{"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/rotate-every-two","entry":"rotate_every_two","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":33,"n_papers_ran":31,"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":18,"n_samples_ran":16,"n_samples_fingerprinted":15,"n_places":35,"n_places_pointer_only":11,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":4,"ran":8,"unverified":2},"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":"2512.02315","paper":"/paper/arxiv-2512-02315","title":"Few-shot Protein Fitness Prediction via In-context Learning and Test-time Training","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"fteufel/PRIMO","path":"primo/zero_shot_utils/modeling_progen.py","file_url":"https://github.com/fteufel/PRIMO/blob/HEAD/primo/zero_shot_utils/modeling_progen.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c66149010337c505","mcp_get_code":{"code_sha256":"c66149010337c505"}},{"arxiv_id":"2507.00698","paper":null,"title":"arXiv:2507.00698","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"5edaeffae06137e0","mcp_get_code":{"code_sha256":"5edaeffae06137e0"}},{"arxiv_id":"2411.07635","paper":"/paper/breaking-the-low-rank-dilemma-of-linear","title":"Breaking the Low-Rank Dilemma of Linear Attention","date":"2024-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qhfan/rala","path":"classfication/RALA.py","file_url":"https://github.com/qhfan/rala/blob/HEAD/classfication/RALA.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5edaeffae06137e0","mcp_get_code":{"code_sha256":"5edaeffae06137e0"}},{"arxiv_id":"2408.08578","paper":"/paper/tamer-tree-aware-transformer-for-handwritten","title":"TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition","date":"2024-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qingzhenduyu/tamer","path":"tamer/model/pos_enc.py","file_url":"https://github.com/qingzhenduyu/tamer/blob/HEAD/tamer/model/pos_enc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e06d2f5f2824ecc6","mcp_get_code":{"code_sha256":"e06d2f5f2824ecc6"}},{"arxiv_id":"2407.14207","paper":"/paper/longhorn-state-space-models-are-amortized","title":"Longhorn: State Space Models are Amortized Online Learners","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Cranial-XIX/longhorn","path":"models/retnet.py","file_url":"https://github.com/Cranial-XIX/longhorn/blob/HEAD/models/retnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a8e846bab37b7243","mcp_get_code":{"code_sha256":"a8e846bab37b7243"}},{"arxiv_id":"2407.07764","paper":"/paper/posformer-recognizing-complex-handwritten","title":"PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjtu-deepvisionlab/posformer","path":"Pos_Former/model/pos_enc.py","file_url":"https://github.com/sjtu-deepvisionlab/posformer/blob/HEAD/Pos_Former/model/pos_enc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e06d2f5f2824ecc6","mcp_get_code":{"code_sha256":"e06d2f5f2824ecc6"}},{"arxiv_id":"2407.05562","paper":"/paper/focus-on-the-whole-character-discriminative","title":"Focus on the Whole Character: Discriminative Character Modeling for Scene Text Recognition","date":"2024-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bang123-box/CFE","path":"strhub/models/cfe/modules.py","file_url":"https://github.com/bang123-box/CFE/blob/HEAD/strhub/models/cfe/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"368e8872aa996b9e","mcp_get_code":{"code_sha256":"368e8872aa996b9e"}},{"arxiv_id":"2406.09279","paper":"/paper/unpacking-dpo-and-ppo-disentangling-best","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hamishivi/easylm","path":"EasyLM/models/gptj/gptj_model.py","file_url":"https://github.com/hamishivi/easylm/blob/HEAD/EasyLM/models/gptj/gptj_model.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":"768565e8f56c5fb0","mcp_get_code":{"code_sha256":"768565e8f56c5fb0"}},{"arxiv_id":"2405.00218","paper":"/paper/constrained-decoding-for-secure-code","title":"Constrained Decoding for Secure Code Generation","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dynamite321/codeguardplus","path":"inference/hf/modeling_codegen.py","file_url":"https://github.com/dynamite321/codeguardplus/blob/HEAD/inference/hf/modeling_codegen.