{"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":"/code/data-collator","entry":"data_collator","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":11,"n_papers_ran":6,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":9,"n_samples_ran":6,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":5,"unverified":3},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2509.25729","paper":"/paper/arxiv-2509-25729","title":"Controlled Generation for Private Synthetic Text","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"zzhao71/Controlled-Generation-for-Private-Synthetic-Text","path":"partially_known_prefix_tuning.py","file_url":"https://github.com/zzhao71/Controlled-Generation-for-Private-Synthetic-Text/blob/HEAD/partially_known_prefix_tuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"46553ac4f837993d","mcp_get_code":{"code_sha256":"46553ac4f837993d"}},{"arxiv_id":"2411.14717","paper":"/paper/fedmllm-federated-fine-tuning-mllm-on","title":"FedMLLM: Federated Fine-tuning MLLM on Multimodal Heterogeneity Data","date":"2024-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1xbq1/fedmllm","path":"finetune/dataset.py","file_url":"https://github.com/1xbq1/fedmllm/blob/HEAD/finetune/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4212780bf7da9ddd","mcp_get_code":{"code_sha256":"4212780bf7da9ddd"}},{"arxiv_id":"2408.01800","paper":"/paper/2408-01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","date":"2024-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenBMB/MiniCPM-o","path":"finetune/dataset.py","file_url":"https://github.com/OpenBMB/MiniCPM-o/blob/HEAD/finetune/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4212780bf7da9ddd","mcp_get_code":{"code_sha256":"4212780bf7da9ddd"}},{"arxiv_id":"2405.17220","paper":"/paper/rlaif-v-aligning-mllms-through-open-source-ai","title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openbmb/omnilmm","path":"finetune/dataset.py","file_url":"https://github.com/openbmb/omnilmm/blob/HEAD/finetune/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4212780bf7da9ddd","mcp_get_code":{"code_sha256":"4212780bf7da9ddd"}},{"arxiv_id":"2405.06649","paper":"/paper/prollm-protein-chain-of-thoughts-enhanced-llm","title":"ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction","date":"2024-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyuj666/prollm","path":"train_ProLLM.py","file_url":"https://github.com/mingyuj666/prollm/blob/HEAD/train_ProLLM.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ce16a86620e8996","mcp_get_code":{"code_sha256":"6ce16a86620e8996"}},{"arxiv_id":"2402.13991","paper":"/paper/analysing-the-impact-of-sequence-composition","title":"Analysing The Impact of Sequence Composition on Language Model Pre-Training","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuzhaouoe/pretraining-data-packing","path":"packing_dataset.py","file_url":"https://github.com/yuzhaouoe/pretraining-data-packing/blob/HEAD/packing_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"874a9519ebeb3c53","mcp_get_code":{"code_sha256":"874a9519ebeb3c53"}},{"arxiv_id":"2402.07945","paper":"/paper/screenagent-a-vision-language-model-driven","title":"ScreenAgent: A Vision Language Model-driven Computer Control Agent","date":"2024-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"niuzaisheng/ScreenAgent","path":"train/finetune_ScreenAgent.py","file_url":"https://github.com/niuzaisheng/ScreenAgent/blob/HEAD/train/finetune_ScreenAgent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ad5ba95300a1cc7a","mcp_get_code":{"code_sha256":"ad5ba95300a1cc7a"}},{"arxiv_id":"2312.08914","paper":"/paper/cogagent-a-visual-language-model-for-gui","title":"CogAgent: A Visual Language Model for GUI Agents","date":"2023-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/cogvlm","path":"finetune_demo/evaluate_cogvlm_demo.py","file_url":"https://github.com/thudm/cogvlm/blob/HEAD/finetune_demo/evaluate_cogvlm_demo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"54a2b4c8804d95b2","mcp_get_code":{"code_sha256":"54a2b4c8804d95b2"}},{"arxiv_id":"2312.08914","paper":"/paper/cogagent-a-visual-language-model-for-gui","title":"CogAgent: A Visual Language Model for GUI Agents","date":"2023-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/cogvlm","path":"finetune_demo/evaluate_cogagent_demo.py","file_url":"https://github.com/thudm/cogvlm/blob/HEAD/finetune_demo/evaluate_cogagent_demo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"afd5a3b7c43f083d","mcp_get_code":{"code_sha256":"afd5a3b7c43f083d"}},{"arxiv_id":"2310.09219","paper":"/paper/kelly-is-a-warm-person-joseph-is-a-role-model","title":"\"Kelly is a Warm Person, Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uclanlp/biases-llm-reference-letters","path":"agency_classifier/finetune_bert_bias.py","file_url":"https://github.com/uclanlp/biases-llm-reference-letters/blob/HEAD/agency_classifier/finetune_bert_bias.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3aca3023253a4a1d","mcp_get_code":{"code_sha256":"3aca3023253a4a1d"}},{"arxiv_id":"Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper","paper":null,"title":"arXiv:Hong_CogAgent_A_Visual_Language_Model_for_GUI_Agents_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"THUDM/CogVLM","path":"finetune_demo/evaluate_cogvlm_demo.py","file_url":"https://github.com/THUDM/CogVLM/blob/HEAD/finetune_demo/evaluate_cogvlm_demo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"54a2b4c8804d95b2","mcp_get_code":{"code_sha256":"54a2b4c8804d95b2"}},{"arxiv_id":"2023.acl-srw.19","paper":null,"title":"arXiv:2023.acl-srw.19","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nyuolab/text2table","path":"text2table/models/data_collator.py","file_url":"https://github.com/nyuolab/text2table/blob/HEAD/text2table/models/data_collator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"86a337949b5251cd","mcp_get_code":{"code_sha256":"86a337949b5251cd"}}]}