{"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/learning-to-solve-constraint-satisfaction","title":"Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer","arxiv_id":"2307.04895","date":"2023-07-10","proceeding":null,"authors":["Zhun Yang","Adam Ishay","Joohyung Lee"],"abstract":"Constraint satisfaction problems (CSPs) are about finding values of variables that satisfy the given constraints. We show that Transformer extended with recurrence is a viable approach to learning to solve CSPs in an end-to-end manner, having clear advantages over state-of-the-art methods such as Graph Neural Networks, SATNet, and some neuro-symbolic models. With the ability of Transformer to handle visual input, the proposed Recurrent Transformer can straightforwardly be applied to visual constraint reasoning problems while successfully addressing the symbol grounding problem. We also show how to leverage deductive knowledge of discrete constraints in the Transformer's inductive learning to achieve sample-efficient learning and semi-supervised learning for CSPs.","url_abs":"https://arxiv.org/abs/2307.04895v1","url_pdf":"https://arxiv.org/pdf/2307.04895v1.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":"learning-to-solve-constraint-satisfaction","repo_url":"https://github.com/azreasoners/recurrent_transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"inductive-learning","task_name":"Inductive Learning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.04895","atlas_url":"https://app.syntology.ai/?focus=2307.04895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.04895"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/azreasoners/recurrent_transformer","reach":null}],"summary":{"ran":3,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":6,"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":1,"samples":[{"code_sha256_prefix":"db4f6eb0540de0f8","entry":"CausalSelfAttention","repo":"azreasoners/recurrent_transformer","repo_kind":"official","path":"mingpt/model.py","file_url":"https://github.com/azreasoners/recurrent_transformer/blob/HEAD/mingpt/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":"db4f6eb0540de0f8"}},{"code_sha256_prefix":"6134c9ccb641ad62","entry":"Disc","repo":"azreasoners/recurrent_transformer","repo_kind":"official","path":"mingpt/model.py","file_url":"https://github.com/azreasoners/recurrent_transformer/blob/HEAD/mingpt/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":"6134c9ccb641ad62"}},{"code_sha256_prefix":"02f8ad27ca4c2227","entry":"GPT","repo":"azreasoners/recurrent_transformer","repo_kind":"official","path":"mingpt/model.py","file_url":"https://github.com/azreasoners/recurrent_transformer/blob/HEAD/mingpt/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":"02f8ad27ca4c2227"}},{"code_sha256_prefix":"7e41f71a107809d1","entry":"bp","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7e41f71a107809d1"}},{"code_sha256_prefix":"f2e9cc2d9abc8708","entry":"reg_att_sudoku_c1","repo":"azreasoners/recurrent_transformer","repo_kind":"official","path":"mingpt/model.py","file_url":"https://github.com/azreasoners/recurrent_transformer/blob/HEAD/mingpt/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2e9cc2d9abc8708"}},{"code_sha256_prefix":"9766fa16fd393d68","entry":"reg_cardinality","repo":"azreasoners/recurrent_transformer","repo_kind":"official","path":"mingpt/model.py","file_url":"https://github.com/azreasoners/recurrent_transformer/blob/HEAD/mingpt/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9766fa16fd393d68"}},{"code_sha256_prefix":"d5a04fb7481be04b","entry":"Block","repo":"azreasoners/recurrent_transformer","repo_kind":"official","path":"mingpt/model.py","file_url":"https://github.com/azreasoners/recurrent_transformer/blob/HEAD/mingpt/model.py","link_basis":"first_harvest_node","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":"d5a04fb7481be04b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}