{"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/score-completions","entry":"score_completions","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":0,"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":3,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2602.13773","paper":"/paper/arxiv-2602-13773","title":"On Representation Redundancy in Large-Scale Instruction Tuning Data Selection","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"tdano1/CRDS","path":"main/eval/utils.py","file_url":"https://github.com/tdano1/CRDS/blob/HEAD/main/eval/utils.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":"d029fa02758da921","mcp_get_code":{"code_sha256":"d029fa02758da921"}},{"arxiv_id":"2602.01539","paper":"/paper/arxiv-2602-01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"BattleWen/MAGIC","path":"eval/safety-eval-fork/src/generation_utils.py","file_url":"https://github.com/BattleWen/MAGIC/blob/HEAD/eval/safety-eval-fork/src/generation_utils.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":"d029fa02758da921","mcp_get_code":{"code_sha256":"d029fa02758da921"}},{"arxiv_id":"2506.20512","paper":"/paper/octothinker-mid-training-incentivizes","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/octothinker","path":"eval/eval/utils.py","file_url":"https://github.com/gair-nlp/octothinker/blob/HEAD/eval/eval/utils.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":"8c63844c66973f8d","mcp_get_code":{"code_sha256":"8c63844c66973f8d"}},{"arxiv_id":"2504.11393","paper":"/paper/datadecide-how-to-predict-best-pretraining","title":"DataDecide: How to Predict Best Pretraining Data with Small Experiments","date":"2025-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/prox","path":"eval/utils.py","file_url":"https://github.com/gair-nlp/prox/blob/HEAD/eval/utils.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":"d029fa02758da921","mcp_get_code":{"code_sha256":"d029fa02758da921"}},{"arxiv_id":"2502.12067","paper":"/paper/tokenskip-controllable-chain-of-thought","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hemingkx/TokenSkip","path":"eval/utils.py","file_url":"https://github.com/hemingkx/TokenSkip/blob/HEAD/eval/utils.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":"8c63844c66973f8d","mcp_get_code":{"code_sha256":"8c63844c66973f8d"}},{"arxiv_id":"2410.24175","paper":"/paper/constraint-back-translation-improves-complex","title":"Constraint Back-translation Improves Complex Instruction Following of Large Language Models","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-keg/crab","path":"eval/utils.py","file_url":"https://github.com/thu-keg/crab/blob/HEAD/eval/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d029fa02758da921","mcp_get_code":{"code_sha256":"d029fa02758da921"}},{"arxiv_id":"2406.18629","paper":"/paper/step-dpo-step-wise-preference-optimization","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/step-dpo","path":"evaluation/eval/utils.py","file_url":"https://github.com/dvlab-research/step-dpo/blob/HEAD/evaluation/eval/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8c63844c66973f8d","mcp_get_code":{"code_sha256":"8c63844c66973f8d"}},{"arxiv_id":"2406.10890","paper":"/paper/rwku-benchmarking-real-world-knowledge","title":"RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models","date":"2024-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinzhuoran/rwku","path":"generation/inference.py","file_url":"https://github.com/jinzhuoran/rwku/blob/HEAD/generation/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d029fa02758da921","mcp_get_code":{"code_sha256":"d029fa02758da921"}},{"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/eval/utils.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/eval/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d029fa02758da921","mcp_get_code":{"code_sha256":"d029fa02758da921"}},{"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/eval/utils.py","file_url":"https://github.com/Blue-Raincoat/SelectIT/blob/HEAD/eval/eval/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d029fa02758da921","mcp_get_code":{"code_sha256":"d029fa02758da921"}},{"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":"eval/utils.py","file_url":"https://github.com/ducdauge/sft-llm/blob/HEAD/eval/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e86d5bc4e595d32c","mcp_get_code":{"code_sha256":"e86d5bc4e595d32c"}}]}