{"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/compute-exact-match","entry":"compute_exact_match","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+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":14,"n_papers_ran":8,"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":13,"n_samples_ran":7,"n_samples_fingerprinted":5,"n_places":14,"n_places_pointer_only":5,"by_status":{"ran_honours":3,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":6},"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":"2603.16654","paper":"/paper/arxiv-2603-16654","title":"Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"XiaojieGu/Omanic","path":"eval/open_eval.py","file_url":"https://github.com/XiaojieGu/Omanic/blob/HEAD/eval/open_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b999af444f951d7","mcp_get_code":{"code_sha256":"9b999af444f951d7"}},{"arxiv_id":"2602.07143","paper":"/paper/arxiv-2602-07143","title":"Massive Sound Embedding Benchmark (MSEB)","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"google-research/mseb","path":"mseb/metrics.py","file_url":"https://github.com/google-research/mseb/blob/HEAD/mseb/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":"db44f20e41014fcf","mcp_get_code":{"code_sha256":"db44f20e41014fcf"}},{"arxiv_id":"2511.19900","paper":"/paper/arxiv-2511-19900","title":"Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"aiming-lab/Agent0","path":"Agent0-VL/verl/evaluation/metrics.py","file_url":"https://github.com/aiming-lab/Agent0/blob/HEAD/Agent0-VL/verl/evaluation/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":"431c8e2d70a7ffee","mcp_get_code":{"code_sha256":"431c8e2d70a7ffee"}},{"arxiv_id":"2511.07328","paper":"/paper/arxiv-2511-07328","title":"Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"griver/Q-RAG","path":"eval_llm_openqa.py","file_url":"https://github.com/griver/Q-RAG/blob/HEAD/eval_llm_openqa.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e01d0df446b366b7","mcp_get_code":{"code_sha256":"e01d0df446b366b7"}},{"arxiv_id":"2509.12132","paper":"/paper/arxiv-2509-12132","title":"Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"jian0805/ClearVQA","path":"eval/metrics.py","file_url":"https://github.com/jian0805/ClearVQA/blob/HEAD/eval/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cf10a77d08a986d6","mcp_get_code":{"code_sha256":"cf10a77d08a986d6"}},{"arxiv_id":"2410.13098","paper":"/paper/a-little-human-data-goes-a-long-way","title":"A Little Human Data Goes A Long Way","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dhananjayashok/littlehumandata","path":"compute_qa_metrics.py","file_url":"https://github.com/dhananjayashok/littlehumandata/blob/HEAD/compute_qa_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d046034742d3fdba","mcp_get_code":{"code_sha256":"d046034742d3fdba"}},{"arxiv_id":"2408.03094","paper":"/paper/2408-03094","title":"500xCompressor: Generalized Prompt Compression for Large Language Models","date":"2024-08-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZongqianLi/500xCompressor","path":"codes/evaluation/evaluate_1.py","file_url":"https://github.com/ZongqianLi/500xCompressor/blob/HEAD/codes/evaluation/evaluate_1.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e590396e43a8d7c9","mcp_get_code":{"code_sha256":"e590396e43a8d7c9"}},{"arxiv_id":"2403.19851","paper":"/paper/localizing-paragraph-memorization-in-language","title":"Localizing Paragraph Memorization in Language Models","date":"2024-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"googleinterns/localizing-paragraph-memorization","path":"utils/evaluation.py","file_url":"https://github.com/googleinterns/localizing-paragraph-memorization/blob/HEAD/utils/evaluation.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":"39e32b875bb32e57","mcp_get_code":{"code_sha256":"39e32b875bb32e57"}},{"arxiv_id":"2310.15047","paper":"/paper/meta-out-of-context-learning-in-neural","title":"Implicit meta-learning may lead language models to trust more reliable sources","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"krasheninnikov/internalization","path":"src/metrics.py","file_url":"https://github.com/krasheninnikov/internalization/blob/HEAD/src/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6e67afebffc30110","mcp_get_code":{"code_sha256":"6e67afebffc30110"}},{"arxiv_id":"2305.12295","paper":"/paper/logic-lm-empowering-large-language-models","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","date":"2023-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"teacherpeterpan/logic-llm","path":"models/evaluation.py","file_url":"https://github.com/teacherpeterpan/logic-llm/blob/HEAD/models/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc9914abc88a7da","mcp_get_code":{"code_sha256":"fdc9914abc88a7da"}},{"arxiv_id":"2304.13007","paper":"/paper/answering-questions-by-meta-reasoning-over","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","date":"2023-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oriyor/reasoning-on-cots","path":"src/pred_evaluators/evaluation.py","file_url":"https://github.com/oriyor/reasoning-on-cots/blob/HEAD/src/pred_evaluators/evaluation.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"86dcd04f5c5623f3","mcp_get_code":{"code_sha256":"86dcd04f5c5623f3"}},{"arxiv_id":"2208.11445","paper":"/paper/induced-natural-language-rationales-and","title":"Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models","date":"2022-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mirelleb/induced-rationales-markup-tokens","path":"SCAN/few-shot-text-davinci-002/evaluate_model.py","file_url":"https://github.com/mirelleb/induced-rationales-markup-tokens/blob/HEAD/SCAN/few-shot-text-davinci-002/evaluate_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"15e1a9b5ae261165","mcp_get_code":{"code_sha256":"15e1a9b5ae261165"}},{"arxiv_id":"2110.07803","paper":"/paper/contraqa-question-answering-under-1","title":"Attacking Open-domain Question Answering by Injecting Misinformation","date":"2021-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"teacherpeterpan/contraqa","path":"evaluate.py","file_url":"https://github.com/teacherpeterpan/contraqa/blob/HEAD/evaluate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"86dcd04f5c5623f3","mcp_get_code":{"code_sha256":"86dcd04f5c5623f3"}},{"arxiv_id":"2109.04672","paper":"/paper/investigating-numeracy-learning-ability-of-a","title":"Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model","date":"2021-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuntalkumarpal/t5numeracy","path":"code/decoding.py","file_url":"https://github.com/kuntalkumarpal/t5numeracy/blob/HEAD/code/decoding.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":"9a405020adf1ed97","mcp_get_code":{"code_sha256":"9a405020adf1ed97"}}]}