{"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/load-benchmark","entry":"load_benchmark","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":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":6,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":4},"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":"2608.21430","paper":"/paper/arxiv-2608-21430","title":"Evaluating Multimodal Narrative Understanding of Popular Hollywood Films","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"bamman-group/chnb","path":"util/benchmark.py","file_url":"https://github.com/bamman-group/chnb/blob/HEAD/util/benchmark.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"13188fd1f5c2dff7","mcp_get_code":{"code_sha256":"13188fd1f5c2dff7"}},{"arxiv_id":"2608.06305","paper":"/paper/arxiv-2608-06305","title":"Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"twospoon/READ","path":"read_eval/runner.py","file_url":"https://github.com/twospoon/READ/blob/HEAD/read_eval/runner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ffbeca37f7514969","mcp_get_code":{"code_sha256":"ffbeca37f7514969"}},{"arxiv_id":"2607.20558","paper":"/paper/arxiv-2607-20558","title":"StabilityBench: a Framework for Benchmarking Instability in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ekmpa/StabilityBench","path":"utils/bench_loaders.py","file_url":"https://github.com/ekmpa/StabilityBench/blob/HEAD/utils/bench_loaders.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e997c1a44311802c","mcp_get_code":{"code_sha256":"e997c1a44311802c"}},{"arxiv_id":"2409.15254","paper":"/paper/archon-an-architecture-search-framework-for","title":"Archon: An Architecture Search Framework for Inference-Time Techniques","date":"2024-09-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scalingintelligence/archon","path":"src/archon/benchmarks/benchmarks.py","file_url":"https://github.com/scalingintelligence/archon/blob/HEAD/src/archon/benchmarks/benchmarks.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":"4a737f68f1c25eef","mcp_get_code":{"code_sha256":"4a737f68f1c25eef"}},{"arxiv_id":"2408.04810","paper":"/paper/unibench-visual-reasoning-requires-rethinking","title":"UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling","date":"2024-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/unibench","path":"unibench/benchmarks_zoo/registry.py","file_url":"https://github.com/facebookresearch/unibench/blob/HEAD/unibench/benchmarks_zoo/registry.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d303d39673c61784","mcp_get_code":{"code_sha256":"d303d39673c61784"}},{"arxiv_id":"2304.10978","paper":"/paper/balancing-simulation-based-inference-for","title":"Balancing Simulation-based Inference for Conservative Posteriors","date":"2023-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adelau/balancing_sbi","path":"src/balancing_sbi/benchmarks/benchmark_util.py","file_url":"https://github.com/adelau/balancing_sbi/blob/HEAD/src/balancing_sbi/benchmarks/benchmark_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"448be4f2ce30078a","mcp_get_code":{"code_sha256":"448be4f2ce30078a"}}]}