{"items":[{"id":"f13205f6-aa84-42df-9ef6-4427659aca0e","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-olmo2-winogrande-microslice","job_id":"60f64123-f4a9-4c58-af04-49f09be8a958","computed_at":"2026-05-15T19:56:36.638Z","is_current":true,"paper":{"arxiv_id":"2501.00656","title":"2 OLMo 2 Furious","venue":"arXiv 2024","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"unknown","citation_validation":null},{"id":"14a07e65-e4c0-44f5-bbe8-0bb416795662","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-roberta-mnli-microslice","job_id":"074d8c16-4f0f-46e3-a29a-41b99d271943","computed_at":"2026-05-15T19:19:53.709Z","is_current":true,"paper":{"arxiv_id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","venue":"arXiv preprint","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"proxy","citation_validation":null},{"id":"817b1eac-5d4c-4337-86d0-a8b701edfa72","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-mamba-wikitext2-3slice8","job_id":"014fa02f-a714-48b5-a8da-45137749dd8b","computed_at":"2026-05-15T19:19:22.054Z","is_current":true,"paper":{"arxiv_id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","venue":"COLM 2024","primary_category":"cs.LG"},"claim_citation":null,"protocol_match":"proxy","citation_validation":null},{"id":"74115808-6f35-468f-a4d6-2088eed2ddf4","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-distilbert-sst2-microslice","job_id":"48d12fe7-4255-474f-b6de-b5b7e15ad297","computed_at":"2026-05-15T19:19:17.785Z","is_current":true,"paper":{"arxiv_id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","venue":"NeurIPS 2019 EMC^2 Workshop","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"proxy","citation_validation":null},{"id":"df87b6ce-701b-4fd1-be28-eae71c2ff904","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-bert-sst2-3slice100","job_id":"b522a4a7-3bf9-4134-a085-11f88c0242f2","computed_at":"2026-05-15T19:19:14.387Z","is_current":true,"paper":{"arxiv_id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","venue":"NAACL 2019","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"exact","citation_validation":null},{"id":"c87ffd32-9207-4da4-b040-5806c8c2bcba","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-stablelm2-winogrande-microslice","job_id":"0025dbdf-99ba-4d60-ab41-cafb511594a6","computed_at":"2026-05-15T18:26:56.768Z","is_current":true,"paper":{"arxiv_id":"2402.17834","title":"Stable LM 2 1.6B Technical Report","venue":"arXiv 2024","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"unknown","citation_validation":null},{"id":"3b503726-e995-4557-8009-b6d5119c6e44","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-olmoe-winogrande-microslice","job_id":"e1b8d2df-e39e-4104-92f1-382cf768c8e6","computed_at":"2026-05-15T17:51:44.730Z","is_current":true,"paper":{"arxiv_id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","venue":"arXiv 2024","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"unknown","citation_validation":null},{"id":"ffa295a5-8c25-422a-8b06-bd7950ca9005","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-deepseek-r1-winogrande-microslice","job_id":"8466b2f1-25b6-44b9-9f36-7fb4df494670","computed_at":"2026-05-15T17:15:16.020Z","is_current":true,"paper":{"arxiv_id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","venue":"arXiv 2025","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"unknown","citation_validation":null},{"id":"626b641c-21df-4405-bb07-cd1e5f5f95bd","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-smollm2-winogrande-microslice","job_id":"372e6c77-520e-4b45-872a-117914aea7c5","computed_at":"2026-05-15T16:33:10.626Z","is_current":true,"paper":{"arxiv_id":"2502.02737","title":"SmolLM2: When Smol Goes Big — Data-Centric Training of a Small Language Model","venue":"arXiv 2025","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"unknown","citation_validation":null},{"id":"a623fa57-5b71-423c-9dd1-617b10b7efd3","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-qwen25-winogrande-microslice","job_id":"58824325-3a3e-47f2-8802-305bf66ed9d6","computed_at":"2026-05-15T16:17:44.682Z","is_current":true,"paper":{"arxiv_id":"2412.15115","title":"Qwen2.5 Technical Report","venue":"arXiv 