{"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/snip-bridging-mathematical-symbolic-and","title":"SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training","arxiv_id":"2310.02227","date":"2023-10-03","proceeding":null,"authors":["Kazem Meidani","Parshin Shojaee","Chandan K. Reddy","Amir Barati Farimani"],"abstract":"In an era where symbolic mathematical equations are indispensable for modeling complex natural phenomena, scientific inquiry often involves collecting observations and translating them into mathematical expressions. Recently, deep learning has emerged as a powerful tool for extracting insights from data. However, existing models typically specialize in either numeric or symbolic domains, and are usually trained in a supervised manner tailored to specific tasks. This approach neglects the substantial benefits that could arise from a task-agnostic multi-modal understanding between symbolic equations and their numeric counterparts. To bridge the gap, we introduce SNIP, a Symbolic-Numeric Integrated Pre-training model, which employs contrastive learning between symbolic and numeric domains, enhancing their mutual similarities in the embeddings. By performing latent space analysis, we observe that SNIP provides cross-domain insights into the representations, revealing that symbolic supervision enhances the embeddings of numeric data and vice versa. We evaluate SNIP across diverse tasks, including symbolic-to-numeric mathematical property prediction and numeric-to-symbolic equation discovery, commonly known as symbolic regression. Results show that SNIP effectively transfers to various tasks, consistently outperforming fully supervised baselines and competing strongly with established task-specific methods, especially in the low data regime scenarios where available data is limited. Code and model are available at: https://github.com/deep-symbolic-mathematics/Multimodal-Math-Pretraining","url_abs":"https://arxiv.org/abs/2310.02227v3","url_pdf":"https://arxiv.org/pdf/2310.02227v3.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":"snip-bridging-mathematical-symbolic-and","repo_url":"https://github.com/deep-symbolic-mathematics/Multimodal-Math-Pretraining","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"snip-bridging-mathematical-symbolic-and","repo_url":"https://github.com/deep-symbolic-mathematics/Multimodal-Symbolic-Regression","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"equation-discovery","task_name":"Equation Discovery"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"math","task_name":"Math"},{"task_slug":"mathematical-induction","task_name":"Mathematical Induction"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"property-prediction","task_name":"Property Prediction"},{"task_slug":"symbolic-regression","task_name":"Symbolic Regression"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"snip","method_name":"SNIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.02227","atlas_url":"https://app.syntology.ai/?focus=2310.02227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02227"}},"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/deep-symbolic-mathematics/Multimodal-Math-Pretraining","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deep-symbolic-mathematics/Multimodal-Symbolic-Regression","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":2}},"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":"a5dd64dfcb014bd2","entry":"calculate_accuracy","repo":"deep-symbolic-mathematics/Multimodal-Math-Pretraining","repo_kind":"official","path":"eval_proppred.py","file_url":"https://github.com/deep-symbolic-mathematics/Multimodal-Math-Pretraining/blob/HEAD/eval_proppred.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5dd64dfcb014bd2"}},{"code_sha256_prefix":"40b1a20fe12de364","entry":"read_file","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":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"40b1a20fe12de364"}},{"code_sha256_prefix":"9f910d4efd4260d7","entry":"reload_checkpoint","repo":"deep-symbolic-mathematics/Multimodal-Math-Pretraining","repo_kind":"official","path":"eval_proppred.py","file_url":"https://github.com/deep-symbolic-mathematics/Multimodal-Math-Pretraining/blob/HEAD/eval_proppred.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f910d4efd4260d7"}},{"code_sha256_prefix":"f73a01df867787bd","entry":"reload_model","repo":"deep-symbolic-mathematics/Multimodal-Symbolic-Regression","repo_kind":"official","path":"LSO_eval.py","file_url":"https://github.com/deep-symbolic-mathematics/Multimodal-Symbolic-Regression/blob/HEAD/LSO_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f73a01df867787bd"}},{"code_sha256_prefix":"48d138bc1e1c269f","entry":"symmetric_mean_absolute_percentage_error","repo":"deep-symbolic-mathematics/Multimodal-Math-Pretraining","repo_kind":"official","path":"eval_proppred.py","file_url":"https://github.com/deep-symbolic-mathematics/Multimodal-Math-Pretraining/blob/HEAD/eval_proppred.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48d138bc1e1c269f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}