{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T02:37:19Z","timestamp":1777775839470,"version":"3.51.4"},"reference-count":90,"publisher":"Emerald","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,30]]},"abstract":"<jats:p>Neurosymbolic programming combines the otherwise complementary worlds of deep learning and symbolic reasoning. It thereby enables more accurate, interpretable, and domain-aware solutions to AI tasks. We introduce Scallop, a general-purpose language and compiler toolchain for developing neurosymbolic applications. A Scallop program specifies a suitable decomposition of an AI task\u2019s computation into separate learning and reasoning modules. Learning modules are built using existing machine learning frameworks and range from custom neural models to foundation models for language, vision, and multi-modal data. Reasoning modules are specified in a declarative logic programming language based on Datalog which supports expressive features such as recursion, aggregation, negation, and probabilistic programming over structured relations.<\/jats:p>\n                  <jats:p>Scallop\u2019s compiler enables to automatically train neurosym- bolic programs in a data- and compute-efficient manner using an end-to-end differentiable reasoning framework. Scallop also supports features useful for building real-world applications such as user-defined data types, and foreign interfaces. We demonstrate programming in Scallop for applications that span the domains of image and video processing, natural language processing, planning, and information retrieval in a variety of learning settings such as supervised learning, reinforcement learning, rule learning, contrastive learning, and in-context learning.<\/jats:p>","DOI":"10.1561\/2500000059","type":"journal-article","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T03:32:46Z","timestamp":1735529566000},"page":"118-249","source":"Crossref","is-referenced-by-count":3,"title":["Neurosymbolic Programming in Scallop: Principles and Practice"],"prefix":"10.1108","volume":"8","author":[{"given":"Ziyang","family":"Li","sequence":"first","affiliation":[{"name":"University of Pennsylvania ,","place":["USA"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiani","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Pennsylvania ,","place":["USA"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Pennsylvania ,","place":["USA"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayur","family":"Naik","sequence":"additional","affiliation":[{"name":"University of Pennsylvania ,","place":["USA"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2024,12,30]]},"reference":[{"key":"2026032910310461500_ref001","volume-title":"Foundations of Databases: The Logical Level","author":"Abiteboul","year":"1995"},{"key":"2026032910310461500_ref002","author":"Albers","year":"2009"},{"key":"2026032910310461500_ref003","doi-asserted-by":"crossref","unstructured":"Alur, R., R.Bod\u00edk, G.Juniwal, M. M. K.Martin, M.Raghothaman, S. A.Seshia, R.Singh, A.Solar-Lezama, E.Torlak, and A.Udupa. (2013). \u201cSyntax-guided synthesis\u201d. 2013 Formal Methods in Computer-Aided Design : 1\u20138. URL: https:\/\/api.semanticscholar.org\/CorpusID:6705760.","DOI":"10.1109\/FMCAD.2013.6679385"},{"key":"2026032910310461500_ref004","article-title":"Prompting Is Programming: A Query Language For Large Language Models","volume-title":"PLDI","author":"Beurer-Kellner","year":"2022"},{"key":"2026032910310461500_ref005","volume-title":"On the Opportunities and Risks of Foundation Models","author":"Bommasani","year":"2021"},{"key":"2026032910310461500_ref006","volume-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023"},{"issue":"4","key":"2026032910310461500_ref007","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1007\/s00165-005-0071-z","article-title":"Concurrent software verification with states, events, and deadlocks","volume":"17","author":"Chaki","year":"2005","journal-title":"Formal Aspects of Computing"},{"key":"2026032910310461500_ref008","first-page":"3546","volume-title":"D3tw: Discriminative differentiable dynamic time warping for weakly supervised action alignment and segmentation","author":"Chang","year":"2019"},{"issue":"3","key":"2026032910310461500_ref009","doi-asserted-by":"publisher","DOI":"10.1561\/2500000049","article-title":"Neurosymbolic