{"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/the-pile","name":"The Pile","full_name":"The Pile","description_markdown":"The Pile is a 825 GiB diverse, open source language modelling data set that consists of 22 smaller, high-quality datasets combined together.\r\n\r\nDatasheet: [Datasheet for the Pile](https://paperswithcode.com/paper/datasheet-for-the-pile)","description_withheld":null,"homepage":"https://pile.eleuther.ai/","introduced_date":"2020-12-31","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","first_author":"Leo Gao","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[],"variants":["The Pile"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/the_pile","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jonatli/the_pile_mystic","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/EleutherAI/the_pile","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/EleutherAI/pile","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/MrAiran/nsfw-spanish","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/MrAiran/nsfw-dataset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/MrAiran/nsfw-pt_br","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":467,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-modelling-on-the-pile","task":"Language Modelling","dataset_variant":"The Pile","rows":39,"metrics":["Bits per byte","Test perplexity"],"first_row_in_archive_order":{"model":"Test-Time Fine-Tuning with SIFT + Llama-3.2 (3B)","paper":"/paper/efficiently-learning-at-test-time-active-fine","metrics":{"Bits per byte":"0.557"},"code_links":[{"title":"jonhue/activeft","url":"https://github.com/jonhue/activeft"}]},"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":7,"of":7,"counts":{"papers_with_a_benchmark_row":7,"with_a_code_link":6,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":7,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"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/efficiently-learning-at-test-time-active-fine","slug":"efficiently-learning-at-test-time-active-fine","title":"Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs","date":"2024-10-10","arxiv_id":"2410.08020","rows_on_this_dataset":15,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jonhue/activeft"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficiently-learning-at-test-time-active-fine#ran","syntology_url":"https://syntology.ai/paper/2410.08020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08020"}}}},{"paper":"/paper/specialized-language-models-with-cheap","slug":"specialized-language-models-with-cheap","title":"Need a Small Specialized Language Model? Plan Early!","date":"2024-02-02","arxiv_id":"2402.01093","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/test-time-training-on-nearest-neighbors-for","slug":"test-time-training-on-nearest-neighbors-for","title":"Test-Time Training on Nearest Neighbors for Large Language Models","date":"2023-05-29","arxiv_id":"2305.18466","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["socialfoundations/tttlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/test-time-training-on-nearest-neighbors-for#ran","syntology_url":"https://syntology.ai/paper/2305.18466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18466"}}}},{"paper":"/paper/hungry-hungry-hippos-towards-language","slug":"hungry-hungry-hippos-towards-language","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","date":"2022-12-28","arxiv_id":"2212.14052","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["hazyresearch/h3"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hungry-hungry-hippos-towards-language#ran","syntology_url":"https://syntology.ai/paper/2212.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14052"}}}},{"paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","slug":"glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","rows_on_this_dataset":3,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["thudm/glm-130b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/glm-130b-an-open-bilingual-pre-trained-model#ran","syntology_url":"https://syntology.ai/paper/2210.02414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02414"}}}},{"paper":"/paper/knowledge-unlearning-for-mitigating-privacy","slug":"knowledge-unlearning-for-mitigating-privacy","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","date":"2022-10-04","arxiv_id":"2210.01504","rows_on_this_dataset":6,"code_links":2,"syntology":null},{"paper":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for","slug":"the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","date":"2020-12-31","arxiv_id":"2101.00027","rows_on_this_dataset":8,"code_links":22,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["EleutherAI/The-Pile"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for#ran","syntology_url":"https://syntology.ai/paper/2101.00027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00027"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/efficiently-learning-at-test-time-active-fine","slug":"efficiently-learning-at-test-time-active-fine","title":"Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs","date":"2024-10-10","arxiv_id":"2410.08020","rows_on_this_dataset":15,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jonhue/activeft"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficiently-learning-at-test-time-active-fine#ran","syntology_url":"https://syntology.ai/paper/2410.08020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08020"}}}},{"paper":"/paper/specialized-language-models-with-cheap","slug":"specialized-language-models-with-cheap","title":"Need a Small Specialized Language Model? Plan Early!","date":"2024-02-02","arxiv_id":"2402.01093","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/test-time-training-on-nearest-neighbors-for","slug":"test-time-training-on-nearest-neighbors-for","title":"Test-Time Training on Nearest Neighbors for Large Language Models","date":"2023-05-29","arxiv_id":"2305.18466","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["socialfoundations/tttlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/test-time-training-on-nearest-neighbors-for#ran","syntology_url":"https://syntology.ai/paper/2305.18466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18466"}}}},{"paper":"/paper/hungry-hungry-hippos-towards-language","slug":"hungry-hungry-hippos-towards-language","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","date":"2022-12-28","arxiv_id":"2212.14052","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["hazyresearch/h3"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hungry-hungry-hippos-towards-language#ran","syntology_url":"https://syntology.ai/paper/2212.14052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14052"}}}},{"paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","slug":"glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","rows_on_this_dataset":3,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["thudm/glm-130b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/glm-130b-an-open-bilingual-pre-trained-model#ran","syntology_url":"https://syntology.ai/paper/2210.02414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02414"}}}},{"paper":"/paper/knowledge-unlearning-for-mitigating-privacy","slug":"knowledge-unlearning-for-mitigating-privacy","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","date":"2022-10-04","arxiv_id":"2210.01504","rows_on_this_dataset":6,"code_links":2,"syntology":null},{"paper":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for","slug":"the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","date":"2020-12-31","arxiv_id":"2101.00027","rows_on_this_dataset":8,"code_links":22,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["EleutherAI/The-Pile"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for#ran","syntology_url":"https://syntology.ai/paper/2101.00027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00027"}}}}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/the-pile/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/the-pile/papers/ran/1","json":"/dataset/the-pile/papers/ran/1.json","rows":5}],"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":5,"samples_harvested":44,"samples_ran":28,"samples_constructed":0,"samples_ran_checked":23,"samples_ran_instrument_failed":5,"samples_unverified":16,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":5,"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":1,"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/language-modelling-on-the-pile","since_archive":"/sota/language-modelling-on-the-pile#since-judged","papers_judged":1,"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":"2b1ef4e3a6de761ff68390e9218af4dfc80e8e0668597e7b395a028188125ff2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}