{"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/encode-with-prompt-completion-format","entry":"encode_with_prompt_completion_format","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":25,"n_papers_ran":14,"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":15,"n_samples_ran":6,"n_samples_fingerprinted":0,"n_places":27,"n_places_pointer_only":15,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":3,"unverified":9},"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":"2604.00536","paper":"/paper/arxiv-2604-00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"FanZT6/OptimSyn","path":"training/influence/get_training_dataset.py","file_url":"https://github.com/FanZT6/OptimSyn/blob/HEAD/training/influence/get_training_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7e98a164bbb50ba8","mcp_get_code":{"code_sha256":"7e98a164bbb50ba8"}},{"arxiv_id":"2511.02213","paper":"/paper/arxiv-2511-02213","title":"IG-Pruning: Input-Guided Block Pruning for Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"ictnlp/IG-Pruning","path":"cluster_samples.py","file_url":"https://github.com/ictnlp/IG-Pruning/blob/HEAD/cluster_samples.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9675ac6bf324cb46","mcp_get_code":{"code_sha256":"9675ac6bf324cb46"}},{"arxiv_id":"2505.07437","paper":"/paper/lead-iterative-data-selection-for-efficient","title":"LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning","date":"2025-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKUSTDial/LEAD","path":"src/online/template.py","file_url":"https://github.com/HKUSTDial/LEAD/blob/HEAD/src/online/template.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57148174b9cdbbea","mcp_get_code":{"code_sha256":"57148174b9cdbbea"}},{"arxiv_id":"2410.16208","paper":"/paper/compute-constrained-data-selection","title":"Compute-Constrained Data Selection","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oseyosey/CCDS","path":"ccds/evaluation/open_instruct/finetune.py","file_url":"https://github.com/oseyosey/CCDS/blob/HEAD/ccds/evaluation/open_instruct/finetune.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":"5966cc3120c46d61","mcp_get_code":{"code_sha256":"5966cc3120c46d61"}},{"arxiv_id":"2410.13184","paper":"/paper/router-tuning-a-simple-and-effective-approach","title":"Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"case-lab-umd/router-tuning","path":"entrypoints/finetune/finetune_router_tuning.py","file_url":"https://github.com/case-lab-umd/router-tuning/blob/HEAD/entrypoints/finetune/finetune_router_tuning.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":"88b8bf1223d522a4","mcp_get_code":{"code_sha256":"88b8bf1223d522a4"}},{"arxiv_id":"2408.04568","paper":"/paper/learning-fine-grained-grounded-citations-for","title":"Learning Fine-Grained Grounded Citations for Attributed Large Language Models","date":"2024-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luckyyysta/fine-grained-attribution","path":"training/stage1_grounding_guided_generation/finetune.py","file_url":"https://github.com/luckyyysta/fine-grained-attribution/blob/HEAD/training/stage1_grounding_guided_generation/finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"46b021a3b51b711f","mcp_get_code":{"code_sha256":"46b021a3b51b711f"}},{"arxiv_id":"2408.04568","paper":"/paper/learning-fine-grained-grounded-citations-for","title":"Learning Fine-Grained Grounded Citations for Attributed Large Language Models","date":"2024-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luckyyysta/fine-grained-attribution","path":"training/stage2_consistency_aware_alignment/dpo_tune.py","file_url":"https://github.com/luckyyysta/fine-grained-attribution/blob/HEAD/training/stage2_consistency_aware_alignment/dpo_tune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d01f5d65c58ed96d","mcp_get_code":{"code_sha256":"d01f5d65c58ed96d"}},{"arxiv_id":"2406.15444","paper":"/paper/investigating-the-robustness-of-llms-on-math","title":"Cutting Through the Noise: Boosting LLM Performance on Math Word