{"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/parse-json","entry":"parse_json","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":19,"n_papers_ran":16,"n_papers_ran_no_instrument_failure":3,"n_papers_ran_instrument_only":13,"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":20,"n_samples_ran":16,"n_samples_constructed":0,"n_samples_ran_checked":3,"n_samples_instrument":13,"n_samples_unverified":4,"n_samples_fingerprinted":7,"n_places":20,"n_places_pointer_only":13,"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":13,"ran_fixture":0,"ran":3,"unverified":4},"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":"2607.26062","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2607-26062","title":"Identifying implicit bias in LLM-based chat AI toward people with intellectual disabilities","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"specialolympics/implicit_bias_llms","path":"code/format_data.py","file_url":"https://github.com/specialolympics/implicit_bias_llms/blob/HEAD/code/format_data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"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, specialolympics/implicit_bias_llms, is not in the permissive set Syntology serves inline","code_sha256":"5eecd4d849e6cd17","code_sha256_prefix":"5eecd4d849e6cd17","mcp_get_code":{"code_sha256":"5eecd4d849e6cd17"}},{"arxiv_id":"2606.22723","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-22723","title":"BLUEX v2: Benchmarking LLMs on Open-Ended Questions from Brazilian University Entrance Exams","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"TropicAI-Research/BLUEXv2","path":"dataset_pipeline/generate_marking_criteria.py","file_url":"https://github.com/TropicAI-Research/BLUEXv2/blob/HEAD/dataset_pipeline/generate_marking_criteria.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, TropicAI-Research/BLUEXv2 when it was checked","code_sha256":"1b6bb60a02b2635c","code_sha256_prefix":"1b6bb60a02b2635c","mcp_get_code":{"code_sha256":"1b6bb60a02b2635c"}},{"arxiv_id":"2606.01204","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-01204","title":"Implicit Geographic Inference in LLM Medical Triage: Language-Driven Disparities in Emergency Recommendations","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"wongqihan/ai-behavioral-experiments","path":"gender-age-triage/run_multimodel.py","file_url":"https://github.com/wongqihan/ai-behavioral-experiments/blob/HEAD/gender-age-triage/run_multimodel.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"49e53fd218f47011","code_sha256_prefix":"49e53fd218f47011","mcp_get_code":{"code_sha256":"49e53fd218f47011"}},{"arxiv_id":"2604.08595","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-08595","title":"Adaptive Rigor in AI System Evaluation using Temperature-Controlled Verdict Aggregation via Generalized Power Mean","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"meshkovQA/Eval-ai-library","path":"eval_lib/connector/dataset_parser.py","file_url":"https://github.com/meshkovQA/Eval-ai-library/blob/HEAD/eval_lib/connector/dataset_parser.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":"edc4bf2406c6ed95","code_sha256_prefix":"edc4bf2406c6ed95","mcp_get_code":{"code_sha256":"edc4bf2406c6ed95"}},{"arxiv_id":"2603.21335","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-21335","title":"TimeTox: An LLM-Based Pipeline for Automated Extraction of Time Toxicity from Clinical Trial Protocols","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"sakethbuild/TimeTox","path":"core/pipeline_with_judge.py","file_url":"https://github.com/sakethbuild/TimeTox/blob/HEAD/core/pipeline_with_judge.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sakethbuild/TimeTox when it was checked","code_sha256":"4bee91347e376ab1","code_sha256_prefix":"4bee91347e376ab1","mcp_get_code":{"code_sha256":"4bee91347e376ab1"}},{"arxiv_id":"2602.10021","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-10021","title":"Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Lancelot-Xie/DRIFT","path":"data_generation/generate_qa.py","file_url":"https://github.com/Lancelot-Xie/DRIFT/blob/HEAD/data_generation/generate_qa.