Programming","volume":"7","author":"Chaudhuri","year":"2021","journal-title":"Foundations and Trends in Programming Languages"},{"key":"2026032910310461500_ref010","volume-title":"Evaluating Large Language Models Trained on Code","author":"Chen","year":"2021"},{"key":"2026032910310461500_ref011","volume-title":"Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension","author":"Chen","year":"2020"},{"key":"2026032910310461500_ref012","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1179","article-title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","volume-title":"EMNLP","author":"Cho","year":"2014"},{"key":"2026032910310461500_ref013","unstructured":"Cong, Y., W.Liao, H.Ackermann, M. Y.Yang, and B.Rosenhahn. (2021). \u201cSpatial-Temporal Transformer for Dynamic Scene Graph Generation\u201d. CoRR. abs\/2107.12309. url: https:\/\/arxiv.org\/abs\/2107.12309."},{"key":"2026032910310461500_ref014","doi-asserted-by":"crossref","unstructured":"Csomay-Shanklin, N., W. D.Compton, I. D. J.Rodriguez, E. R.Ambrose, Y.Yue, and A. D.Ames. (2024). \u201cRobust Agility via Learned Zero Dynamics Policies\u201d. url: https:\/\/arxiv.org\/abs\/2409.06125.","DOI":"10.1109\/IROS58592.2024.10801322"},{"key":"2026032910310461500_ref015","volume-title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","author":"Damen","year":"2018"},{"key":"2026032910310461500_ref016","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","article-title":"Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100","volume":"130","author":"Damen","year":"2022","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"2026032910310461500_ref017","doi-asserted-by":"publisher","DOI":"10.4230\/LIPIcs.CSL.2021.17","volume-title":"Semiring Provenance for Fixed-Point Logic","author":"Dannert","year":"2021"},{"key":"2026032910310461500_ref018","doi-asserted-by":"publisher","DOI":"10.5591\/978-1-57735-516-8\/IJCAI11-143","volume-title":"SDD: A New Canonical Representation of Propositional Knowledge Bases","author":"Darwiche","year":"2011"},{"key":"2026032910310461500_ref019","first-page":"854","volume-title":"Linear temporal logic and linear dynamic logic on finite traces","author":"De Giacomo","year":"2013"},{"key":"2026032910310461500_ref020","volume-title":"HOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DETECT AND FIX BUGS IN PROGRAMS","author":"Dinella","year":"2020"},{"issue":"5","key":"2026032910310461500_ref021","doi-asserted-by":"crossref","first-page":"1244","DOI":"10.1109\/TAC.2014.2298143","article-title":"Optimal control of Markov decision processes with linear temporal logic constraints","volume":"59","author":"Ding","year":"2014","journal-title":"IEEE Transactions on Automatic Control"},{"key":"2026032910310461500_ref022","doi-asserted-by":"crossref","unstructured":"Ellis, K., A.Albright, A.Solar-Lezama, J. B.Tenenbaum, and T.J.O\u2019Donnell. (2022). \u201cSynthesizing theories of human language with Bayesian program induction\u201d. Nature Communications. 13. URL: https:\/\/api.semanticscholar.org\/CorpusID:251951680.","DOI":"10.1038\/s41467-022-32012-w"},{"key":"2026032910310461500_ref023","unstructured":"Ellis, K., C.Wong, M. I.Nye, M.Sabl\u00e9-Meyer, L.Cary, L.Morales, L. B.Hewitt, A.Solar-Lezama, and J. B.Tenenbaum. (2020). \u201cDreamCoder: Growing generalizable, interpretable knowledge with wakesleep Bayesian program learning\u201d. CoRR. abs\/2006.08381. URL: https:\/\/arxiv.org\/abs\/2006.08381."},{"key":"2026032910310461500_ref024","volume-title":"Violet: End-to-end video-language transformers with masked visualtoken modeling","author":"Fu","year":"2021"},{"key":"2026032910310461500_ref025","volume-title":"PAL: Program-aided Language Models","author":"Gao","year":"2023"},{"key":"2026032910310461500_ref026","doi-asserted-by":"crossref","unstructured":"Grauman, K., A.Westbury, E.Byrne, Z.Chavis, A.Furnari, R.Girdhar, J.Hamburger, H.Jiang, M.Liu, X.Liu, M.Martin, T.Nagarajan, I.Radosavovic, S. K.Ramakrishnan, F.Ryan, J.Sharma, M.Wray, M.Xu, E. Z.Xu, C.Zhao, S.Bansal, D.Batra, V.Cartillier, S.Crane, T.Do, M.Doulaty, A.Erapalli, C.Feichtenhofer, A.Fragomeni, Q.Fu, C.Fuegen, A.Gebreselasie, C.Gonz\u00e1lez, J.Hillis, X.Huang, Y.Huang, W.Jia, W.Khoo, J.Kol\u00e1r, S.Kottur, A.Kumar, F.Landini, C.Li, Y.Li, Z.Li, K.Mangalam, R.Modhugu, J.Munro, T.Murrell, T.Nishiyasu, W.Price, P. R.Puentes, M.Ramazanova, L.Sari, K.Somasundaram, A.Southerland, Y.Sugano, R.Tao, M.Vo, Y.Wang, X.Wu, T.Yagi, Y.Zhu, P.Arbelaez, D.Crandall, D.Damen, G. M.Farinella, B.Ghanem, V. K.Ithapu, C. V.Jawahar, H.Joo, K.Kitani, H.Li, R. A.Newcombe, A.Oliva, H. S.Park, J. M.Rehg, Y.Sato, J.Shi, M. Z.Shou, A.Torralba, L.Torresani, M.Yan, and