{"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-combinations","entry":"get_combinations","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":6,"n_papers_ran":4,"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":6,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":2,"unverified":2},"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":"compute_res.py","file_url":"https://github.com/HowieHwong/ObscurePrompt/blob/HEAD/compute_res.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b00f44b4cdd4ac43","mcp_get_code":{"code_sha256":"b00f44b4cdd4ac43"}},{"arxiv_id":"2405.01719","paper":"/paper/inherent-trade-offs-between-diversity-and","title":"Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks","date":"2024-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"socialfoundations/benchbench","path":"benchbench/utils/base.py","file_url":"https://github.com/socialfoundations/benchbench/blob/HEAD/benchbench/utils/base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d8821cf389d6c663","mcp_get_code":{"code_sha256":"d8821cf389d6c663"}},{"arxiv_id":"2404.11184","paper":"/paper/fizz-factual-inconsistency-detection-by-zoom","title":"FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"plm3332/FIZZ","path":"fizz/atomic_fact_scoring.py","file_url":"https://github.com/plm3332/FIZZ/blob/HEAD/fizz/atomic_fact_scoring.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b16fc41e81a03e71","mcp_get_code":{"code_sha256":"b16fc41e81a03e71"}},{"arxiv_id":"2305.14907","paper":"/paper/coverage-based-example-selection-for-in","title":"Coverage-based Example Selection for In-Context Learning","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shivanshu-gupta/icl-coverage","path":"src/selector/base.py","file_url":"https://github.com/shivanshu-gupta/icl-coverage/blob/HEAD/src/selector/base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4390839db3bfd07d","mcp_get_code":{"code_sha256":"4390839db3bfd07d"}},{"arxiv_id":"2204.11714","paper":"/paper/the-causal-news-corpus-annotating-causal","title":"The Causal News Corpus: Annotating Causal Relations in Event Sentences from News","date":"2022-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tanfiona/causalnewscorpus","path":"curation/subtask2.py","file_url":"https://github.com/tanfiona/causalnewscorpus/blob/HEAD/curation/subtask2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"2404dcb4ab95c45d","mcp_get_code":{"code_sha256":"2404dcb4ab95c45d"}},{"arxiv_id":"1905.04616","paper":"/paper/viznet-towards-a-large-scale-visualization","title":"VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository","date":"2019-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mitmedialab/viznet","path":"experiment/sample_CQQ_specs_with_data.py","file_url":"https://github.com/mitmedialab/viznet/blob/HEAD/experiment/sample_CQQ_specs_with_data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"48622d938ff1498d","mcp_get_code":{"code_sha256":"48622d938ff1498d"}}]}