{"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/symmetrize","entry":"symmetrize","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":19,"n_papers_ran":10,"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":13,"n_samples_ran":5,"n_samples_fingerprinted":5,"n_places":19,"n_places_pointer_only":2,"by_status":{"ran_honours":1,"ran_violates":2,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":8},"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":"2607.23518","paper":"/paper/arxiv-2607-23518","title":"Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"caohengyuan/Chamaileon","path":"colabdesign/esm_msa/modules.py","file_url":"https://github.com/caohengyuan/Chamaileon/blob/HEAD/colabdesign/esm_msa/modules.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":"33dd253d7169953c","mcp_get_code":{"code_sha256":"33dd253d7169953c"}},{"arxiv_id":"2606.18703","paper":"/paper/arxiv-2606-18703","title":"Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"facebookresearch/esm","path":"esm/modules.py","file_url":"https://github.com/facebookresearch/esm/blob/HEAD/esm/modules.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b385be9826c4a8b3","mcp_get_code":{"code_sha256":"b385be9826c4a8b3"}},{"arxiv_id":"2606.17995","paper":"/paper/arxiv-2606-17995","title":"Differential Privacy of Gaussian Process Posterior Sampling","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"tmaciazek/gaussian_process_dp","path":"prior_average_gridsearch_exp_excursion_set_bce_L_release.py","file_url":"https://github.com/tmaciazek/gaussian_process_dp/blob/HEAD/prior_average_gridsearch_exp_excursion_set_bce_L_release.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77a789f8d30dc5ed","mcp_get_code":{"code_sha256":"77a789f8d30dc5ed"}},{"arxiv_id":"2606.15442","paper":"/paper/arxiv-2606-15442","title":"The Reverse Telescoping Coordinate System for Positive Definite Matrices: Geometry, Computation, and Generative Modeling","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"anindyabhadra/RT_SPD","path":"basic_rt/rt_core.py","file_url":"https://github.com/anindyabhadra/RT_SPD/blob/HEAD/basic_rt/rt_core.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0fb7c31d032456c9","mcp_get_code":{"code_sha256":"0fb7c31d032456c9"}},{"arxiv_id":"2605.18106","paper":"/paper/arxiv-2605-18106","title":"Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"timlautk/equivariant_optimizers","path":"optim/leftpolargrad.py","file_url":"https://github.com/timlautk/equivariant_optimizers/blob/HEAD/optim/leftpolargrad.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3fba78841d11b568","mcp_get_code":{"code_sha256":"3fba78841d11b568"}},{"arxiv_id":"2605.11189","paper":"/paper/arxiv-2605-11189","title":"Deep Learning for Protein Complex Prediction and Design by","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"zw2x/glinter","path":"glinter/esm_embed/modules.py","file_url":"https://github.com/zw2x/glinter/blob/HEAD/glinter/esm_embed/modules.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b385be9826c4a8b3","mcp_get_code":{"code_sha256":"b385be9826c4a8b3"}},{"arxiv_id":"2604.15742","paper":"/paper/arxiv-2604-15742","title":"Collective Kernel EFT for Pre-activation ResNets: Exact Block Law and Finite Validity Window of G-only Closure","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"kavvase/resnet_eft","path":"src/resnet_eft/backend.py","file_url":"https://github.com/kavvase/resnet_eft/blob/HEAD/src/resnet_eft/backend.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7178642fe015d295","mcp_get_code":{"code_sha256":"7178642fe015d295"}},{"arxiv_id":"2602.01186","paper":"/paper/arxiv-2602-01186","title":"The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"FabioTur-dev/One-Shot-FL","path":"server/GH_OFL_server.py","file_url":"https://github.com/FabioTur-dev/One-Shot-FL/blob/HEAD/server/GH_OFL_server.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6613c4330f785f3b","mcp_get_code":{"code_sha256":"6613c4330f785f3b"}},{"arxiv_id":"2408.11363","paper":"/paper/proteingpt-multimodal-llm-for-protein","title":"ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding","date":"2024-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ProteinGPT/ProteinGPT","path":"src/esm/modules.py","file_url":"https://github.com/ProteinGPT/ProteinGPT/blob/HEAD/src/esm/modules.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b385be9826c4a8b3","mcp_get_code":{"code_sha256":"b385be9826c4a8b3"}},{"arxiv_id":"2406.10391","paper":"/paper/beacon-benchmark-for-comprehensive-rna-tasks","title":"BEACON: Benchmark for Comprehensive RNA Tasks and Language Models","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"terry-r123/rnabenchmark","path":"model/rnalm/modeling_rnalm.py","file_url":"https://github.com/terry-r123/rnabenchmark/blob/HEAD/model/rnalm/modeling_rnalm.