{"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/causalselfattention","entry":"CausalSelfAttention","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":28,"n_papers_ran":23,"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":32,"n_samples_ran":27,"n_samples_fingerprinted":5,"n_places":32,"n_places_pointer_only":14,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":27,"unverified":5},"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":"2608.15062","paper":"/paper/arxiv-2608-15062","title":"Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Amr-Hegazy1/gated-recurrent-transformer","path":"model.py","file_url":"https://github.com/Amr-Hegazy1/gated-recurrent-transformer/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cf67a1a0d7a92283","mcp_get_code":{"code_sha256":"cf67a1a0d7a92283"}},{"arxiv_id":"2605.14200","paper":"/paper/arxiv-2605-14200","title":"How to Scale Mixture-of-Experts: From µP to the Maximally Scale-Stable Parameterization","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"vankadara-lab/mssp-moe","path":"transformer-moe-experiments/model.py","file_url":"https://github.com/vankadara-lab/mssp-moe/blob/HEAD/transformer-moe-experiments/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"79206b63d6c2a4cc","mcp_get_code":{"code_sha256":"79206b63d6c2a4cc"}},{"arxiv_id":"2604.06155","paper":"/paper/arxiv-2604-06155","title":"Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"QiminZhong/LSE-MTP","path":"model.py","file_url":"https://github.com/QiminZhong/LSE-MTP/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"783559fa04a5409b","mcp_get_code":{"code_sha256":"783559fa04a5409b"}},{"arxiv_id":"2603.24298","paper":"/paper/arxiv-2603-24298","title":"SpinGQE: A generative quantum eigensolver for spin Hamiltonians","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Mindbeam-AI/SpinGQE","path":"SpinGQE.py","file_url":"https://github.com/Mindbeam-AI/SpinGQE/blob/HEAD/SpinGQE.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"768cae7bf6f49689","mcp_get_code":{"code_sha256":"768cae7bf6f49689"}},{"arxiv_id":"2603.22315","paper":"/paper/arxiv-2603-22315","title":"Emergency Preemption Without Online Exploration: A Decision Transformer Approach","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"AnthonySu/decision-transformer-traffic","path":"src/models/madt.py","file_url":"https://github.com/AnthonySu/decision-transformer-traffic/blob/HEAD/src/models/madt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6d7951efe561a3b4","mcp_get_code":{"code_sha256":"6d7951efe561a3b4"}},{"arxiv_id":"2510.11321","paper":"/paper/arxiv-2510-11321","title":"HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"zrllrz/HiMaCon","path":"src/hminfocon.py","file_url":"https://github.com/zrllrz/HiMaCon/blob/HEAD/src/hminfocon.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":"af5af5f52454b307","mcp_get_code":{"code_sha256":"af5af5f52454b307"}},{"arxiv_id":"2510.04577","paper":"/paper/arxiv-2510-04577","title":"Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"wjc2830/Siren","path":"src/siren/model.py","file_url":"https://github.com/wjc2830/Siren/blob/HEAD/src/siren/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0f22591f0eeeaeb3","mcp_get_code":{"code_sha256":"0f22591f0eeeaeb3"}},{"arxiv_id":"2506.19935","paper":"/paper/any-order-gpt-as-masked-diffusion-model","title":"Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture","date":"2025-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scxue/AO-GPT-MDM","path":"model_AOGPT_AdaLN6_NoRep_cond_128_trunc_qknorm.py","file_url":"https://github.com/scxue/AO-GPT-MDM/blob/HEAD/model_AOGPT_AdaLN6_NoRep_cond_128_trunc_qknorm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"311dd4150ecf301e","mcp_get_code":{"code_sha256":"311dd4150ecf301e"}},{"arxiv_id":"2504.14587","paper":"/paper/generative-auto-bidding-with-value-guided","title":"Generative Auto-Bidding with Value-Guided Explorations","date":"2025-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"applied-machine-learning-lab/gave","path":"code/bidding_train_env/baseline/dt/dt.py","file_url":"https://github.com/applied-machine-learning-lab/gave/blob/HEAD/code/bidding_train_env/baseline/dt/dt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e1d87efc6af581e3","mcp_get_code":{"code_sha256":"e1d87efc6af581e3"}},{"arxiv_id":"2503.12295","paper":"/paper/towards-learning-high-precision-least-squares","title":"Towards Learning High-Precision Least Squares Algorithms with Sequence