2024","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"unknown","citation_validation":null},{"id":"2ba18f97-832d-477a-ae6f-416b99135f13","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-yi-lambada-microslice","job_id":"55abc116-6e50-473a-85e8-76b3b69e46f1","computed_at":"2026-05-15T16:10:30.561Z","is_current":true,"paper":{"arxiv_id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","venue":"arXiv 2024","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"unknown","citation_validation":null},{"id":"6ae737f0-1e86-437c-8ecc-0e522fdbabf2","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-phi3-winogrande-microslice","job_id":"58aae606-be57-47bf-a5a7-039fcbee3357","computed_at":"2026-05-15T16:10:04.346Z","is_current":true,"paper":{"arxiv_id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","venue":"arXiv 2024","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"unknown","citation_validation":null},{"id":"f3bde1fb-fe23-4526-9c73-33d86506b489","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-mobilenet-v3-large-microslice","job_id":"926e1673-437b-447e-9f44-76339bfc50ad","computed_at":"2026-05-15T16:08:31.875Z","is_current":true,"paper":{"arxiv_id":"1905.02244","title":"Searching for MobileNetV3","venue":"ICCV 2019","primary_category":"cs.CV"},"claim_citation":null,"protocol_match":"proxy","citation_validation":null},{"id":"5b7e4405-024f-4564-b245-5f8d3a45716e","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-mistral-hellaswag-microslice","job_id":"1443722c-e65d-4154-a3ac-03f76b55df10","computed_at":"2026-05-15T03:04:31.055Z","is_current":true,"paper":{"arxiv_id":"2310.06825","title":"Mistral 7B","venue":"arXiv 2023","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"proxy","citation_validation":null},{"id":"512e19da-e020-4dfb-a7ab-2facf6f99a1e","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-minicpm-mmlu5shot-microslice","job_id":"6bce556a-498b-48be-a9e9-49195f54e1d5","computed_at":"2026-05-15T00:04:42.753Z","is_current":true,"paper":{"arxiv_id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","venue":"COLM 2024","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"proxy","citation_validation":null},{"id":"0fbfc48c-515e-42a7-9844-06aa3a4318bb","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-gemma-hellaswag-microslice","job_id":"4dce19e8-ae7a-4477-bd6b-8ec4c03522b4","computed_at":"2026-05-14T23:57:33.041Z","is_current":true,"paper":{"arxiv_id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","venue":"arXiv 2024","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"proxy","citation_validation":null},{"id":"4538fa12-ff82-48ef-8b80-7770c856abef","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-tinyllama-hellaswag-microslice","job_id":"8a552848-b38a-4fe9-b558-f4d6cfd8eb6a","computed_at":"2026-05-14T23:56:41.156Z","is_current":true,"paper":{"arxiv_id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","venue":"arXiv 2024","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"proxy","citation_validation":null},{"id":"da59c566-d0cc-40b4-9fe7-2f6cdf566087","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-deberta-mnli-microslice","job_id":"e35cb267-b959-4799-8ff8-1c3cef746b69","computed_at":"2026-05-14T23:56:01.683Z","is_current":true,"paper":{"arxiv_id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","venue":"ICLR 2023","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"proxy","citation_validation":null},{"id":"2aad0cac-5272-4d71-b9f6-8290bc62e5f2","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-bloom-lambada-microslice","job_id":"ef84e4f5-038d-4751-83c7-8ca4bb190a00","computed_at":"2026-05-14T23:54:50.378Z","is_current":true,"paper":{"arxiv_id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","venue":"arXiv 2022","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"proxy","citation_validation":null},{"id":"f156bd8c-aca4-4a2d-9c66-bf50bf28965e","kind":"POST","status":"pending","score":null,"confidence":null,"agent_version":"v0.1.0-codellama-pythonppl-microslice","job_id":"8e5b0bcf-edb9-49f3-9120-b3ff5ee82535","computed_at":"2026-05-14T23:53:26.429Z","is_current":true,"paper":{"arxiv_id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","venue":"arXiv 2023","primary_category":"cs.CL"},"claim_citation":null,"protocol_match":"unknown","citation_validation":null}],"next_cursor":"MjAyNi0wNS0xNFQyMzo1MzoyNi40MjlafGYxNTZiZDhjLWFjYTQtNGEyZC05YzY2LWJmNTBiZjI4OTY1ZQ"}