{"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-llm","entry":"get_llm","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":16,"n_papers_ran":4,"n_papers_ran_no_instrument_failure":4,"n_papers_ran_instrument_only":0,"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":17,"n_samples_ran":5,"n_samples_constructed":0,"n_samples_ran_checked":4,"n_samples_instrument":1,"n_samples_unverified":12,"n_samples_fingerprinted":0,"n_places":17,"n_places_pointer_only":8,"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":1,"ran_fixture":0,"ran":4,"unverified":12},"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":"2606.25285","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-25285","title":"EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"xuke225/EPTS","path":"inference.py","file_url":"https://github.com/xuke225/EPTS/blob/HEAD/inference.py","status":"ran","verification_level":1,"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, xuke225/EPTS when it was checked","code_sha256":"0809140f7f488d09","code_sha256_prefix":"0809140f7f488d09","mcp_get_code":{"code_sha256":"0809140f7f488d09"}},{"arxiv_id":"2606.25285","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-25285","title":"EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"xuke225/EPTS","path":"precomputer_wanda_importance.py","file_url":"https://github.com/xuke225/EPTS/blob/HEAD/precomputer_wanda_importance.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, xuke225/EPTS when it was checked","code_sha256":"b52566618ab18da7","code_sha256_prefix":"b52566618ab18da7","mcp_get_code":{"code_sha256":"b52566618ab18da7"}},{"arxiv_id":"2510.01650","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2510-01650","title":"The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"log-postech/elsa","path":"lib/utils.py","file_url":"https://github.com/log-postech/elsa/blob/HEAD/lib/utils.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, log-postech/elsa when it was checked","code_sha256":"e4eab462181ea68a","code_sha256_prefix":"e4eab462181ea68a","mcp_get_code":{"code_sha256":"e4eab462181ea68a"}},{"arxiv_id":"2505.10046","arxiv_id_is_arxiv":true,"paper":"/paper/exploring-the-deep-fusion-of-large-language","title":"Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis","date":"2025-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tang-bd/fuse-dit","path":"diffusion/models.py","file_url":"https://github.com/tang-bd/fuse-dit/blob/HEAD/diffusion/models.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":"c48edbd3d7f74874","code_sha256_prefix":"c48edbd3d7f74874","mcp_get_code":{"code_sha256":"c48edbd3d7f74874"}},{"arxiv_id":"2411.07130","arxiv_id_is_arxiv":true,"paper":"/paper/retrieval-or-global-context-understanding-on","title":"Retrieval or Global Context Understanding? On Many-Shot In-Context Learning for Long-Context Evaluation","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"launchnlp/ManyICLBench","path":"call_api.py","file_url":"https://github.com/launchnlp/ManyICLBench/blob/HEAD/call_api.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, launchnlp/ManyICLBench when it was checked","code_sha256":"607e308b4bc4b406","code_sha256_prefix":"607e308b4bc4b406","mcp_get_code":{"code_sha256":"607e308b4bc4b406"}},{"arxiv_id":"2410.16179","arxiv_id_is_arxiv":true,"paper":"/paper/magicpig-lsh-sampling-for-efficient-llm","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"infini-ai-lab/magicpig","path":"evaluations/RULER/pred/call_api.py","file_url":"https://github.com/infini-ai-lab/magicpig/blob/HEAD/evaluations/RULER/pred/call_api.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":"f9d3901bdfa358a9","code_sha256_prefix":"f9d3901bdfa358a9","mcp_get_code":{"code_sha256":"f9d3901bdfa358a9"}},{"arxiv_id":"2409.17481","arxiv_id_is_arxiv":true,"paper":"/paper/maskllm-learnable-semi-structured-sparsity","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/MaskLLM","path":"tool_compute_mask_hf.py","file_url":"https://github.com/NVlabs/MaskLLM/blob/HEAD/tool_compute_mask_hf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, NVlabs/MaskLLM (NOASSERTION)","code_sha256":"1b16cd00fbac2ce5","code_sha256_prefix":"1b16cd00fbac2ce5","mcp_get_code":{"code_sha256":"1b16cd00fbac2ce5"}},{"arxiv_id":"2406.15524","arxiv_id_is_arxiv":true,"paper":"/paper/rethinking-pruning-large-language-models","title":"Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization","date":"2024-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"log-postech/rethinking-llm-pruning","path":"opt.py","file_url":"https://github.com/log-postech/rethinking-llm-pruning/blob/HEAD/opt.