Models","date":"2025-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HazyResearch/precision-ls","path":"src/models/gpt2.py","file_url":"https://github.com/HazyResearch/precision-ls/blob/HEAD/src/models/gpt2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"099feb2cb11280c5","mcp_get_code":{"code_sha256":"099feb2cb11280c5"}},{"arxiv_id":"2411.16375","paper":"/paper/ca2-vdm-efficient-autoregressive-video","title":"Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing","date":"2024-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"songweige/TATS","path":"tats/tats_transformer.py","file_url":"https://github.com/songweige/TATS/blob/HEAD/tats/tats_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0dcc3d2b5989bb48","mcp_get_code":{"code_sha256":"0dcc3d2b5989bb48"}},{"arxiv_id":"2411.12872","paper":"/paper/from-text-to-pose-to-image-improving","title":"From Text to Pose to Image: Improving Diffusion Model Control and Quality","date":"2024-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clement-bonnet/text-to-pose","path":"t2p/model.py","file_url":"https://github.com/clement-bonnet/text-to-pose/blob/HEAD/t2p/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"023c96154955c6a3","mcp_get_code":{"code_sha256":"023c96154955c6a3"}},{"arxiv_id":"2407.11588","paper":"/paper/progressive-pretext-task-learning-for-human","title":"Progressive Pretext Task Learning for Human Trajectory Prediction","date":"2024-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iSEE-Laboratory/PPT","path":"models/model.py","file_url":"https://github.com/iSEE-Laboratory/PPT/blob/HEAD/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"545a9e074c969fcb","mcp_get_code":{"code_sha256":"545a9e074c969fcb"}},{"arxiv_id":"2402.04161","paper":"/paper/attention-with-markov-a-framework-for","title":"Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bond1995/markov","path":"Markov-LLM-k/src/models/base.py","file_url":"https://github.com/bond1995/markov/blob/HEAD/Markov-LLM-k/src/models/base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"19f2a8bc1fab2872","mcp_get_code":{"code_sha256":"19f2a8bc1fab2872"}},{"arxiv_id":"2401.06155","paper":"/paper/de-novo-drug-design-using-reinforcement-1","title":"De novo Drug Design using Reinforcement Learning with Multiple GPT Agents","date":"2023-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hxyfighter/molrl-mgpt","path":"codes/model.py","file_url":"https://github.com/hxyfighter/molrl-mgpt/blob/HEAD/codes/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"58787d8bc93d2270","mcp_get_code":{"code_sha256":"58787d8bc93d2270"}},{"arxiv_id":"2310.04948","paper":"/paper/tempo-prompt-based-generative-pre-trained","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","date":"2023-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liaoyuhua/tempo-pytorch","path":"src/model.py","file_url":"https://github.com/liaoyuhua/tempo-pytorch/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"78c68ccc3b7915e0","mcp_get_code":{"code_sha256":"78c68ccc3b7915e0"}},{"arxiv_id":"2307.04895","paper":"/paper/learning-to-solve-constraint-satisfaction","title":"Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer","date":"2023-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"azreasoners/recurrent_transformer","path":"mingpt/model.py","file_url":"https://github.com/azreasoners/recurrent_transformer/blob/HEAD/mingpt/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"db4f6eb0540de0f8","mcp_get_code":{"code_sha256":"db4f6eb0540de0f8"}},{"arxiv_id":"2305.16338","paper":"/paper/think-before-you-act-decision-transformers","title":"Think Before You Act: Decision Transformers with Working Memory","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luciferkonn/dt_mem","path":"src/model.py","file_url":"https://github.com/luciferkonn/dt_mem/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c59ed427653b94b7","mcp_get_code":{"code_sha256":"c59ed427653b94b7"}},{"arxiv_id":"2305.04073","paper":"/paper/explaining-rl-decisions-with-trajectories","title":"Explaining RL Decisions with Trajectories","date":"2023-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"karim-abdel/fact","path":"Breakout/mk_patch_decision_transformer_atari.py","file_url":"https://github.com/karim-abdel/fact/blob/HEAD/Breakout/mk_patch_decision_transformer_atari.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"690f3d0fe57d14fd","mcp_get_code":{"code_sha256":"690f3d0fe57d14fd"}},{"arxiv_id":"2302.13971","paper":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lightning-AI/lit-llama","path":"lit_llama/model.py","file_url":"https://github.com/Lightning-AI/lit-llama/blob/HEAD/lit_llama/model.