{"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/calculate-entropy","entry":"calculate_entropy","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":22,"n_papers_ran":7,"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":22,"n_samples_ran":7,"n_samples_fingerprinted":4,"n_places":23,"n_places_pointer_only":8,"by_status":{"ran_honours":1,"ran_violates":1,"ran_draft_wrong":1,"ran_fixture":0,"ran":4,"unverified":15},"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":"2604.14925","paper":"/paper/arxiv-2604-14925","title":"Improving Sparse Autoencoder with Dynamic Attention","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"qyj-bkjx/Sparsemax-SAE","path":"analysis/utils.py","file_url":"https://github.com/qyj-bkjx/Sparsemax-SAE/blob/HEAD/analysis/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0113839c1642005","mcp_get_code":{"code_sha256":"c0113839c1642005"}},{"arxiv_id":"2602.22278","paper":"/paper/arxiv-2602-22278","title":"RETLLM: Training and Data-Free MLLMs for Multimodal Information Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"alivecat05/RETLLM","path":"Codes/Qwen_vl.py","file_url":"https://github.com/alivecat05/RETLLM/blob/HEAD/Codes/Qwen_vl.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":"76755f6879d57a39","mcp_get_code":{"code_sha256":"76755f6879d57a39"}},{"arxiv_id":"2601.21709","paper":"/paper/arxiv-2601-21709","title":"Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"MIRALab-USTC/LLM-TAPPA","path":"KVCache/tappa/model/llama_forward.py","file_url":"https://github.com/MIRALab-USTC/LLM-TAPPA/blob/HEAD/KVCache/tappa/model/llama_forward.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"518b8a174b0afc4e","mcp_get_code":{"code_sha256":"518b8a174b0afc4e"}},{"arxiv_id":"2601.11161","paper":"/paper/arxiv-2601-11161","title":"GMM-COMET: Continual Source-Free Universal Domain Adaptation via a Mean Teacher and Gaussian Mixture Model-Based Pseudo-Labeling","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"pascalschlachter/GMM-COMET","path":"adaptation.py","file_url":"https://github.com/pascalschlachter/GMM-COMET/blob/HEAD/adaptation.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3a14e072b8171e33","mcp_get_code":{"code_sha256":"3a14e072b8171e33"}},{"arxiv_id":"2506.17709","paper":"/paper/cega-a-cost-effective-approach-for-graph","title":"CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition","date":"2025-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"labrai/cega","path":"attacks/attack_0_cega.py","file_url":"https://github.com/labrai/cega/blob/HEAD/attacks/attack_0_cega.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90eef8ab7e8c113f","mcp_get_code":{"code_sha256":"90eef8ab7e8c113f"}},{"arxiv_id":"2506.17709","paper":"/paper/cega-a-cost-effective-approach-for-graph","title":"CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition","date":"2025-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"labrai/cega","path":"attacks/attack_0_age.py","file_url":"https://github.com/labrai/cega/blob/HEAD/attacks/attack_0_age.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f77dc13db482d1e3","mcp_get_code":{"code_sha256":"f77dc13db482d1e3"}},{"arxiv_id":"2506.13406","paper":"/paper/calm-consensus-aware-localized-merging-for","title":"CALM: Consensus-Aware Localized Merging for Multi-Task Learning","date":"2025-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yankd22/calm","path":"src/logits_extraction.py","file_url":"https://github.com/yankd22/calm/blob/HEAD/src/logits_extraction.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"818a9b04389c065d","mcp_get_code":{"code_sha256":"818a9b04389c065d"}},{"arxiv_id":"2503.23913","paper":"/paper/entropy-based-adaptive-weighting-for-self","title":"Entropy-Based Adaptive Weighting for Self-Training","date":"2025-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mandyyyyii/east","path":"data_generation/util.py","file_url":"https://github.com/mandyyyyii/east/blob/HEAD/data_generation/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bf4fc86ee78e60ce","mcp_get_code":{"code_sha256":"bf4fc86ee78e60ce"}},{"arxiv_id":"2412.11803","paper":"/paper/ualign-leveraging-uncertainty-estimations-for","title":"UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amourwaltz/ualign","path":"code/uncertainty.py","file_url":"https://github.com/amourwaltz/ualign/blob/HEAD/code/uncertainty.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"23b0e66b13795f6e","mcp_get_code":{"code_sha256":"23b0e66b13795f6e"}},{"arxiv_id":"2412.05276","paper":"/paper/sparse-autoencoders-reveal-selective","title":"Sparse autoencoders reveal selective remapping of visual concepts during adaptation","date":"2024-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dynamical-inference/patchsae","path":"analysis/utils.py","file_url":"https://github.com/dynamical-inference/patchsae/blob/HEAD/analysis/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0113839c1642005","mcp_get_code":{"code_sha256":"c0113839c1642005"}},{"arxiv_id":"2410.17897","paper":"/paper/value-residual-learning-for-alleviating","title":"Value Residual Learning For Alleviating Attention Concentration In Transformers","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zcchill/Value-Residual-Learning","path":"analyze/get_entropy.py","file_url":"https://github.com/Zcchill/Value-Residual-Learning/blob/HEAD/analyze/get_entropy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ed28cdaf289e0435","mcp_get_code":{"code_sha256":"ed28cdaf289e0435"}},{"arxiv_id":"2410.04139","paper":"/paper/from-reading-to-compressing-exploring-the","title":"From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression","date":"2024-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eunseongc/r2c","path":"compress.py","file_url":"https://github.com/eunseongc/r2c/blob/HEAD/compress.