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b385be9826c4a8b3","mcp_get_code":{"code_sha256":"b385be9826c4a8b3"}},{"arxiv_id":"2306.10161","paper":"/paper/building-the-bridge-of-schrodinger-a-1","title":"Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark","date":"2023-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ngushchin/entropicotbenchmark","path":"benchmark/distributions.py","file_url":"https://github.com/ngushchin/entropicotbenchmark/blob/HEAD/benchmark/distributions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c1eb471d75746958","mcp_get_code":{"code_sha256":"c1eb471d75746958"}},{"arxiv_id":"2209.06861","paper":"/paper/landmark-free-statistical-shape-modeling-via","title":"Landmark-free Statistical Shape Modeling via Neural Flow Deformations","date":"2022-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davecasp/flowssm","path":"shapeflow/layers/deformation_layer.py","file_url":"https://github.com/davecasp/flowssm/blob/HEAD/shapeflow/layers/deformation_layer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"30748540875d14ec","mcp_get_code":{"code_sha256":"30748540875d14ec"}},{"arxiv_id":"2206.06583","paper":"/paper/exploring-evolution-based-free-protein","title":"Exploring evolution-aware & -free protein language models as protein function predictors","date":"2022-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"elttaes/revisiting-plms","path":"ESM-1b_Pretrain/esm/modules.py","file_url":"https://github.com/elttaes/revisiting-plms/blob/HEAD/ESM-1b_Pretrain/esm/modules.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b385be9826c4a8b3","mcp_get_code":{"code_sha256":"b385be9826c4a8b3"}},{"arxiv_id":"2201.12245","paper":"/paper/wasserstein-iterative-networks-for-barycenter","title":"Wasserstein Iterative Networks for Barycenter Estimation","date":"2022-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iamalexkorotin/wassersteiniterativenetworks","path":"src/bar_benchmark.py","file_url":"https://github.com/iamalexkorotin/wassersteiniterativenetworks/blob/HEAD/src/bar_benchmark.py","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"06fde2e68ab125fa","mcp_get_code":{"code_sha256":"06fde2e68ab125fa"}},{"arxiv_id":"2106.02584","paper":"/paper/self-attention-between-datapoints-going","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","date":"2021-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oatml-markslab/proteinnpt","path":"proteinnpt/utils/esm/modules.py","file_url":"https://github.com/oatml-markslab/proteinnpt/blob/HEAD/proteinnpt/utils/esm/modules.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b385be9826c4a8b3","mcp_get_code":{"code_sha256":"b385be9826c4a8b3"}},{"arxiv_id":"2106.01954","paper":"/paper/do-neural-optimal-transport-solvers-work-a","title":"Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iamalexkorotin/Wasserstein2Barycenters","path":"src/benchmarks.py","file_url":"https://github.com/iamalexkorotin/Wasserstein2Barycenters/blob/HEAD/src/benchmarks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c1eb471d75746958","mcp_get_code":{"code_sha256":"c1eb471d75746958"}},{"arxiv_id":"2104.03113","paper":"/paper/scaling-scaling-laws-with-board-games","title":"Scaling Scaling Laws with Board Games","date":"2021-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andyljones/boardlaw","path":"boardlaw/elos.py","file_url":"https://github.com/andyljones/boardlaw/blob/HEAD/boardlaw/elos.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"834bf0198db420c4","mcp_get_code":{"code_sha256":"834bf0198db420c4"}},{"arxiv_id":"2006.16908","paper":"/paper/mdp-homomorphic-networks-group-symmetries-in","title":"MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning","date":"2020-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ElisevanderPol/symmetrizer","path":"symmetrizer/ops/ops.py","file_url":"https://github.com/ElisevanderPol/symmetrizer/blob/HEAD/symmetrizer/ops/ops.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"772c37cc22f9d339","mcp_get_code":{"code_sha256":"772c37cc22f9d339"}},{"arxiv_id":"1612.00847","paper":"/paper/data-driven-interpretable-photometric","title":"Data-driven, interpretable photometric redshifts trained on heterogeneous and unrepresentative data","date":null,"month_inferred_from_arxiv_id":"2016-12","title_source":"archive","repo":"ixkael/Delight","path":"delight/utils.py","file_url":"https://github.com/ixkael/Delight/blob/HEAD/delight/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e546f98e1af5673c","mcp_get_code":{"code_sha256":"e546f98e1af5673c"}}]}