{"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/create-npz-from-sample-folder","entry":"create_npz_from_sample_folder","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":30,"n_papers_ran":26,"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":11,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":31,"n_places_pointer_only":17,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":0,"ran":3,"unverified":4},"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":"2601.07293","paper":"/paper/arxiv-2601-07293","title":"Inference-Time Scaling for Visual AutoRegressive modeling by Searching Representative Samples","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"WD7ang/VAR-Scaling","path":"VAR-main/create_ngz.py","file_url":"https://github.com/WD7ang/VAR-Scaling/blob/HEAD/VAR-main/create_ngz.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"280dae1512c7b50f","mcp_get_code":{"code_sha256":"280dae1512c7b50f"}},{"arxiv_id":"2506.05350","paper":"/paper/contrastive-flow-matching","title":"Contrastive Flow Matching","date":"2025-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2506.05289","paper":"/paper/alitok-towards-sequence-modeling-alignment-1","title":"AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model","date":"2025-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ali-vilab/alitok","path":"sample_imagenet.py","file_url":"https://github.com/ali-vilab/alitok/blob/HEAD/sample_imagenet.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"19a5b88fdb546606","mcp_get_code":{"code_sha256":"19a5b88fdb546606"}},{"arxiv_id":"2505.16792","paper":"/paper/repa-works-until-it-doesn-t-early-stopped","title":"REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2504.07963","paper":"/paper/pixelflow-pixel-space-generative-models-with","title":"PixelFlow: Pixel-Space Generative Models with Flow","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shoufachen/pixelflow","path":"sample_ddp.py","file_url":"https://github.com/shoufachen/pixelflow/blob/HEAD/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c43ca4c65f3079a7","mcp_get_code":{"code_sha256":"c43ca4c65f3079a7"}},{"arxiv_id":"2503.10568","paper":"/paper/autoregressive-image-generation-with","title":"Autoregressive Image Generation with Randomized Parallel Decoding","date":"2025-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hp-l33/ARPG","path":"sample_c2i_ddp.py","file_url":"https://github.com/hp-l33/ARPG/blob/HEAD/sample_c2i_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2501.00603","paper":"/paper/dic-rethinking-conv3x3-designs-in-diffusion","title":"DiC: Rethinking Conv3x3 Designs in Diffusion Models","date":"2024-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2412.12095","paper":"/paper/causal-diffusion-transformers-for-generative","title":"Causal Diffusion Transformers for Generative Modeling","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"causalfusion/causalfusion","path":"sample.py","file_url":"https://github.com/causalfusion/causalfusion/blob/HEAD/sample.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"84e2a647a1c4db79","mcp_get_code":{"code_sha256":"84e2a647a1c4db79"}},{"arxiv_id":"2412.05628","paper":"/paper/remix-dit-mixing-diffusion-transformers-for","title":"Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising","date":"2024-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vainf/remix-dit","path":"sample_ddp.py","file_url":"https://github.com/vainf/remix-dit/blob/HEAD/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2412.01199","paper":"/paper/tinyfusion-diffusion-transformers-learned","title":"TinyFusion: Diffusion Transformers Learned Shallow","date":"2024-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vainf/tinyfusion","path":"sample_ddp.py","file_url":"https://github.com/vainf/tinyfusion/blob/HEAD/sample_ddp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"404991021d3508d4","mcp_get_code":{"code_sha256":"404991021d3508d4"}},{"arxiv_id":"2411.17787","paper":"/paper/collaborative-decoding-makes-visual-auto","title":"Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient","date":"2024-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"czg1225/code","path":"sample_CoDe.py","file_url":"https://github.com/czg1225/code/blob/HEAD/sample_CoDe.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"78f71e05e187283b","mcp_get_code":{"code_sha256":"78f71e05e187283b"}},{"arxiv_id":"2411.17616","paper":"/paper/accelerating-vision-diffusion-transformers","title":"Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints","date":"2024-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opensparsellms/skip-dit","path":"class-to-image/sample_ddp.py","file_url":"https://github.com/opensparsellms/skip-dit/blob/HEAD/class-to-image/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2410.23788","paper":"/paper/edt-an-efficient-diffusion-transformer","title":"EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2410.09347","paper":"/paper/toward-guidance-free-ar-visual-generation-via","title":"Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-ml/cca","path":"LlamaGen_sample_ddp.py","file_url":"https://github.com/thu-ml/cca/blob/HEAD/LlamaGen_sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2410.09347","paper":"/paper/toward-guidance-free-ar-visual-generation-via","title":"Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-ml/cca","path":"VAR_sample.py","file_url":"https://github.com/thu-ml/cca/blob/HEAD/VAR_sample.