{"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/get-pred","entry":"get_pred","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":20,"n_papers_ran":8,"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":20,"n_samples_ran":8,"n_samples_fingerprinted":0,"n_places":21,"n_places_pointer_only":3,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":5,"unverified":12},"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":"2604.10900","paper":"/paper/arxiv-2604-10900","title":"CASK: Core-Aware Selective KV Compression for Reasoning Traces","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"THUDM/LongBench","path":"LongBench/retrieval/pred.py","file_url":"https://github.com/THUDM/LongBench/blob/HEAD/LongBench/retrieval/pred.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7de062709da87b4f","mcp_get_code":{"code_sha256":"7de062709da87b4f"}},{"arxiv_id":"2603.14238","paper":"/paper/arxiv-2603-14238","title":"Domain-Skewed Federated Learning with Feature Decoupling and Calibration","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"mala-lab/F2DC","path":"models/f2dc.py","file_url":"https://github.com/mala-lab/F2DC/blob/HEAD/models/f2dc.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":"bf281d515e42470d","mcp_get_code":{"code_sha256":"bf281d515e42470d"}},{"arxiv_id":"2505.20322","paper":"/paper/beyond-prompt-engineering-robust-behavior","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","date":"2025-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/steer-target-atoms","path":"dataloader.py","file_url":"https://github.com/zjunlp/steer-target-atoms/blob/HEAD/dataloader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4e409608d73ba8ed","mcp_get_code":{"code_sha256":"4e409608d73ba8ed"}},{"arxiv_id":"2409.12181","paper":"/paper/a-controlled-study-on-long-context-extension","title":"A Controlled Study on Long Context Extension and Generalization in LLMs","date":"2024-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leooyii/lceg","path":"longbench/pred.py","file_url":"https://github.com/leooyii/lceg/blob/HEAD/longbench/pred.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ac5698be4313ef23","mcp_get_code":{"code_sha256":"ac5698be4313ef23"}},{"arxiv_id":"2409.00101","paper":"/paper/neurolm-a-universal-multi-task-foundation","title":"NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals","date":"2024-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"935963004/neurolm","path":"train_instruction.py","file_url":"https://github.com/935963004/neurolm/blob/HEAD/train_instruction.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c26a6321cdb66be7","mcp_get_code":{"code_sha256":"c26a6321cdb66be7"}},{"arxiv_id":"2407.08972","paper":"/paper/revealing-the-dark-secrets-of-extremely-large","title":"Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness","date":"2024-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lauch1ng/lkrobust","path":"adversarial_attack/utils.py","file_url":"https://github.com/lauch1ng/lkrobust/blob/HEAD/adversarial_attack/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":"317cf3d87d623d14","mcp_get_code":{"code_sha256":"317cf3d87d623d14"}},{"arxiv_id":"2407.04842","paper":"/paper/mj-bench-is-your-multimodal-reward-model","title":"MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?","date":"2024-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MJ-Bench/MJ-Bench","path":"experimental/ddpo_finetune_with_vlm.py","file_url":"https://github.com/MJ-Bench/MJ-Bench/blob/HEAD/experimental/ddpo_finetune_with_vlm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"17ad7536db5b4682","mcp_get_code":{"code_sha256":"17ad7536db5b4682"}},{"arxiv_id":"2406.03143","paper":"/paper/zeropur-succinct-training-free-adversarial","title":"ZeroPur: Succinct Training-Free Adversarial Purification","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"erhul/ZeroPur","path":"utils.py","file_url":"https://github.com/erhul/ZeroPur/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5105d577deca7c37","mcp_get_code":{"code_sha256":"5105d577deca7c37"}},{"arxiv_id":"2405.04434","paper":"/paper/deepseek-v2-a-strong-economical-and-efficient","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shadowpa0327/Palu","path":"run_long_bench.py","file_url":"https://github.com/shadowpa0327/Palu/blob/HEAD/run_long_bench.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87b9a0c596eea7a8","mcp_get_code":{"code_sha256":"87b9a0c596eea7a8"}},{"arxiv_id":"2402.19167","paper":"/paper/teaching-large-language-models-an-unseen","title":"Teaching Large Language Models an Unseen Language on the Fly","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luciusssss/zhuangbench","path":"src/model.py","file_url":"https://github.com/luciusssss/zhuangbench/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c70a55ce586ba43d","mcp_get_code":{"code_sha256":"c70a55ce586ba43d"}},{"arxiv_id":"2402.02750","paper":"/paper/kivi-a-tuning-free-asymmetric-2bit","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jy-yuan/kivi","path":"pred_long_bench.py","file_url":"https://github.com/jy-yuan/kivi/blob/HEAD/pred_long_bench.