{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/gradient-normalizers","entry":"gradient_normalizers","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":17,"n_papers_ran":9,"n_papers_ran_no_instrument_failure":8,"n_papers_ran_instrument_only":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":11,"n_samples_ran":8,"n_samples_constructed":0,"n_samples_ran_checked":7,"n_samples_instrument":1,"n_samples_unverified":3,"n_samples_fingerprinted":1,"n_places":17,"n_places_pointer_only":9,"n_places_pointer_only_link_open":2,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":7,"unverified":3},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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":"2605.10047","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-10047","title":"Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"tongzixin716716/Inverse-Loss-Reweighting","path":"min_norm_solvers.py","file_url":"https://github.com/tongzixin716716/Inverse-Loss-Reweighting/blob/HEAD/min_norm_solvers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, tongzixin716716/Inverse-Loss-Reweighting when it was checked","code_sha256":"9c12115c283ca5af","code_sha256_prefix":"9c12115c283ca5af","mcp_get_code":{"code_sha256":"9c12115c283ca5af"}},{"arxiv_id":"2412.01773","arxiv_id_is_arxiv":true,"paper":"/paper/ferero-a-flexible-framework-for-preference","title":"FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning","date":"2024-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lisha-chen/ferero","path":"multiMNIST/ferero_solvers.py","file_url":"https://github.com/lisha-chen/ferero/blob/HEAD/multiMNIST/ferero_solvers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, lisha-chen/ferero when it was checked","code_sha256":"fe93d608f889f824","code_sha256_prefix":"fe93d608f889f824","mcp_get_code":{"code_sha256":"fe93d608f889f824"}},{"arxiv_id":"2408.11104","arxiv_id_is_arxiv":true,"paper":"/paper/config-towards-conflict-free-training-of","title":"ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks","date":"2024-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tum-pbs/ConFIG","path":"experiments/MTL/methods/min_norm_solvers.py","file_url":"https://github.com/tum-pbs/ConFIG/blob/HEAD/experiments/MTL/methods/min_norm_solvers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2d5ff72859c98459","code_sha256_prefix":"2d5ff72859c98459","mcp_get_code":{"code_sha256":"2d5ff72859c98459"}},{"arxiv_id":"2407.05082","arxiv_id_is_arxiv":true,"paper":"/paper/dmtg-one-shot-differentiable-multi-task","title":"DMTG: One-Shot Differentiable Multi-Task Grouping","date":"2024-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ethanygao/DMTG","path":"models/ozan_min_norm_solvers.py","file_url":"https://github.com/ethanygao/DMTG/blob/HEAD/models/ozan_min_norm_solvers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ethanygao/DMTG when it was checked","code_sha256":"fe93d608f889f824","code_sha256_prefix":"fe93d608f889f824","mcp_get_code":{"code_sha256":"fe93d608f889f824"}},{"arxiv_id":"2407.04493","arxiv_id_is_arxiv":true,"paper":"/paper/proud-pareto-guided-diffusion-model-for-multi","title":"PROUD: PaRetO-gUided Diffusion Model for Multi-objective Generation","date":"2024-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EvaFlower/Pareto-guided-diffusion-model","path":"CIFAR10/models/min_norm_solver.py","file_url":"https://github.com/EvaFlower/Pareto-guided-diffusion-model/blob/HEAD/CIFAR10/models/min_norm_solver.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, EvaFlower/Pareto-guided-diffusion-model when it was checked","code_sha256":"736b65e3f76a3dfd","code_sha256_prefix":"736b65e3f76a3dfd","mcp_get_code":{"code_sha256":"736b65e3f76a3dfd"}},{"arxiv_id":"2402.15638","arxiv_id_is_arxiv":true,"paper":"/paper/fair-resource-allocation-in-multi-task","title":"Fair Resource Allocation in Multi-Task Learning","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"optmn-lab/fairgrad","path":"methods/min_norm_solvers.py","file_url":"https://github.com/optmn-lab/fairgrad/blob/HEAD/methods/min_norm_solvers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2d5ff72859c98459","code_sha256_prefix":"2d5ff72859c98459","mcp_get_code":{"code_sha256":"2d5ff72859c98459"}},{"arxiv_id":"2312.07401","arxiv_id_is_arxiv":true,"paper":"/paper/on-diverse-preferences-for-large-language","title":"On Diversified Preferences of Large Language Model Alignment","date":"2023-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dunzeng/more","path":"min_norm_solvers.py","file_url":"https://github.com/dunzeng/more/blob/HEAD/min_norm_solvers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dunzeng/more when it was