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, log-postech/rethinking-llm-pruning when it was checked","code_sha256":"bea08127e3c1ac0f","code_sha256_prefix":"bea08127e3c1ac0f","mcp_get_code":{"code_sha256":"bea08127e3c1ac0f"}},{"arxiv_id":"2406.08747","arxiv_id_is_arxiv":true,"paper":"/paper/streambench-towards-benchmarking-continuous","title":"StreamBench: Towards Benchmarking Continuous Improvement of Language Agents","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stream-bench/stream-bench","path":"stream_bench/agents/utils.py","file_url":"https://github.com/stream-bench/stream-bench/blob/HEAD/stream_bench/agents/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":"0c1edfffcab96dfd","code_sha256_prefix":"0c1edfffcab96dfd","mcp_get_code":{"code_sha256":"0c1edfffcab96dfd"}},{"arxiv_id":"2406.02924","arxiv_id_is_arxiv":true,"paper":"/paper/pruner-zero-evolving-symbolic-pruning-metric","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pprp/pruner-zero","path":"main_opt.py","file_url":"https://github.com/pprp/pruner-zero/blob/HEAD/main_opt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"612df986c51330d9","code_sha256_prefix":"612df986c51330d9","mcp_get_code":{"code_sha256":"612df986c51330d9"}},{"arxiv_id":"2405.04215","arxiv_id_is_arxiv":true,"paper":"/paper/nl2plan-robust-llm-driven-planning-from","title":"NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mrlab-ai/NL2Plan","path":"NL2Plan/utils/llm_model.py","file_url":"https://github.com/mrlab-ai/NL2Plan/blob/HEAD/NL2Plan/utils/llm_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, mrlab-ai/NL2Plan, is not in the permissive set Syntology serves inline","code_sha256":"1e4b2d02f76da8ec","code_sha256_prefix":"1e4b2d02f76da8ec","mcp_get_code":{"code_sha256":"1e4b2d02f76da8ec"}},{"arxiv_id":"2402.09025","arxiv_id_is_arxiv":true,"paper":"/paper/sleb-streamlining-llms-through-redundancy","title":"SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiwonsong-dev/sleb","path":"sleb.py","file_url":"https://github.com/jiwonsong-dev/sleb/blob/HEAD/sleb.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":"3d35b1f3a44e3c8d","code_sha256_prefix":"3d35b1f3a44e3c8d","mcp_get_code":{"code_sha256":"3d35b1f3a44e3c8d"}},{"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":"in-context_summarization/compressed_model.py","file_url":"https://github.com/VITA-Group/llm-kick/blob/HEAD/in-context_summarization/compressed_model.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":"4b6935721148ba31","code_sha256_prefix":"4b6935721148ba31","mcp_get_code":{"code_sha256":"4b6935721148ba31"}},{"arxiv_id":"2025.findings-acl.394","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2025.findings-acl.394","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"TheShineyue/HSR","path":"alignment-attribution-hsr/main_low_rank.py","file_url":"https://github.com/TheShineyue/HSR/blob/HEAD/alignment-attribution-hsr/main_low_rank.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"5638e4d0804fdac3","code_sha256_prefix":"5638e4d0804fdac3","mcp_get_code":{"code_sha256":"5638e4d0804fdac3"}},{"arxiv_id":"2025.findings-acl.193","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2025.findings-acl.193","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"THUDM/SWE-Dev","path":"swedev/issues/filter.py","file_url":"https://github.com/THUDM/SWE-Dev/blob/HEAD/swedev/issues/filter.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":"e734ad0e4e9f2560","code_sha256_prefix":"e734ad0e4e9f2560","mcp_get_code":{"code_sha256":"e734ad0e4e9f2560"}},{"arxiv_id":"2025.acl-long.590","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2025.acl-long.590","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ChnQ/SPIN","path":"src/utils.py","file_url":"https://github.com/ChnQ/SPIN/blob/HEAD/src/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":"a03b500b5777ce37","code_sha256_prefix":"a03b500b5777ce37","mcp_get_code":{"code_sha256":"a03b500b5777ce37"}},{"arxiv_id":"2021.findings-acl.342","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2021.findings-acl.342","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"mitre/tmnt","path":"tmnt/data_loading.py","file_url":"https://github.com/mitre/tmnt/blob/HEAD/tmnt/data_loading.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":"7112b31dc5fe605d","code_sha256_prefix":"7112b31dc5fe605d","mcp_get_code":{"code_sha256":"7112b31dc5fe605d"}}],"record_sha256":"d6c50150af7e7e9cbf80e919cdec68803cd5fa9dc87dfdfdc003422c33de615b","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}