{"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/beyond-atomic-geometry-representations-in","title":"Beyond Atomic Geometry Representations in Materials Science: A Human-in-the-Loop Multimodal Framework","arxiv_id":"2506.00302","date":"2025-05-30","proceeding":null,"authors":["Can Polat","Hasan Kurban","Erchin Serpedin","Mustafa Kurban"],"abstract":"Most materials science datasets are limited to atomic geometries (e.g., XYZ files), restricting their utility for multimodal learning and comprehensive data-centric analysis. These constraints have historically impeded the adoption of advanced machine learning techniques in the field. This work introduces MultiCrystalSpectrumSet (MCS-Set), a curated framework that expands materials datasets by integrating atomic structures with 2D projections and structured textual annotations, including lattice parameters and coordination metrics. MCS-Set enables two key tasks: (1) multimodal property and summary prediction, and (2) constrained crystal generation with partial cluster supervision. Leveraging a human-in-the-loop pipeline, MCS-Set combines domain expertise with standardized descriptors for high-quality annotation. Evaluations using state-of-the-art language and vision-language models reveal substantial modality-specific performance gaps and highlight the importance of annotation quality for generalization. MCS-Set offers a foundation for benchmarking multimodal models, advancing annotation practices, and promoting accessible, versatile materials science datasets. The dataset and implementations are available at https://github.com/KurbanIntelligenceLab/MultiCrystalSpectrumSet.","url_abs":"https://arxiv.org/abs/2506.00302v1","url_pdf":"https://arxiv.org/pdf/2506.00302v1.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":"beyond-atomic-geometry-representations-in","repo_url":"https://github.com/kurbanintelligencelab/multicrystalspectrumset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.00302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00302"}},"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/kurbanintelligencelab/multicrystalspectrumset","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":"61d9150ace7df395","entry":"build_samples_from_dataset","repo":"kurbanintelligencelab/multicrystalspectrumset","repo_kind":"official","path":"llm_scripts/task_1.py","file_url":"https://github.com/kurbanintelligencelab/multicrystalspectrumset/blob/HEAD/llm_scripts/task_1.py","link_basis":"harvester_set","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":"61d9150ace7df395"}},{"code_sha256_prefix":"ef4452f3cd620c23","entry":"convert_structured_to_xyz","repo":"kurbanintelligencelab/multicrystalspectrumset","repo_kind":"official","path":"llm_scripts/task_2.py","file_url":"https://github.com/kurbanintelligencelab/multicrystalspectrumset/blob/HEAD/llm_scripts/task_2.py","link_basis":"harvester_set","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":"ef4452f3cd620c23"}},{"code_sha256_prefix":"17a415707bf433c0","entry":"create_3d_plot","repo":"kurbanintelligencelab/multicrystalspectrumset","repo_kind":"official","path":"framework_flow.py","file_url":"https://github.com/kurbanintelligencelab/multicrystalspectrumset/blob/HEAD/framework_flow.py","link_basis":"harvester_set","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":"17a415707bf433c0"}},{"code_sha256_prefix":"9b9d1e2eab9b7e9d","entry":"format_xyz_to_2decimals","repo":"kurbanintelligencelab/multicrystalspectrumset","repo_kind":"official","path":"llm_scripts/task_2.py","file_url":"https://github.com/kurbanintelligencelab/multicrystalspectrumset/blob/HEAD/llm_scripts/task_2.py","link_basis":"harvester_set","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":"9b9d1e2eab9b7e9d"}},{"code_sha256_prefix":"4e1e5282c2ad8110","entry":"load_xyz","repo":"kurbanintelligencelab/multicrystalspectrumset","repo_kind":"official","path":"framework_flow.py","file_url":"https://github.com/kurbanintelligencelab/multicrystalspectrumset/blob/HEAD/framework_flow.py","link_basis":"harvester_set","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":"4e1e5282c2ad8110"}},{"code_sha256_prefix":"7c7119e833a431d5","entry":"parse_xyz","repo":"kurbanintelligencelab/multicrystalspectrumset","repo_kind":"official","path":"llm_scripts/task_2.py","file_url":"https://github.com/kurbanintelligencelab/multicrystalspectrumset/blob/HEAD/llm_scripts/task_2.py","link_basis":"harvester_set","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":"7c7119e833a431d5"}},{"code_sha256_prefix":"d0bc0e669932028f","entry":"process_samples","repo":"kurbanintelligencelab/multicrystalspectrumset","repo_kind":"official","path":"llm_scripts/task_1.py","file_url":"https://github.com/kurbanintelligencelab/multicrystalspectrumset/blob/HEAD/llm_scripts/task_1.py","link_basis":"harvester_set","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":"d0bc0e669932028f"}},{"code_sha256_prefix":"96fb836f1327f580","entry":"rotate_coords","repo":"kurbanintelligencelab/multicrystalspectrumset","repo_kind":"official","path":"framework_flow.py","file_url":"https://github.com/kurbanintelligencelab/multicrystalspectrumset/blob/HEAD/framework_flow.py","link_basis":"harvester_set","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":"96fb836f1327f580"}},{"code_sha256_prefix":"2eedbc22a3aa7bac","entry":"select_subset","repo":"kurbanintelligencelab/multicrystalspectrumset","repo_kind":"official","path":"llm_scripts/task_1.py","file_url":"https://github.com/kurbanintelligencelab/multicrystalspectrumset/blob/HEAD/llm_scripts/task_1.py","link_basis":"harvester_set","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":"2eedbc22a3aa7bac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}