checked","code_sha256":"1b7ba4d146c226aa","code_sha256_prefix":"1b7ba4d146c226aa","mcp_get_code":{"code_sha256":"1b7ba4d146c226aa"}},{"arxiv_id":"2310.00800","arxiv_id_is_arxiv":true,"paper":null,"title":"arXiv:2310.00800","date":null,"month_inferred_from_arxiv_id":"2023-10","title_source":null,"repo":"jumxglhf/ParetoGNN","path":"src/min_norm_solvers.py","file_url":"https://github.com/jumxglhf/ParetoGNN/blob/HEAD/src/min_norm_solvers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"31d9547f7a6e800c","code_sha256_prefix":"31d9547f7a6e800c","mcp_get_code":{"code_sha256":"31d9547f7a6e800c"}},{"arxiv_id":"2305.18409","arxiv_id_is_arxiv":true,"paper":"/paper/direction-oriented-multi-objective-learning","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","date":"2023-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-opt-lab/sdmgrad","path":"methods/min_norm_solvers.py","file_url":"https://github.com/ml-opt-lab/sdmgrad/blob/HEAD/methods/min_norm_solvers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2d5ff72859c98459","code_sha256_prefix":"2d5ff72859c98459","mcp_get_code":{"code_sha256":"2d5ff72859c98459"}},{"arxiv_id":"2209.12241","arxiv_id_is_arxiv":true,"paper":"/paper/exploring-example-influence-in-continual","title":"Exploring Example Influence in Continual Learning","date":"2022-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sssunqing/example_influence_cl","path":"min_norm_solvers.py","file_url":"https://github.com/sssunqing/example_influence_cl/blob/HEAD/min_norm_solvers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sssunqing/example_influence_cl when it was checked","code_sha256":"f776c4e34e34039d","code_sha256_prefix":"f776c4e34e34039d","mcp_get_code":{"code_sha256":"f776c4e34e34039d"}},{"arxiv_id":"2206.01934","arxiv_id_is_arxiv":true,"paper":"/paper/stochastic-multiple-target-sampling-gradient","title":"Stochastic Multiple Target Sampling Gradient Descent","date":"2022-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"isl-org/MultiObjectiveOptimization","path":"multi_task/min_norm_solvers.py","file_url":"https://github.com/isl-org/MultiObjectiveOptimization/blob/HEAD/multi_task/min_norm_solvers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"faa96c0ba935fc57","code_sha256_prefix":"faa96c0ba935fc57","mcp_get_code":{"code_sha256":"faa96c0ba935fc57"}},{"arxiv_id":"2202.01017","arxiv_id_is_arxiv":true,"paper":"/paper/multi-task-learning-as-a-bargaining-game","title":"Multi-Task Learning as a Bargaining Game","date":"2022-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AvivNavon/nash-mtl","path":"methods/min_norm_solvers.py","file_url":"https://github.com/AvivNavon/nash-mtl/blob/HEAD/methods/min_norm_solvers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, AvivNavon/nash-mtl when it was checked","code_sha256":"def129ab34b9f0f8","code_sha256_prefix":"def129ab34b9f0f8","mcp_get_code":{"code_sha256":"def129ab34b9f0f8"}},{"arxiv_id":"2103.13392","arxiv_id_is_arxiv":true,"paper":"/paper/efficient-multi-objective-optimization-for","title":"Scalable Pareto Front Approximation for Deep Multi-Objective Learning","date":"2021-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruchtem/cosmos","path":"multi_objective/min_norm_solvers.py","file_url":"https://github.com/ruchtem/cosmos/blob/HEAD/multi_objective/min_norm_solvers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"466422ddd5626f12","code_sha256_prefix":"466422ddd5626f12","mcp_get_code":{"code_sha256":"466422ddd5626f12"}},{"arxiv_id":"2007.06889","arxiv_id_is_arxiv":true,"paper":"/paper/knowledge-distillation-for-multi-task","title":"Knowledge Distillation for Multi-task Learning","date":"2020-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VICO-UoE/KD4MTL","path":"mgda/min_norm_solvers.py","file_url":"https://github.com/VICO-UoE/KD4MTL/blob/HEAD/mgda/min_norm_solvers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f7316cdac3b90bc6","code_sha256_prefix":"f7316cdac3b90bc6","mcp_get_code":{"code_sha256":"f7316cdac3b90bc6"}},{"arxiv_id":"1912.12854","arxiv_id_is_arxiv":true,"paper":"/paper/pareto-multi-task-learning-1","title":"Pareto Multi-Task Learning","date":"2019-12-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xi-L/ParetoMTL","path":"multiMNIST/min_norm_solvers.py","file_url":"https://github.com/Xi-L/ParetoMTL/blob/HEAD/multiMNIST/min_norm_solvers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lisha-chen/ferero, and GitHub detected no licence in that repository when it was checked","code_sha256":"fe93d608f889f824","code_sha256_prefix":"fe93d608f889f824","mcp_get_code":{"code_sha256":"fe93d608f889f824"}},{"arxiv_id":"1810.04650","arxiv_id_is_arxiv":true,"paper":"/paper/multi-task-learning-as-multi-objective","title":"Multi-Task Learning as Multi-Objective Optimization","date":"2018-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IntelVCL/MultiObjectiveOptimization","path":"multi_task/min_norm_solvers.py","file_url":"https://github.com/IntelVCL/MultiObjectiveOptimization/blob/HEAD/multi_task/min_norm_solvers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"faa96c0ba935fc57","code_sha256_prefix":"faa96c0ba935fc57","mcp_get_code":{"code_sha256":"faa96c0ba935fc57"}},{"arxiv_id":"aaai_33460","arxiv_id_is_arxiv":false,"paper":null,"title":"AAAI id aaai_33460","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"persai-lab/2025-NANSKoBeM","path":"utils/min_norm_solvers.py","file_url":"https://github.com/persai-lab/2025-NANSKoBeM/blob/HEAD/utils/min_norm_solvers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lisha-chen/ferero, and GitHub detected no licence in that repository when it was checked","code_sha256":"fe93d608f889f824","code_sha256_prefix":"fe93d608f889f824","mcp_get_code":{"code_sha256":"fe93d608f889f824"}}],"record_sha256":"a4b97aa534efb571a507129167a821242d75abece8330571778ef00272a62fbc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}