{"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/grailqa","name":"GrailQA","full_name":"Strongly Generalizable Question Answering","description_markdown":"GrailQA is a new large-scale, high-quality dataset for question answering on knowledge bases (KBQA) on Freebase with 64,331 questions annotated with both answers and corresponding logical forms in different syntax (i.e., SPARQL, S-expression, etc.). It can be used to test three levels of generalization in KBQA: i.i.d., compositional, and zero-shot.","description_withheld":null,"homepage":"https://dki-lab.github.io/GrailQA/","introduced_date":"2020-11-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/beyond-i-i-d-three-levels-of-generalization","title":"Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases","first_author":"Yu Gu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Generation","url":"/task/question-generation","datasets_with_task":"/datasets/task/question-generation"},{"name":"Knowledge Base Question Answering","url":"/task/knowledge-base-question-answering","datasets_with_task":"/datasets/task/knowledge-base-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GrailQA","GrailQA-IID","GrailQA-Zero-Shot","GrailQA-Compositional"],"data_loaders":[],"num_papers_in_archive":34,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-generation-on-grailqa-compositional","task":"Question Generation","dataset_variant":"GrailQA-Compositional","rows":4,"metrics":["METEOR","BLEU","FactSpotter"],"first_row_in_archive_order":{"model":"FactJointGT","paper":"/paper/factspotter-evaluating-the-factual","metrics":{"BLEU":"31.25","FactSpotter":"97.10","METEOR":"36.21"},"code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-generation-on-grailqa-iid","task":"Question Generation","dataset_variant":"GrailQA-IID","rows":4,"metrics":["BLEU","METEOR","FactSpotter"],"first_row_in_archive_order":{"model":"FactT5B","paper":"/paper/factspotter-evaluating-the-factual","metrics":{"BLEU":"46.10","FactSpotter":"99.50","METEOR":"42.67"},"code_links":[{"title":"guihuzhang/FactSpotter","url":"https://github.com/guihuzhang/FactSpotter"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-generation-on-grailqa-zero-shot","task":"Question Generation","dataset_variant":"GrailQA-Zero-Shot","rows":4,"metrics":["METEOR","bleu","FactSpotter"],"first_row_in_archive_order":{"model":"JointGT","paper":"/paper/jointgt-graph-text-joint-representation","metrics":{"FactSpotter":"94.15","METEOR":"37.69","bleu":"32.94"},"code_links":[{"title":"thu-coai/JointGT","url":"https://github.com/thu-coai/JointGT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/knowledge-base-question-answering-on-grailqa","task":"Knowledge Base Question Answering","dataset_variant":"GrailQA","rows":2,"metrics":["Compositional EM","Compositional F1","EM","I.I.D. EM","I.I.D. F1","Overall EM","Overall F1","Zero-shot EM","Zero-shot F1"],"first_row_in_archive_order":{"model":"ReTraCk","paper":"/paper/retrack-a-flexible-and-efficient-framework","metrics":{"Compositional EM":"61.5","Compositional F1":"70.9","I.I.D. EM":"84.4","I.I.D. F1":"87.5","Overall EM":"58.1","Overall F1":"65.3","Zero-shot EM":"44.6","Zero-shot F1":"52.5"},"code_links":[{"title":"microsoft/KC","url":"https://github.com/microsoft/KC/tree/main/papers/ReTraCk"}]},"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":5,"of":5,"counts":{"papers_with_a_benchmark_row":5,"with_a_code_link":5,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"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/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/paths-over-graph-knowledge-graph-enpowered#ran","syntology_url":"https://syntology.ai/paper/2410.14211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14211"}}}},{"paper":"/paper/factspotter-evaluating-the-factual","slug":"factspotter-evaluating-the-factual","title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","date":"2023-10-25","arxiv_id":null,"rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/retrack-a-flexible-and-efficient-framework","slug":"retrack-a-flexible-and-efficient-framework","title":"ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering","date":"2021-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/jointgt-graph-text-joint-representation","slug":"jointgt-graph-text-joint-representation","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","date":"2021-06-19","arxiv_id":"2106.10502","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/investigating-pretrained-language-models-for","slug":"investigating-pretrained-language-models-for","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","date":"2020-07-16","arxiv_id":"2007.08426","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["UKPLab/plms-graph2text"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/investigating-pretrained-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2007.08426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08426"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/paths-over-graph-knowledge-graph-enpowered#ran","syntology_url":"https://syntology.ai/paper/2410.14211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14211"}}}},{"paper":"/paper/factspotter-evaluating-the-factual","slug":"factspotter-evaluating-the-factual","title":"FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation","date":"2023-10-25","arxiv_id":null,"rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/retrack-a-flexible-and-efficient-framework","slug":"retrack-a-flexible-and-efficient-framework","title":"ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering","date":"2021-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/jointgt-graph-text-joint-representation","slug":"jointgt-graph-text-joint-representation","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","date":"2021-06-19","arxiv_id":"2106.10502","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/investigating-pretrained-language-models-for","slug":"investigating-pretrained-language-models-for","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","date":"2020-07-16","arxiv_id":"2007.08426","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["UKPLab/plms-graph2text"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/investigating-pretrained-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2007.08426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08426"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/grailqa/papers/ran/1","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":[{"order":"ran","page":1,"of":1,"url":"/dataset/grailqa/papers/ran/1","json":"/dataset/grailqa/papers/ran/1.json","rows":2}],"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":2,"samples_harvested":24,"samples_ran":18,"samples_constructed":0,"samples_ran_checked":18,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"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":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/knowledge-base-question-answering-on-grailqa","since_archive":"/sota/knowledge-base-question-answering-on-grailqa#since-judged","papers_judged":2,"placed":0}]},"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":"3a7e3db633ec51329a8f26df3f1a0c241d2f930d84fe8cca6f65d7a591d20c0e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}