{"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/sum-except-batch","entry":"sum_except_batch","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":25,"n_papers_ran":22,"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":9,"n_samples_ran":6,"n_samples_fingerprinted":6,"n_places":30,"n_places_pointer_only":9,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":3,"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":"2607.06546","paper":"/paper/arxiv-2607-06546","title":"Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"shervinkhalafi/graph_conv_att","path":"src/tmgg/diffusion/diffusion_math.py","file_url":"https://github.com/shervinkhalafi/graph_conv_att/blob/HEAD/src/tmgg/diffusion/diffusion_math.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"EUPL-1.2","inline_ok":false,"code_sha256_prefix":"a76116170bb86ac3","mcp_get_code":{"code_sha256":"a76116170bb86ac3"}},{"arxiv_id":"2606.27361","paper":"/paper/arxiv-2606-27361","title":"Autoregressive Boltzmann Generators","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"danyalrehman/autobg","path":"src/models/utils.py","file_url":"https://github.com/danyalrehman/autobg/blob/HEAD/src/models/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2cee3f8f2583fd9d","mcp_get_code":{"code_sha256":"2cee3f8f2583fd9d"}},{"arxiv_id":"2606.01595","paper":"/paper/arxiv-2606-01595","title":"Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"jiuguaiwf/UCD","path":"edm/qm9/losses.py","file_url":"https://github.com/jiuguaiwf/UCD/blob/HEAD/edm/qm9/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90c529ca8e85d3db","mcp_get_code":{"code_sha256":"90c529ca8e85d3db"}},{"arxiv_id":"2603.23719","paper":"/paper/arxiv-2603-23719","title":"CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"MuhangTian/TimeDiff","path":"models/ETDiff/mixed_diffusion.py","file_url":"https://github.com/MuhangTian/TimeDiff/blob/HEAD/models/ETDiff/mixed_diffusion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5eb945b1f970f6af","mcp_get_code":{"code_sha256":"5eb945b1f970f6af"}},{"arxiv_id":"2509.01486","paper":"/paper/arxiv-2509-01486","title":"Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"CMACH508/PAFlow","path":"models/en_diffusion.py","file_url":"https://github.com/CMACH508/PAFlow/blob/HEAD/models/en_diffusion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"076381011e4298d5","mcp_get_code":{"code_sha256":"076381011e4298d5"}},{"arxiv_id":"2509.01486","paper":"/paper/arxiv-2509-01486","title":"Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"CMACH508/PAFlow","path":"models/utils.py","file_url":"https://github.com/CMACH508/PAFlow/blob/HEAD/models/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2cee3f8f2583fd9d","mcp_get_code":{"code_sha256":"2cee3f8f2583fd9d"}},{"arxiv_id":"2410.06502","paper":"/paper/chemistry-inspired-diffusion-with-non","title":"Chemistry-Inspired Diffusion with Non-Differentiable Guidance","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"A-Chicharito-S/ChemGuide","path":"qm9/losses.py","file_url":"https://github.com/A-Chicharito-S/ChemGuide/blob/HEAD/qm9/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90c529ca8e85d3db","mcp_get_code":{"code_sha256":"90c529ca8e85d3db"}},{"arxiv_id":"2410.06262","paper":"/paper/symdiff-equivariant-diffusion-via-stochastic","title":"SymDiff: Equivariant Diffusion via Stochastic Symmetrisation","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leozhangML/SymDiff","path":"qm9/losses.py","file_url":"https://github.com/leozhangML/SymDiff/blob/HEAD/qm9/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90c529ca8e85d3db","mcp_get_code":{"code_sha256":"90c529ca8e85d3db"}},{"arxiv_id":"2407.16193","paper":"/paper/cloudfixer-test-time-adaptation-for-3d-point","title":"CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shimazing/CloudFixer","path":"utils/losses.py","file_url":"https://github.com/shimazing/CloudFixer/blob/HEAD/utils/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90c529ca8e85d3db","mcp_get_code":{"code_sha256":"90c529ca8e85d3db"}},{"arxiv_id":"2405.15252","paper":"/paper/fast-3d-molecule-generation-via-unified","title":"Fast 3D Molecule Generation via Unified Geometric Optimal Transport","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HaokaiHong/GOAT","path":"models/goat.py","file_url":"https://github.com/HaokaiHong/GOAT/blob/HEAD/models/goat.