J.Malik. (2021). \u201cEgo4D: Around the World in 3, 000 Hours of Egocentric Video\u201d. CoRR. abs\/2110.07058. url: https:\/\/arxiv.org\/abs\/2110.07058.","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"2026032910310461500_ref027","doi-asserted-by":"publisher","DOI":"10.1145\/1265530.1265535","volume-title":"Provenance Semirings","author":"Green","year":"2007"},{"key":"2026032910310461500_ref028","volume-title":"Visual Programming: Compositional visual reasoning without training","author":"Gupta","year":"2022"},{"key":"2026032910310461500_ref029","doi-asserted-by":"crossref","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume-title":"Neural computation","author":"Hochreiter","year":"1997"},{"key":"2026032910310461500_ref030","volume-title":"Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning","author":"Huang","year":"2021"},{"key":"2026032910310461500_ref031","article-title":"Compositional Attention Networks for Machine Reasoning","volume-title":"ICLR","author":"Hudson","year":"2018"},{"key":"2026032910310461500_ref032","doi-asserted-by":"crossref","unstructured":"Johnson, J., B.Hariharan, L.van der Maaten, L.Fei-Fei, C. L.Zitnick, and R. B.Girshick. (2016). \u201cCLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning\u201d. url: http:\/\/arxiv.org\/abs\/1612.06890.","DOI":"10.1109\/CVPR.2017.215"},{"key":"2026032910310461500_ref033","article-title":"BERT: Pretraining of Deep Bidirectional Transformers for Language Understanding","volume-title":"NAACL","author":"Kenton","year":"2019"},{"key":"2026032910310461500_ref034","first-page":"1","volume-title":"Algorithmic verification of linear temporal logic specifications","author":"Kesten","year":"1998"},{"key":"2026032910310461500_ref035","volume-title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","author":"Kim","year":"2021"},{"key":"2026032910310461500_ref036","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00371","volume-title":"Segment Anything","author":"Kirillov","year":"2023"},{"key":"2026032910310461500_ref037","article-title":"Large language models are zero-shot reasoners","volume-title":"NeurIPS","author":"Kojima","year":"2022"},{"key":"2026032910310461500_ref038","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791","volume-title":"GradientBased Learning Applied to Document Recognition","author":"Lecun","year":"1998"},{"key":"2026032910310461500_ref039","volume-title":"Solving Quantitative Reasoning Problems with Language Models","author":"Lewkowycz","year":"2022"},{"key":"2026032910310461500_ref040","unstructured":"Li, J., Y.Wang, C.Wang, Y.Tai, J.Qian, J.Yang, C.Wang, J.Li, and F.Huang. (2018). \u201cDSFD: Dual Shot Face Detector\u201d. url: http:\/\/arxiv.org\/abs\/1810.10220."},{"key":"2026032910310461500_ref041","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.06649","article-title":"Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning","volume-title":"ICML","author":"Li","year":"2020"},{"key":"2026032910310461500_ref042","volume-title":"From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering","author":"Li","year":"2022"},{"key":"2026032910310461500_ref043","doi-asserted-by":"publisher","DOI":"10.1145\/3591280","article-title":"Scallop: A Language for Neurosymbolic Programming","volume-title":"PLDI","author":"Li","year":"2023"},{"key":"2026032910310461500_ref044","doi-asserted-by":"publisher","first-page":"1400","DOI":"10.1109\/SP40001.2021.00090","volume-title":"ARBITRAR: User-Guided API Misuse Detection","author":"Li","year":"2021"},{"key":"2026032910310461500_ref045","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","author":"Liu","year":"2019"},{"key":"2026032910310461500_ref046","unstructured":"Ma, Y. J., W.Liang, G.Wang, D.-A.Huang, O.Bastani, D.Jayaraman, Y.Zhu, L.Fan, and A.Anandkumar. (2024). \u201cEureka: HumanLevel Reward Design via Coding Large Language Models\u201d. url: https:\/\/arxiv.org\/abs\/2310.12931."