Problems","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"him1411/problemathic","path":"scripts/finetune.py","file_url":"https://github.com/him1411/problemathic/blob/HEAD/scripts/finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"119cad9954acc960","mcp_get_code":{"code_sha256":"119cad9954acc960"}},{"arxiv_id":"2405.20974","paper":"/paper/sayself-teaching-llms-to-express-confidence","title":"SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xu1868/SaySelf","path":"training/finetune.py","file_url":"https://github.com/xu1868/SaySelf/blob/HEAD/training/finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"119cad9954acc960","mcp_get_code":{"code_sha256":"119cad9954acc960"}},{"arxiv_id":"2405.14394","paper":"/paper/instruction-tuning-with-loss-over","title":"Instruction Tuning With Loss Over Instructions","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhengxiangshi/instructionmodelling","path":"src/compute_loss.py","file_url":"https://github.com/zhengxiangshi/instructionmodelling/blob/HEAD/src/compute_loss.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":"c90f3a5ec6457c6d","mcp_get_code":{"code_sha256":"c90f3a5ec6457c6d"}},{"arxiv_id":"2405.14394","paper":"/paper/instruction-tuning-with-loss-over","title":"Instruction Tuning With Loss Over Instructions","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhengxiangShi/InstructionModelling","path":"src/finetune.py","file_url":"https://github.com/ZhengxiangShi/InstructionModelling/blob/HEAD/src/finetune.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e7170ef85d1fec78","mcp_get_code":{"code_sha256":"e7170ef85d1fec78"}},{"arxiv_id":"2405.05008","paper":"/paper/adelie-aligning-large-language-models-on","title":"ADELIE: Aligning Large Language Models on Information Extraction","date":"2024-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THU-KEG/ADELIE","path":"train4llama/open_instruct/finetune.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5966cc3120c46d61","mcp_get_code":{"code_sha256":"5966cc3120c46d61"}},{"arxiv_id":"2403.04945","paper":"/paper/electrocardiogram-instruction-tuning-for","title":"MEIT: Multi-Modal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aiot-mlsys-lab/meit","path":"ECG_LLMs/finetune_ecgllm_with_lora_mimic_without_IT.py","file_url":"https://github.com/aiot-mlsys-lab/meit/blob/HEAD/ECG_LLMs/finetune_ecgllm_with_lora_mimic_without_IT.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":"88b8bf1223d522a4","mcp_get_code":{"code_sha256":"88b8bf1223d522a4"}},{"arxiv_id":"2403.03870","paper":"/paper/learning-to-decode-collaboratively-with","title":"Learning to Decode Collaboratively with Multiple Language Models","date":"2024-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clinicalml/co-llm","path":"collm/training/qlora_finetuning.py","file_url":"https://github.com/clinicalml/co-llm/blob/HEAD/collm/training/qlora_finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"661419d69a095bfe","mcp_get_code":{"code_sha256":"661419d69a095bfe"}},{"arxiv_id":"2403.00799","paper":"/paper/an-empirical-study-of-data-ability-boundary","title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cyzhh/MMOS","path":"train/finetune.py","file_url":"https://github.com/cyzhh/MMOS/blob/HEAD/train/finetune.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":"1906977026be9a86","mcp_get_code":{"code_sha256":"1906977026be9a86"}},{"arxiv_id":"2402.16705","paper":"/paper/selectit-selective-instruction-tuning-for","title":"SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Blue-Raincoat/SelectIT","path":"eval/open_instruct/finetune.py","file_url":"https://github.com/Blue-Raincoat/SelectIT/blob/HEAD/eval/open_instruct/finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"119cad9954acc960","mcp_get_code":{"code_sha256":"119cad9954acc960"}},{"arxiv_id":"2402.01469","paper":"/paper/amor-a-recipe-for-building-adaptable-modular","title":"AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JianGuanTHU/AMOR","path":"code/finetune.py","file_url":"https://github.com/JianGuanTHU/AMOR/blob/HEAD/code/finetune.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"99e4a58eb23854c4","mcp_get_code":{"code_sha256":"99e4a58eb23854c4"}},{"arxiv_id":"2401.16405","paper":"/paper/scaling-sparse-fine-tuning-to-large-language","title":"Scaling Sparse Fine-Tuning to Large Language Models","date":"2024-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ducdauge/sft-llm","path":"finetune/finetune.py","file_url":"https://github.com/ducdauge/sft-llm/blob/HEAD/finetune/finetune.