{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:29:06Z","timestamp":1766068146900,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709415","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:42:22Z","timestamp":1743792142000},"page":"2768-2778","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SWaT: Statistical Modeling of Video Watch Time through User Behavior Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8058-3149","authenticated-orcid":false,"given":"Shentao","family":"Yang","sequence":"first","affiliation":[{"name":"University of Texas at Austin, Austin, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5714-4174","authenticated-orcid":false,"given":"Haichuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Meta AI, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2640-7531","authenticated-orcid":false,"given":"Linna","family":"Du","sequence":"additional","affiliation":[{"name":"Meta AI, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5868-499X","authenticated-orcid":false,"given":"Adithya","family":"Ganesh","sequence":"additional","affiliation":[{"name":"Meta AI, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7569-1828","authenticated-orcid":false,"given":"Bo","family":"Peng","sequence":"additional","affiliation":[{"name":"Ohio State University, Columbus, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3019-5763","authenticated-orcid":false,"given":"Boying","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta AI, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9644-7988","authenticated-orcid":false,"given":"Serena","family":"Li","sequence":"additional","affiliation":[{"name":"Meta AI, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4921-4643","authenticated-orcid":false,"given":"Ji","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta AI, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635816"},{"key":"e_1_3_2_2_2_1","volume-title":"International Conference on Machine Learning. PMLR, 411--419","author":"Beckham Christopher","year":"2017","unstructured":"Christopher Beckham and Christopher Pal. 2017. Unimodal probability distributions for deep ordinal classification. In International Conference on Machine Learning. PMLR, 411--419."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3584640"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583259"},{"key":"e_1_3_2_2_5_1","volume-title":"Multitask learning. Machine learning","author":"Caruana Rich","year":"1997","unstructured":"Rich Caruana. 1997. Multitask learning. Machine learning, Vol. 28 (1997), 41--75."},{"volume-title":"Statistical Inference","author":"Casella George","key":"e_1_3_2_2_6_1","unstructured":"George Casella and Roger Berger. 2001. Statistical Inference. Duxbury Resource Center."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_2_8_1","volume-title":"Pranking with ranking. Advances in neural information processing systems","author":"Crammer Koby","year":"2001","unstructured":"Koby Crammer and Yoram Singer. 2001. Pranking with ranking. Advances in neural information processing systems, Vol. 14 (2001)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1864708.1864770"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00487"},{"key":"e_1_3_2_2_11_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Feng Yihao","year":"2023","unstructured":"Yihao Feng, Shentao Yang, Shujian Zhang, Jianguo Zhang, Caiming Xiong, Mingyuan Zhou, and Huan Wang. 2023. Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-Oriented Dialogue Systems. In The Eleventh International Conference on Learning Representations."},{"volume-title":"A Course in Large Sample Theory","author":"Ferguson Thomas S.","key":"e_1_3_2_2_12_1","unstructured":"Thomas S. Ferguson. 1996. A Course in Large Sample Theory. Chapman & Hall, London."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44795-4_13"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3501396"},{"key":"e_1_3_2_2_17_1","first-page":"24991","article-title":"On embeddings for numerical features in tabular deep learning","volume":"35","author":"Gorishniy Yury","year":"2022","unstructured":"Yury Gorishniy, Ivan Rubachev, and Artem Babenko. 2022. On embeddings for numerical features in tabular deep learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 24991--25004.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"The elements of statistical learning: data mining, inference, and prediction","author":"Hastie Trevor","key":"e_1_3_2_2_18_1","unstructured":"Trevor Hastie, Robert Tibshirani, Jerome H Friedman, and Jerome H Friedman. 2009. The elements of statistical learning: data mining, inference, and prediction. Vol. 2. Springer."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2866770"},{"volume-title":"Quantile regression","author":"Koenker Roger","key":"e_1_3_2_2_20_1","unstructured":"Roger Koenker. 2005. Quantile regression. Vol. 38. Cambridge university press."},{"key":"e_1_3_2_2_21_1","volume-title":"Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation. arXiv preprint arXiv:2407.12223","author":"Lin Chengzhi","year":"2024","unstructured":"Chengzhi Lin, Shuchang Liu, Chuyuan Wang, and Yongqi Liu. 2024. Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation. arXiv preprint arXiv:2407.12223 (2024)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599919"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Shang Liu Zhenzhong Chen Hongyi Liu and Xinghai Hu. 2019. User-video co-attention network for personalized micro-video recommendation. In The world wide web conference. 