},{"key":"2026032910310461500_ref047","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1016\/j.artint.2021.103504","article-title":"Neural Probabilistic Logic Programming in DeepProbLog","volume-title":"Artificial Intelligence","author":"Manhaeve","year":"2021"},{"key":"2026032910310461500_ref048","volume-title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","author":"Mao","year":"2019"},{"key":"2026032910310461500_ref049","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.findings-emnlp.182","volume-title":"Sources of Hallucination by Large Language Models on Inference Tasks","author":"McKenna","year":"2023"},{"key":"2026032910310461500_ref050","volume-title":"Simple OpenVocabulary Object Detection with Vision Transformers","author":"Minderer","year":"2022"},{"key":"2026032910310461500_ref051","article-title":"Learning Reasoning Strategies in End-to-End Differentiable Proving","volume-title":"ICML","author":"Minervini","year":"2020"},{"key":"2026032910310461500_ref052","article-title":"Learning reasoning strategies in end-to-end differentiable proving","volume-title":"ICML","author":"Minervini","year":"2020"},{"issue":"7540","key":"2026032910310461500_ref053","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236","article-title":"Human-level Control Through Deep Reinforcement Learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"2026032910310461500_ref054","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.02184","volume-title":"Unbiased Scene Graph Generation in Videos","author":"Nag","year":"2023"},{"key":"2026032910310461500_ref055","unstructured":"Nakano, R., J.Hilton, S.Balaji, J.Wu, L.Ouyang, C.Kim, C.Hesse, S.Jain, V.Kosaraju, W.Saunders, X.Jiang, K.Cobbe, T.Eloundou, G.Krueger, K.Button, M.Knight, B.Chess, and J.Schulman. (2021). \u201cWebGPT: Browser-assisted question-answering with human feedback\u201d. url: https:\/\/arxiv.org\/abs\/2112.09332."},{"key":"2026032910310461500_ref056","volume-title":"Passage Re-ranking with BERT","author":"Nogueira","year":"2019"},{"issue":"66","key":"2026032910310461500_ref057","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6597","article-title":"Neural-Fly enables rapid learning for agile flight in strong winds","volume":"7","author":"O\u2019Connell","year":"2022","journal-title":"Science Robotics"},{"key":"2026032910310461500_ref058","unstructured":"OpenAI\n          . (2023a). \u201cChatGPT Plugins\u201d. url: https:\/\/openai.com\/index\/chatgpt-plugins\/."},{"key":"2026032910310461500_ref059","volume-title":"GPT-4 Technical Report","author":"OpenAI","year":"2023"},{"key":"2026032910310461500_ref060","volume-title":"GPT-4 Technical Report","author":"OpenAI","year":"2024"},{"key":"2026032910310461500_ref061","volume-title":"Learning with Differentiable Algorithms","author":"Petersen","year":"2022"},{"key":"2026032910310461500_ref062","first-page":"46","volume-title":"The temporal logic of programs","author":"Pnueli","year":"1977"},{"key":"2026032910310461500_ref063","unstructured":"Radford, A., J. W.Kim, C.Hallacy, A.Ramesh, G.Goh, S.Agarwal, G.Sastry, A.Askell, P.Mishkin, J.Clark, G.Krueger, and I.Sutskever. (2021). \u201cLearning Transferable Visual Models From Natural Language Supervision\u201d. url: https:\/\/arxiv.org\/abs\/2103.00020."},{"key":"2026032910310461500_ref064","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264","volume-title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","author":"Rajpurkar","year":"2016"},{"key":"2026032910310461500_ref065","article-title":"Zero-shot text-to-image generation","volume-title":"ICML","author":"Ramesh","year":"2021"},{"key":"2026032910310461500_ref066","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01042","article-title":"High-Resolution Image Synthesis With Latent Diffusion Models","volume-title":"CVPR","author":"Rombach","year":"2022"},{"key":"2026032910310461500_ref067","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.21236\/ADA623517","volume-title":"A learning based approach to control synthesis of markov decision processes for linear temporal logic specifications","author":"Sadigh","year":"2014"},{"key":"2026032910310461500_ref068","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.emnlp-main.110","article-title":"RuleBERT: Teaching Soft Rules to Pre-Trained Language Models","volume-title":"EMNLP","author":"Saeed","year":"2021"},{"key":"2026032910310461500_ref069","article-title":"A simple neural network module for relational