{"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/format-options","entry":"format_options","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":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":6,"n_samples_ran":4,"n_samples_fingerprinted":3,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"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":"2605.05973","paper":"/paper/arxiv-2605-05973","title":"Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"jznmsl/siren","path":"03_analysis_scripts/build_tensor.py","file_url":"https://github.com/jznmsl/siren/blob/HEAD/03_analysis_scripts/build_tensor.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"20ef5b27be91837f","mcp_get_code":{"code_sha256":"20ef5b27be91837f"}},{"arxiv_id":"2605.05973","paper":"/paper/arxiv-2605-05973","title":"Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"jznmsl/siren","path":"03_analysis_scripts/study_e_dspy_randsearch_law.py","file_url":"https://github.com/jznmsl/siren/blob/HEAD/03_analysis_scripts/study_e_dspy_randsearch_law.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f9f073eb2c03fd6","mcp_get_code":{"code_sha256":"7f9f073eb2c03fd6"}},{"arxiv_id":"2601.22162","paper":"/paper/arxiv-2601-22162","title":"UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"aifinlab/UniFinEval","path":"evaluate_py/prompts.py","file_url":"https://github.com/aifinlab/UniFinEval/blob/HEAD/evaluate_py/prompts.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":"15d98731e128c61f","mcp_get_code":{"code_sha256":"15d98731e128c61f"}},{"arxiv_id":"2505.22823","paper":"/paper/self-critique-and-refinement-for-faithful","title":"Self-Critique and Refinement for Faithful Natural Language Explanations","date":"2025-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ymwangv/SR-NLE","path":"src/modules/refinement_generator.py","file_url":"https://github.com/ymwangv/SR-NLE/blob/HEAD/src/modules/refinement_generator.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":"93b536159e7d6e60","mcp_get_code":{"code_sha256":"93b536159e7d6e60"}},{"arxiv_id":"2401.01614","paper":"/paper/gpt-4v-ision-is-a-generalist-web-agent-if","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","date":"2024-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"osu-nlp-group/seeact","path":"seeact_package/seeact/data_utils/format_prompt_utils.py","file_url":"https://github.com/osu-nlp-group/seeact/blob/HEAD/seeact_package/seeact/data_utils/format_prompt_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4e2d871fbcfa490d","mcp_get_code":{"code_sha256":"4e2d871fbcfa490d"}},{"arxiv_id":"2304.03442","paper":"/paper/generative-agents-interactive-simulacra-of","title":"Generative Agents: Interactive Simulacra of Human Behavior","date":"2023-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jina-ai/thinkgpt","path":"thinkgpt/gpt_select.py","file_url":"https://github.com/jina-ai/thinkgpt/blob/HEAD/thinkgpt/gpt_select.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":"d52b33b77d35e4ed","mcp_get_code":{"code_sha256":"d52b33b77d35e4ed"}}]}