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"076381011e4298d5","mcp_get_code":{"code_sha256":"076381011e4298d5"}},{"arxiv_id":"2401.13858","paper":"/paper/inverse-molecular-design-with-multi","title":"Graph Diffusion Transformers for Multi-Conditional Molecular Generation","date":"2024-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liugangcode/MCD","path":"graph_dit/diffusion/diffusion_utils.py","file_url":"https://github.com/liugangcode/MCD/blob/HEAD/graph_dit/diffusion/diffusion_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2cee3f8f2583fd9d","mcp_get_code":{"code_sha256":"2cee3f8f2583fd9d"}},{"arxiv_id":"2401.03349","paper":"/paper/image-inpainting-via-tractable-steering-of","title":"Image Inpainting via Tractable Steering of Diffusion Models","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucla-starai/tiramisu","path":"controlled_img_modeling/latent_transformer_2d/diffusion_transformer.py","file_url":"https://github.com/ucla-starai/tiramisu/blob/HEAD/controlled_img_modeling/latent_transformer_2d/diffusion_transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5eb945b1f970f6af","mcp_get_code":{"code_sha256":"5eb945b1f970f6af"}},{"arxiv_id":"2311.12085","paper":"/paper/pyramid-diffusion-for-fine-3d-large-scene","title":"Pyramid Diffusion for Fine 3D Large Scene Generation","date":"2023-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yuheng-SWJTU/pyramid-discrete-diffusion","path":"models/conditional_diffusion/con_diffusion.py","file_url":"https://github.com/Yuheng-SWJTU/pyramid-discrete-diffusion/blob/HEAD/models/conditional_diffusion/con_diffusion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5eb945b1f970f6af","mcp_get_code":{"code_sha256":"5eb945b1f970f6af"}},{"arxiv_id":"2308.16212","paper":"/paper/retrobridge-modeling-retrosynthesis-with","title":"RetroBridge: Modeling Retrosynthesis with Markov Bridges","date":"2023-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"igashov/retrobridge","path":"src/frameworks/diffusion_utils.py","file_url":"https://github.com/igashov/retrobridge/blob/HEAD/src/frameworks/diffusion_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2cee3f8f2583fd9d","mcp_get_code":{"code_sha256":"2cee3f8f2583fd9d"}},{"arxiv_id":"2306.16819","paper":"/paper/graph-denoising-diffusion-for-inverse-protein","title":"Graph Denoising Diffusion for Inverse Protein Folding","date":"2023-06-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ykiiiiii/GraDe_IF","path":"diffusion/utils.py","file_url":"https://github.com/ykiiiiii/GraDe_IF/blob/HEAD/diffusion/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2cee3f8f2583fd9d","mcp_get_code":{"code_sha256":"2cee3f8f2583fd9d"}},{"arxiv_id":"2305.04111","paper":"/paper/efficient-and-degree-guided-graph-generation","title":"Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling","date":"2023-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tufts-ml/graph-generation-EDGE","path":"diffusion/diffusion_base.py","file_url":"https://github.com/tufts-ml/graph-generation-EDGE/blob/HEAD/diffusion/diffusion_base.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":"38d8ef27c0f4b98a","mcp_get_code":{"code_sha256":"38d8ef27c0f4b98a"}},{"arxiv_id":"2305.01140","paper":"/paper/geometric-latent-diffusion-models-for-3d","title":"Geometric Latent Diffusion Models for 3D Molecule Generation","date":"2023-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlacombe/accgeoldm","path":"qm9/losses.py","file_url":"https://github.com/rlacombe/accgeoldm/blob/HEAD/qm9/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90c529ca8e85d3db","mcp_get_code":{"code_sha256":"90c529ca8e85d3db"}},{"arxiv_id":"2301.00527","paper":"/paper/diffusion-probabilistic-models-for-scene","title":"Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data","date":"2023-01-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zoomin-lee/scene-scale-diffusion","path":"layers/Voxel_Level/Con_Diffusion.py","file_url":"https://github.com/zoomin-lee/scene-scale-diffusion/blob/HEAD/layers/Voxel_Level/Con_Diffusion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5eb945b1f970f6af","mcp_get_code":{"code_sha256":"5eb945b1f970f6af"}},{"arxiv_id":"2205.16007","paper":"/paper/improved-vector-quantized-diffusion-models","title":"Improved Vector Quantized Diffusion Models","date":"2022-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/vq-diffusion","path":"image_synthesis/modeling/transformers/diffusion_transformer.py","file_url":"https://github.com/microsoft/vq-diffusion/blob/HEAD/image_synthesis/modeling/transformers/diffusion_transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5eb945b1f970f6af","mcp_get_code":{"code_sha256":"5eb945b1f970f6af"}},{"arxiv_id":"2203.17003","paper":"/paper/equivariant-diffusion-for-molecule-generation","title":"Equivariant Diffusion for Molecule Generation in 3D","date":"2022-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ehoogeboom/e3_diffusion_for_molecules","path":"equivariant_diffusion/en_diffusion.py","file_url":"https://github.com/ehoogeboom/e3_diffusion_for_molecules/blob/HEAD/equivariant_diffusion/en_diffusion.