{"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/probabilistic-abduction-for-visual-abstract","title":"Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures","arxiv_id":"2401.16024","date":"2024-01-29","proceeding":null,"authors":["Michael Hersche","Francesco Di Stefano","Thomas Hofmann","Abu Sebastian","Abbas Rahimi"],"abstract":"Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving Raven's progressive matrices (RPM), a visual test for assessing abstract reasoning abilities, by using distributed computation and operators provided by vector-symbolic architectures (VSA). Instead of hard-coding the rule formulations associated with RPMs, our approach can learn the VSA rule formulations (hence the name Learn-VRF) with just one pass through the training data. Yet, our approach, with compact parameters, remains transparent and interpretable. Learn-VRF yields accurate predictions on I-RAVEN's in-distribution data, and exhibits strong out-of-distribution capabilities concerning unseen attribute-rule pairs, significantly outperforming pure connectionist baselines including large language models. Our code is available at https://github.com/IBM/learn-vector-symbolic-architectures-rule-formulations.","url_abs":"https://arxiv.org/abs/2401.16024v1","url_pdf":"https://arxiv.org/pdf/2401.16024v1.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":"probabilistic-abduction-for-visual-abstract","repo_url":"https://github.com/ibm/learn-vector-symbolic-architectures-rule-formulations","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.16024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16024"}},"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/ibm/learn-vector-symbolic-architectures-rule-formulations","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"a410048e8b196351","entry":"create_one_hot","repo":"ibm/learn-vector-symbolic-architectures-rule-formulations","repo_kind":"official","path":"src/raven_one_hot.py","file_url":"https://github.com/ibm/learn-vector-symbolic-architectures-rule-formulations/blob/HEAD/src/raven_one_hot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a410048e8b196351"}},{"code_sha256_prefix":"1c8dd285caf66c7d","entry":"gaussian_kernel","repo":"ibm/learn-vector-symbolic-architectures-rule-formulations","repo_kind":"official","path":"src/attribute_level_backend.py","file_url":"https://github.com/ibm/learn-vector-symbolic-architectures-rule-formulations/blob/HEAD/src/attribute_level_backend.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1c8dd285caf66c7d"}},{"code_sha256_prefix":"a5f9c9e59af2eb45","entry":"gaussian_smooth","repo":"ibm/learn-vector-symbolic-architectures-rule-formulations","repo_kind":"official","path":"src/attribute_level_backend.py","file_url":"https://github.com/ibm/learn-vector-symbolic-architectures-rule-formulations/blob/HEAD/src/attribute_level_backend.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a5f9c9e59af2eb45"}},{"code_sha256_prefix":"aebe978a8b616291","entry":"smooth_dist","repo":"ibm/learn-vector-symbolic-architectures-rule-formulations","repo_kind":"official","path":"src/raven_one_hot.py","file_url":"https://github.com/ibm/learn-vector-symbolic-architectures-rule-formulations/blob/HEAD/src/raven_one_hot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"aebe978a8b616291"}},{"code_sha256_prefix":"22258d05f577d42b","entry":"compute_loss_and_scores","repo":"ibm/learn-vector-symbolic-architectures-rule-formulations","repo_kind":"official","path":"src/rule_level_backend.py","file_url":"https://github.com/ibm/learn-vector-symbolic-architectures-rule-formulations/blob/HEAD/src/rule_level_backend.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"22258d05f577d42b"}},{"code_sha256_prefix":"e4106e226e7ddf33","entry":"scene_gaussian_smooth","repo":"ibm/learn-vector-symbolic-architectures-rule-formulations","repo_kind":"official","path":"src/attribute_level_backend.py","file_url":"https://github.com/ibm/learn-vector-symbolic-architectures-rule-formulations/blob/HEAD/src/attribute_level_backend.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e4106e226e7ddf33"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}