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Lancelot-Xie/DRIFT when it was checked","code_sha256":"0e717fa81bd2de66","code_sha256_prefix":"0e717fa81bd2de66","mcp_get_code":{"code_sha256":"0e717fa81bd2de66"}},{"arxiv_id":"2507.22171","arxiv_id_is_arxiv":true,"paper":null,"title":"arXiv:2507.22171","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"CjangCjengh/Generic_Persona","path":"utils.py","file_url":"https://github.com/CjangCjengh/Generic_Persona/blob/HEAD/utils.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, CjangCjengh/Generic_Persona when it was checked","code_sha256":"383e31f1b4a47340","code_sha256_prefix":"383e31f1b4a47340","mcp_get_code":{"code_sha256":"383e31f1b4a47340"}},{"arxiv_id":"2505.15810","arxiv_id_is_arxiv":true,"paper":"/paper/gui-g1-understanding-r1-zero-like-training","title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuqi-zhou/gui-g1","path":"src/open-r1-multimodal/src/open_r1/grpo_rec.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/src/open_r1/grpo_rec.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c7446a6215a66f72","code_sha256_prefix":"c7446a6215a66f72","mcp_get_code":{"code_sha256":"c7446a6215a66f72"}},{"arxiv_id":"2505.07581","arxiv_id_is_arxiv":true,"paper":"/paper/yulan-onesim-towards-the-next-generation-of","title":"YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language Models","date":"2025-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RUC-GSAI/YuLan-OneSim","path":"src/onesim/config.py","file_url":"https://github.com/RUC-GSAI/YuLan-OneSim/blob/HEAD/src/onesim/config.py","status":"ran","verification_level":1,"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":"c390007bcf87f7af","code_sha256_prefix":"c390007bcf87f7af","mcp_get_code":{"code_sha256":"c390007bcf87f7af"}},{"arxiv_id":"2409.13682","arxiv_id_is_arxiv":true,"paper":"/paper/remembr-building-and-reasoning-over-long","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","date":"2024-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA-AI-IOT/remembr","path":"remembr/agents/non_agent.py","file_url":"https://github.com/NVIDIA-AI-IOT/remembr/blob/HEAD/remembr/agents/non_agent.py","status":"unverified","verification_level":0,"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, NVIDIA-AI-IOT/remembr (NOASSERTION)","code_sha256":"6785d3e60dfb7ca5","code_sha256_prefix":"6785d3e60dfb7ca5","mcp_get_code":{"code_sha256":"6785d3e60dfb7ca5"}},{"arxiv_id":"2409.13682","arxiv_id_is_arxiv":true,"paper":"/paper/remembr-building-and-reasoning-over-long","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","date":"2024-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA-AI-IOT/remembr","path":"remembr/agents/remembr_agent.py","file_url":"https://github.com/NVIDIA-AI-IOT/remembr/blob/HEAD/remembr/agents/remembr_agent.py","status":"unverified","verification_level":0,"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, NVIDIA-AI-IOT/remembr (NOASSERTION)","code_sha256":"383192b3ef21d786","code_sha256_prefix":"383192b3ef21d786","mcp_get_code":{"code_sha256":"383192b3ef21d786"}},{"arxiv_id":"2406.16306","arxiv_id_is_arxiv":true,"paper":"/paper/cascade-reward-sampling-for-efficient","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lblaoke/CARDS","path":"data_loader.py","file_url":"https://github.com/lblaoke/CARDS/blob/HEAD/data_loader.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, lblaoke/CARDS when it was checked","code_sha256":"e24a02f57af303dc","code_sha256_prefix":"e24a02f57af303dc","mcp_get_code":{"code_sha256":"e24a02f57af303dc"}},{"arxiv_id":"2403.12844","arxiv_id_is_arxiv":true,"paper":"/paper/melting-point-mobile-evaluation-of-language","title":"MELTing point: Mobile Evaluation of Language Transformers","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brave-experiments/melt-public","path":"src/parsers/utils/mlc_utils.py","file_url":"https://github.com/brave-experiments/melt-public/blob/HEAD/src/parsers/utils/mlc_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","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, brave-experiments/melt-public (NOASSERTION)","code_sha256":"3c0cac5e5b160574","code_sha256_prefix":"3c0cac5e5b160574","mcp_get_code":{"code_sha256":"3c0cac5e5b160574"}},{"arxiv_id":"2403.05004","arxiv_id_is_arxiv":true,"paper":"/paper/can-t-remember-details-in-long-documents-you","title":"Can't Remember Details in Long Documents? You Need Some R&R","date":"2024-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"casetext/r-and-r","path":"src/parsers.py","file_url":"https://github.com/casetext/r-and-r/blob/HEAD/src/parsers.