{"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/kl-2","entry":"kl","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":17,"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":14,"n_samples_ran":11,"n_samples_fingerprinted":8,"n_places":20,"n_places_pointer_only":4,"by_status":{"ran_honours":1,"ran_violates":1,"ran_draft_wrong":2,"ran_fixture":0,"ran":7,"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":"2608.03967","paper":"/paper/arxiv-2608-03967","title":"Information-Geometric Forward Policy Training in GFlowNets","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"rodsveiga/infogeometric_gflows","path":"gflows/utils.py","file_url":"https://github.com/rodsveiga/infogeometric_gflows/blob/HEAD/gflows/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"73e9084f185f41d1","mcp_get_code":{"code_sha256":"73e9084f185f41d1"}},{"arxiv_id":"2608.01743","paper":"/paper/arxiv-2608-01743","title":"Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Lumina04/CoKL","path":"analysis_exp/condition_kl_mlp_fair_stepwise_large.py","file_url":"https://github.com/Lumina04/CoKL/blob/HEAD/analysis_exp/condition_kl_mlp_fair_stepwise_large.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b102816daec53fbd","mcp_get_code":{"code_sha256":"b102816daec53fbd"}},{"arxiv_id":"2606.19542","paper":"/paper/arxiv-2606-19542","title":"Tracking Representation Dynamics in Large Language Models with Persistent Homology","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"malhotranaman/tracking-representation-dynamics-with-persistent-homology","path":"src/phlatent/analysis/divergence.py","file_url":"https://github.com/malhotranaman/tracking-representation-dynamics-with-persistent-homology/blob/HEAD/src/phlatent/analysis/divergence.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"626cff0e7fb7d225","mcp_get_code":{"code_sha256":"626cff0e7fb7d225"}},{"arxiv_id":"2605.11983","paper":"/paper/arxiv-2605-11983","title":"QDSB: Quantized Diffusion Schrödinger Bridges","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"mathefuchs/qdsb","path":"ALAE/losses.py","file_url":"https://github.com/mathefuchs/qdsb/blob/HEAD/ALAE/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96e5a2bdc93b101d","mcp_get_code":{"code_sha256":"96e5a2bdc93b101d"}},{"arxiv_id":"2603.18202","paper":"/paper/arxiv-2603-18202","title":"R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"NM512/r2dreamer","path":"dreamer.py","file_url":"https://github.com/NM512/r2dreamer/blob/HEAD/dreamer.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":"485e845ae6cf8417","mcp_get_code":{"code_sha256":"485e845ae6cf8417"}},{"arxiv_id":"2602.02241","paper":"/paper/arxiv-2602-02241","title":"Variational Entropic Optimal Transport","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"DrEternity/VarEOT","path":"ALAE/losses.py","file_url":"https://github.com/DrEternity/VarEOT/blob/HEAD/ALAE/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96e5a2bdc93b101d","mcp_get_code":{"code_sha256":"96e5a2bdc93b101d"}},{"arxiv_id":"2511.06856","paper":"/paper/arxiv-2511-06856","title":"Contact Wasserstein Geodesics for Non-Conservative Schrödinger Bridges","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"ngushchin/LightSB","path":"ALAE/losses.py","file_url":"https://github.com/ngushchin/LightSB/blob/HEAD/ALAE/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96e5a2bdc93b101d","mcp_get_code":{"code_sha256":"96e5a2bdc93b101d"}},{"arxiv_id":"2410.03968","paper":"/paper/decoding-game-on-minimax-optimality-of","title":"Decoding Game: On Minimax Optimality of Heuristic Text Generation Strategies","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"omar-hagrass/decoding-game","path":"src/metrics.py","file_url":"https://github.com/omar-hagrass/decoding-game/blob/HEAD/src/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"13bc3a2c1b6935e2","mcp_get_code":{"code_sha256":"13bc3a2c1b6935e2"}},{"arxiv_id":"2408.03330","paper":"/paper/modeling-latent-neural-dynamics-with-gaussian","title":"Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lindermanlab/gpslds","path":"gpslds/em.py","file_url":"https://github.com/lindermanlab/gpslds/blob/HEAD/gpslds/em.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":"f9158e7f06fbf8cd","mcp_get_code":{"code_sha256":"f9158e7f06fbf8cd"}},{"arxiv_id":"2407.19547","paper":"/paper/temporal-feature-matters-a-framework-for","title":"Temporal Feature Matters: A Framework for Diffusion Model Quantization","date":"2024-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"modeltc/tfmq-dm","path":"quant/quant_layer.py","file_url":"https://github.com/modeltc/tfmq-dm/blob/HEAD/quant/quant_layer.