{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T20:54:11Z","timestamp":1782161651449,"version":"3.54.5"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032299208","type":"print"},{"value":"9783032299215","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-29921-5_19","type":"book-chapter","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T20:21:23Z","timestamp":1782159683000},"page":"276-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["What Properties of Reasoning Supervision are Associated with Improved Downstream Model Quality?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9531-5329","authenticated-orcid":false,"given":"Miko\u0142aj","family":"Langner","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5434-4696","authenticated-orcid":false,"given":"Dzmitry","family":"Pihulski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0851-1816","authenticated-orcid":false,"given":"Jan","family":"Eliasz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2983-4324","authenticated-orcid":false,"given":"Micha\u0142","family":"Rajkowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5868-356X","authenticated-orcid":false,"given":"Przemys\u0142aw","family":"Kazienko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1503-0993","authenticated-orcid":false,"given":"Maciej","family":"Piasecki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7665-6896","authenticated-orcid":false,"given":"Jan","family":"Koco\u0144","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3701-3502","authenticated-orcid":false,"given":"Teddy","family":"Ferdinan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Bandarkar, L., et al.: The belebele benchmark: a parallel reading comprehension dataset in 122 language variants. In: ACL, pp. 749\u2013775 (2024)","DOI":"10.18653\/v1\/2024.acl-long.44"},{"key":"19_CR2","unstructured":"Bercovich, A., et al.: Llama-nemotron: efficient reasoning models (2025)"},{"key":"19_CR3","unstructured":"Chang, T.A., et\u00a0al.: Global PIQA: evaluating physical commonsense reasoning across 100+ languages and cultures. arXiv preprint arXiv:2510.24081 (2025)"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Chen, D., et al.: Data-juicer: a one-stop data processing system for large language models. In: Proceedings of SIGMOD, pp. 120\u2013134 (2024)","DOI":"10.1145\/3626246.3653385"},{"key":"19_CR5","unstructured":"Chen, Y., et al.: Reasoning models don\u2019t always say what they think. arXiv preprint arXiv:2505.05410 (2025)"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Chodak, G., et al.: Typology of image crises using large language models: a novel approach to crisis classification. J. Conting. Crisis Manag. (2025)","DOI":"10.1111\/1468-5973.70092"},{"key":"19_CR7","unstructured":"Chua, J., Evans, O.: Are deepseek R1 and other reasoning models more faithful? In: ICLR Workshop on Foundation Models in the Wild (2025)"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Dadas, S., et al.: PIRB: a comprehensive benchmark of Polish dense and hybrid text retrieval methods. In: Proceedings of LREC-COLING, pp. 12761\u201312774 (2024)","DOI":"10.63317\/5k34i9y3njz2"},{"key":"19_CR9","unstructured":"DeepSeek-AI: Deepseek-v3 technical report (2024)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Ferdinan, T., et al.: Architectural concepts for integrating fundamental drives and emotions into artificial intelligence. IEEE Intell. Syst. (2025)","DOI":"10.1109\/MIS.2025.3622004"},{"key":"19_CR11","unstructured":"Grattafiori, A., et al.: The llama 3 herd of models (2024)"},{"key":"19_CR12","unstructured":"Guo, D., et al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"19_CR13","unstructured":"HuggingFace: Open R1: a fully open reproduction of deepseek-r1 (2025). https:\/\/github.com\/huggingface\/open-r1"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Hwang, H., et al.: Assessing LLM reasoning steps via principal knowledge grounding. In: Findings of EMNLP, pp. 19925\u201319948 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.1085"},{"key":"19_CR15","unstructured":"Jiang, A.Q., et al.: Mistral 7b (2023)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Jin, M., et al.: The impact of reasoning step length on large language models. In: Findings of ACL, pp. 1830\u20131842 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.108"},{"key":"19_CR17","unstructured":"Kambhampati, S., et al.: Stop anthropomorphizing intermediate tokens as reasoning\/thinking traces! arXiv preprint arXiv:2504.09762 (2025)"},{"key":"19_CR18","unstructured":"Koco\u0144, J., et al.: PLLuM: A Family of Polish Large Language Models. arXiv