_at":"2024-10-16T00:06:13Z","title":"Rethinking Token Reduction for State Space Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.14725","snapshot_observed_at":"2026-08-07T13:10:04.982237Z","title":"Rethinking token reduction for state space models.arXiv preprint arXiv:2410.14725, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:04.982237Z"},"links":{"cited_paper":"/paper/2410.14725","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:a09c9c0da15664e5d2fd343eeae8cf684b76407d4b553779037531ea333f789e","observation_id":"89bb4ac7-8d3a-4131-9d6f-c0a8f0fb3c84","resolution":{"observed_at":"2026-08-07T13:10:04.982237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:09.517954Z","title":"Towards the law of capacity gap in distilling language models","venue":null,"work_id":"3b18f2fa-dc99-4cc2-a918-5264294849a7","year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:05.094467Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:5120cde22254ea98e6de1a3ae3c9185bb4a5989d023dbd5c09ac2760955e829a","observation_id":"8217dea7-38ac-4481-8500-408097c0ab37","resolution":{"observed_at":"2026-08-07T13:10:09.639848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:05.222437Z","title":"Composing parameter-efficient modules with arithmetic operation.Advances in Neural Information Processing Systems, 36:12589–12610, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:05.222437Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:7e97549db193c669edaaf8032923267941951949b98f5dda41d45bfffc84209a","observation_id":"a34fcd6e-9c8a-4b53-8ffe-3c4fa2bdd54b","resolution":{"observed_at":"2026-08-07T13:10:05.222437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:05.390040Z","title":"Alpacare:instruction-tuned large language models for medical application, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:05.390040Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:a5b0925f487782591b32977b097ce1adeae5a10e48f2f647ab4001b26c915a43","observation_id":"5bfc5bfb-17d0-439a-bcec-b84995098a57","resolution":{"observed_at":"2026-08-07T13:10:05.390040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:09.133604Z","title":"7b fully open source moxin-llm – from pretraining to grpo-based reinforcement learning enhancement, 2025","venue":null,"work_id":"68501903-d2a6-41dd-9b0d-ef74c2c59107","year":2025},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:05.522990Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:d9434340e658e9efe1d9247173401abb2434a3f6d30f01bbd539a1af2ef96172","observation_id":"5c230dab-5178-467d-b275-b439168d6105","resolution":{"observed_at":"2026-08-07T13:10:09.261976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15567","last_updated":"2024-10-21T01:23:34Z","snapshot_observed_at":"2026-08-03T23:42:46.455706Z","submitted_at":"2024-10-21T01:23:34Z","title":"Pruning Foundation Models for High Accuracy without Retraining","version":1},"cited_work":{"arxiv_id":"2410.15567","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.15567","snapshot_observed_at":"2026-08-07T13:10:06.560526Z","title":"Pruning Foundation Models for High Accuracy without Retraining","venue":"cs.LG","work_id":"99edfc17-7d17-455d-962c-39361003b96a","year":2024},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:05.648905Z"},"links":{"cited_paper":"/paper/2410.15567","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:6e256ee9dc7992210d069719d56f04f199540828b3fd121d361431c8281b46f0","observation_id":"de9973e7-f742-483a-81ab-dc2e73cc6ed6","resolution":{"observed_at":"2026-08-07T13:10:06.691603Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:05.850820Z","title":"Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:05.850820Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:59edf70cd09f94a1b7190314b6cce9bf67e21f51fec38c6f4f37caf6097fc4c5","observation_id":"639b5b44-00a8-4c2b-9426-458c606cf95d","resolution":{"observed_at":"2026-08-07T13:10:05.850820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:08.755266Z","title":"Enhancing thyroid disease prediction using machine learning: A comparative study of ensemble models and class balancing techniques","venue":null,"work_id":"3ef29a69-0585-448c-83e4-e3db3225aa55","year":2025},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:06.058590Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:99b8c800fc349ec5ea553929b0a31548653ade11d79e21df6f36fe42dabb9174","observation_id":"cb711217-dbb6-4db2-8967-78feaa1f1f01","resolution":{"observed_at":"2026-08-07T13:10:08.896337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08906","last_updated":"2022-04-29T23:24:20Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-02-17T21:39:10Z","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08906","snapshot_observed_at":"2026-08-07T13:10:06.176625Z","title":"St-moe: Designing stable and transferable sparse expert models.arXiv preprint arXiv:2202.08906, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:06.176625Z"},"links":{"cited_paper":"/paper/2202.08906","citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:6da994078600aee609890e9a58ff44cd8afb8a8542798520e4100464f19fa0a8","observation_id":"d843ddd4-9177-4a21-907c-151242151d75","resolution":{"observed_at":"2026-08-07T13:10:06.176625Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:08.452572Z","title":"Building on this foun- dation, GShard [26] and Switch Transformers [12] presented some of the first large-scale models leveraging SMoE","venue":null,"work_id":"3c54d87c-ec6d-4192-bbc7-4db7b759d2c4","year":null},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:06.295584Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:08b578bf9486a539240eaa542e85e07ff21710595d9345f17ff54313400bc845","observation_id":"bd4a21e6-4b51-4667-87c4-3c988445dca9","resolution":{"observed_at":"2026-08-07T13:10:08.565503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:10:00.105321Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T13:10:00.105321Z"},"links":{"citing_paper":"/paper/2505.23844"},"observation_digest":"sha256:a9713887c8097b4f52c77eb9e449ce9a23b48d40f9c7c01bf18e8c499ac3b13e","observation_id":"250ed7d9-5d9e-453a-a617-d958ef58afd3","resolution":{"observed_at":"2026-08-07T13:10:00.105321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.23844","last_updated":"2025-05-28T16:24:50Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T20:58:51.092258Z","submitted_at":"2025-05-28T16:24:50Z","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation"},"reference_resolution":{"displayed":70,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":37,"verified_exact":3,"verified_fuzzy":29},"total_outbound_references":70},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 0 inbound Pith citation observations for arXiv:2505.23844."}