{"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/tokenize-and-mask","entry":"tokenize_and_mask","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":12,"n_papers_ran":4,"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":8,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":13,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":5},"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":"2602.08031","paper":"/paper/arxiv-2602-08031","title":"Beyond Raw Detection Scores: Markov-Informed Calibration for Boosting Machine-Generated Text Detection","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"tmlr-group/MRF_Calibration","path":"methods/detectgpt.py","file_url":"https://github.com/tmlr-group/MRF_Calibration/blob/HEAD/methods/detectgpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e4025e69a644bfcf","mcp_get_code":{"code_sha256":"e4025e69a644bfcf"}},{"arxiv_id":"2411.12764","paper":"/paper/sefd-semantic-enhanced-framework-for","title":"SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text","date":"2024-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hwq0726/sefd","path":"dipper_paraphrases/detectgpt_run.py","file_url":"https://github.com/hwq0726/sefd/blob/HEAD/dipper_paraphrases/detectgpt_run.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d1d1b68e224fca00","mcp_get_code":{"code_sha256":"d1d1b68e224fca00"}},{"arxiv_id":"2410.23746","paper":"/paper/detectrl-benchmarking-llm-generated-text","title":"DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlp2ct/detectrl","path":"Detectors/DetectGPT.py","file_url":"https://github.com/nlp2ct/detectrl/blob/HEAD/Detectors/DetectGPT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bef9b8781ddec1a","mcp_get_code":{"code_sha256":"6bef9b8781ddec1a"}},{"arxiv_id":"2408.08661","paper":"/paper/mia-tuner-adapting-large-language-models-as","title":"MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector","date":"2024-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wjfu99/mia-tuner","path":"dataset_perturb.py","file_url":"https://github.com/wjfu99/mia-tuner/blob/HEAD/dataset_perturb.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ef526c6711c4bf8","mcp_get_code":{"code_sha256":"7ef526c6711c4bf8"}},{"arxiv_id":"2403.03506","paper":"/paper/towards-detecting-ai-generated-text-within","title":"Detecting AI-Generated Sentences in Human-AI Collaborative Hybrid Texts: Challenges, Strategies, and Insights","date":"2024-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"douglashiwo/aisentencedetection","path":"B-Segment_Classification_Models/SeqXGPT/SeqXGPT_compress/backend_t5.py","file_url":"https://github.com/douglashiwo/aisentencedetection/blob/HEAD/B-Segment_Classification_Models/SeqXGPT/SeqXGPT_compress/backend_t5.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"52cd472fa9521fd1","mcp_get_code":{"code_sha256":"52cd472fa9521fd1"}},{"arxiv_id":"2402.16041","paper":"/paper/detecting-machine-generated-texts-by-multi","title":"Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZSHsh98/MMD-MP","path":"run_meta_mmd_trans.py","file_url":"https://github.com/ZSHsh98/MMD-MP/blob/HEAD/run_meta_mmd_trans.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"374e995ebc355414","mcp_get_code":{"code_sha256":"374e995ebc355414"}},{"arxiv_id":"2401.05952","paper":"/paper/llm-as-a-coauthor-the-challenges-of-detecting","title":"LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected?","date":"2024-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dongping-chen/mixset","path":"methods/detectgpt.py","file_url":"https://github.com/dongping-chen/mixset/blob/HEAD/methods/detectgpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"639b00cb6787d6d0","mcp_get_code":{"code_sha256":"639b00cb6787d6d0"}},{"arxiv_id":"2307.11729","paper":"/paper/outfox-llm-generated-essay-detection-through","title":"OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples","date":"2023-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryuryukke/OUTFOX","path":"src/detection/baseline_detection_dev.py","file_url":"https://github.com/ryuryukke/OUTFOX/blob/HEAD/src/detection/baseline_detection_dev.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":"374e995ebc355414","mcp_get_code":{"code_sha256":"374e995ebc355414"}},{"arxiv_id":"2305.19713","paper":"/paper/red-teaming-language-model-detectors-with","title":"Red Teaming Language Model Detectors with Language Models","date":"2023-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shizhouxing/LLM-Detector-Robustness","path":"DetectGPT/run_attack.py","file_url":"https://github.com/shizhouxing/LLM-Detector-Robustness/blob/HEAD/DetectGPT/run_attack.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"374e995ebc355414","mcp_get_code":{"code_sha256":"374e995ebc355414"}},{"arxiv_id":"2305.18462","paper":"/paper/membership-inference-attacks-against-language","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mireshghallah/neighborhood-curvature-mia","path":"run_mia_unified.py","file_url":"https://github.com/mireshghallah/neighborhood-curvature-mia/blob/HEAD/run_mia_unified.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ef526c6711c4bf8","mcp_get_code":{"code_sha256":"7ef526c6711c4bf8"}},{"arxiv_id":"2303.14822","paper":"/paper/mgtbench-benchmarking-machine-generated-text","title":"MGTBench: Benchmarking Machine-Generated Text Detection","date":"2023-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michalspiegel/imgtb","path":"methods/abstract_methods/pertubation_based_experiment.py","file_url":"https://github.com/michalspiegel/imgtb/blob/HEAD/methods/abstract_methods/pertubation_based_experiment.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"639b00cb6787d6d0","mcp_get_code":{"code_sha256":"639b00cb6787d6d0"}},{"arxiv_id":"2303.14822","paper":"/paper/mgtbench-benchmarking-machine-generated-text","title":"MGTBench: Benchmarking Machine-Generated Text Detection","date":"2023-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trustairlab/mgtbench","path":"methods/detectgpt.py","file_url":"https://github.com/trustairlab/mgtbench/blob/HEAD/methods/detectgpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4fed12f8c019459e","mcp_get_code":{"code_sha256":"4fed12f8c019459e"}},{"arxiv_id":"2023.emnlp-main.616","paper":null,"title":"arXiv:2023.emnlp-main.616","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"xinleihe/MGTBench","path":"methods/detectgpt.py","file_url":"https://github.com/xinleihe/MGTBench/blob/HEAD/methods/detectgpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4fed12f8c019459e","mcp_get_code":{"code_sha256":"4fed12f8c019459e"}}]}