{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T06:29:18Z","timestamp":1763706558748,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031334689"},{"type":"electronic","value":"9783031334696"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-33469-6_17","type":"book-chapter","created":{"date-parts":[[2023,5,23]],"date-time":"2023-05-23T21:02:01Z","timestamp":1684875721000},"page":"167-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Context-Rich Evaluation of Machine Common Sense"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5988-8305","authenticated-orcid":false,"given":"Mayank","family":"Kejriwal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henrique","family":"Santos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alice M.","family":"Mulvehill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deborah L.","family":"McGuinness","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,24]]},"reference":[{"issue":"11","key":"17_CR1","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1145\/182.358434","volume":"26","author":"JF Allen","year":"1983","unstructured":"Allen, J.F.: Maintaining knowledge about temporal intervals. Commun. ACM 26(11), 832\u2013843 (1983). https:\/\/doi.org\/10.1145\/182.358434","journal-title":"Commun. ACM"},{"key":"17_CR2","unstructured":"Ammanabrolu, P., Broniec, W., Mueller, A., Paul, J., Riedl, M.: Toward automated quest generation in text-adventure games. In: Proceedings of the 4th Workshop on Computational Creativity in Language Generation, pp. 1\u201312. Association for Computational Linguistics, Tokyo, Japan (2019). https:\/\/aclanthology.org\/2019.ccnlg-1.1"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Bang, Y., et al.: A multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023 (2023)","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"17_CR4","unstructured":"Blagec, K., Dorffner, G., Moradi, M., Samwald, M.: A critical analysis of metrics used for measuring progress in artificial intelligence. arXiv preprint arXiv:2008.02577 (2020)"},{"key":"17_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR6","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"17_CR7","doi-asserted-by":"publisher","DOI":"10.1017\/9781316584705","volume-title":"A Formal Theory of Commonsense Psychology: How People Think People Think","author":"AS Gordon","year":"2017","unstructured":"Gordon, A.S., Hobbs, J.R.: A Formal Theory of Commonsense Psychology: How People Think People Think. Cambridge University Press, Cambridge (2017). https:\/\/doi.org\/10.1017\/9781316584705"},{"key":"17_CR8","unstructured":"Gunning, D.: Machine common sense concept paper. arXiv preprint arXiv:1810.07528 (2018)"},{"key":"17_CR9","unstructured":"Kahneman, D.: Thinking, Fast and Slow. Macmillan (2011). Google-Books-ID: SHvzzuCnuv8C"},{"issue":"4","key":"17_CR10","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1038\/s42256-022-00478-4","volume":"4","author":"M Kejriwal","year":"2022","unstructured":"Kejriwal, M., Santos, H., Mulvehill, A.M., McGuinness, D.L.: Designing a strong test for measuring true common-sense reasoning. Nat. Mach. Intell. 4(4), 318\u2013322 (2022). https:\/\/doi.org\/10.1038\/s42256-022-00478-4","journal-title":"Nat. Mach. Intell."},{"key":"17_CR11","unstructured":"Kejriwal, M., Shen, K.: Do fine-tuned commonsense language models really generalize? arXiv preprint arXiv:2011.09159 (2020)"},{"key":"17_CR12","doi-asserted-by":"publisher","unstructured":"Lin, B.Y., et al.: CommonGen: a constrained text generation challenge for generative commonsense reasoning. In: Findings of the Association for Computational Linguistics (EMNLP 2020), pp. 1823\u20131840. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.165","DOI":"10.18653\/v1\/2020.findings-emnlp.165"},{"key":"17_CR13","unstructured":"Mitra, A., Banerjee, P., Pal, K.K., Mishra, S., Baral, C.: How additional knowledge can improve natural language commonsense question answering? arXiv preprint arXiv:1909.08855 (2020)"},{"key":"17_CR14","unstructured":"Neelakandan, N.: Creating multiple-choice questions: the dos and don\u2019ts (2019). https:\/\/elearningindustry.com\/creating-multiple-choice-questions"},{"key":"17_CR15","doi-asserted-by":"publisher","DOI":"10.1017\/exp.2021.9","volume":"2","author":"H Santos","year":"2021","unstructured":"Santos, H., Kejriwal, M., Mulvehill, A.M., Forbush, G., McGuinness, D.L., Rivera, A.R.: An experimental study measuring human annotator categorization agreement on commonsense sentences. Exp. Res. 2, e19 (2021)","journal-title":"Exp. Res."},{"key":"17_CR16","doi-asserted-by":"publisher","unstructured":"Santos, H., Shen, K., Mulvehill, A.M., Razeghi, Y., McGuinness, D.L., Kejriwal, M.: A theoretically grounded benchmark for evaluating machine commonsense (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.12184","DOI":"10.48550\/arXiv.2203.12184"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Shen, K., Kejriwal, M.: An experimental study measuring the generalization of fine-tuned language representation models across commonsense reasoning benchmarks. Expert Syst. e13243 (2023)","DOI":"10.1111\/exsy.13243"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-33469-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T23:43:42Z","timestamp":1729467822000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-33469-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031334689","9783031334696"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-33469-6_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"24 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial General Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Stockholm","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"agi2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/agi-conf.org\/2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"72","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}