{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/cicero","name":"CICERO","full_name":"Contextualized Commonsense Inference in Dialogues","description_markdown":"**CICERO** contains 53,000 inferences for five commonsense dimensions -- cause, subsequent event, prerequisite, motivation, and emotional reaction -- collected from 5600 dialogues. It involves two challenging generative and multi-choice alternative selection tasks for the state-of-the-art NLP models to solve. Download the dataset using [this link](https://github.com/declare-lab/CICERO/releases/download/v1.0.0/data.zip).","description_withheld":null,"homepage":"https://declare-lab.net/CICERO/","introduced_date":"2022-03-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/cicero-a-dataset-for-contextualized","title":"CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues","first_author":"Deepanway Ghosal","url":null},"license":{"name":"MIT","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Answer Selection","url":"/task/answer-selection","datasets_with_task":"/datasets/task/answer-selection"},{"name":"Generative Question Answering","url":"/task/generative-question-answering","datasets_with_task":"/datasets/task/generative-question-answering"},{"name":"Answer Generation","url":"/task/answer-generation","datasets_with_task":"/datasets/task/answer-generation"},{"name":"Multiview Contextual Commonsense Inference","url":"/task/multiview-contextual-commonsense-inference","datasets_with_task":"/datasets/task/multiview-contextual-commonsense-inference"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CICERO"],"data_loaders":[{"repo":"https://github.com/declare-lab/CICERO","url":"https://github.com/declare-lab/CICERO","frameworks":["pytorch"]}],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/generative-question-answering-on-cicero","task":"Generative Question Answering","dataset_variant":"CICERO","rows":4,"metrics":["ROUGE"],"first_row_in_archive_order":{"model":"T5-large pre-trained on GLUCOSE","paper":"/paper/cicero-a-dataset-for-contextualized","metrics":{"ROUGE":"0.2980"},"code_links":[{"title":"declare-lab/CICERO","url":"https://github.com/declare-lab/CICERO"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/answer-generation-on-cicero","task":"Answer Generation","dataset_variant":"CICERO","rows":2,"metrics":["ROUGE"],"first_row_in_archive_order":{"model":"T5-large pre-trained on GLUCOSE","paper":"/paper/cicero-a-dataset-for-contextualized","metrics":{"ROUGE":"0.2980"},"code_links":[{"title":"declare-lab/CICERO","url":"https://github.com/declare-lab/CICERO"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/answer-selection-on-cicero","task":"Answer Selection","dataset_variant":"CICERO","rows":2,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"T5-large","paper":"/paper/cicero-a-dataset-for-contextualized","metrics":{"Exact Match":"77.68"},"code_links":[{"title":"declare-lab/CICERO","url":"https://github.com/declare-lab/CICERO"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiview-contextual-commonsense-inference-on-1","task":"Multiview Contextual Commonsense Inference","dataset_variant":"CICERO","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DIALECT","paper":"/paper/multiview-contextual-commonsense-inference-a","metrics":{"Accuracy":"27.54"},"code_links":[{"title":"declare-lab/CICERO","url":"https://github.com/declare-lab/CICERO"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":2,"of":2,"counts":{"papers_with_a_benchmark_row":2,"with_a_code_link":2,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/multiview-contextual-commonsense-inference-a","slug":"multiview-contextual-commonsense-inference-a","title":"Multiview Contextual Commonsense Inference: A New Dataset and Task","date":"2022-10-06","arxiv_id":"2210.02890","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/cicero-a-dataset-for-contextualized","slug":"cicero-a-dataset-for-contextualized","title":"CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues","date":"2022-03-25","arxiv_id":"2203.13926","rows_on_this_dataset":8,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/multiview-contextual-commonsense-inference-a","slug":"multiview-contextual-commonsense-inference-a","title":"Multiview Contextual Commonsense Inference: A New Dataset and Task","date":"2022-10-06","arxiv_id":"2210.02890","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/cicero-a-dataset-for-contextualized","slug":"cicero-a-dataset-for-contextualized","title":"CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues","date":"2022-03-25","arxiv_id":"2203.13926","rows_on_this_dataset":8,"code_links":1,"syntology":null}],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"40706c024de270bf0af09d3a366e5a059e5f73b6b47966e1a9e9795f6d9b59a8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}