{"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/finetune","entry":"finetune","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":0,"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":5,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":5},"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":"2604.12479","paper":"/paper/arxiv-2604-12479","title":"Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"nrimsky/CAA","path":"finetune_llama.py","file_url":"https://github.com/nrimsky/CAA/blob/HEAD/finetune_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"283eacb9f62af715","mcp_get_code":{"code_sha256":"283eacb9f62af715"}},{"arxiv_id":"2403.17188","paper":"/paper/lotus-evasive-and-resilient-backdoor-attacks","title":"LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"megum1/lotus","path":"misc/mitigation.py","file_url":"https://github.com/megum1/lotus/blob/HEAD/misc/mitigation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87497271d48656a3","mcp_get_code":{"code_sha256":"87497271d48656a3"}},{"arxiv_id":"2305.19726","paper":"/paper/learning-representations-without","title":"Learning Representations without Compositional Assumptions","date":"2023-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tennisonliu/legato","path":"training_utils/train_evaluate.py","file_url":"https://github.com/tennisonliu/legato/blob/HEAD/training_utils/train_evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4ed7ffc371b401df","mcp_get_code":{"code_sha256":"4ed7ffc371b401df"}},{"arxiv_id":"2301.06241","paper":"/paper/beagle-forensics-of-deep-learning-backdoor","title":"BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense","date":"2023-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"megum1/beagle","path":"cifar10/backdoor_removal.py","file_url":"https://github.com/megum1/beagle/blob/HEAD/cifar10/backdoor_removal.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77e08b7f9cbe0290","mcp_get_code":{"code_sha256":"77e08b7f9cbe0290"}},{"arxiv_id":"1909.08174","paper":"/paper/gate-decorator-global-filter-pruning-method","title":"Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks","date":"2019-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"youzhonghui/gate-decorator-pruning","path":"prune/utils.py","file_url":"https://github.com/youzhonghui/gate-decorator-pruning/blob/HEAD/prune/utils.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":"443447da85da3fcc","mcp_get_code":{"code_sha256":"443447da85da3fcc"}}]}