{"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/basetrainer","entry":"BaseTrainer","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":16,"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":16,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":16,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"unverified":9},"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":"2606.23155","paper":"/paper/arxiv-2606-23155","title":"Neural Parameter Calibration for Finite-State Mean Field Games","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"KachmanLab/MFGParameterCalibration","path":"src/calibration/BaseTrainer.py","file_url":"https://github.com/KachmanLab/MFGParameterCalibration/blob/HEAD/src/calibration/BaseTrainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18835f28278eb0a9","mcp_get_code":{"code_sha256":"18835f28278eb0a9"}},{"arxiv_id":"2605.13612","paper":"/paper/arxiv-2605-13612","title":"Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"IdePHICS/Neural-LoFi-Theory","path":"src/train_hierarchically/training/kernel_spectral.py","file_url":"https://github.com/IdePHICS/Neural-LoFi-Theory/blob/HEAD/src/train_hierarchically/training/kernel_spectral.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5241b31e984ec04a","mcp_get_code":{"code_sha256":"5241b31e984ec04a"}},{"arxiv_id":"2602.04651","paper":"/paper/arxiv-2602-04651","title":"SAFE: Stable Alignment Finetuning with Entropy-Aware Predictive Control for RLHF Combining Double Soft-Min Critics with Adaptive KL Thresholding","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ryyzn9/SAFE","path":"safe/trainers/safe.py","file_url":"https://github.com/ryyzn9/SAFE/blob/HEAD/safe/trainers/safe.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e6545e6f0ce1a83","mcp_get_code":{"code_sha256":"5e6545e6f0ce1a83"}},{"arxiv_id":"2511.10859","paper":"/paper/arxiv-2511-10859","title":"Private Zeroth-Order Optimization with Public Data","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"xuchengong/pazo","path":"experiments/pazo-p.py","file_url":"https://github.com/xuchengong/pazo/blob/HEAD/experiments/pazo-p.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bd6d028a5f2b25c7","mcp_get_code":{"code_sha256":"bd6d028a5f2b25c7"}},{"arxiv_id":"2411.17511","paper":"/paper/training-hamiltonian-neural-networks-without","title":"Training Hamiltonian neural networks without backpropagation","date":"2024-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AlphaGergedan/Sampling-HNNs","path":"src/trainer/sampler.py","file_url":"https://github.com/AlphaGergedan/Sampling-HNNs/blob/HEAD/src/trainer/sampler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e8879005ea7b17a5","mcp_get_code":{"code_sha256":"e8879005ea7b17a5"}},{"arxiv_id":"2405.17111","paper":"/paper/diffusion-bridge-autoencoders-for","title":"Diffusion Bridge AutoEncoders for Unsupervised Representation Learning","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ckczzj/PDAE","path":"trainer/train_representation_learning.py","file_url":"https://github.com/ckczzj/PDAE/blob/HEAD/trainer/train_representation_learning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59d0f7c7bd4e6720","mcp_get_code":{"code_sha256":"59d0f7c7bd4e6720"}},{"arxiv_id":"2405.06264","paper":"/paper/selective-focus-investigating-semantics","title":"Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection","date":"2024-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PannenetsF/SelectiveFocus","path":"pad/utils/runners/lane_det_quant_trainer.py","file_url":"https://github.com/PannenetsF/SelectiveFocus/blob/HEAD/pad/utils/runners/lane_det_quant_trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ddbb781402a89bb4","mcp_get_code":{"code_sha256":"ddbb781402a89bb4"}},{"arxiv_id":"2307.08114","paper":"/paper/tangent-model-composition-for-ensembling-and","title":"Tangent Model Composition for Ensembling and Continual Fine-tuning","date":"2023-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianyu139/tangent-model-composition","path":"tangent_trainer.py","file_url":"https://github.com/tianyu139/tangent-model-composition/blob/HEAD/tangent_trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f090911c87dea79d","mcp_get_code":{"code_sha256":"f090911c87dea79d"}},{"arxiv_id":"2212.12990","paper":"/paper/unsupervised-representation-learning-from-pre","title":"Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models","date":"2022-12-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yue-zhongqi/diti","path":"trainer/representation_learning_trainer.py","file_url":"https://github.com/yue-zhongqi/diti/blob/HEAD/trainer/representation_learning_trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4169604fb1fae5cb","mcp_get_code":{"code_sha256":"4169604fb1fae5cb"}},{"arxiv_id":"2212.00309","paper":"/paper/differentially-private-adaptive-optimization","title":"Differentially Private Adaptive Optimization with Delayed Preconditioners","date":"2022-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kenziyuliu/dp2","path":"trainers/dp2_adagrad.py","file_url":"https://github.com/kenziyuliu/dp2/blob/HEAD/trainers/dp2_adagrad.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":"dca6afaa2e23a3be","mcp_get_code":{"code_sha256":"dca6afaa2e23a3be"}},{"arxiv_id":"2208.05810","paper":"/paper/towards-sequence-level-training-for-visual","title":"Towards Sequence-Level Training for Visual Tracking","date":"2022-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"byminji/SLTtrack","path":"ltr/trainers/slt_transt_trainer.py","file_url":"https://github.com/byminji/SLTtrack/blob/HEAD/ltr/trainers/slt_transt_trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"b1a9819a687a220f","mcp_get_code":{"code_sha256":"b1a9819a687a220f"}},{"arxiv_id":"2112.00791","paper":"/paper/controlling-conditional-language-models-with","title":"Controlling Conditional Language Models without Catastrophic Forgetting","date":"2021-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver/gdc","path":"cdpg/cdpg/pointwise_gdc.py","file_url":"https://github.com/naver/gdc/blob/HEAD/cdpg/cdpg/pointwise_gdc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4e11394481ba47b3","mcp_get_code":{"code_sha256":"4e11394481ba47b3"}},{"arxiv_id":"2108.12777","paper":"/paper/searching-for-an-effective-defender","title":"Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution","date":"2021-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RockyLzy/TextDefender","path":"trainer/ascc.py","file_url":"https://github.com/RockyLzy/TextDefender/blob/HEAD/trainer/ascc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"875a0b28ba40c0a5","mcp_get_code":{"code_sha256":"875a0b28ba40c0a5"}},{"arxiv_id":"2108.11941","paper":"/paper/semantically-coherent-out-of-distribution","title":"Semantically Coherent Out-of-Distribution Detection","date":"2021-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jingkang50/ICCV21_SCOOD","path":"scood/trainers/udg_trainer.py","file_url":"https://github.com/Jingkang50/ICCV21_SCOOD/blob/HEAD/scood/trainers/udg_trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca74574f5cf44300","mcp_get_code":{"code_sha256":"ca74574f5cf44300"}},{"arxiv_id":"2103.13575","paper":"/paper/metaalign-coordinating-domain-alignment-and","title":"MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/UDA","path":"trainer/da/toalign.py","file_url":"https://github.com/microsoft/UDA/blob/HEAD/trainer/da/toalign.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e4d8b30d56dbb7f3","mcp_get_code":{"code_sha256":"e4d8b30d56dbb7f3"}},{"arxiv_id":"2012.11635","paper":"/paper/2012-11635","title":"A Distributional Approach to Controlled Text Generation","date":"2020-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver/gdc","path":"dpg/gdc/gdc/gdc.py","file_url":"https://github.com/naver/gdc/blob/HEAD/dpg/gdc/gdc/gdc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"825da61438abc2b7","mcp_get_code":{"code_sha256":"825da61438abc2b7"}}]}