{"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/bleu-score","entry":"bleu_score","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":7,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":10,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":3},"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":"2605.17932","paper":"/paper/arxiv-2605-17932","title":"Prompt Compression for Diffusion Large Language Models: An Empirical Evaluation of LLMLingua-2 and LLaDA","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"axxx129-ops/DLLM-Compression","path":"evaluation/evaluate.py","file_url":"https://github.com/axxx129-ops/DLLM-Compression/blob/HEAD/evaluation/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"432d5314a4ebadbd","mcp_get_code":{"code_sha256":"432d5314a4ebadbd"}},{"arxiv_id":"2404.16789","paper":"/paper/continual-learning-of-large-language-models-a","title":"Continual Learning of Large Language Models: A Comprehensive Survey","date":"2024-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beyonderxx/trace","path":"metrics.py","file_url":"https://github.com/beyonderxx/trace/blob/HEAD/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ab795c060d39c540","mcp_get_code":{"code_sha256":"ab795c060d39c540"}},{"arxiv_id":"2403.11322","paper":"/paper/stateflow-enhancing-llm-task-solving-through","title":"StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows","date":"2024-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kevin666aa/stateflow","path":"ALFWorld/src/chat_utils.py","file_url":"https://github.com/kevin666aa/stateflow/blob/HEAD/ALFWorld/src/chat_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"88c3f0a98558ec2f","mcp_get_code":{"code_sha256":"88c3f0a98558ec2f"}},{"arxiv_id":"2311.09816","paper":"/paper/performance-trade-offs-of-watermarking-large","title":"Downstream Trade-offs of a Family of Text Watermarks","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"flair-iisc/watermark_tradeoffs","path":"evaluation/utils.py","file_url":"https://github.com/flair-iisc/watermark_tradeoffs/blob/HEAD/evaluation/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08cb85fd2c4518cc","mcp_get_code":{"code_sha256":"08cb85fd2c4518cc"}},{"arxiv_id":"2308.12241","paper":"/paper/llmrec-benchmarking-large-language-models-on","title":"LLMRec: Benchmarking Large Language Models on Recommendation Task","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"williamliujl/llmrec","path":"utils/evaluate/utils.py","file_url":"https://github.com/williamliujl/llmrec/blob/HEAD/utils/evaluate/utils.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":"c212cb768b5261af","mcp_get_code":{"code_sha256":"c212cb768b5261af"}},{"arxiv_id":"2307.12626","paper":"/paper/enhancing-human-like-multi-modal-reasoning-a","title":"Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework","date":"2023-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weijingxuan/COCO-MMR","path":"evaluations.py","file_url":"https://github.com/weijingxuan/COCO-MMR/blob/HEAD/evaluations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ab795c060d39c540","mcp_get_code":{"code_sha256":"ab795c060d39c540"}},{"arxiv_id":"2302.00923","paper":"/paper/multimodal-chain-of-thought-reasoning-in","title":"Multimodal Chain-of-Thought Reasoning in Language Models","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/mm-cot","path":"evaluations.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/evaluations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ab795c060d39c540","mcp_get_code":{"code_sha256":"ab795c060d39c540"}},{"arxiv_id":"2003.04807","paper":"/paper/efficient-intent-detection-with-dual-sentence","title":"Efficient Intent Detection with Dual Sentence Encoders","date":"2020-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/intent-aware-encoder","path":"downstream/protaugment/paraphrase/modeling.py","file_url":"https://github.com/amazon-science/intent-aware-encoder/blob/HEAD/downstream/protaugment/paraphrase/modeling.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":"26105291c088d807","mcp_get_code":{"code_sha256":"26105291c088d807"}},{"arxiv_id":"1911.12986","paper":"/paper/merging-weak-and-active-supervision-for","title":"Merging Weak and Active Supervision for Semantic Parsing","date":"2019-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"niansong1996/wassp","path":"nsm/nlp_utils.py","file_url":"https://github.com/niansong1996/wassp/blob/HEAD/nsm/nlp_utils.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":"9073ba6a227f3a75","mcp_get_code":{"code_sha256":"9073ba6a227f3a75"}},{"arxiv_id":"1807.02322","paper":"/paper/memory-augmented-policy-optimization-for","title":"Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing","date":"2018-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crazydonkey200/neural-symbolic-machines","path":"nsm/nlp_utils.py","file_url":"https://github.com/crazydonkey200/neural-symbolic-machines/blob/HEAD/nsm/nlp_utils.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":"9073ba6a227f3a75","mcp_get_code":{"code_sha256":"9073ba6a227f3a75"}}]}