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"621a8a98538cd46d","mcp_get_code":{"code_sha256":"621a8a98538cd46d"}},{"arxiv_id":"2404.10933","paper":"/paper/llmem-estimating-gpu-memory-usage-for-fine","title":"LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taehokim20/llmem","path":"real_models/modeling_codegen.py","file_url":"https://github.com/taehokim20/llmem/blob/HEAD/real_models/modeling_codegen.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e3bec9f0c9b1973","mcp_get_code":{"code_sha256":"2e3bec9f0c9b1973"}},{"arxiv_id":"2403.09054","paper":"/paper/keyformer-kv-cache-reduction-through-key","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"d-matrix-ai/keyformer-llm","path":"models/gptj-keyformer-lib/modeling_gptj.py","file_url":"https://github.com/d-matrix-ai/keyformer-llm/blob/HEAD/models/gptj-keyformer-lib/modeling_gptj.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":"2e3bec9f0c9b1973","mcp_get_code":{"code_sha256":"2e3bec9f0c9b1973"}},{"arxiv_id":"2403.04945","paper":"/paper/electrocardiogram-instruction-tuning-for","title":"MEIT: Multi-Modal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aiot-mlsys-lab/meit","path":"ECG_LLMs/models/modeling_ecg_gpt_j.py","file_url":"https://github.com/aiot-mlsys-lab/meit/blob/HEAD/ECG_LLMs/models/modeling_ecg_gpt_j.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"be7c0ed30787664f","mcp_get_code":{"code_sha256":"be7c0ed30787664f"}},{"arxiv_id":"2403.00818","paper":"/paper/densemamba-state-space-models-with-dense","title":"DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wailordhe/densessm","path":"modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py","file_url":"https://github.com/wailordhe/densessm/blob/HEAD/modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"621a8a98538cd46d","mcp_get_code":{"code_sha256":"621a8a98538cd46d"}},{"arxiv_id":"2311.13230","paper":"/paper/enhancing-uncertainty-based-hallucination","title":"Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus","date":"2023-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zthang/focus","path":"models/modeling_gptj.py","file_url":"https://github.com/zthang/focus/blob/HEAD/models/modeling_gptj.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2e3bec9f0c9b1973","mcp_get_code":{"code_sha256":"2e3bec9f0c9b1973"}},{"arxiv_id":"2309.11523","paper":"/paper/rmt-retentive-networks-meet-vision","title":"RMT: Retentive Networks Meet Vision Transformers","date":"2023-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qhfan/RMT","path":"classfication_release/RMT.py","file_url":"https://github.com/qhfan/RMT/blob/HEAD/classfication_release/RMT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e8e82ae4792b09f9","mcp_get_code":{"code_sha256":"e8e82ae4792b09f9"}},{"arxiv_id":"2309.01327","paper":"/paper/can-i-trust-your-answer-visually-grounded","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","date":"2023-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"doc-doc/next-gqa","path":"code/FrozenGQA/model/gptj.py","file_url":"https://github.com/doc-doc/next-gqa/blob/HEAD/code/FrozenGQA/model/gptj.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c66149010337c505","mcp_get_code":{"code_sha256":"c66149010337c505"}},{"arxiv_id":"2308.10882","paper":"/paper/giraffe-adventures-in-expanding-context","title":"Giraffe: Adventures in Expanding Context Lengths in LLMs","date":"2023-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abacusai/long-context","path":"python/models/xpos.py","file_url":"https://github.com/abacusai/long-context/blob/HEAD/python/models/xpos.