{"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/the-kandy-benchmark-incremental-neuro","title":"The KANDY Benchmark: Incremental Neuro-Symbolic Learning and Reasoning with Kandinsky Patterns","arxiv_id":"2402.17431","date":"2024-02-27","proceeding":null,"authors":["Luca Salvatore Lorello","Marco Lippi","Stefano Melacci"],"abstract":"Artificial intelligence is continuously seeking novel challenges and benchmarks to effectively measure performance and to advance the state-of-the-art. In this paper we introduce KANDY, a benchmarking framework that can be used to generate a variety of learning and reasoning tasks inspired by Kandinsky patterns. By creating curricula of binary classification tasks with increasing complexity and with sparse supervisions, KANDY can be used to implement benchmarks for continual and semi-supervised learning, with a specific focus on symbol compositionality. Classification rules are also provided in the ground truth to enable analysis of interpretable solutions. Together with the benchmark generation pipeline, we release two curricula, an easier and a harder one, that we propose as new challenges for the research community. With a thorough experimental evaluation, we show how both state-of-the-art neural models and purely symbolic approaches struggle with solving most of the tasks, thus calling for the application of advanced neuro-symbolic methods trained over time.","url_abs":"https://arxiv.org/abs/2402.17431v1","url_pdf":"https://arxiv.org/pdf/2402.17431v1.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":"the-kandy-benchmark-incremental-neuro","repo_url":"https://github.com/continual-nesy/kandybenchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"binary-classification","task_name":"Binary Classification"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.17431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17431"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/continual-nesy/kandybenchmark","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"ac997f6c68022ffb","entry":"elapsed_time","repo":"continual-nesy/kandybenchmark","repo_kind":"official","path":"baselines/ilp_baselines/utils.py","file_url":"https://github.com/continual-nesy/kandybenchmark/blob/HEAD/baselines/ilp_baselines/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ac997f6c68022ffb"}},{"code_sha256_prefix":"3a5cad450fae1051","entry":"generate_experiment_name","repo":"continual-nesy/kandybenchmark","repo_kind":"official","path":"baselines/ilp_baselines/utils.py","file_url":"https://github.com/continual-nesy/kandybenchmark/blob/HEAD/baselines/ilp_baselines/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3a5cad450fae1051"}},{"code_sha256_prefix":"517511da44bce0c8","entry":"generate_net","repo":"continual-nesy/kandybenchmark","repo_kind":"official","path":"baselines/neural_baselines/networks.py","file_url":"https://github.com/continual-nesy/kandybenchmark/blob/HEAD/baselines/neural_baselines/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"517511da44bce0c8"}},{"code_sha256_prefix":"f3fae54d3ac27a4b","entry":"load_dict","repo":"continual-nesy/kandybenchmark","repo_kind":"official","path":"baselines/neural_baselines/utils.py","file_url":"https://github.com/continual-nesy/kandybenchmark/blob/HEAD/baselines/neural_baselines/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f3fae54d3ac27a4b"}},{"code_sha256_prefix":"9a1f5db1c4d375d0","entry":"symbol_to_prolog_natural","repo":"continual-nesy/kandybenchmark","repo_kind":"official","path":"baselines/ilp_baselines/utils.py","file_url":"https://github.com/continual-nesy/kandybenchmark/blob/HEAD/baselines/ilp_baselines/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9a1f5db1c4d375d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}