{"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/holstep","name":"HolStep","full_name":null,"description_markdown":"HolStep is a dataset based on higher-order logic (HOL) proofs, for the purpose of developing new machine learning-based theorem-proving strategies. \r\n\r\nSource: [HolStep: A Machine Learning Dataset for Higher-order Logic Theorem Proving](/paper/holstep-a-machine-learning-dataset-for-higher)","description_withheld":null,"homepage":"http://cl-informatik.uibk.ac.at/cek/holstep/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/holstep-a-machine-learning-dataset-for-higher","title":"HolStep: A Machine Learning Dataset for Higher-order Logic Theorem Proving","first_author":"Cezary Kaliszyk","url":null},"license":{"name":"BSD-3-Clause","url":null},"modalities":[],"tasks":[{"name":"Automated Theorem Proving","url":"/task/automated-theorem-proving","datasets_with_task":"/datasets/task/automated-theorem-proving"},{"name":"Mathematical Proofs","url":"/task/mathematical-proofs","datasets_with_task":"/datasets/task/mathematical-proofs"},{"name":"Dimensionality Reduction","url":"/task/dimensionality-reduction","datasets_with_task":"/datasets/task/dimensionality-reduction"}],"languages":[],"variants":["HolStep (Conditional)","HolStep (Unconditional)","HolStep"],"data_loaders":[],"num_papers_in_archive":10,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/automated-theorem-proving-on-holstep","task":"Automated Theorem Proving","dataset_variant":"HolStep (Conditional)","rows":5,"metrics":["Classification Accuracy"],"first_row_in_archive_order":{"model":"MPNN-DagLSTM","paper":"/paper/improving-graph-neural-network","metrics":{"Classification Accuracy":"0.916"},"code_links":[{"title":"IBM/LogicalFormulaEmbedder","url":"https://github.com/IBM/LogicalFormulaEmbedder"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/automated-theorem-proving-on-holstep-1","task":"Automated Theorem Proving","dataset_variant":"HolStep (Unconditional)","rows":4,"metrics":["Classification Accuracy"],"first_row_in_archive_order":{"model":"FormulaNet","paper":"/paper/premise-selection-for-theorem-proving-by-deep","metrics":{"Classification Accuracy":"0.900"},"code_links":[{"title":"princeton-vl/FormulaNet","url":"https://github.com/princeton-vl/FormulaNet"}]},"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":3,"of":3,"counts":{"papers_with_a_benchmark_row":3,"with_a_code_link":3,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/improving-graph-neural-network","slug":"improving-graph-neural-network","title":"Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling","date":"2019-11-15","arxiv_id":"1911.06904","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-graph-neural-network#ran","syntology_url":"https://syntology.ai/paper/1911.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06904"}}}},{"paper":"/paper/premise-selection-for-theorem-proving-by-deep","slug":"premise-selection-for-theorem-proving-by-deep","title":"Premise Selection for Theorem Proving by Deep Graph Embedding","date":"2017-09-28","arxiv_id":"1709.09994","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["princeton-vl/FormulaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/premise-selection-for-theorem-proving-by-deep#ran","syntology_url":"https://syntology.ai/paper/1709.09994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.09994"}}}},{"paper":"/paper/holstep-a-machine-learning-dataset-for-higher","slug":"holstep-a-machine-learning-dataset-for-higher","title":"HolStep: A Machine Learning Dataset for Higher-order Logic Theorem Proving","date":"2017-03-01","arxiv_id":"1703.00426","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/holstep-a-machine-learning-dataset-for-higher#ran","syntology_url":"https://syntology.ai/paper/1703.00426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.00426"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/improving-graph-neural-network","slug":"improving-graph-neural-network","title":"Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling","date":"2019-11-15","arxiv_id":"1911.06904","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-graph-neural-network#ran","syntology_url":"https://syntology.ai/paper/1911.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06904"}}}},{"paper":"/paper/premise-selection-for-theorem-proving-by-deep","slug":"premise-selection-for-theorem-proving-by-deep","title":"Premise Selection for Theorem Proving by Deep Graph Embedding","date":"2017-09-28","arxiv_id":"1709.09994","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["princeton-vl/FormulaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/premise-selection-for-theorem-proving-by-deep#ran","syntology_url":"https://syntology.ai/paper/1709.09994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.09994"}}}},{"paper":"/paper/holstep-a-machine-learning-dataset-for-higher","slug":"holstep-a-machine-learning-dataset-for-higher","title":"HolStep: A Machine Learning Dataset for Higher-order Logic Theorem Proving","date":"2017-03-01","arxiv_id":"1703.00426","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/holstep-a-machine-learning-dataset-for-higher#ran","syntology_url":"https://syntology.ai/paper/1703.00426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.00426"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/holstep/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/holstep/papers/ran/1","json":"/dataset/holstep/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":3,"samples_harvested":10,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":8,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":1,"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":"2c27792cdd85b479c54b43bae1d3fc64ff5ff722f2a5672516eeaaf80cac073a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}