reasoning","volume-title":"NeurIPS","author":"Santoro","year":"2017"},{"key":"2026032910310461500_ref070","volume-title":"Toolformer: Language Models Can Teach Themselves to Use Tools","author":"Schick","year":"2023"},{"key":"2026032910310461500_ref071","first-page":"279","volume-title":"Annotating Objects and Relations in User-Generated Videos","author":"Shang","year":"2019"},{"key":"2026032910310461500_ref072","first-page":"1300","volume-title":"Video visual relation detection","author":"Shang","year":"2017"},{"key":"2026032910310461500_ref073","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"2026032910310461500_ref074","volume-title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","author":"Sinha","year":"2019"},{"key":"2026032910310461500_ref075","article-title":"Matching the Blanks: Distributional Similarity for Relation Learning","volume-title":"ACL","author":"Soares","year":"2019"},{"key":"2026032910310461500_ref076","volume-title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2023"},{"key":"2026032910310461500_ref077","unstructured":"Sun, J. J., M.Tjandrasuwita, A.Sehgal, A.Solar-Lezama, S.Chaudhuri, Y.Yue, and O.Costilla-Reyes. (2022). \u201cNeurosymbolic Programming for Science\u201d. url: https:\/\/arxiv.org\/abs\/2210.05050."},{"key":"2026032910310461500_ref078","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1452","article-title":"BERT Rediscovers the Classical NLP Pipeline","volume-title":"ACL","author":"Tenney","year":"2019"},{"issue":"2","key":"2026032910310461500_ref079","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1145\/2812802","article-title":"YFCC100M: The New Data in Multimedia Research","volume":"59","author":"Thomee","year":"2016","journal-title":"Communications of the ACM"},{"key":"2026032910310461500_ref080","volume-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023"},{"key":"2026032910310461500_ref081","article-title":"Graph Attention Networks","volume-title":"ICLR","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"2026032910310461500_ref082","volume-title":"SATNet: Bridging Deep Learning and Logical Reasoning Using a Differentiable Satisfiability Solver","author":"Wang","year":"2019"},{"key":"2026032910310461500_ref083","volume-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"2026032910310461500_ref084","unstructured":"Wu, Y., M.Keoliya, K.Chen, N.Velingker, Z.Li, E. J.Getzen, Q.Long, M.Naik, R. B.Parikh, and E.Wong. (2024). \u201cDISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation\u201d. url: https:\/\/arxiv.org\/abs\/2406.00611."},{"key":"2026032910310461500_ref085","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.01791","volume-title":"Panoptic Video Scene Graph Generation","author":"Yang","year":"2023"},{"key":"2026032910310461500_ref086","volume-title":"HotpotQA: A dataset for diverse, explainable multi-hop question answering","author":"Yang","year":"2018"},{"key":"2026032910310461500_ref087","volume-title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","author":"Yi","year":"2018"},{"key":"2026032910310461500_ref088","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.01100","volume-title":"Sigmoid Loss for Language Image Pre-Training","author":"Zhai","year":"2023"},{"key":"2026032910310461500_ref089","first-page":"4283","volume-title":"TYGR: Type Inference on Stripped Binaries using Graph Neural Networks","author":"Zhu","year":"2024"},{"key":"2026032910310461500_ref090","volume-title":"Scene graph generation: A comprehensive survey","author":"Zhu","year":"2022"}],"container-title":["Foundations and Trends\u00ae in Programming Languages"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftpgl\/article-pdf\/8\/2\/118\/11025718\/2500000059en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftpgl\/article-pdf\/8\/2\/118\/11025718\/2500000059en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:16:49Z","timestamp":1777486609000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftpgl\/article\/8\/2\/118\/1326575\/Neurosymbolic-Programming-in-Scallop-Principles"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,30]]},"references-count":90,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,12,30]]}},"URL":"https:\/\/doi.org\/10.1561\/2500000059","relation":{},"ISSN":["2325-1107","2325-1131"],"issn-type":[{"value":"2325-1107","type":"print"},{"value":"2325-1131","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,30]]}}}