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1b63810f36de324d","mcp_get_code":{"code_sha256":"1b63810f36de324d"}},{"arxiv_id":"2311.09198","paper":"/paper/never-lost-in-the-middle-improving-large","title":"Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hejunqing/never-lost-in-the-middle","path":"LongBench/src/baichuan_pred_shuffle.py","file_url":"https://github.com/hejunqing/never-lost-in-the-middle/blob/HEAD/LongBench/src/baichuan_pred_shuffle.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9ac0485160d687f7","mcp_get_code":{"code_sha256":"9ac0485160d687f7"}},{"arxiv_id":"2304.03935","paper":"/paper/last-layer-fairness-fine-tuning-is-simple-and","title":"Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks","date":"2023-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"modar7/the_fairness_stitch","path":"src/utils.py","file_url":"https://github.com/modar7/the_fairness_stitch/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c691b280c17d59c0","mcp_get_code":{"code_sha256":"c691b280c17d59c0"}},{"arxiv_id":"2302.07257","paper":"/paper/chatcad-interactive-computer-aided-diagnosis","title":"ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models","date":"2023-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaozh10/ChatCAD","path":"cxr/diagnosis.py","file_url":"https://github.com/zhaozh10/ChatCAD/blob/HEAD/cxr/diagnosis.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f0d6025716c6e55a","mcp_get_code":{"code_sha256":"f0d6025716c6e55a"}},{"arxiv_id":"2211.04279","paper":"/paper/detecting-shortcuts-in-medical-images-a-case","title":"Detecting Shortcuts in Medical Images -- A Case Study in Chest X-rays","date":"2022-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ameliajimenez/shortcuts-chest-xray","path":"bin/test_model.py","file_url":"https://github.com/ameliajimenez/shortcuts-chest-xray/blob/HEAD/bin/test_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a925c89a990e4ad6","mcp_get_code":{"code_sha256":"a925c89a990e4ad6"}},{"arxiv_id":"2210.02419","paper":"/paper/explanation-uncertainty-with-decision","title":"Boundary-Aware Uncertainty for Feature Attribution Explainers","date":"2022-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davinhill/gpec","path":"GPEC/GP.py","file_url":"https://github.com/davinhill/gpec/blob/HEAD/GPEC/GP.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"86bab81e90151905","mcp_get_code":{"code_sha256":"86bab81e90151905"}},{"arxiv_id":"2203.03802","paper":"/paper/understanding-iterative-revision-from-human","title":"Understanding Iterative Revision from Human-Written Text","date":"2022-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vipulraheja/iterater","path":"code/IteraTeR_ACL2022/model/generation/bart_inference_and_metrics.py","file_url":"https://github.com/vipulraheja/iterater/blob/HEAD/code/IteraTeR_ACL2022/model/generation/bart_inference_and_metrics.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":"08582d047537b71e","mcp_get_code":{"code_sha256":"08582d047537b71e"}},{"arxiv_id":"2203.03802","paper":"/paper/understanding-iterative-revision-from-human","title":"Understanding Iterative Revision from Human-Written Text","date":"2022-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vipulraheja/iterater","path":"code/IteraTeR_ACL2022/model/generation/pegasus_inference_and_metrics.py","file_url":"https://github.com/vipulraheja/iterater/blob/HEAD/code/IteraTeR_ACL2022/model/generation/pegasus_inference_and_metrics.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":"d683a5a86dabd653","mcp_get_code":{"code_sha256":"d683a5a86dabd653"}},{"arxiv_id":"2011.05864","paper":"/paper/on-the-sentence-embeddings-from-pre-trained","title":"On the Sentence Embeddings from Pre-trained Language Models","date":"2020-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bohanli/BERT-flow","path":"scripts/eval_stsb.py","file_url":"https://github.com/bohanli/BERT-flow/blob/HEAD/scripts/eval_stsb.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3b6418910c030c74","mcp_get_code":{"code_sha256":"3b6418910c030c74"}},{"arxiv_id":"2025.findings-acl.433","paper":null,"title":"arXiv:2025.findings-acl.433","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"haon-chen/mmE5","path":"evaluation/eval_utils.py","file_url":"https://github.com/haon-chen/mmE5/blob/HEAD/evaluation/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":"1a5d849f73e20d05","mcp_get_code":{"code_sha256":"1a5d849f73e20d05"}},{"arxiv_id":"2025.emnlp-main.1179","paper":null,"title":"arXiv:2025.emnlp-main.1179","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"csdq777/Lotus","path":"X/model.py","file_url":"https://github.com/csdq777/Lotus/blob/HEAD/X/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c70a55ce586ba43d","mcp_get_code":{"code_sha256":"c70a55ce586ba43d"}}]}