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":"5a58d3796ebd39f1","mcp_get_code":{"code_sha256":"5a58d3796ebd39f1"}},{"arxiv_id":"2302.11939","paper":"/paper/power-time-series-forecasting-by-pretrained","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","date":"2023-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liaoyuhua/GPT-TS","path":"src/model.py","file_url":"https://github.com/liaoyuhua/GPT-TS/blob/HEAD/src/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ad66bcf4514af931","mcp_get_code":{"code_sha256":"ad66bcf4514af931"}},{"arxiv_id":"2206.10786","paper":"/paper/generative-pretraining-for-black-box","title":"Generative Pretraining for Black-Box Optimization","date":"2022-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siddarthk97/bonet","path":"mingpt/model_discrete.py","file_url":"https://github.com/siddarthk97/bonet/blob/HEAD/mingpt/model_discrete.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"774a4c768efc371a","mcp_get_code":{"code_sha256":"774a4c768efc371a"}},{"arxiv_id":"2206.08569","paper":"/paper/bootstrapped-transformer-for-offline","title":"Bootstrapped Transformer for Offline Reinforcement Learning","date":"2022-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jannerm/trajectory-transformer","path":"trajectory/models/transformers.py","file_url":"https://github.com/jannerm/trajectory-transformer/blob/HEAD/trajectory/models/transformers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"855bb84cf5832f74","mcp_get_code":{"code_sha256":"855bb84cf5832f74"}},{"arxiv_id":"2203.00867","paper":"/paper/incremental-transformer-structure-enhanced","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","date":"2022-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DQiaole/ZITS_inpainting","path":"src/models/TSR_model.py","file_url":"https://github.com/DQiaole/ZITS_inpainting/blob/HEAD/src/models/TSR_model.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":"374b0040c780395d","mcp_get_code":{"code_sha256":"374b0040c780395d"}},{"arxiv_id":"2201.08821","paper":"/paper/representing-long-range-context-for-graph-1","title":"Representing Long-Range Context for Graph Neural Networks with Global Attention","date":"2022-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucbrise/graphtrans","path":"models/gnn_transformer.py","file_url":"https://github.com/ucbrise/graphtrans/blob/HEAD/models/gnn_transformer.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":"54f4034695672c97","mcp_get_code":{"code_sha256":"54f4034695672c97"}},{"arxiv_id":"2106.01345","paper":"/paper/decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yun-kwak/decision-transformer-jax","path":"dt_jax/gpt.py","file_url":"https://github.com/yun-kwak/decision-transformer-jax/blob/HEAD/dt_jax/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"143914639aea2cb9","mcp_get_code":{"code_sha256":"143914639aea2cb9"}},{"arxiv_id":"2103.14031","paper":"/paper/high-fidelity-pluralistic-image-completion","title":"High-Fidelity Pluralistic Image Completion with Transformers","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"karynaur/High-Fidelity-Pluralistic-ICT","path":"transformer/model.py","file_url":"https://github.com/karynaur/High-Fidelity-Pluralistic-ICT/blob/HEAD/transformer/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fb2f67ff573fae6f","mcp_get_code":{"code_sha256":"fb2f67ff573fae6f"}},{"arxiv_id":"2103.14031","paper":"/paper/high-fidelity-pluralistic-image-completion","title":"High-Fidelity Pluralistic Image Completion with Transformers","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raywzy/ICT","path":"Transformer/models/model.py","file_url":"https://github.com/raywzy/ICT/blob/HEAD/Transformer/models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e88ff3b87c736b3","mcp_get_code":{"code_sha256":"4e88ff3b87c736b3"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hannibal046/nanorwkv","path":"modeling_gpt.py","file_url":"https://github.com/hannibal046/nanorwkv/blob/HEAD/modeling_gpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ade15669c2944986","mcp_get_code":{"code_sha256":"ade15669c2944986"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"karpathy/makemore","path":"makemore.py","file_url":"https://github.com/karpathy/makemore/blob/HEAD/makemore.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1891051ae1596526","mcp_get_code":{"code_sha256":"1891051ae1596526"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"karpathy/minGPT","path":"mingpt/model.py","file_url":"https://github.com/karpathy/minGPT/blob/HEAD/mingpt/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"78af90d15381d27e","mcp_get_code":{"code_sha256":"78af90d15381d27e"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akanyaani/minGPTF","path":"mingptf/model.py","file_url":"https://github.com/akanyaani/minGPTF/blob/HEAD/mingptf/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39042b872a709fbe","mcp_get_code":{"code_sha256":"39042b872a709fbe"}}]}