{"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/dec","entry":"dec","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":5,"n_papers_ran":5,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":0},"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":"2606.28044","paper":"/paper/arxiv-2606-28044","title":"A Tree-of-Thoughts Hybrid Approach for Legal Case Judgement Summarization using LLMs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Yale-LILY/SummEval","path":"evaluation/summ_eval/meteor_metric.py","file_url":"https://github.com/Yale-LILY/SummEval/blob/HEAD/evaluation/summ_eval/meteor_metric.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba9348aac71a3f72","mcp_get_code":{"code_sha256":"ba9348aac71a3f72"}},{"arxiv_id":"2309.09812","paper":"/paper/r2gengpt-radiology-report-generation-with","title":"R2GenGPT: Radiology Report Generation with Frozen LLMs","date":"2023-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wang-zhanyu/r2gengpt","path":"evalcap/meteor/meteor.py","file_url":"https://github.com/wang-zhanyu/r2gengpt/blob/HEAD/evalcap/meteor/meteor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"ba9348aac71a3f72","mcp_get_code":{"code_sha256":"ba9348aac71a3f72"}},{"arxiv_id":"2109.08365","paper":"/paper/codeqa-a-question-answering-dataset-for","title":"CodeQA: A Question Answering Dataset for Source Code Comprehension","date":"2021-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jadecxliu/codeqa","path":"codeBERT/code/eval/meteor/meteor.py","file_url":"https://github.com/jadecxliu/codeqa/blob/HEAD/codeBERT/code/eval/meteor/meteor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba9348aac71a3f72","mcp_get_code":{"code_sha256":"ba9348aac71a3f72"}},{"arxiv_id":"1706.09799","paper":"/paper/relevance-of-unsupervised-metrics-in-task","title":"Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation","date":"2017-06-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Maluuba/nlg-eval","path":"nlgeval/pycocoevalcap/meteor/meteor.py","file_url":"https://github.com/Maluuba/nlg-eval/blob/HEAD/nlgeval/pycocoevalcap/meteor/meteor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ba9348aac71a3f72","mcp_get_code":{"code_sha256":"ba9348aac71a3f72"}},{"arxiv_id":"2022.findings-naacl.160","paper":null,"title":"arXiv:2022.findings-naacl.160","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"malllabiisc/SGCP","path":"src/evaluation/eval_utils.py","file_url":"https://github.com/malllabiisc/SGCP/blob/HEAD/src/evaluation/eval_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ba9348aac71a3f72","mcp_get_code":{"code_sha256":"ba9348aac71a3f72"}}]}