{"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/get-res","entry":"get_res","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":7,"n_papers_ran":3,"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":9,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":9,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":7},"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":"2406.13662","paper":"/paper/obscureprompt-jailbreaking-large-language","title":"Jailbreaking Large Language Models Through Alignment Vulnerabilities in Out-of-Distribution Settings","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HowieHwong/ObscurePrompt","path":"preprocess/obscure_generation.py","file_url":"https://github.com/HowieHwong/ObscurePrompt/blob/HEAD/preprocess/obscure_generation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df3495a55bdcd3cd","mcp_get_code":{"code_sha256":"df3495a55bdcd3cd"}},{"arxiv_id":"2404.15846","paper":"/paper/from-complex-to-simple-enhancing-multi","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meowpass/followcomplexinstruction","path":"get_data/GPT_api.py","file_url":"https://github.com/meowpass/followcomplexinstruction/blob/HEAD/get_data/GPT_api.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c1a7db24cb308eb","mcp_get_code":{"code_sha256":"6c1a7db24cb308eb"}},{"arxiv_id":"2403.00425","paper":"/paper/halc-object-hallucination-reduction-via","title":"HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BillChan226/HALC","path":"models/questioner.py","file_url":"https://github.com/BillChan226/HALC/blob/HEAD/models/questioner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71e7ce8bf939f5d4","mcp_get_code":{"code_sha256":"71e7ce8bf939f5d4"}},{"arxiv_id":"2403.00425","paper":"/paper/halc-object-hallucination-reduction-via","title":"HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BillChan226/HALC","path":"models/entity_extractor.py","file_url":"https://github.com/BillChan226/HALC/blob/HEAD/models/entity_extractor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8dbb0079cf7049ec","mcp_get_code":{"code_sha256":"8dbb0079cf7049ec"}},{"arxiv_id":"2402.18865","paper":"/paper/analyzing-and-reducing-catastrophic","title":"Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"which47/llmcl","path":"evaluation.py","file_url":"https://github.com/which47/llmcl/blob/HEAD/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f6fd640bd5fb5f16","mcp_get_code":{"code_sha256":"f6fd640bd5fb5f16"}},{"arxiv_id":"2312.09817","paper":"/paper/calibrated-one-round-federated-learning-with","title":"Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space","date":"2023-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hasanmohsin/betapredbayes_fl","path":"noniid_plot.py","file_url":"https://github.com/hasanmohsin/betapredbayes_fl/blob/HEAD/noniid_plot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"de875c40c3a69d9d","mcp_get_code":{"code_sha256":"de875c40c3a69d9d"}},{"arxiv_id":"2312.09817","paper":"/paper/calibrated-one-round-federated-learning-with","title":"Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space","date":"2023-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hasanmohsin/betapredbayes_fl","path":"process_results.py","file_url":"https://github.com/hasanmohsin/betapredbayes_fl/blob/HEAD/process_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"061d71155895e2ea","mcp_get_code":{"code_sha256":"061d71155895e2ea"}},{"arxiv_id":"2312.09817","paper":"/paper/calibrated-one-round-federated-learning-with","title":"Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space","date":"2023-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hasanmohsin/betapredbayes_fl","path":"process_results_regr.py","file_url":"https://github.com/hasanmohsin/betapredbayes_fl/blob/HEAD/process_results_regr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"456c3390fb625e86","mcp_get_code":{"code_sha256":"456c3390fb625e86"}},{"arxiv_id":"2311.17600","paper":"/paper/query-relevant-images-jailbreak-large-multi","title":"MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models","date":"2023-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"isxinliu/mm-safetybench","path":"evaluation.py","file_url":"https://github.com/isxinliu/mm-safetybench/blob/HEAD/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"03209937b405b2af","mcp_get_code":{"code_sha256":"03209937b405b2af"}},{"arxiv_id":"2310.16045","paper":"/paper/woodpecker-hallucination-correction-for","title":"Woodpecker: Hallucination Correction for Multimodal Large Language Models","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bradyfu/woodpecker","path":"models/questioner.py","file_url":"https://github.com/bradyfu/woodpecker/blob/HEAD/models/questioner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"71e7ce8bf939f5d4","mcp_get_code":{"code_sha256":"71e7ce8bf939f5d4"}},{"arxiv_id":"2310.16045","paper":"/paper/woodpecker-hallucination-correction-for","title":"Woodpecker: Hallucination Correction for Multimodal Large Language Models","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bradyfu/woodpecker","path":"models/entity_extractor.py","file_url":"https://github.com/bradyfu/woodpecker/blob/HEAD/models/entity_extractor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8dbb0079cf7049ec","mcp_get_code":{"code_sha256":"8dbb0079cf7049ec"}}]}