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":"368e8872aa996b9e","mcp_get_code":{"code_sha256":"368e8872aa996b9e"}},{"arxiv_id":"2307.08621","paper":"/paper/retentive-network-a-successor-to-transformer","title":"Retentive Network: A Successor to Transformer for Large Language Models","date":"2023-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jamie-Stirling/RetNet","path":"src/xpos_relative_position.py","file_url":"https://github.com/Jamie-Stirling/RetNet/blob/HEAD/src/xpos_relative_position.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2a514c2dffaca20","mcp_get_code":{"code_sha256":"b2a514c2dffaca20"}},{"arxiv_id":"2307.04349","paper":"/paper/rltf-reinforcement-learning-from-unit-test","title":"RLTF: Reinforcement Learning from Unit Test Feedback","date":"2023-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zyq-scut/rltf","path":"trainers/modeling_codegen.py","file_url":"https://github.com/zyq-scut/rltf/blob/HEAD/trainers/modeling_codegen.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"621a8a98538cd46d","mcp_get_code":{"code_sha256":"621a8a98538cd46d"}},{"arxiv_id":"2305.10314","paper":"/paper/leti-learning-to-generate-from-textual","title":"LeTI: Learning to Generate from Textual Interactions","date":"2023-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xingyaoww/leti","path":"leti/models/codegen/modeling_flax_codegen.py","file_url":"https://github.com/xingyaoww/leti/blob/HEAD/leti/models/codegen/modeling_flax_codegen.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":"768565e8f56c5fb0","mcp_get_code":{"code_sha256":"768565e8f56c5fb0"}},{"arxiv_id":"2303.01903","paper":"/paper/prompting-large-language-models-with-answer","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","date":"2023-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"milvlg/prophet","path":"prophet/stage1/model/rope2d.py","file_url":"https://github.com/milvlg/prophet/blob/HEAD/prophet/stage1/model/rope2d.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":"8ad5d5cfe019a6ae","mcp_get_code":{"code_sha256":"8ad5d5cfe019a6ae"}},{"arxiv_id":"2302.02676","paper":"/paper/languages-are-rewards-hindsight-finetuning","title":"Chain of Hindsight Aligns Language Models with Feedback","date":"2023-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lhao499/CoH","path":"coh/gptj.py","file_url":"https://github.com/lhao499/CoH/blob/HEAD/coh/gptj.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":"768565e8f56c5fb0","mcp_get_code":{"code_sha256":"768565e8f56c5fb0"}},{"arxiv_id":"2206.13517","paper":"/paper/progen2-exploring-the-boundaries-of-protein","title":"ProGen2: Exploring the Boundaries of Protein Language Models","date":"2022-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"c66149010337c505","mcp_get_code":{"code_sha256":"c66149010337c505"}},{"arxiv_id":"2206.13517","paper":"/paper/progen2-exploring-the-boundaries-of-protein","title":"ProGen2: Exploring the Boundaries of Protein Language Models","date":"2022-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/jaxformer","path":"jaxformer/hf/codegen/modeling_codegen.py","file_url":"https://github.com/salesforce/jaxformer/blob/HEAD/jaxformer/hf/codegen/modeling_codegen.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"621a8a98538cd46d","mcp_get_code":{"code_sha256":"621a8a98538cd46d"}},{"arxiv_id":"2206.06888","paper":"/paper/cert-continual-pre-training-on-sketches-for","title":"CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation","date":"2022-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/PyCodeGPT","path":"apicoder/CodeGenAPI/nl2code/modeling_codegen.py","file_url":"https://github.com/microsoft/PyCodeGPT/blob/HEAD/apicoder/CodeGenAPI/nl2code/modeling_codegen.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"965428aef96cf65e","mcp_get_code":{"code_sha256":"965428aef96cf65e"}},{"arxiv_id":"2204.02311","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/PaLM-jax","path":"palm_jax/palm.py","file_url":"https://github.com/lucidrains/PaLM-jax/blob/HEAD/palm_jax/palm.