{"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-bleu","entry":"calculate_bleu","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":10,"n_papers_ran":6,"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":10,"n_samples_ran":6,"n_samples_fingerprinted":3,"n_places":10,"n_places_pointer_only":6,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":4},"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":"2501.09993","paper":"/paper/agent-as-judge-for-factual-summarization-of","title":"Agent-as-Judge for Factual Summarization of Long Narratives","date":"2025-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YeonseokJeong/NarrativeFactScore","path":"calculate_metrics.py","file_url":"https://github.com/YeonseokJeong/NarrativeFactScore/blob/HEAD/calculate_metrics.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":"50254ec8b6e5f2d1","mcp_get_code":{"code_sha256":"50254ec8b6e5f2d1"}},{"arxiv_id":"2412.13341","paper":"/paper/concept-rot-poisoning-concepts-in-large","title":"Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing","date":"2024-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"keltin13/concept-rot","path":"dsets/generate_concept_dataset.py","file_url":"https://github.com/keltin13/concept-rot/blob/HEAD/dsets/generate_concept_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"77c6066c3e1c8642","mcp_get_code":{"code_sha256":"77c6066c3e1c8642"}},{"arxiv_id":"2406.13173","paper":"/paper/biomedical-visual-instruction-tuning-with","title":"Biomedical Visual Instruction Tuning with Clinician Preference Alignment","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mao1207/BioMed-VITAL","path":"eval/evaluate_metrics.py","file_url":"https://github.com/mao1207/BioMed-VITAL/blob/HEAD/eval/evaluate_metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ce631affee8e32d","mcp_get_code":{"code_sha256":"7ce631affee8e32d"}},{"arxiv_id":"2406.11614","paper":"/paper/intrinsic-evaluation-of-unlearning-using","title":"Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihuaihong/conceptvectors","path":"evaluate_util.py","file_url":"https://github.com/yihuaihong/conceptvectors/blob/HEAD/evaluate_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"CC-BY-4.0","inline_ok":false,"code_sha256_prefix":"7f57090da94e6a92","mcp_get_code":{"code_sha256":"7f57090da94e6a92"}},{"arxiv_id":"2406.05688","paper":"/paper/peer-review-as-a-multi-turn-and-long-context","title":"Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chengtan9907/reviewmt","path":"src/metric.py","file_url":"https://github.com/chengtan9907/reviewmt/blob/HEAD/src/metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"26fe2ad3bcb38a7e","mcp_get_code":{"code_sha256":"26fe2ad3bcb38a7e"}},{"arxiv_id":"2405.18406","paper":"/paper/raccoon-remove-add-and-change-video-content","title":"RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adymaharana/adapt-inf","path":"llava/eval/model_caption.py","file_url":"https://github.com/adymaharana/adapt-inf/blob/HEAD/llava/eval/model_caption.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"53ecd0b8db99f236","mcp_get_code":{"code_sha256":"53ecd0b8db99f236"}},{"arxiv_id":"2310.08129","paper":"/paper/tailored-visions-enhancing-text-to-image","title":"Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzjchen/tailored-visions","path":"metrics.py","file_url":"https://github.com/zzjchen/tailored-visions/blob/HEAD/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e895dbffbe807390","mcp_get_code":{"code_sha256":"e895dbffbe807390"}},{"arxiv_id":"2307.08775","paper":"/paper/gear-augmenting-language-models-with","title":"GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution","date":"2023-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yining610/gear","path":"evaluation/eva.py","file_url":"https://github.com/yining610/gear/blob/HEAD/evaluation/eva.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45b3499acead6c78","mcp_get_code":{"code_sha256":"45b3499acead6c78"}},{"arxiv_id":"1906.00363","paper":"/paper/190600363","title":"Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation","date":"2019-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangcunxiang/SemEval2020-Task4-Commonsense-Validation-and-Explanation","path":"starting_kit/scoring_program/evaluate.py","file_url":"https://github.com/wangcunxiang/SemEval2020-Task4-Commonsense-Validation-and-Explanation/blob/HEAD/starting_kit/scoring_program/evaluate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d648a5f0839ef50a","mcp_get_code":{"code_sha256":"d648a5f0839ef50a"}},{"arxiv_id":"2022.findings-emnlp.176","paper":null,"title":"arXiv:2022.findings-emnlp.176","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LuJunru/TranCLR","path":"code/utils.py","file_url":"https://github.com/LuJunru/TranCLR/blob/HEAD/code/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e17cefacb78ba40e","mcp_get_code":{"code_sha256":"e17cefacb78ba40e"}}]}