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":"77865748740d72a6","mcp_get_code":{"code_sha256":"77865748740d72a6"}},{"arxiv_id":"2402.03207","paper":"/paper/light-and-optimal-schrodinger-bridge-matching","title":"Light and Optimal Schrödinger Bridge Matching","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skholkin/lightsb-matching","path":"ALAE/losses.py","file_url":"https://github.com/skholkin/lightsb-matching/blob/HEAD/ALAE/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96e5a2bdc93b101d","mcp_get_code":{"code_sha256":"96e5a2bdc93b101d"}},{"arxiv_id":"2310.01174","paper":"/paper/light-schrodinger-bridge","title":"Light Schrödinger Bridge","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ngushchin/lightsb","path":"ALAE/losses.py","file_url":"https://github.com/ngushchin/lightsb/blob/HEAD/ALAE/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96e5a2bdc93b101d","mcp_get_code":{"code_sha256":"96e5a2bdc93b101d"}},{"arxiv_id":"2308.12648","paper":"/paper/from-chatter-to-matter-addressing-critical","title":"From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue","date":"2023-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ConvLab/ConvLab-3","path":"convlab/util/custom_modules.py","file_url":"https://github.com/ConvLab/ConvLab-3/blob/HEAD/convlab/util/custom_modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2c36f59c1bc2e121","mcp_get_code":{"code_sha256":"2c36f59c1bc2e121"}},{"arxiv_id":"2306.00826","paper":"/paper/in-or-out-fixing-imagenet-out-of-distribution","title":"In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation","date":"2023-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"j-cb/NINCO","path":"detection_methods.py","file_url":"https://github.com/j-cb/NINCO/blob/HEAD/detection_methods.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0fbaed8e9101241","mcp_get_code":{"code_sha256":"d0fbaed8e9101241"}},{"arxiv_id":"2305.12394","paper":"/paper/pruning-pre-trained-language-models-with","title":"Pruning Pre-trained Language Models with Principled Importance and Self-regularization","date":"2023-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"drsy/pins","path":"run_glue.py","file_url":"https://github.com/drsy/pins/blob/HEAD/run_glue.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"03110400058b8a87","mcp_get_code":{"code_sha256":"03110400058b8a87"}},{"arxiv_id":"2110.11444","paper":"/paper/density-of-states-prediction-for-materials","title":"Density of States Prediction for Materials Discovery via Contrastive Learning from Probabilistic Embeddings","date":null,"month_inferred_from_arxiv_id":"2021-10","title_source":"archive","repo":"gomes-lab/mat2spec","path":"Mat2Spec_Codes/Mat2Spec/Mat2Spec.py","file_url":"https://github.com/gomes-lab/mat2spec/blob/HEAD/Mat2Spec_Codes/Mat2Spec/Mat2Spec.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2273ec7e81f79f85","mcp_get_code":{"code_sha256":"2273ec7e81f79f85"}},{"arxiv_id":"1912.07414","paper":"/paper/learning-canonical-representations-for-scene","title":"Learning Canonical Representations for Scene Graph to Image Generation","date":"2019-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roeiherz/CanonicalSg2Im","path":"evaluation/fid.py","file_url":"https://github.com/roeiherz/CanonicalSg2Im/blob/HEAD/evaluation/fid.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df860a11dd4c724c","mcp_get_code":{"code_sha256":"df860a11dd4c724c"}},{"arxiv_id":"1807.07543","paper":"/paper/understanding-and-improving-interpolation-in","title":"Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer","date":"2018-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ivanvovk/controllable-face-generation","path":"losses.py","file_url":"https://github.com/ivanvovk/controllable-face-generation/blob/HEAD/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96e5a2bdc93b101d","mcp_get_code":{"code_sha256":"96e5a2bdc93b101d"}},{"arxiv_id":"Huang_TFMQ-DM_Temporal_Feature_Maintenance_Quantization_for_Diffusion_Models_CVPR_2024_paper","paper":null,"title":"arXiv:Huang_TFMQ-DM_Temporal_Feature_Maintenance_Quantization_for_Diffusion_Models_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ModelTC/TFMQ-DM","path":"quant/quant_layer.py","file_url":"https://github.com/ModelTC/TFMQ-DM/blob/HEAD/quant/quant_layer.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":"77865748740d72a6","mcp_get_code":{"code_sha256":"77865748740d72a6"}},{"arxiv_id":"2023.emnlp-main.803","paper":null,"title":"arXiv:2023.emnlp-main.803","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yisunlp/Anti-CF","path":"AntiCF.py","file_url":"https://github.com/yisunlp/Anti-CF/blob/HEAD/AntiCF.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"861d146045f11402","mcp_get_code":{"code_sha256":"861d146045f11402"}}]}