{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/bedd-the-minerl-basalt-evaluation-and-1","title":"BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks","arxiv_id":"2312.02405","date":"2023-12-05","proceeding":"NeurIPS 2023 11","authors":["Stephanie Milani","Anssi Kanervisto","Karolis Ramanauskas","Sander Schulhoff","Brandon Houghton","Rohin Shah"],"abstract":"The MineRL BASALT competition has served to catalyze advances in learning from human feedback through four hard-to-specify tasks in Minecraft, such as create and photograph a waterfall. Given the completion of two years of BASALT competitions, we offer to the community a formalized benchmark through the BASALT Evaluation and Demonstrations Dataset (BEDD), which serves as a resource for algorithm development and performance assessment. BEDD consists of a collection of 26 million image-action pairs from nearly 14,000 videos of human players completing the BASALT tasks in Minecraft. It also includes over 3,000 dense pairwise human evaluations of human and algorithmic agents. These comparisons serve as a fixed, preliminary leaderboard for evaluating newly-developed algorithms. To enable this comparison, we present a streamlined codebase for benchmarking new algorithms against the leaderboard. In addition to presenting these datasets, we conduct a detailed analysis of the data from both datasets to guide algorithm development and evaluation. The released code and data are available at https://github.com/minerllabs/basalt-benchmark .","url_abs":"https://arxiv.org/abs/2312.02405v1","url_pdf":"https://arxiv.org/pdf/2312.02405v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bedd-the-minerl-basalt-evaluation-and-1","repo_url":"https://github.com/minerllabs/basalt-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"minecraft","task_name":"Minecraft"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.02405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02405"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/minerllabs/basalt-benchmark","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":11,"ran":10,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4459e00c3d091105","entry":"create_json_entry_dict","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/rollout_model.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/rollout_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4459e00c3d091105"}},{"code_sha256_prefix":"2bcf842598e9b062","entry":"get_band_diagonal_mask","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/vpt_lib/masked_attention.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/vpt_lib/masked_attention.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2bcf842598e9b062"}},{"code_sha256_prefix":"eb197d6a76f63639","entry":"get_mask","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/vpt_lib/masked_attention.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/vpt_lib/masked_attention.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb197d6a76f63639"}},{"code_sha256_prefix":"5234c0dfb707f813","entry":"intprod","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/vpt_lib/misc.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/vpt_lib/misc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5234c0dfb707f813"}},{"code_sha256_prefix":"b5f9bf2f6cbd78b7","entry":"load_model_parameters","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/embed_trajectories.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/embed_trajectories.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5f9bf2f6cbd78b7"}},{"code_sha256_prefix":"abb7428785776805","entry":"remove_numpyness_and_remove_zeros","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/rollout_model.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/rollout_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abb7428785776805"}},{"code_sha256_prefix":"69a190b789185068","entry":"resize_image","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/vpt_lib/agent.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/vpt_lib/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"69a190b789185068"}},{"code_sha256_prefix":"e9f218ee05e29fad","entry":"store_args","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/vpt_lib/minecraft_util.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/vpt_lib/minecraft_util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9f218ee05e29fad"}},{"code_sha256_prefix":"6e2674f0120e0c29","entry":"transpose","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/vpt_lib/misc.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/vpt_lib/misc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e2674f0120e0c29"}},{"code_sha256_prefix":"5760c363cbb2cc44","entry":"transpose_undo","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/vpt_lib/misc.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/vpt_lib/misc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5760c363cbb2cc44"}},{"code_sha256_prefix":"46d393af0ba227d6","entry":"get_norm_entropy_from_cat_head","repo":"minerllabs/basalt-benchmark","repo_kind":"official","path":"basalt/vpt_lib/minecraft_util.py","file_url":"https://github.com/minerllabs/basalt-benchmark/blob/HEAD/basalt/vpt_lib/minecraft_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46d393af0ba227d6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}