{"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/calculate-perplexity","entry":"calculate_perplexity","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":9,"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":9,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":5,"by_status":{"ran_honours":1,"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":"2606.14122","paper":"/paper/arxiv-2606-14122","title":"Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"cynthia/bytecanary","path":"src/bytecanary/evaluate.py","file_url":"https://github.com/cynthia/bytecanary/blob/HEAD/src/bytecanary/evaluate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c1f2418ee44b141","mcp_get_code":{"code_sha256":"5c1f2418ee44b141"}},{"arxiv_id":"2604.24470","paper":"/paper/arxiv-2604-24470","title":"Zero-shot Large Language Models for Automatic Readability Assessment","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"kinimod23/GRANT","path":"unsupervised/BERT/apply.py","file_url":"https://github.com/kinimod23/GRANT/blob/HEAD/unsupervised/BERT/apply.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ac0d85fa1d5b36df","mcp_get_code":{"code_sha256":"ac0d85fa1d5b36df"}},{"arxiv_id":"2511.00177","paper":"/paper/arxiv-2511-00177","title":"Can SAEs reveal and mitigate racial biases of LLMs in healthcare?","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"hibaahsan/sae_bias","path":"src/steer_bhcs.py","file_url":"https://github.com/hibaahsan/sae_bias/blob/HEAD/src/steer_bhcs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d120118971ebf2cb","mcp_get_code":{"code_sha256":"d120118971ebf2cb"}},{"arxiv_id":"2412.12979","paper":"/paper/guiding-generative-protein-language-models","title":"Guiding Generative Protein Language Models with Reinforcement Learning","date":"2024-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ai4pdlab/dpo_plm","path":"seq_gen.py","file_url":"https://github.com/ai4pdlab/dpo_plm/blob/HEAD/seq_gen.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7eb95b024fabf1cc","mcp_get_code":{"code_sha256":"7eb95b024fabf1cc"}},{"arxiv_id":"2406.17746","paper":"/paper/recite-reconstruct-recollect-memorization-in","title":"Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eleutherai/semantic-memorization","path":"inference.py","file_url":"https://github.com/eleutherai/semantic-memorization/blob/HEAD/inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f6beaa0ccde5ca7b","mcp_get_code":{"code_sha256":"f6beaa0ccde5ca7b"}},{"arxiv_id":"2405.18400","paper":"/paper/superposed-decoding-multiple-generations-from","title":"Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RAIVNLab/SuperposedDecoding","path":"superposed/llama/metrics.py","file_url":"https://github.com/RAIVNLab/SuperposedDecoding/blob/HEAD/superposed/llama/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"9844eb34712feeb4","mcp_get_code":{"code_sha256":"9844eb34712feeb4"}},{"arxiv_id":"2402.09394","paper":"/paper/long-form-evaluation-of-model-editing","title":"Long-form evaluation of model editing","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"domenicrosati/longform-evaluation-model-editing","path":"src/automatic_metrics.py","file_url":"https://github.com/domenicrosati/longform-evaluation-model-editing/blob/HEAD/src/automatic_metrics.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6be6c7d3f948ef58","mcp_get_code":{"code_sha256":"6be6c7d3f948ef58"}},{"arxiv_id":"2012.07805","paper":"/paper/extracting-training-data-from-large-language","title":"Extracting Training Data from Large Language Models","date":"2020-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shreyansh26/Extracting-Training-Data-from-Large-Langauge-Models","path":"extraction_top_n.py","file_url":"https://github.com/shreyansh26/Extracting-Training-Data-from-Large-Langauge-Models/blob/HEAD/extraction_top_n.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c59c1720bffdb7a5","mcp_get_code":{"code_sha256":"c59c1720bffdb7a5"}},{"arxiv_id":"2023.findings-emnlp.139","paper":null,"title":"arXiv:2023.findings-emnlp.139","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"TrustedLLM/LLMDet","path":"llmdet/truth_perplexity.py","file_url":"https://github.com/TrustedLLM/LLMDet/blob/HEAD/llmdet/truth_perplexity.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23f93efbe9cb73dd","mcp_get_code":{"code_sha256":"23f93efbe9cb73dd"}}]}