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":"076381011e4298d5","mcp_get_code":{"code_sha256":"076381011e4298d5"}},{"arxiv_id":"2203.17003","paper":"/paper/equivariant-diffusion-for-molecule-generation","title":"Equivariant Diffusion for Molecule Generation in 3D","date":"2022-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ehoogeboom/e3_diffusion_for_molecules","path":"equivariant_diffusion/utils.py","file_url":"https://github.com/ehoogeboom/e3_diffusion_for_molecules/blob/HEAD/equivariant_diffusion/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2cee3f8f2583fd9d","mcp_get_code":{"code_sha256":"2cee3f8f2583fd9d"}},{"arxiv_id":"2203.17003","paper":"/paper/equivariant-diffusion-for-molecule-generation","title":"Equivariant Diffusion for Molecule Generation in 3D","date":"2022-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ehoogeboom/e3_diffusion_for_molecules","path":"qm9/losses.py","file_url":"https://github.com/ehoogeboom/e3_diffusion_for_molecules/blob/HEAD/qm9/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90c529ca8e85d3db","mcp_get_code":{"code_sha256":"90c529ca8e85d3db"}},{"arxiv_id":"2203.09470","paper":"/paper/curtains-for-your-sliding-window-constructing","title":"CURTAINs for your Sliding Window: Constructing Unobserved Regions by Transforming Adjacent Intervals","date":null,"month_inferred_from_arxiv_id":"2022-03","title_source":"archive","repo":"sambklein/CURTAINS","path":"models/cathode_flows.py","file_url":"https://github.com/sambklein/CURTAINS/blob/HEAD/models/cathode_flows.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"68419341a6380e20","mcp_get_code":{"code_sha256":"68419341a6380e20"}},{"arxiv_id":"2109.00546","paper":"/paper/classifying-anomalies-through-outer-density","title":"Classifying Anomalies THrough Outer Density Estimation (CATHODE)","date":null,"month_inferred_from_arxiv_id":"2021-09","title_source":"archive","repo":"uhh-pd-ml/sk_cathode","path":"sk_cathode/generative_models/flows.py","file_url":"https://github.com/uhh-pd-ml/sk_cathode/blob/HEAD/sk_cathode/generative_models/flows.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0286a0665361e516","mcp_get_code":{"code_sha256":"0286a0665361e516"}},{"arxiv_id":"2105.09016","paper":"/paper/e-n-equivariant-normalizing-flows-for","title":"E(n) Equivariant Normalizing Flows","date":"2021-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vgsatorras/en_flows","path":"flows/ffjord.py","file_url":"https://github.com/vgsatorras/en_flows/blob/HEAD/flows/ffjord.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":"076381011e4298d5","mcp_get_code":{"code_sha256":"076381011e4298d5"}},{"arxiv_id":"2105.09016","paper":"/paper/e-n-equivariant-normalizing-flows-for","title":"E(n) Equivariant Normalizing Flows","date":"2021-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vgsatorras/en_flows","path":"flows/utils.py","file_url":"https://github.com/vgsatorras/en_flows/blob/HEAD/flows/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2cee3f8f2583fd9d","mcp_get_code":{"code_sha256":"2cee3f8f2583fd9d"}},{"arxiv_id":"2105.09016","paper":"/paper/e-n-equivariant-normalizing-flows-for","title":"E(n) Equivariant Normalizing Flows","date":"2021-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vgsatorras/en_flows","path":"dw4_experiment/losses.py","file_url":"https://github.com/vgsatorras/en_flows/blob/HEAD/dw4_experiment/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90c529ca8e85d3db","mcp_get_code":{"code_sha256":"90c529ca8e85d3db"}},{"arxiv_id":"2102.05379","paper":"/paper/argmax-flows-and-multinomial-diffusion","title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","date":"2021-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuzheZhang-1999/DiffTSR","path":"model/TDM/models/diffusion_multinomial.py","file_url":"https://github.com/YuzheZhang-1999/DiffTSR/blob/HEAD/model/TDM/models/diffusion_multinomial.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"38d8ef27c0f4b98a","mcp_get_code":{"code_sha256":"38d8ef27c0f4b98a"}},{"arxiv_id":"2007.02731","paper":"/paper/survae-flows-surjections-to-bridge-the-gap","title":"SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows","date":"2020-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"revsic/tf-survae-flows","path":"survaeflow/utils.py","file_url":"https://github.com/revsic/tf-survae-flows/blob/HEAD/survaeflow/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d29caa5dfe0cdcf7","mcp_get_code":{"code_sha256":"d29caa5dfe0cdcf7"}},{"arxiv_id":"Gu_Vector_Quantized_Diffusion_Model_for_Text-to-Image_Synthesis_CVPR_2022_paper","paper":null,"title":"arXiv:Gu_Vector_Quantized_Diffusion_Model_for_Text-to-Image_Synthesis_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"cientgu/VQ-Diffusion","path":"image_synthesis/modeling/transformers/diffusion_transformer.py","file_url":"https://github.com/cientgu/VQ-Diffusion/blob/HEAD/image_synthesis/modeling/transformers/diffusion_transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5eb945b1f970f6af","mcp_get_code":{"code_sha256":"5eb945b1f970f6af"}}]}