{"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/build-rope-cache","entry":"build_rope_cache","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":16,"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":10,"n_samples_ran":6,"n_samples_fingerprinted":1,"n_places":26,"n_places_pointer_only":9,"by_status":{"ran_honours":3,"ran_violates":0,"ran_draft_wrong":0,"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":"2608.22347","paper":"/paper/arxiv-2608-22347","title":"Where Cognition Lives: Dissecting Emergent from Computed Function in a Minimal Complete Cognitive Architecture","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"fmarrabal/miuracognitive","path":"model/transformer.py","file_url":"https://github.com/fmarrabal/miuracognitive/blob/HEAD/model/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8892691c595d30d4","mcp_get_code":{"code_sha256":"8892691c595d30d4"}},{"arxiv_id":"2606.14971","paper":"/paper/arxiv-2606-14971","title":"FastMix: Fast Data Mixture Optimization via Gradient Descent","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"hrtan/fastmix","path":"lit_gpt/model.py","file_url":"https://github.com/hrtan/fastmix/blob/HEAD/lit_gpt/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a30c7463cb6330d7","mcp_get_code":{"code_sha256":"a30c7463cb6330d7"}},{"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_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"60caeaf416ffdf78","mcp_get_code":{"code_sha256":"60caeaf416ffdf78"}},{"arxiv_id":"2605.08587","paper":"/paper/arxiv-2605-08587","title":"Kaczmarz Linear Attention","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"anonymous-kla-review/kla-anonymous","path":"lit_gpt/model.py","file_url":"https://github.com/anonymous-kla-review/kla-anonymous/blob/HEAD/lit_gpt/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a30c7463cb6330d7","mcp_get_code":{"code_sha256":"a30c7463cb6330d7"}},{"arxiv_id":"2601.08078","paper":"/paper/arxiv-2601-08078","title":"Exploiting DINOv3-Based Self-Supervised Features for Robust Few-Shot Medical Image Segmentation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"apple1986/DINO-AugSeg","path":"model/Dinov3_WTAUG_UNet.py","file_url":"https://github.com/apple1986/DINO-AugSeg/blob/HEAD/model/Dinov3_WTAUG_UNet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"acf59ae645db45b8","mcp_get_code":{"code_sha256":"acf59ae645db45b8"}},{"arxiv_id":"2504.11393","paper":"/paper/datadecide-how-to-predict-best-pretraining","title":"DataDecide: How to Predict Best Pretraining Data with Small Experiments","date":"2025-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/prox","path":"train/lit_gpt/model.py","file_url":"https://github.com/gair-nlp/prox/blob/HEAD/train/lit_gpt/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a30c7463cb6330d7","mcp_get_code":{"code_sha256":"a30c7463cb6330d7"}},{"arxiv_id":"2503.15450","paper":"/paper/skyladder-better-and-faster-pretraining-via","title":"SkyLadder: Better and Faster Pretraining via Context Window Scheduling","date":"2025-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/skyladder","path":"lit_gpt/model.py","file_url":"https://github.com/sail-sg/skyladder/blob/HEAD/lit_gpt/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a30c7463cb6330d7","mcp_get_code":{"code_sha256":"a30c7463cb6330d7"}},{"arxiv_id":"2412.06464","paper":"/paper/gated-delta-networks-improving-mamba2-with","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/GatedDeltaNet","path":"lit_gpt/model.py","file_url":"https://github.com/NVlabs/GatedDeltaNet/blob/HEAD/lit_gpt/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a30c7463cb6330d7","mcp_get_code":{"code_sha256":"a30c7463cb6330d7"}},{"arxiv_id":"2411.12892","paper":"/paper/selective-attention-enhancing-transformer","title":"Selective Attention: Enhancing Transformer through Principled Context Control","date":"2024-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umich-sota/selective_attention","path":"lit_gpt/model.py","file_url":"https://github.com/umich-sota/selective_attention/blob/HEAD/lit_gpt/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":"c0cabd60c81402a5","mcp_get_code":{"code_sha256":"c0cabd60c81402a5"}},{"arxiv_id":"2410.11190","paper":"/paper/mini-omni2-towards-open-source-gpt-4o-model","title":"Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpt-omni/mini-omni2","path":"litgpt/model.py","file_url":"https://github.com/gpt-omni/mini-omni2/blob/HEAD/litgpt/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0cabd60c81402a5","mcp_get_code":{"code_sha256":"c0cabd60c81402a5"}},{"arxiv_id":"2410.10781","paper":"/paper/when-attention-sink-emerges-in-language","title":"When Attention Sink Emerges in Language Models: An Empirical