{"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/get-leaf-modules-with-grad","entry":"get_leaf_modules_with_grad","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":1,"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":4,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2503.00555","paper":"/paper/2503-00555","title":"Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable","date":"2025-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"git-disl/safety-tax","path":"train/trainer.py","file_url":"https://github.com/git-disl/safety-tax/blob/HEAD/train/trainer.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":"88c8a24923c625a1","mcp_get_code":{"code_sha256":"88c8a24923c625a1"}},{"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":"trainer.py","file_url":"https://github.com/git-disl/virus/blob/HEAD/trainer.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":"88c8a24923c625a1","mcp_get_code":{"code_sha256":"88c8a24923c625a1"}},{"arxiv_id":"2410.09760","paper":"/paper/targeted-vaccine-safety-alignment-for-large","title":"Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation","date":"2024-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lslland/t-vaccine","path":"trainer.py","file_url":"https://github.com/lslland/t-vaccine/blob/HEAD/trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"582b8f13a818c0e2","mcp_get_code":{"code_sha256":"582b8f13a818c0e2"}},{"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":"trainer.py","file_url":"https://github.com/git-disl/booster/blob/HEAD/trainer.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":"88c8a24923c625a1","mcp_get_code":{"code_sha256":"88c8a24923c625a1"}},{"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":"trainer.py","file_url":"https://github.com/git-disl/lisa/blob/HEAD/trainer.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":"33c80aca0e2e7b3f","mcp_get_code":{"code_sha256":"33c80aca0e2e7b3f"}},{"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/vaccine","path":"trainer.py","file_url":"https://github.com/git-disl/vaccine/blob/HEAD/trainer.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":"cb8c9e314f3db1ed","mcp_get_code":{"code_sha256":"cb8c9e314f3db1ed"}}]}