{"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/prepare-prompt","entry":"prepare_prompt","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":8,"n_papers_ran":5,"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":5,"n_samples_fingerprinted":3,"n_places":8,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":2,"unverified":3},"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":"2608.09209","paper":"/paper/arxiv-2608-09209","title":"UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"chidaksh/spurious_mitigator","path":"src/civil_comments/spurfinder.py","file_url":"https://github.com/chidaksh/spurious_mitigator/blob/HEAD/src/civil_comments/spurfinder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"995d99f342d7b16d","mcp_get_code":{"code_sha256":"995d99f342d7b16d"}},{"arxiv_id":"2607.00605","paper":"/paper/arxiv-2607-00605","title":"Auditing Forgetting in Limited Memory Language Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"raeesiarya/LMLMAudit","path":"src/lmlm-audit/run_audit.py","file_url":"https://github.com/raeesiarya/LMLMAudit/blob/HEAD/src/lmlm-audit/run_audit.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7a44c18a1cf3b39","mcp_get_code":{"code_sha256":"f7a44c18a1cf3b39"}},{"arxiv_id":"2603.15892","paper":"/paper/arxiv-2603-15892","title":"Temporal Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"terrierteam/temporal_conflicts","path":"fact_mutability/bkp_inference.py","file_url":"https://github.com/terrierteam/temporal_conflicts/blob/HEAD/fact_mutability/bkp_inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"087a8df73a06c291","mcp_get_code":{"code_sha256":"087a8df73a06c291"}},{"arxiv_id":"2507.17539","paper":null,"title":"arXiv:2507.17539","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"MeteorElf/FundusExpert","path":"src/eval/eval_api/call_api.py","file_url":"https://github.com/MeteorElf/FundusExpert/blob/HEAD/src/eval/eval_api/call_api.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":"c0da0a953e4ec70f","mcp_get_code":{"code_sha256":"c0da0a953e4ec70f"}},{"arxiv_id":"2501.15140","paper":"/paper/analyzing-and-boosting-the-power-of-fine","title":"Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models","date":"2025-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pku-icst-mipl/finedefics_iclr2025","path":"FOCI-Benchmark/benchmark/model/model.py","file_url":"https://github.com/pku-icst-mipl/finedefics_iclr2025/blob/HEAD/FOCI-Benchmark/benchmark/model/model.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":"97922863aafd3d20","mcp_get_code":{"code_sha256":"97922863aafd3d20"}},{"arxiv_id":"2406.11171","paper":"/paper/sugarcrepe-dataset-vision-language-model","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Sri-Harsha/scpp","path":"generate_sugarcrepe_plus-mistral.py","file_url":"https://github.com/Sri-Harsha/scpp/blob/HEAD/generate_sugarcrepe_plus-mistral.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cd7870b8098d6090","mcp_get_code":{"code_sha256":"cd7870b8098d6090"}},{"arxiv_id":"2403.00843","paper":"/paper/enhancing-long-term-recommendation-with-bi","title":"Large Language Models are Learnable Planners for Long-Term Recommendation","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jizhi-zhang/billp","path":"generation_rec_agents.py","file_url":"https://github.com/jizhi-zhang/billp/blob/HEAD/generation_rec_agents.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"709bc4884360648d","mcp_get_code":{"code_sha256":"709bc4884360648d"}},{"arxiv_id":"2310.13332","paper":"/paper/democratizing-reasoning-ability-tailored","title":"Democratizing Reasoning Ability: Tailored Learning from Large Language Model","date":"2023-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Raibows/Learn-to-Reason","path":"preprocessors.py","file_url":"https://github.com/Raibows/Learn-to-Reason/blob/HEAD/preprocessors.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"838de4f52529652c","mcp_get_code":{"code_sha256":"838de4f52529652c"}}]}