{"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-messages-format","entry":"encode_with_messages_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":21,"n_papers_ran":18,"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":9,"n_samples_fingerprinted":0,"n_places":29,"n_places_pointer_only":16,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":6,"unverified":6},"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":"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":"c2ede6469ba3ba33","mcp_get_code":{"code_sha256":"c2ede6469ba3ba33"}},{"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":"1d1694af124350b8","mcp_get_code":{"code_sha256":"1d1694af124350b8"}},{"arxiv_id":"2504.03553","paper":"/paper/agentic-knowledgeable-self-awareness","title":"Agentic Knowledgeable Self-awareness","date":"2025-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/knowself","path":"train/train_stage1.py","file_url":"https://github.com/zjunlp/knowself/blob/HEAD/train/train_stage1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"413afba62a8952fc","mcp_get_code":{"code_sha256":"413afba62a8952fc"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"97229c97d4273595","mcp_get_code":{"code_sha256":"97229c97d4273595"}},{"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/dpo_tune.py","file_url":"https://github.com/oseyosey/ccds/blob/HEAD/ccds/evaluation/open_instruct/dpo_tune.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":"254ab4972fe2c4e2","mcp_get_code":{"code_sha256":"254ab4972fe2c4e2"}},{"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":"1cb0eeb16cf04ee3","mcp_get_code":{"code_sha256":"1cb0eeb16cf04ee3"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"97229c97d4273595","mcp_get_code":{"code_sha256":"97229c97d4273595"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0fe2c5386a8e7ffe","mcp_get_code":{"code_sha256":"0fe2c5386a8e7ffe"}},{"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":"evaluation/evaluate.py","file_url":"https://github.com/xu1868/SaySelf/blob/HEAD/evaluation/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2ff0831de5949f6c","mcp_get_code":{"code_sha256":"2ff0831de5949f6c"}},{"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/rlhf_train.py","file_url":"https://github.com/xu1868/sayself/blob/HEAD/training/rlhf_train.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a6a6be18e0e76d28","mcp_get_code":{"code_sha256":"a6a6be18e0e76d28"}},{"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":"1cb0eeb16cf04ee3","mcp_get_code":{"code_sha256":"1cb0eeb16cf04ee3"}},{"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":"8a32cc283c5e5807","mcp_get_code":{"code_sha256":"8a32cc283c5e5807"}},{"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_kl.py","file_url":"https://github.com/ZhengxiangShi/InstructionModelling/blob/HEAD/src/finetune_kl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fc23892a28f95bc1","mcp_get_code":{"code_sha256":"fc23892a28f95bc1"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"97229c97d4273595","mcp_get_code":{"code_sha256":"97229c97d4273595"}},{"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/ds_configs/finetune_ecgllm_with_lora_mimic.py","file_url":"https://github.com/aiot-mlsys-lab/meit/blob/HEAD/ECG_LLMs/ds_configs/finetune_ecgllm_with_lora_mimic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"70e6efcabc56da63","mcp_get_code":{"code_sha256":"70e6efcabc56da63"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0965c5d99ff0f81d","mcp_get_code":{"code_sha256":"0965c5d99ff0f81d"}},{"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_ptbxl.py","file_url":"https://github.com/aiot-mlsys-lab/meit/blob/HEAD/ECG_LLMs/finetune_ecgllm_with_lora_ptbxl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"10deefcbaed6584f","mcp_get_code":{"code_sha256":"10deefcbaed6584f"}},{"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1cb0eeb16cf04ee3","mcp_get_code":{"code_sha256":"1cb0eeb16cf04ee3"}},{"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":"bc1a96ec28a11a5f","mcp_get_code":{"code_sha256":"bc1a96ec28a11a5f"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"97229c97d4273595","mcp_get_code":{"code_sha256":"97229c97d4273595"}},{"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/dpo_tune.py","file_url":"https://github.com/Blue-Raincoat/SelectIT/blob/HEAD/eval/open_instruct/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":"254ab4972fe2c4e2","mcp_get_code":{"code_sha256":"254ab4972fe2c4e2"}},{"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":"1cb0eeb16cf04ee3","mcp_get_code":{"code_sha256":"1cb0eeb16cf04ee3"}},{"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1cb0eeb16cf04ee3","mcp_get_code":{"code_sha256":"1cb0eeb16cf04ee3"}},{"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":"1cb0eeb16cf04ee3","mcp_get_code":{"code_sha256":"1cb0eeb16cf04ee3"}},{"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":"1cb0eeb16cf04ee3","mcp_get_code":{"code_sha256":"1cb0eeb16cf04ee3"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1cb0eeb16cf04ee3","mcp_get_code":{"code_sha256":"1cb0eeb16cf04ee3"}},{"arxiv_id":"2310.08491","paper":"/paper/prometheus-inducing-fine-grained-evaluation","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaistAI/Prometheus","path":"train/utils.py","file_url":"https://github.com/kaistAI/Prometheus/blob/HEAD/train/utils.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":"1cb0eeb16cf04ee3","mcp_get_code":{"code_sha256":"1cb0eeb16cf04ee3"}},{"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":"bc1a96ec28a11a5f","mcp_get_code":{"code_sha256":"bc1a96ec28a11a5f"}},{"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":"bc1a96ec28a11a5f","mcp_get_code":{"code_sha256":"bc1a96ec28a11a5f"}}]}