3020--3026.","DOI":"10.1145\/3308558.3313513"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482417"},{"key":"e_1_3_2_2_25_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1980.tb01109.x"},{"key":"e_1_3_2_2_27_1","volume-title":"The impact of confounder selection criteria on effect estimation. American journal of epidemiology","author":"Mickey Ruth M","year":"1989","unstructured":"Ruth M Mickey and Sander Greenland. 1989. The impact of confounder selection criteria on effect estimation. American journal of epidemiology, Vol. 129, 1 (1989), 125--137."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.532"},{"key":"e_1_3_2_2_29_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_2_30_1","unstructured":"Judea Pearl. 2009. Causality. Cambridge university press."},{"key":"e_1_3_2_2_31_1","volume-title":"Ranking with large margin principle: Two approaches. Advances in neural information processing systems","author":"Shashua Amnon","year":"2002","unstructured":"Amnon Shashua and Anat Levin. 2002. Ranking with large margin principle: Two approaches. Advances in neural information processing systems, Vol. 15 (2002)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28752"},{"key":"e_1_3_2_2_33_1","volume-title":"2017 USENIX Annual Technical Conference (USENIX ATC 17)","author":"Tang Linpeng","year":"2017","unstructured":"Linpeng Tang, Qi Huang, Amit Puntambekar, Ymir Vigfusson, Wyatt Lloyd, and Kai Li. 2017. Popularity prediction of facebook videos for higher quality streaming. In 2017 USENIX Annual Technical Conference (USENIX ATC 17). 111--123."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599797"},{"key":"e_1_3_2_2_35_1","volume-title":"International conference on machine learning. PMLR, 1747--1756","author":"Den Oord A\u00e4ron Van","year":"2016","unstructured":"A\u00e4ron Van Den Oord, Nal Kalchbrenner, and Koray Kavukcuoglu. 2016. Pixel recurrent neural networks. In International conference on machine learning. PMLR, 1747--1756."},{"key":"e_1_3_2_2_36_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems Vol. 30 (2017)."},{"volume-title":"Extending and benchmarking Cascade-Correlation: extensions to the Cascade-Correlation architecture and benchmarking of feed-forward supervised artificial neural networks. Ph.,D. Dissertation","author":"Waugh Samuel George","key":"e_1_3_2_2_37_1","unstructured":"Samuel George Waugh. 1995. Extending and benchmarking Cascade-Correlation: extensions to the Cascade-Correlation architecture and benchmarking of feed-forward supervised artificial neural networks. Ph.,D. Dissertation. University of Tasmania."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.15031"},{"key":"e_1_3_2_2_39_1","volume-title":"Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=xVXnXk9I3I","author":"Yang Shentao","year":"2024","unstructured":"Shentao Yang, Tianqi Chen, and Mingyuan Zhou. 2024. A Dense Reward View on Aligning Text-to-Image Diffusion with Preference. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=xVXnXk9I3I"},{"key":"e_1_3_2_2_40_1","volume-title":"International Conference on Machine Learning. PMLR, 24980--25006","author":"Yang Shentao","year":"2022","unstructured":"Shentao Yang, Yihao Feng, Shujian Zhang, and Mingyuan Zhou. 2022a. Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning. In International Conference on Machine Learning. PMLR, 24980--25006."},{"key":"e_1_3_2_2_41_1","volume-title":"A behavior regularized implicit policy for offline reinforcement learning. arXiv preprint arXiv:2202.09673","author":"Yang Shentao","year":"2022","unstructured":"Shentao Yang, Zhendong Wang, Huangjie Zheng, Yihao Feng, and Mingyuan Zhou. 2022b. A behavior regularized implicit policy for offline reinforcement learning. arXiv preprint arXiv:2202.09673 (2022)."},{"key":"e_1_3_2_2_42_1","unstructured":"Shentao Yang Shujian Zhang Yihao Feng and Mingyuan Zhou. 2022c. A Unified Framework for Alternating Offline Model Training and Policy Learning. In Advances in Neural Information Processing Systems Alice H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.)."},{"key":"e_1_3_2_2_43_1","volume-title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=6SRE9GZ9s6","author":"Yang Shentao","year":"2023","unstructured":"Shentao Yang, Shujian Zhang, Congying Xia, Yihao Feng, Caiming Xiong, and Mingyuan Zhou. 2023. Preference-grounded Token-level Guidance for Language Model Fine-tuning. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=6SRE9GZ9s6"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539092"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608797"},{"key":"e_1_3_2_2_46_1","unstructured":"Zhuokai Zhao Yang Yang Wenyu Wang Chihuang Liu Yu Shi Wenjie Hu Haotian Zhang and Shuang Yang. 2023a. Breaking the Curse of Quality Saturation with User-Centric Ranking. arxiv: 2305.15333 [cs.IR] https:\/\/arxiv.org\/abs\/2305.15333"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548428"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1879141.1879193"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709415","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:34:30Z","timestamp":1755358470000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709415"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":48,"alternative-id":["10.1145\/3690624.3709415","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709415","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}