{"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-sinusoidal-positions","entry":"create_sinusoidal_positions","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":14,"n_papers_ran":14,"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":5,"n_samples_ran":5,"n_samples_fingerprinted":4,"n_places":14,"n_places_pointer_only":7,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":0},"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":"2505.16270","paper":"/paper/transformer-copilot-learning-from-the-mistake","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiaruzouu/transformercopilot","path":"src/Decoder_Only/copilot/modeling_flax_llama.py","file_url":"https://github.com/jiaruzouu/transformercopilot/blob/HEAD/src/Decoder_Only/copilot/modeling_flax_llama.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"660ecba66bbbf2c0","mcp_get_code":{"code_sha256":"660ecba66bbbf2c0"}},{"arxiv_id":"2503.05631","paper":"/paper/strategy-coopetition-explains-the-emergence","title":"Strategy Coopetition Explains the Emergence and Transience of In-Context Learning","date":"2025-03-07","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":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"6c3305fbafc272c8","mcp_get_code":{"code_sha256":"6c3305fbafc272c8"}},{"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":"ff574bc6676f34f1","mcp_get_code":{"code_sha256":"ff574bc6676f34f1"}},{"arxiv_id":"2406.05317","paper":"/paper/lococo-dropping-in-convolutions-for-long","title":"LoCoCo: Dropping In Convolutions for Long Context Compression","date":"2024-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/LoCoCo","path":"llama/modeling_flax_llama.py","file_url":"https://github.com/VITA-Group/LoCoCo/blob/HEAD/llama/modeling_flax_llama.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"660ecba66bbbf2c0","mcp_get_code":{"code_sha256":"660ecba66bbbf2c0"}},{"arxiv_id":"2405.13053","paper":"/paper/meteora-multiple-tasks-embedded-lora-for","title":"MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models","date":"2024-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paragonlight/meteor-of-lora","path":"base_model/llama/modeling_flax_llama_meteor.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/modeling_flax_llama_meteor.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"660ecba66bbbf2c0","mcp_get_code":{"code_sha256":"660ecba66bbbf2c0"}},{"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":"c2217cd556fe5607","mcp_get_code":{"code_sha256":"c2217cd556fe5607"}},{"arxiv_id":"2404.07129","paper":"/paper/what-needs-to-go-right-for-an-induction-head","title":"What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation","date":"2024-04-10","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":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"6c3305fbafc272c8","mcp_get_code":{"code_sha256":"6c3305fbafc272c8"}},{"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":"c2217cd556fe5607","mcp_get_code":{"code_sha256":"c2217cd556fe5607"}},{"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":"dd26c6cbc300bf99","mcp_get_code":{"code_sha256":"dd26c6cbc300bf99"}},{"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":"c2217cd556fe5607","mcp_get_code":{"code_sha256":"c2217cd556fe5607"}},{"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":"ff574bc6676f34f1","mcp_get_code":{"code_sha256":"ff574bc6676f34f1"}},{"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":"ff574bc6676f34f1","mcp_get_code":{"code_sha256":"ff574bc6676f34f1"}},{"arxiv_id":"2205.05055","paper":"/paper/data-distributional-properties-drive-emergent","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","date":"2022-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aadityasingh/icl-dynamics","path":"models.py","file_url":"https://github.com/aadityasingh/icl-dynamics/blob/HEAD/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c3305fbafc272c8","mcp_get_code":{"code_sha256":"6c3305fbafc272c8"}},{"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":"c2217cd556fe5607","mcp_get_code":{"code_sha256":"c2217cd556fe5607"}}]}