{"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-env","entry":"load_env","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":8,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"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":"2609.03047","paper":"/paper/arxiv-2609-03047","title":"SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"mjbommar/shelf-benchmark","path":"src/shelf/config/env.py","file_url":"https://github.com/mjbommar/shelf-benchmark/blob/HEAD/src/shelf/config/env.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"943cbcdbc4ab245e","mcp_get_code":{"code_sha256":"943cbcdbc4ab245e"}},{"arxiv_id":"2608.25218","paper":"/paper/arxiv-2608-25218","title":"TURNBENCH: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"SesameAILabs/turnbench","path":"turnbench/build_eot_validation.py","file_url":"https://github.com/SesameAILabs/turnbench/blob/HEAD/turnbench/build_eot_validation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0624cb8afa73c30c","mcp_get_code":{"code_sha256":"0624cb8afa73c30c"}},{"arxiv_id":"2608.25218","paper":"/paper/arxiv-2608-25218","title":"TURNBENCH: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"SesameAILabs/turnbench","path":"turnbench/make_splits.py","file_url":"https://github.com/SesameAILabs/turnbench/blob/HEAD/turnbench/make_splits.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce524303f86102c9","mcp_get_code":{"code_sha256":"ce524303f86102c9"}},{"arxiv_id":"2608.25218","paper":"/paper/arxiv-2608-25218","title":"TURNBENCH: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"SesameAILabs/turnbench","path":"turnbench/analysis/analyze.py","file_url":"https://github.com/SesameAILabs/turnbench/blob/HEAD/turnbench/analysis/analyze.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14f8fff951c0239d","mcp_get_code":{"code_sha256":"14f8fff951c0239d"}},{"arxiv_id":"2608.07508","paper":"/paper/arxiv-2608-07508","title":"JaleesBench: Are AI Assistants Good Spiritual Company?","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"iaser-ai/jaleesbench","path":"jaleesbench/jaleesbench/collect.py","file_url":"https://github.com/iaser-ai/jaleesbench/blob/HEAD/jaleesbench/jaleesbench/collect.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f94c789f9001e97b","mcp_get_code":{"code_sha256":"f94c789f9001e97b"}},{"arxiv_id":"2606.01204","paper":"/paper/arxiv-2606-01204","title":"Implicit Geographic Inference in LLM Medical Triage: Language-Driven Disparities in Emergency Recommendations","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"wongqihan/ai-behavioral-experiments","path":"customer-refund/run_experiment.py","file_url":"https://github.com/wongqihan/ai-behavioral-experiments/blob/HEAD/customer-refund/run_experiment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"880b98e0cc23dd7a","mcp_get_code":{"code_sha256":"880b98e0cc23dd7a"}},{"arxiv_id":"2310.18409","paper":"/paper/state-action-similarity-based-representations-1","title":"State-Action Similarity-Based Representations for Off-Policy Evaluation","date":"2023-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Badger-RL/ROPE","path":"utils.py","file_url":"https://github.com/Badger-RL/ROPE/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c288d13b595ca6a6","mcp_get_code":{"code_sha256":"c288d13b595ca6a6"}},{"arxiv_id":"2007.15543","paper":"/paper/pixl2r-guiding-reinforcement-learning-using","title":"PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards","date":"2020-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prasoongoyal/PixL2R","path":"src/rl/train_policy.py","file_url":"https://github.com/prasoongoyal/PixL2R/blob/HEAD/src/rl/train_policy.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9a2bb35a6449803","mcp_get_code":{"code_sha256":"d9a2bb35a6449803"}}]}