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88b8bf1223d522a4","mcp_get_code":{"code_sha256":"88b8bf1223d522a4"}},{"arxiv_id":"2401.15006","paper":"/paper/airavata-introducing-hindi-instruction-tuned","title":"Airavata: Introducing Hindi Instruction-tuned LLM","date":"2024-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ai4bharat/indicinstruct","path":"open_instruct/finetune.py","file_url":"https://github.com/ai4bharat/indicinstruct/blob/HEAD/open_instruct/finetune.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":"661419d69a095bfe","mcp_get_code":{"code_sha256":"661419d69a095bfe"}},{"arxiv_id":"2401.10768","paper":"/paper/mitigating-hallucinations-of-large-language","title":"Knowledge Verification to Nip Hallucination in the Bud","date":"2024-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fanqiwan/KCA","path":"examination/utils.py","file_url":"https://github.com/fanqiwan/KCA/blob/HEAD/examination/utils.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":"661419d69a095bfe","mcp_get_code":{"code_sha256":"661419d69a095bfe"}},{"arxiv_id":"2401.08565","paper":"/paper/tuning-language-models-by-proxy","title":"Tuning Language Models by Proxy","date":"2024-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alisawuffles/proxy-tuning","path":"open_instruct/finetune.py","file_url":"https://github.com/alisawuffles/proxy-tuning/blob/HEAD/open_instruct/finetune.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":"88b8bf1223d522a4","mcp_get_code":{"code_sha256":"88b8bf1223d522a4"}},{"arxiv_id":"2312.07540","paper":"/paper/diff-history-for-long-context-language-agents","title":"diff History for Neural Language Agents","date":"2023-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"upiterbarg/diff_history","path":"finetune.py","file_url":"https://github.com/upiterbarg/diff_history/blob/HEAD/finetune.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"661419d69a095bfe","mcp_get_code":{"code_sha256":"661419d69a095bfe"}},{"arxiv_id":"2311.05657","paper":"/paper/lumos-learning-agents-with-unified-data","title":"Agent Lumos: Unified and Modular Training for Open-Source Language Agents","date":"2023-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/lumos","path":"model/finetune.py","file_url":"https://github.com/allenai/lumos/blob/HEAD/model/finetune.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88b8bf1223d522a4","mcp_get_code":{"code_sha256":"88b8bf1223d522a4"}},{"arxiv_id":"2310.11511","paper":"/paper/self-rag-learning-to-retrieve-generate-and","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","date":"2023-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AkariAsai/self-rag","path":"retrieval_lm/finetune.py","file_url":"https://github.com/AkariAsai/self-rag/blob/HEAD/retrieval_lm/finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aac14d7de4178849","mcp_get_code":{"code_sha256":"aac14d7de4178849"}},{"arxiv_id":"2309.17452","paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/ToRA","path":"src/train/finetune.py","file_url":"https://github.com/microsoft/ToRA/blob/HEAD/src/train/finetune.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1906977026be9a86","mcp_get_code":{"code_sha256":"1906977026be9a86"}},{"arxiv_id":"2308.04371","paper":"/paper/cumulative-reasoning-with-large-language","title":"Cumulative Reasoning with Large Language Models","date":"2023-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iiis-ai/cumulative-reasoning","path":"CR-Agent/train/finetune.py","file_url":"https://github.com/iiis-ai/cumulative-reasoning/blob/HEAD/CR-Agent/train/finetune.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":"1906977026be9a86","mcp_get_code":{"code_sha256":"1906977026be9a86"}},{"arxiv_id":"2024.findings-emnlp.575","paper":null,"title":"arXiv:2024.findings-emnlp.575","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"shirley-wu/vdebugger","path":"vdebugger/finetune.py","file_url":"https://github.com/shirley-wu/vdebugger/blob/HEAD/vdebugger/finetune.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":"aaf01f77204b6898","mcp_get_code":{"code_sha256":"aaf01f77204b6898"}}]}