{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/get-llama","entry":"get_llama","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":21,"n_papers_ran":14,"n_papers_ran_no_instrument_failure":0,"n_papers_ran_instrument_only":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":13,"n_samples_ran":5,"n_samples_constructed":0,"n_samples_ran_checked":0,"n_samples_instrument":5,"n_samples_unverified":8,"n_samples_fingerprinted":0,"n_places":22,"n_places_pointer_only":10,"n_places_pointer_only_link_open":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":1,"ran":0,"unverified":8},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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":"2505.23049","arxiv_id_is_arxiv":true,"paper":"/paper/denoiserotator-enhance-pruning-robustness-for","title":"DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"axel-gu/denoiserotator","path":"llama_prune.py","file_url":"https://github.com/axel-gu/denoiserotator/blob/HEAD/llama_prune.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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"708c67f2479aa444","code_sha256_prefix":"708c67f2479aa444","mcp_get_code":{"code_sha256":"708c67f2479aa444"}},{"arxiv_id":"2412.11041","arxiv_id_is_arxiv":true,"paper":"/paper/separate-the-wheat-from-the-chaff-a-post-hoc","title":"Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models","date":"2024-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pikepokenew/IRR","path":"IRR/llama.py","file_url":"https://github.com/pikepokenew/IRR/blob/HEAD/IRR/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, pikepokenew/IRR when it was checked","code_sha256":"99abb5717e4763c2","code_sha256_prefix":"99abb5717e4763c2","mcp_get_code":{"code_sha256":"99abb5717e4763c2"}},{"arxiv_id":"2411.05282","arxiv_id_is_arxiv":true,"paper":"/paper/microscopiq-accelerating-foundational-models","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","date":"2024-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","path":"llm/llama.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/llm/llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"d1d25542bf6a73b0","code_sha256_prefix":"d1d25542bf6a73b0","mcp_get_code":{"code_sha256":"d1d25542bf6a73b0"}},{"arxiv_id":"2409.18850","arxiv_id_is_arxiv":true,"paper":"/paper/two-sparse-matrices-are-better-than-one","title":"Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization","date":"2024-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"usamec/double_sparse","path":"llama.py","file_url":"https://github.com/usamec/double_sparse/blob/HEAD/llama.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"bf5b0ce87ee19903","code_sha256_prefix":"bf5b0ce87ee19903","mcp_get_code":{"code_sha256":"bf5b0ce87ee19903"}},{"arxiv_id":"2407.10032","arxiv_id_is_arxiv":true,"paper":"/paper/leanquant-accurate-large-language-model","title":"LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid","date":"2024-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LeanModels/LeanQuant","path":"llama.py","file_url":"https://github.com/LeanModels/LeanQuant/blob/HEAD/llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, LeanModels/LeanQuant when it was checked","code_sha256":"9c16d58cb9509ae5","code_sha256_prefix":"9c16d58cb9509ae5","mcp_get_code":{"code_sha256":"9c16d58cb9509ae5"}},{"arxiv_id":"2406.05981","arxiv_id_is_arxiv":true,"paper":"/paper/shiftaddllm-accelerating-pretrained-llms-via","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gatech-eic/shiftaddllm","path":"llama_analysis.py","file_url":"https://github.com/gatech-eic/shiftaddllm/blob/HEAD/llama_analysis.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"88d590323ed219c8","code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"arxiv_id":"2406.00800","arxiv_id_is_arxiv":true,"paper":"/paper/magr-weight-magnitude-reduction-for-enhancing","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","date":"2024-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aozhongzhang/magr","path":"llama.py","file_url":"https://github.com/aozhongzhang/magr/blob/HEAD/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"88d590323ed219c8","code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"arxiv_id":"2405.15756","arxiv_id_is_arxiv":true,"paper":"/paper/sparse-expansion-and-neuronal-disentanglement","title":"Sparse Expansion and Neuronal Disentanglement","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shavit-lab/sparse-expansion","path":"utils/modelutils.py","file_url":"https://github.com/shavit-lab/sparse-expansion/blob/HEAD/utils/modelutils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c6dd03f3342d1724","code_sha256_prefix":"c6dd03f3342d1724","mcp_get_code":{"code_sha256":"c6dd03f3342d1724"}},{"arxiv_id":"2404.14047","arxiv_id_is_arxiv":true,"paper":"/paper/how-good-are-low-bit-quantized-llama3-models","title":"An empirical study of LLaMA3 quantization: from LLMs to MLLMs","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"macaronlin/llama3-quantization","path":"llama.py","file_url":"https://github.com/macaronlin/llama3-quantization/blob/HEAD/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, macaronlin/llama3-quantization when it was checked","code_sha256":"2c201f017173954b","code_sha256_prefix":"2c201f017173954b","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"arxiv_id":"2403.06082","arxiv_id_is_arxiv":true,"paper":"/paper/framequant-flexible-low-bit-quantization-for","title":"FrameQuant: Flexible Low-Bit Quantization for Transformers","date":"2024-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vsingh-group/framequant","path":"llama.py","file_url":"https://github.com/vsingh-group/framequant/blob/HEAD/llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, vsingh-group/framequant when it was checked","code_sha256":"7ca52cb5d1719b2f","code_sha256_prefix":"7ca52cb5d1719b2f","mcp_get_code":{"code_sha256":"7ca52cb5d1719b2f"}},{"arxiv_id":"2402.17946","arxiv_id_is_arxiv":true,"paper":"/paper/gradient-free-adaptive-global-pruning-for-pre","title":"SparseLLM: Towards Global Pruning for Pre-trained Language Models","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BaiTheBest/SparseLLM","path":"model_utils.py","file_url":"https://github.com/BaiTheBest/SparseLLM/blob/HEAD/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0ac474c6b7daab48","code_sha256_prefix":"0ac474c6b7daab48","mcp_get_code":{"code_sha256":"0ac474c6b7daab48"}},{"arxiv_id":"2312.05693","arxiv_id_is_arxiv":true,"paper":"/paper/agile-quant-activation-guided-quantization","title":"Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge","date":"2023-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shawnricecake/agile-quant","path":"gptq_fq_quant_llama.py","file_url":"https://github.com/shawnricecake/agile-quant/blob/HEAD/gptq_fq_quant_llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, shawnricecake/agile-quant when it was checked","code_sha256":"2c201f017173954b","code_sha256_prefix":"2c201f017173954b","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"arxiv_id":"2310.09499","arxiv_id_is_arxiv":true,"paper":"/paper/one-shot-sensitivity-aware-mixed-sparsity","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","date":"2023-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"talkking/MixGPT","path":"llama.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, talkking/MixGPT when it was checked","code_sha256":"88d590323ed219c8","code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"arxiv_id":"2310.01382","arxiv_id_is_arxiv":true,"paper":"/paper/compressing-llms-the-truth-is-rarely-pure-and","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/llm-kick","path":"GPTQ_experiment/llama.py","file_url":"https://github.com/VITA-Group/llm-kick/blob/HEAD/GPTQ_experiment/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, VITA-Group/llm-kick when it was checked","code_sha256":"2c201f017173954b","code_sha256_prefix":"2c201f017173954b","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"arxiv_id":"2310.01382","arxiv_id_is_arxiv":true,"paper":"/paper/compressing-llms-the-truth-is-rarely-pure-and","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/llm-kick","path":"GPTQ_experiment/llama_inference.py","file_url":"https://github.com/VITA-Group/llm-kick/blob/HEAD/GPTQ_experiment/llama_inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, VITA-Group/llm-kick when it was checked","code_sha256":"ffa71b6ff9b64407","code_sha256_prefix":"ffa71b6ff9b64407","mcp_get_code":{"code_sha256":"ffa71b6ff9b64407"}},{"arxiv_id":"2307.15290","arxiv_id_is_arxiv":true,"paper":"/paper/chathome-development-and-evaluation-of-a","title":"ChatHome: Development and Evaluation of a Domain-Specific Language Model for Home Renovation","date":"2023-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lianjiatech/belle","path":"models/gptq/llama.py","file_url":"https://github.com/lianjiatech/belle/blob/HEAD/models/gptq/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"88d590323ed219c8","code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"arxiv_id":"2307.08072","arxiv_id_is_arxiv":true,"paper":"/paper/do-emergent-abilities-exist-in-quantized","title":"Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study","date":"2023-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/quantizedempirical","path":"models/llama.py","file_url":"https://github.com/rucaibox/quantizedempirical/blob/HEAD/models/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, rucaibox/quantizedempirical when it was checked","code_sha256":"2c201f017173954b","code_sha256_prefix":"2c201f017173954b","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"arxiv_id":"2302.13971","arxiv_id_is_arxiv":true,"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":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,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","code_sha256":"2c201f017173954b","code_sha256_prefix":"2c201f017173954b","mcp_get_code":{"code_sha256":"2c201f017173954b"}},{"arxiv_id":"openreview_d3RFDLBw01","arxiv_id_is_arxiv":false,"paper":null,"title":"OpenReview id openreview_d3RFDLBw01","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AI2C-Lab/STLA","path":"model_utils.py","file_url":"https://github.com/AI2C-Lab/STLA/blob/HEAD/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"00f92653e59d38b4","code_sha256_prefix":"00f92653e59d38b4","mcp_get_code":{"code_sha256":"00f92653e59d38b4"}},{"arxiv_id":"2025.findings-emnlp.1054","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2025.findings-emnlp.1054","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"IST-DASLab/sparsegpt","path":"llama.py","file_url":"https://github.com/IST-DASLab/sparsegpt/blob/HEAD/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"88d590323ed219c8","code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"arxiv_id":"2024.findings-naacl.145","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2024.findings-naacl.145","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LianjiaTech/BELLE","path":"models/gptq/llama.py","file_url":"https://github.com/LianjiaTech/BELLE/blob/HEAD/models/gptq/llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"88d590323ed219c8","code_sha256_prefix":"88d590323ed219c8","mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"arxiv_id":"2023.emnlp-main.892","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2023.emnlp-main.892","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SamsungLabs/Z-Fold","path":"llama.py","file_url":"https://github.com/SamsungLabs/Z-Fold/blob/HEAD/llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"6897a8caeb3dedd0","code_sha256_prefix":"6897a8caeb3dedd0","mcp_get_code":{"code_sha256":"6897a8caeb3dedd0"}}],"record_sha256":"c42abbcb59bb328c6121eeb9c7df2a14d7876450981f4a0cd8c3eeda855303a6","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}