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6aa7304ec358cbea","mcp_get_code":{"code_sha256":"6aa7304ec358cbea"}},{"arxiv_id":"2203.13474","paper":"/paper/a-conversational-paradigm-for-program","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","date":"2022-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/CodeGen","path":"codegen1/jaxformer/hf/codegen/modeling_codegen.py","file_url":"https://github.com/salesforce/CodeGen/blob/HEAD/codegen1/jaxformer/hf/codegen/modeling_codegen.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c66149010337c505","mcp_get_code":{"code_sha256":"c66149010337c505"}},{"arxiv_id":"2203.13474","paper":"/paper/a-conversational-paradigm-for-program","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","date":"2022-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openlmlab/moss","path":"models/modeling_moss.py","file_url":"https://github.com/openlmlab/moss/blob/HEAD/models/modeling_moss.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":"2e3bec9f0c9b1973","mcp_get_code":{"code_sha256":"2e3bec9f0c9b1973"}},{"arxiv_id":"2105.02412","paper":"/paper/handwritten-mathematical-expression","title":"Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer","date":"2021-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Green-Wood/BTTR","path":"bttr/model/pos_enc.py","file_url":"https://github.com/Green-Wood/BTTR/blob/HEAD/bttr/model/pos_enc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e06d2f5f2824ecc6","mcp_get_code":{"code_sha256":"e06d2f5f2824ecc6"}},{"arxiv_id":"2103.01209","paper":"/paper/generative-adversarial-transformers","title":"Generative Adversarial Transformers","date":"2021-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/transganformer","path":"transganformer/transganformer.py","file_url":"https://github.com/lucidrains/transganformer/blob/HEAD/transganformer/transganformer.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":"1ac67506c6a0368b","mcp_get_code":{"code_sha256":"1ac67506c6a0368b"}},{"arxiv_id":"2102.05095","paper":"/paper/is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/TimeSformer-pytorch","path":"timesformer_pytorch/timesformer_pytorch.py","file_url":"https://github.com/lucidrains/TimeSformer-pytorch/blob/HEAD/timesformer_pytorch/timesformer_pytorch.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":"07e3c5417d5f77fc","mcp_get_code":{"code_sha256":"07e3c5417d5f77fc"}},{"arxiv_id":"2004.03497","paper":"/paper/progen-language-modeling-for-protein","title":"ProGen: Language Modeling for Protein Generation","date":"2020-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/progen","path":"progen_transformer/progen.py","file_url":"https://github.com/lucidrains/progen/blob/HEAD/progen_transformer/progen.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59c0bfea601f828d","mcp_get_code":{"code_sha256":"59c0bfea601f828d"}},{"arxiv_id":"1909.08053","paper":"/paper/megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kingoflolz/mesh-transformer-jax","path":"mesh_transformer/transformer_shard.py","file_url":"https://github.com/kingoflolz/mesh-transformer-jax/blob/HEAD/mesh_transformer/transformer_shard.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5efa020fabe4b20b","mcp_get_code":{"code_sha256":"5efa020fabe4b20b"}},{"arxiv_id":"Fu_SegMAN_Omni-scale_Context_Modeling_with_State_Space_Models_and_Local_CVPR_2025_paper","paper":null,"title":"arXiv:Fu_SegMAN_Omni-scale_Context_Modeling_with_State_Space_Models_and_Local_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yunxiangfu2001/SegMAN","path":"models/segman_encoder.py","file_url":"https://github.com/yunxiangfu2001/SegMAN/blob/HEAD/models/segman_encoder.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":"e8e82ae4792b09f9","mcp_get_code":{"code_sha256":"e8e82ae4792b09f9"}},{"arxiv_id":"04820","paper":null,"title":"arXiv:04820","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Kelly510/PoseRetNet","path":"common/model/retention.py","file_url":"https://github.com/Kelly510/PoseRetNet/blob/HEAD/common/model/retention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a8e846bab37b7243","mcp_get_code":{"code_sha256":"a8e846bab37b7243"}}]}