{"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/explainable-neural-computation-via-stack","title":"Explainable Neural Computation via Stack Neural Module Networks","arxiv_id":"1807.08556","date":"2018-07-23","proceeding":"ECCV 2018 9","authors":["Ronghang Hu","Jacob Andreas","Trevor Darrell","Kate Saenko"],"abstract":"In complex inferential tasks like question answering, machine learning models\nmust confront two challenges: the need to implement a compositional reasoning\nprocess, and, in many applications, the need for this reasoning process to be\ninterpretable to assist users in both development and prediction. Existing\nmodels designed to produce interpretable traces of their decision-making\nprocess typically require these traces to be supervised at training time. In\nthis paper, we present a novel neural modular approach that performs\ncompositional reasoning by automatically inducing a desired sub-task\ndecomposition without relying on strong supervision. Our model allows linking\ndifferent reasoning tasks though shared modules that handle common routines\nacross tasks. Experiments show that the model is more interpretable to human\nevaluators compared to other state-of-the-art models: users can better\nunderstand the model's underlying reasoning procedure and predict when it will\nsucceed or fail based on observing its intermediate outputs.","url_abs":"http://arxiv.org/abs/1807.08556v3","url_pdf":"http://arxiv.org/pdf/1807.08556v3.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":"explainable-neural-computation-via-stack","repo_url":"https://github.com/ronghanghu/snmn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.08556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.08556"}},"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/ronghanghu/snmn","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"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":"405776da9abb82d7","entry":"attention_interpolation","repo":"ronghanghu/snmn","repo_kind":"listed","path":"models_clevr_snmn/vis.py","file_url":"https://github.com/ronghanghu/snmn/blob/HEAD/models_clevr_snmn/vis.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"405776da9abb82d7"}},{"code_sha256_prefix":"b54010212bc5a4a3","entry":"build_input_unit","repo":"ronghanghu/snmn","repo_kind":"listed","path":"models_clevr_snmn/input_unit.py","file_url":"https://github.com/ronghanghu/snmn/blob/HEAD/models_clevr_snmn/input_unit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b54010212bc5a4a3"}},{"code_sha256_prefix":"a806de89f4b9d955","entry":"get_positional_encoding","repo":"ronghanghu/snmn","repo_kind":"listed","path":"models_clevr_snmn/input_unit.py","file_url":"https://github.com/ronghanghu/snmn/blob/HEAD/models_clevr_snmn/input_unit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a806de89f4b9d955"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}