{"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/diaforge-utc-r-0725","name":"diaforge-utc-r-0725","full_name":"DiaFORGE UTC: Unified Tool-Calling Conversations Dataset","description_markdown":"Dataset for our paper Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky which includes 5000 enterprise tools and the corresponding dialogues generated using DiaFORGE UTC data engine.\r\n\r\nThe dataset is generated with the data generation engine. The engine simulates a user agent and an assistant agent in a dialogue, where the user agent has a persona and the assistant agent has access to a set of tools. Detailed information about the data generation process can be found in the paper.\r\n\r\nEach entry in the dataset contains:\r\n- seed: Gold tool for the generated dialogue.\r\n- user_persona: Persona of the simulated user agent.\r\n- messages: List of messages in the dialogue, where each message is a dictionary containing:\r\n- distractor_tools: List of distractor tools that are not the gold tool but are relevant to the dialogue. These tools are used by user agent to generate utterances that are hard to disambiguate from the gold tool.\r\n- retrieved_tools: List of tools retrieved by the assistant agent and used by the assistant agent in order to ask clarifying questions to the user agent.","description_withheld":null,"homepage":"https://huggingface.co/datasets/sap-ai-research/diaforge-utc-r-0725","introduced_date":"2025-07-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/disambiguation-centric-finetuning-makes","title":"Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky","first_author":"Ashutosh Hathidara","url":null},"license":{"name":"CC BY-NC-SA","url":"https://spdx.org/licenses/CC-BY-NC-SA-4.0"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Dialog","url":"/datasets/modality/dialog"},{"name":"Actions","url":"/datasets/modality/actions"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Intent Detection","url":"/task/intent-detection","datasets_with_task":"/datasets/task/intent-detection"},{"name":"Large Language Model","url":"/task/large-language-model","datasets_with_task":"/datasets/task/large-language-model"},{"name":"Slot Filling","url":"/task/slot-filling","datasets_with_task":"/datasets/task/slot-filling"},{"name":"Entity Resolution","url":"/task/entity-resolution","datasets_with_task":"/datasets/task/entity-resolution"},{"name":"Dialogue Generation","url":"/task/dialogue-generation","datasets_with_task":"/datasets/task/dialogue-generation"},{"name":"Question Generation","url":"/task/question-generation","datasets_with_task":"/datasets/task/question-generation"},{"name":"Entity Disambiguation","url":"/task/entity-disambiguation","datasets_with_task":"/datasets/task/entity-disambiguation"},{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","datasets_with_task":"/datasets/task/self-supervised-learning"},{"name":"Dialogue State Tracking","url":"/task/dialogue-state-tracking","datasets_with_task":"/datasets/task/dialogue-state-tracking"},{"name":"Task-Oriented Dialogue Systems","url":"/task/task-oriented-dialogue-systems","datasets_with_task":"/datasets/task/task-oriented-dialogue-systems"},{"name":"Synthetic Data Generation","url":"/task/synthetic-data-generation","datasets_with_task":"/datasets/task/synthetic-data-generation"},{"name":"Intent Classification","url":"/task/intent-classification","datasets_with_task":"/datasets/task/intent-classification"},{"name":"Intent Recognition","url":"/task/intent-recognition","datasets_with_task":"/datasets/task/intent-recognition"},{"name":"Intent Discovery","url":"/task/intent-discovery","datasets_with_task":"/datasets/task/intent-discovery"},{"name":"Dialogue Evaluation","url":"/task/dialogue-evaluation","datasets_with_task":"/datasets/task/dialogue-evaluation"},{"name":"Intent Classification and Slot Filling","url":"/task/intent-classification-and-slot-filling","datasets_with_task":"/datasets/task/intent-classification-and-slot-filling"},{"name":"Text2text Generation","url":"/task/text2text-generation-1","datasets_with_task":"/datasets/task/text2text-generation-1"},{"name":"Conversational Question Answering","url":"/task/conversational-question-answering","datasets_with_task":"/datasets/task/conversational-question-answering"},{"name":"Conversational Response Generation","url":"/task/conversational-response-generation","datasets_with_task":"/datasets/task/conversational-response-generation"},{"name":"AI Agent","url":"/task/ai-agent","datasets_with_task":"/datasets/task/ai-agent"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["diaforge-utc-r-0725"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"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":0,"of":0,"counts":{"papers_with_a_benchmark_row":0,"with_a_code_link":0,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":0,"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":[],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[],"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":"4ac4d79252dbd0108fb95c9a9b4531b882340845fc78abd8db3039c9c58dbbbb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}