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"011fa22b8040e461","mcp_get_code":{"code_sha256":"011fa22b8040e461"}},{"arxiv_id":"2408.12076","paper":"/paper/conflictbank-a-benchmark-for-evaluating-the","title":"ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM","date":"2024-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaochen0110/conflictbank","path":"evaluate.py","file_url":"https://github.com/zhaochen0110/conflictbank/blob/HEAD/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"68dfae5ca75de5c4","mcp_get_code":{"code_sha256":"68dfae5ca75de5c4"}},{"arxiv_id":"2406.19032","paper":"/paper/improving-weak-to-strong-generalization-with-1","title":"Improving Weak-to-Strong Generalization with Reliability-Aware Alignment","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"irenehere/reliablealignment","path":"ETHICS/commonsense/our_method_uncertainty_filtering.py","file_url":"https://github.com/irenehere/reliablealignment/blob/HEAD/ETHICS/commonsense/our_method_uncertainty_filtering.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3a2bf35d401300c4","mcp_get_code":{"code_sha256":"3a2bf35d401300c4"}},{"arxiv_id":"2406.07145","paper":"/paper/failures-are-fated-but-can-be-faded","title":"Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"somsagar07/FailureShiftRL","path":"Utils/plots.py","file_url":"https://github.com/somsagar07/FailureShiftRL/blob/HEAD/Utils/plots.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4c3d4d72af55afa2","mcp_get_code":{"code_sha256":"4c3d4d72af55afa2"}},{"arxiv_id":"2402.18059","paper":"/paper/token-specific-watermarking-with-enhanced","title":"Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mignonjia/ts_watermark","path":"utils/generation.py","file_url":"https://github.com/mignonjia/ts_watermark/blob/HEAD/utils/generation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f3e19b647ed821b","mcp_get_code":{"code_sha256":"6f3e19b647ed821b"}},{"arxiv_id":"2310.15638","paper":"/paper/coannotating-uncertainty-guided-work","title":"CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SALT-NLP/CoAnnotating","path":"Expertise_Estimation.py","file_url":"https://github.com/SALT-NLP/CoAnnotating/blob/HEAD/Expertise_Estimation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5cb041415ae2ab05","mcp_get_code":{"code_sha256":"5cb041415ae2ab05"}},{"arxiv_id":"2309.16240","paper":"/paper/beyond-reverse-kl-generalizing-direct","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alecwangcq/f-divergence-dpo","path":"generation.py","file_url":"https://github.com/alecwangcq/f-divergence-dpo/blob/HEAD/generation.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":"194f8dc522933267","mcp_get_code":{"code_sha256":"194f8dc522933267"}},{"arxiv_id":"2209.12396","paper":"/paper/deep-fair-clustering-via-maximizing-and","title":"Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric","date":"2022-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PengxinZeng/2023-CVPR-FCMI","path":"evaluate.py","file_url":"https://github.com/PengxinZeng/2023-CVPR-FCMI/blob/HEAD/evaluate.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":"4f0406f99019587b","mcp_get_code":{"code_sha256":"4f0406f99019587b"}},{"arxiv_id":"2104.10956","paper":"/paper/fcos3d-fully-convolutional-one-stage","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","date":"2021-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Discover304/MMDetection3D-Eloss","path":"mmdet3d/models/losses/eloss.py","file_url":"https://github.com/Discover304/MMDetection3D-Eloss/blob/HEAD/mmdet3d/models/losses/eloss.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":"356e77e178d28771","mcp_get_code":{"code_sha256":"356e77e178d28771"}},{"arxiv_id":"2010.03010","paper":"/paper/exploring-bert-s-sensitivity-to-lexical-cues","title":"Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming","date":"2020-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kanishkamisra/emnlp-bert-priming","path":"python/entropy_constraint.py","file_url":"https://github.com/kanishkamisra/emnlp-bert-priming/blob/HEAD/python/entropy_constraint.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f24935725a6bbf1","mcp_get_code":{"code_sha256":"0f24935725a6bbf1"}},{"arxiv_id":"ijcai2025_0850","paper":null,"title":"arXiv:ijcai2025_0850","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Hongyi-Lyu-MQ/SULI","path":"methods/unlearning.py","file_url":"https://github.com/Hongyi-Lyu-MQ/SULI/blob/HEAD/methods/unlearning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8081b8874aeff47c","mcp_get_code":{"code_sha256":"8081b8874aeff47c"}},{"arxiv_id":"2024.findings-naacl.117","paper":null,"title":"arXiv:2024.findings-naacl.117","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"qqplot/dcpmi","path":"utils/text_utils.py","file_url":"https://github.com/qqplot/dcpmi/blob/HEAD/utils/text_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ee95ddca5554890","mcp_get_code":{"code_sha256":"0ee95ddca5554890"}}]}