{"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/evaluate-acc","entry":"evaluate_acc","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":2,"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":5,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2404.00860","paper":"/paper/lipsum-ft-robust-fine-tuning-of-zero-shot","title":"Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance","date":"2024-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cs-giung/lipsum-ft","path":"src/metrics.py","file_url":"https://github.com/cs-giung/lipsum-ft/blob/HEAD/src/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b8e9ddb2c01d62ce","mcp_get_code":{"code_sha256":"b8e9ddb2c01d62ce"}},{"arxiv_id":"2311.08803","paper":"/paper/strategyllm-large-language-models-as-strategy","title":"StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gao-xiao-bai/StrategyLLM","path":"source/dataset/utils.py","file_url":"https://github.com/gao-xiao-bai/StrategyLLM/blob/HEAD/source/dataset/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b1b3d6edbf300b96","mcp_get_code":{"code_sha256":"b1b3d6edbf300b96"}},{"arxiv_id":"2310.19156","paper":"/paper/poisoning-retrieval-corpora-by-injecting","title":"Poisoning Retrieval Corpora by Injecting Adversarial Passages","date":"2023-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/corpus-poisoning","path":"src/attack_poison.py","file_url":"https://github.com/princeton-nlp/corpus-poisoning/blob/HEAD/src/attack_poison.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b111b224b552b7a7","mcp_get_code":{"code_sha256":"b111b224b552b7a7"}},{"arxiv_id":"2007.00216","paper":"/paper/an-efficient-neighborhood-based-interaction","title":"An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph","date":"2020-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jinjiarui/GraphHINGE","path":"utils/utils.py","file_url":"https://github.com/Jinjiarui/GraphHINGE/blob/HEAD/utils/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":"bdb91d9ddc5951f8","mcp_get_code":{"code_sha256":"bdb91d9ddc5951f8"}},{"arxiv_id":"1505.00468","paper":"/paper/vqa-visual-question-answering","title":"VQA: Visual Question Answering","date":"2015-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luomancs/alternative_answer_set","path":"evaluation/evaluation.py","file_url":"https://github.com/luomancs/alternative_answer_set/blob/HEAD/evaluation/evaluation.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":"a4063279bd752ead","mcp_get_code":{"code_sha256":"a4063279bd752ead"}}]}