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, casetext/r-and-r when it was checked","code_sha256":"71a5af9ea11d13f8","code_sha256_prefix":"71a5af9ea11d13f8","mcp_get_code":{"code_sha256":"71a5af9ea11d13f8"}},{"arxiv_id":"2308.12519","arxiv_id_is_arxiv":true,"paper":"/paper/large-language-model-as-autonomous-decision","title":"Rational Decision-Making Agent with Internalized Utility Judgment","date":"2023-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenBMB/RaD-Agent","path":"Algorithms/ETS.py","file_url":"https://github.com/OpenBMB/RaD-Agent/blob/HEAD/Algorithms/ETS.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, OpenBMB/RaD-Agent when it was checked","code_sha256":"2d522169c96708ab","code_sha256_prefix":"2d522169c96708ab","mcp_get_code":{"code_sha256":"2d522169c96708ab"}},{"arxiv_id":"2305.04658","arxiv_id_is_arxiv":true,"paper":"/paper/csgcl-community-strength-enhanced-graph","title":"CSGCL: Community-Strength-Enhanced Graph Contrastive Learning","date":"2023-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanchen-hust/csgcl","path":"src/sp.py","file_url":"https://github.com/hanchen-hust/csgcl/blob/HEAD/src/sp.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":"302c6c94764d906c","code_sha256_prefix":"302c6c94764d906c","mcp_get_code":{"code_sha256":"302c6c94764d906c"}},{"arxiv_id":"2111.02194","arxiv_id_is_arxiv":true,"paper":"/paper/learning-implicit-sentiment-in-aspect-based","title":"Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training","date":"2021-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Tribleave/SCAPT-ABSA","path":"preprocess/utils.py","file_url":"https://github.com/Tribleave/SCAPT-ABSA/blob/HEAD/preprocess/utils.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":"5cf320d5a6726479","code_sha256_prefix":"5cf320d5a6726479","mcp_get_code":{"code_sha256":"5cf320d5a6726479"}},{"arxiv_id":"2102.07988","arxiv_id_is_arxiv":true,"paper":"/paper/terapipe-token-level-pipeline-parallelism-for","title":"TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models","date":"2021-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhuohan123/terapipe","path":"latency_model.py","file_url":"https://github.com/zhuohan123/terapipe/blob/HEAD/latency_model.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, zhuohan123/terapipe when it was checked","code_sha256":"b2bdcb303f86d948","code_sha256_prefix":"b2bdcb303f86d948","mcp_get_code":{"code_sha256":"b2bdcb303f86d948"}},{"arxiv_id":"1908.09791","arxiv_id_is_arxiv":true,"paper":"/paper/once-for-all-train-one-network-and-specialize","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","date":"2019-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MaximIntegratedAI/ai8x-synthesis","path":"izer/assets.py","file_url":"https://github.com/MaximIntegratedAI/ai8x-synthesis/blob/HEAD/izer/assets.py","status":"ran","verification_level":1,"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":"a6fe7c130778ca63","code_sha256_prefix":"a6fe7c130778ca63","mcp_get_code":{"code_sha256":"a6fe7c130778ca63"}},{"arxiv_id":"2025.acl-long.1207","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2025.acl-long.1207","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AI45Lab/ActorAttack","path":"inattack.py","file_url":"https://github.com/AI45Lab/ActorAttack/blob/HEAD/inattack.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, AI45Lab/ActorAttack when it was checked","code_sha256":"2b8814701b39030c","code_sha256_prefix":"2b8814701b39030c","mcp_get_code":{"code_sha256":"2b8814701b39030c"}}],"record_sha256":"6b5596ac15b31a109161f3bf138b33f8aa98d38022b96206ea7633ad7e10fcf4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}