preprint arXiv:2511.03823 (2025)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Langner, M., et al.: Divide, cache, conquer: dichotomic prompting for efficient multi-label LLM-based classification. In: 2025 IEEE International Conference on Data Mining Workshops (ICDMW) (2025)","DOI":"10.1109\/ICDMW69685.2025.00253"},{"key":"19_CR20","unstructured":"Lawsen, A.: Comment on the illusion of thinking: understanding the strengths and limitations of reasoning models via the lens of problem complexity (2025)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Lee, J., Hockenmaier, J.: Evaluating step-by-step reasoning traces: a survey. In: Findings of EMNLP, pp. 1789\u20131814 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.94"},{"key":"19_CR22","unstructured":"Lightman, H., et al.: Let\u2019s verify step by step. In: ICLR (2024)"},{"key":"19_CR23","unstructured":"Lozhkov, A., et al.: Openr1-math-220k (2025). https:\/\/huggingface.co\/datasets\/open-r1\/OpenR1-Math-220k"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Matys, P., et al.: AggTruth: contextual hallucination detection using aggregated attention scores in LLMs. In: ICCS 2025, pp. 227\u2013243. Springer (2025)","DOI":"10.1007\/978-3-031-97570-7_18"},{"key":"19_CR25","unstructured":"Ociepa, K., et al.: Bielik 11b v2 technical report (2025)"},{"key":"19_CR26","unstructured":"OpenAI: Introducing OpenAI o3 and o4-mini (2025). https:\/\/openai.com\/index\/introducing-o3-and-o4-mini"},{"key":"19_CR27","unstructured":"Penedo, G., et al.: Codeforces cots (2025). https:\/\/huggingface.co\/datasets\/open-r1\/codeforces-cots"},{"key":"19_CR28","unstructured":"P\u0119zik, P., et al.: The PLLuM Instruction Corpus. arXiv preprint arXiv:2511.17161 (2025)"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Pihulski, D., et al.: Breaking the illusion of reasoning in Polish LLMs: quality over quantity of thought. In: Findings of EACL, pp. 1796\u20131811. ACL (2026)","DOI":"10.18653\/v1\/2026.findings-eacl.92"},{"key":"19_CR30","unstructured":"Qwen Team: Qwen3 technical report (2025)"},{"key":"19_CR31","unstructured":"Rae, J.W., et\u00a0al.: Scaling language models: methods, analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021)"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Shojaee, P., et al.: The illusion of thinking: understanding the strengths and limitations of reasoning models via the lens of problem complexity (2025)","DOI":"10.70777\/si.v2i6.15919"},{"key":"19_CR33","unstructured":"Singh, S., et al.: Aya dataset: an open-access collection for multilingual instruction tuning. In: Proceedings of ACL (2024)"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Szcz\u0119sny, A., et al.: Leveraging positional bias of LLM in-context learning with class-few-shot and maj-min alternating ordering. In: ICCS 2025, pp. 54\u201362 (2025)","DOI":"10.1007\/978-3-031-97635-3_7"},{"key":"19_CR35","unstructured":"Teng, F., et al.: Atom of thoughts for Markov LLM test-time scaling (2025)"},{"key":"19_CR36","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. NeurIPS 35, 24824\u201324837 (2022)","journal-title":"NeurIPS"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Wen, L., et al.: Light-R1: curriculum SFT, DPO and RL for long cot from scratch and beyond (2025)","DOI":"10.18653\/v1\/2025.acl-industry.24"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Wo\u017aniak, S., et al.: Personalized large language models. In: 2024 IEEE International Conference on Data Mining Workshops (ICDMW) (2024)","DOI":"10.1109\/ICDMW65004.2024.00071"},{"key":"19_CR39","unstructured":"Wu, Y., et al.: When more is less: understanding chain-of-thought length in LLMs. arXiv preprint arXiv:2502.07266 (2025)"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Zanotto, S.E., Aroyehun, S.: Linguistic and embedding-based profiling of texts generated by humans and large language models. In: Proceedings of EMNLP (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1163"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-29921-5_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T20:21:41Z","timestamp":1782159701000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29921-5_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032299208","9783032299215"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29921-5_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"23 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"All authors have received funding from the Ministry of Digital Affairs of Poland, Polish National Science Center, and the European Union.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}