View","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/attention-sink","path":"lit_gpt/model.py","file_url":"https://github.com/sail-sg/attention-sink/blob/HEAD/lit_gpt/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a30c7463cb6330d7","mcp_get_code":{"code_sha256":"a30c7463cb6330d7"}},{"arxiv_id":"2410.08102","paper":"/paper/multi-agent-collaborative-data-selection-for","title":"Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beccabai/multi-agent-data-selection","path":"src/lit_gpt/model.py","file_url":"https://github.com/beccabai/multi-agent-data-selection/blob/HEAD/src/lit_gpt/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c0cabd60c81402a5","mcp_get_code":{"code_sha256":"c0cabd60c81402a5"}},{"arxiv_id":"2409.17115","paper":"/paper/programming-every-example-lifting-pre","title":"Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale","date":"2024-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"a30c7463cb6330d7","mcp_get_code":{"code_sha256":"a30c7463cb6330d7"}},{"arxiv_id":"2408.16725","paper":"/paper/mini-omni-language-models-can-hear-talk-while","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpt-omni/mini-omni","path":"litgpt/model.py","file_url":"https://github.com/gpt-omni/mini-omni/blob/HEAD/litgpt/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0cabd60c81402a5","mcp_get_code":{"code_sha256":"c0cabd60c81402a5"}},{"arxiv_id":"2408.03506","paper":"/paper/1-5-pints-technical-report-pretraining-in","title":"1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data","date":"2024-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Pints-AI/1.5-Pints","path":"lit_gpt/model.py","file_url":"https://github.com/Pints-AI/1.5-Pints/blob/HEAD/lit_gpt/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a30c7463cb6330d7","mcp_get_code":{"code_sha256":"a30c7463cb6330d7"}},{"arxiv_id":"2406.10209","paper":"/paper/be-like-a-goldfish-don-t-memorize-mitigating","title":"Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ahans30/goldfish-loss","path":"lit_gpt/model.py","file_url":"https://github.com/ahans30/goldfish-loss/blob/HEAD/lit_gpt/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":"c0cabd60c81402a5","mcp_get_code":{"code_sha256":"c0cabd60c81402a5"}},{"arxiv_id":"2406.06046","paper":"/paper/mates-model-aware-data-selection-for","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cxcscmu/MATES","path":"src/lit_gpt/model.py","file_url":"https://github.com/cxcscmu/MATES/blob/HEAD/src/lit_gpt/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0cabd60c81402a5","mcp_get_code":{"code_sha256":"c0cabd60c81402a5"}},{"arxiv_id":"2405.20340","paper":"/paper/motionllm-understanding-human-behaviors-from","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-Research/MotionLLM","path":"lit_llama/model.py","file_url":"https://github.com/IDEA-Research/MotionLLM/blob/HEAD/lit_llama/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"57b678d36ceb14f0","mcp_get_code":{"code_sha256":"57b678d36ceb14f0"}},{"arxiv_id":"2405.20340","paper":"/paper/motionllm-understanding-human-behaviors-from","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-Research/MotionLLM","path":"lit_gpt/model.py","file_url":"https://github.com/IDEA-Research/MotionLLM/blob/HEAD/lit_gpt/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c0cabd60c81402a5","mcp_get_code":{"code_sha256":"c0cabd60c81402a5"}},{"arxiv_id":"2402.05457","paper":"/paper/it-s-never-too-late-fusing-acoustic","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hypotheses-Paradise/UADF","path":"lit_llama/model.py","file_url":"https://github.com/Hypotheses-Paradise/UADF/blob/HEAD/lit_llama/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8a187cb05b43141d","mcp_get_code":{"code_sha256":"8a187cb05b43141d"}},{"arxiv_id":"2402.03563","paper":"/paper/distinguishing-the-knowable-from-the","title":"Distinguishing the Knowable from the Unknowable with Language Models","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gahdritz/llm_uncertainty","path":"lit-llama/model.py","file_url":"https://github.com/gahdritz/llm_uncertainty/blob/HEAD/lit-llama/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":"fd462b61b82d4e41","mcp_get_code":{"code_sha256":"fd462b61b82d4e41"}},{"arxiv_id":"2401.02385","paper":"/paper/tinyllama-an-open-source-small-language-model","title":"TinyLlama: An Open-Source Small Language Model","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jzhang38/tinyllama","path":"lit_gpt/model.py","file_url":"https://github.com/jzhang38/tinyllama/blob/HEAD/lit_gpt/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a30c7463cb6330d7","mcp_get_code":{"code_sha256":"a30c7463cb6330d7"}},{"arxiv_id":"2310.08581","paper":"/paper/universal-visual-decomposer-long-horizon","title":"Universal Visual Decomposer: Long-Horizon Manipulation Made Easy","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zcczhang/uvd","path":"uvd/models/nn/transformer.py","file_url":"https://github.com/zcczhang/uvd/blob/HEAD/uvd/models/nn/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1800f2d56d86239c","mcp_get_code":{"code_sha256":"1800f2d56d86239c"}},{"arxiv_id":"2310.06434","paper":"/paper/whispering-llama-a-cross-modal-generative","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","date":"2023-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"srijith-rkr/whispering-llama","path":"lit_llama/model.py","file_url":"https://github.com/srijith-rkr/whispering-llama/blob/HEAD/lit_llama/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a187cb05b43141d","mcp_get_code":{"code_sha256":"8a187cb05b43141d"}},{"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":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8a187cb05b43141d","mcp_get_code":{"code_sha256":"8a187cb05b43141d"}},{"arxiv_id":"2025.acl-industry.15","paper":null,"title":"arXiv:2025.acl-industry.15","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Lightning-AI/litgpt","path":"litgpt/model.py","file_url":"https://github.com/Lightning-AI/litgpt/blob/HEAD/litgpt/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":"3a230f27a8cf6977","mcp_get_code":{"code_sha256":"3a230f27a8cf6977"}}]}