{"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/extract-answer-number","entry":"extract_answer_number","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":9,"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":7,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":9,"n_places_pointer_only":1,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"2507.05158","paper":null,"title":"arXiv:2507.05158","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"chili-lab/InfoSteer","path":"compute_metrics.py","file_url":"https://github.com/chili-lab/InfoSteer/blob/HEAD/compute_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"471cb6e15f48b1fa","mcp_get_code":{"code_sha256":"471cb6e15f48b1fa"}},{"arxiv_id":"2502.04780","paper":"/paper/sirius-self-improving-multi-agent-systems-via","title":"SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning","date":"2025-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zou-group/sirius","path":"libs/data_loader.py","file_url":"https://github.com/zou-group/sirius/blob/HEAD/libs/data_loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"729efb31374ad186","mcp_get_code":{"code_sha256":"729efb31374ad186"}},{"arxiv_id":"2501.17433","paper":"/paper/virus-harmful-fine-tuning-attack-for-large","title":"Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation","date":"2025-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"git-disl/virus","path":"gsm8k/pred_eval.py","file_url":"https://github.com/git-disl/virus/blob/HEAD/gsm8k/pred_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c9b7e712eaf8afe1","mcp_get_code":{"code_sha256":"c9b7e712eaf8afe1"}},{"arxiv_id":"2409.18169","paper":"/paper/harmful-fine-tuning-attacks-and-defenses-for","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"git-disl/booster","path":"gsm8k/pred_eval.py","file_url":"https://github.com/git-disl/booster/blob/HEAD/gsm8k/pred_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c9b7e712eaf8afe1","mcp_get_code":{"code_sha256":"c9b7e712eaf8afe1"}},{"arxiv_id":"2408.09600","paper":"/paper/antidote-post-fine-tuning-safety-alignment","title":"Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning","date":"2024-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"git-disl/lisa","path":"gsm8k/pred_eval.py","file_url":"https://github.com/git-disl/lisa/blob/HEAD/gsm8k/pred_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c9b7e712eaf8afe1","mcp_get_code":{"code_sha256":"c9b7e712eaf8afe1"}},{"arxiv_id":"2403.13187","paper":"/paper/evolutionary-optimization-of-model-merging","title":"Evolutionary Optimization of Model Merging Recipes","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sakanaai/evolutionary-model-merge","path":"evomerge/eval/ja_mgsm.py","file_url":"https://github.com/sakanaai/evolutionary-model-merge/blob/HEAD/evomerge/eval/ja_mgsm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e193a4012af89dcf","mcp_get_code":{"code_sha256":"e193a4012af89dcf"}},{"arxiv_id":"2403.01165","paper":"/paper/star-constraint-lora-with-dynamic-active","title":"STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models","date":"2024-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"callanwu/star","path":"src/utils.py","file_url":"https://github.com/callanwu/star/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b5fa3dd31bc0ce52","mcp_get_code":{"code_sha256":"b5fa3dd31bc0ce52"}},{"arxiv_id":"2310.08659","paper":"/paper/loftq-lora-fine-tuning-aware-quantization-for","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yxli2123/loftq","path":"test_gsm8k.py","file_url":"https://github.com/yxli2123/loftq/blob/HEAD/test_gsm8k.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61d9388cf15f428e","mcp_get_code":{"code_sha256":"61d9388cf15f428e"}},{"arxiv_id":"2025.findings-acl.1225","paper":null,"title":"arXiv:2025.findings-acl.1225","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HieuNT91/attention_pruning","path":"src/gsm8k_utils.py","file_url":"https://github.com/HieuNT91/attention_pruning/blob/HEAD/src/gsm8k_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4fc5125ed17db0eb","mcp_get_code":{"code_sha256":"4fc5125ed17db0eb"}}]}