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4f771efa92658445","mcp_get_code":{"code_sha256":"4f771efa92658445"}},{"arxiv_id":"2410.06940","paper":"/paper/representation-alignment-for-generation","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sihyun-yu/REPA","path":"generate.py","file_url":"https://github.com/sihyun-yu/REPA/blob/HEAD/generate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2410.03456","paper":"/paper/dynamic-diffusion-transformer","title":"Dynamic Diffusion Transformer","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nus-hpc-ai-lab/dynamic-diffusion-transformer","path":"sample_ddp.py","file_url":"https://github.com/nus-hpc-ai-lab/dynamic-diffusion-transformer/blob/HEAD/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2410.02705","paper":"/paper/controlar-controllable-image-generation-with","title":"ControlAR: Controllable Image Generation with Autoregressive Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/ControlAR","path":"create_npz.py","file_url":"https://github.com/hustvl/ControlAR/blob/HEAD/create_npz.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":"432162d12f959985","mcp_get_code":{"code_sha256":"432162d12f959985"}},{"arxiv_id":"2409.18128","paper":"/paper/flowturbo-towards-real-time-flow-based-image","title":"FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shiml20/FlowTurbo","path":"sample_ddp_feature.py","file_url":"https://github.com/shiml20/FlowTurbo/blob/HEAD/sample_ddp_feature.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fa92e506df16d054","mcp_get_code":{"code_sha256":"fa92e506df16d054"}},{"arxiv_id":"2409.16280","paper":"/paper/monoformer-one-transformer-for-both-diffusion","title":"MonoFormer: One Transformer for Both Diffusion and Autoregression","date":"2024-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MonoFormer/MonoFormer","path":"sample_ddp.py","file_url":"https://github.com/MonoFormer/MonoFormer/blob/HEAD/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2409.10695","paper":"/paper/playground-v3-improving-text-to-image","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","date":"2024-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuchuantian/u-dit","path":"sample_ddp.py","file_url":"https://github.com/yuchuantian/u-dit/blob/HEAD/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2409.07756","paper":"/paper/ditas-quantizing-diffusion-transformers-via","title":"DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing","date":"2024-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DZY122/DiTAS","path":"sample_merge_TAS.py","file_url":"https://github.com/DZY122/DiTAS/blob/HEAD/sample_merge_TAS.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c43ca4c65f3079a7","mcp_get_code":{"code_sha256":"c43ca4c65f3079a7"}},{"arxiv_id":"2408.05710","paper":"/paper/efficient-diffusion-transformer-with-step","title":"Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators","date":"2024-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/attention-mediators","path":"attention_mediator/sample_ddp.py","file_url":"https://github.com/leaplabthu/attention-mediators/blob/HEAD/attention_mediator/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2407.11633","paper":"/paper/scaling-diffusion-transformers-to-16-billion","title":"Scaling Diffusion Transformers to 16 Billion Parameters","date":"2024-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feizc/dit-moe","path":"sample_ddp.py","file_url":"https://github.com/feizc/dit-moe/blob/HEAD/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2407.01425","paper":"/paper/fora-fast-forward-caching-in-diffusion","title":"FORA: Fast-Forward Caching in Diffusion Transformer Acceleration","date":"2024-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prathebaselva/fora","path":"src/sample_ddp.py","file_url":"https://github.com/prathebaselva/fora/blob/HEAD/src/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2406.17343","paper":"/paper/q-dit-accurate-post-training-quantization-for","title":"Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"19a5b88fdb546606","mcp_get_code":{"code_sha256":"19a5b88fdb546606"}},{"arxiv_id":"2405.02730","paper":"/paper/u-dits-downsample-tokens-in-u-shaped","title":"U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers","date":"2024-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2403.09176","paper":"/paper/switch-diffusion-transformer-synergizing","title":"Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"byeongjun-park/Switch-DiT","path":"sample_ddp.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2402.14167","paper":"/paper/t-stitch-accelerating-sampling-in-pre-trained","title":"T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nvlabs/t-stitch","path":"dit/sample_ddp_t_stitch.py","file_url":"https://github.com/nvlabs/t-stitch/blob/HEAD/dit/sample_ddp_t_stitch.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"arxiv_id":"2402.12376","paper":"/paper/fit-flexible-vision-transformer-for-diffusion","title":"FiT: Flexible Vision Transformer for Diffusion Model","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whlzy/fit","path":"fit/utils/eval_utils.py","file_url":"https://github.com/whlzy/fit/blob/HEAD/fit/utils/eval_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":"7a6ba78116641182","mcp_get_code":{"code_sha256":"7a6ba78116641182"}},{"arxiv_id":"2401.08740","paper":"/paper/sit-exploring-flow-and-diffusion-based","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","date":"2024-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"willisma/sit","path":"sample_ddp.py","file_url":"https://github.com/willisma/sit/blob/HEAD/sample_ddp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b21a01ae77703a3","mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}}]}