{"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/information-based-explanation-methods-for","title":"Information based explanation methods for deep learning agents -- with applications on large open-source chess models","arxiv_id":"2309.09702","date":"2023-09-18","proceeding":null,"authors":["Patrik Hammersborg","Inga Strümke"],"abstract":"With large chess-playing neural network models like AlphaZero contesting the state of the art within the world of computerised chess, two challenges present themselves: The question of how to explain the domain knowledge internalised by such models, and the problem that such models are not made openly available. This work presents the re-implementation of the concept detection methodology applied to AlphaZero in McGrath et al. (2022), by using large, open-source chess models with comparable performance. We obtain results similar to those achieved on AlphaZero, while relying solely on open-source resources. We also present a novel explainable AI (XAI) method, which is guaranteed to highlight exhaustively and exclusively the information used by the explained model. This method generates visual explanations tailored to domains characterised by discrete input spaces, as is the case for chess. Our presented method has the desirable property of controlling the information flow between any input vector and the given model, which in turn provides strict guarantees regarding what information is used by the trained model during inference. We demonstrate the viability of our method by applying it to standard 8x8 chess, using large open-source chess models.","url_abs":"https://arxiv.org/abs/2309.09702v1","url_pdf":"https://arxiv.org/pdf/2309.09702v1.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":"information-based-explanation-methods-for","repo_url":"https://github.com/patrik-ha/ii-map","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"alphazero","method_name":"AlphaZero"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.09702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09702"}},"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/patrik-ha/ii-map","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"21261ebb4b523acc","entry":"binary_accuracy_with_guessing","repo":"patrik-ha/ii-map","repo_kind":"official","path":"processing/concept_detection.py","file_url":"https://github.com/patrik-ha/ii-map/blob/HEAD/processing/concept_detection.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"21261ebb4b523acc"}},{"code_sha256_prefix":"eb8427fc25ff410d","entry":"make_probe","repo":"patrik-ha/ii-map","repo_kind":"official","path":"processing/concept_detection.py","file_url":"https://github.com/patrik-ha/ii-map/blob/HEAD/processing/concept_detection.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb8427fc25ff410d"}},{"code_sha256_prefix":"b79a670f9cc52ccf","entry":"pc_board_property","repo":"patrik-ha/ii-map","repo_kind":"official","path":"processing/leela_board.py","file_url":"https://github.com/patrik-ha/ii-map/blob/HEAD/processing/leela_board.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b79a670f9cc52ccf"}},{"code_sha256_prefix":"7f022cdba5374f4d","entry":"softmax","repo":"patrik-ha/ii-map","repo_kind":"official","path":"processing/ii_map.py","file_url":"https://github.com/patrik-ha/ii-map/blob/HEAD/processing/ii_map.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7f022cdba5374f4d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}