{"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/data-juicer-sandbox-a-comprehensive-suite-for","title":"Data-Juicer Sandbox: A Comprehensive Suite for Multimodal Data-Model Co-development","arxiv_id":"2407.11784","date":"2024-07-16","proceeding":null,"authors":["Daoyuan Chen","Haibin Wang","Yilun Huang","Ce Ge","Yaliang Li","Bolin Ding","Jingren Zhou"],"abstract":"The emergence of large-scale multi-modal generative models has drastically advanced artificial intelligence, introducing unprecedented levels of performance and functionality. However, optimizing these models remains challenging due to historically isolated paths of model-centric and data-centric developments, leading to suboptimal outcomes and inefficient resource utilization. In response, we present a novel sandbox suite tailored for integrated data-model co-development. This sandbox provides a comprehensive experimental platform, enabling rapid iteration and insight-driven refinement of both data and models. Our proposed \"Probe-Analyze-Refine\" workflow, validated through applications on state-of-the-art LLaVA-like and DiT based models, yields significant performance boosts, such as topping the VBench leaderboard. We also uncover fruitful insights gleaned from exhaustive benchmarks, shedding light on the critical interplay between data quality, diversity, and model behavior. With the hope of fostering deeper understanding and future progress in multi-modal data and generative modeling, our codes, datasets, and models are maintained and accessible at https://github.com/modelscope/data-juicer/blob/main/docs/Sandbox.md.","url_abs":"https://arxiv.org/abs/2407.11784v1","url_pdf":"https://arxiv.org/pdf/2407.11784v1.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":"data-juicer-sandbox-a-comprehensive-suite-for","repo_url":"https://github.com/modelscope/data-juicer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.11784","atlas_url":"https://app.syntology.ai/?focus=2407.11784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11784"}},"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/modelscope/data-juicer","reach":null}],"summary":{"ran":3,"ran_fixture":1,"unverified":6},"by_repo_kind":{"official":{"samples":10,"ran":4,"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":"3ffdac1f9fe42290","entry":"PartitionedDAGStrategy","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/core/executor/dag_execution_mixin.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/core/executor/dag_execution_mixin.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ffdac1f9fe42290"}},{"code_sha256_prefix":"b8e00b9ff0a49608","entry":"PipelineDAG","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/core/executor/dag_execution_mixin.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/core/executor/dag_execution_mixin.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b8e00b9ff0a49608"}},{"code_sha256_prefix":"2216173936ba88c4","entry":"ScatterGatherNode","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/core/executor/dag_execution_mixin.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/core/executor/dag_execution_mixin.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2216173936ba88c4"}},{"code_sha256_prefix":"20647d3165062ad5","entry":"is_global_operation","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/core/executor/dag_execution_mixin.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/core/executor/dag_execution_mixin.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20647d3165062ad5"}},{"code_sha256_prefix":"2ad62cd47a823b20","entry":"DAGExecutionMixin","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/core/executor/dag_execution_mixin.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/core/executor/dag_execution_mixin.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ad62cd47a823b20"}},{"code_sha256_prefix":"a0472b5af9cfd25c","entry":"DAGExecutionStrategy","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/core/executor/dag_execution_mixin.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/core/executor/dag_execution_mixin.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a0472b5af9cfd25c"}},{"code_sha256_prefix":"1f8ece291249d70a","entry":"DAGNodeStatusTransition","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/core/executor/dag_execution_mixin.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/core/executor/dag_execution_mixin.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f8ece291249d70a"}},{"code_sha256_prefix":"5dd6308a11d247fc","entry":"DAGNodeType","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/core/executor/dag_execution_mixin.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/core/executor/dag_execution_mixin.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5dd6308a11d247fc"}},{"code_sha256_prefix":"c63fd2ec15a736f3","entry":"EventType","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/core/executor/dag_execution_mixin.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/core/executor/dag_execution_mixin.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c63fd2ec15a736f3"}},{"code_sha256_prefix":"27256aeeb1e862df","entry":"NonPartitionedDAGStrategy","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/core/executor/dag_execution_mixin.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/core/executor/dag_execution_mixin.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"27256aeeb1e862df"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}