{"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-layers","entry":"get_layers","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":20,"n_papers_ran":3,"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":16,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":20,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":13},"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":"2605.15491","paper":"/paper/arxiv-2605-15491","title":"Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"chenxinrui-tsinghua/LinearPatch","path":"rotate_utils/model_utils.py","file_url":"https://github.com/chenxinrui-tsinghua/LinearPatch/blob/HEAD/rotate_utils/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb59d0a73734e449","mcp_get_code":{"code_sha256":"eb59d0a73734e449"}},{"arxiv_id":"2604.07955","paper":"/paper/arxiv-2604-07955","title":"Rethinking Residual Errors in Compensation-based LLM Quantization","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"list0830/ResComp","path":"fake_quant/model_utils.py","file_url":"https://github.com/list0830/ResComp/blob/HEAD/fake_quant/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb59d0a73734e449","mcp_get_code":{"code_sha256":"eb59d0a73734e449"}},{"arxiv_id":"2602.15902","paper":"/paper/arxiv-2602-15902","title":"Doc-to-LoRA: Learning to Instantly Internalize Contexts","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"SakanaAI/doc-to-lora","path":"src/ctx_to_lora/modeling/text_to_lora.py","file_url":"https://github.com/SakanaAI/doc-to-lora/blob/HEAD/src/ctx_to_lora/modeling/text_to_lora.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb1fa1a3b994be5d","mcp_get_code":{"code_sha256":"eb1fa1a3b994be5d"}},{"arxiv_id":"2602.02546","paper":"/paper/arxiv-2602-02546","title":"D 2 Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"XIANGLONGYAN/D2Quant","path":"d2quant/model_utils.py","file_url":"https://github.com/XIANGLONGYAN/D2Quant/blob/HEAD/d2quant/model_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":"5cfb768c5400311b","mcp_get_code":{"code_sha256":"5cfb768c5400311b"}},{"arxiv_id":"2511.04063","paper":"/paper/arxiv-2511-04063","title":"DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"CAS-CLab/DartQuant","path":"NPU_DartQuant/fake_quant/model_utils.py","file_url":"https://github.com/CAS-CLab/DartQuant/blob/HEAD/NPU_DartQuant/fake_quant/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb59d0a73734e449","mcp_get_code":{"code_sha256":"eb59d0a73734e449"}},{"arxiv_id":"2501.13987","paper":"/paper/ostquant-refining-large-language-model","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","date":"2025-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brotherhappy/ostquant","path":"utils/model_utils.py","file_url":"https://github.com/brotherhappy/ostquant/blob/HEAD/utils/model_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":"402d788d51ddf8ca","mcp_get_code":{"code_sha256":"402d788d51ddf8ca"}},{"arxiv_id":"2411.17525","paper":"/paper/pushing-the-limits-of-large-language-model","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","date":"2024-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"goodevening13/aquakv","path":"aquakv/modelutils.py","file_url":"https://github.com/goodevening13/aquakv/blob/HEAD/aquakv/modelutils.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":"6af39b9342e5f24f","mcp_get_code":{"code_sha256":"6af39b9342e5f24f"}},{"arxiv_id":"2404.00456","paper":"/paper/quarot-outlier-free-4-bit-inference-in","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","date":"2024-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"spcl/quarot","path":"fake_quant/model_utils.py","file_url":"https://github.com/spcl/quarot/blob/HEAD/fake_quant/model_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":"eb59d0a73734e449","mcp_get_code":{"code_sha256":"eb59d0a73734e449"}},{"arxiv_id":"2402.17762","paper":"/paper/massive-activations-in-large-language-models","title":"Massive Activations in Large Language Models","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bluorion-com/refine_massive_activations","path":"utils/model.py","file_url":"https://github.com/bluorion-com/refine_massive_activations/blob/HEAD/utils/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16dc8236499dd526","mcp_get_code":{"code_sha256":"16dc8236499dd526"}},{"arxiv_id":"2311.16833","paper":"/paper/1-lipschitz-layers-compared-memory-speed-and","title":"1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"berndprach/1lipschitzlayerscompared","path":"models/simplified_conv_net.py","file_url":"https://github.com/berndprach/1lipschitzlayerscompared/blob/HEAD/models/simplified_conv_net.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c7c9cb838427bef2","mcp_get_code":{"code_sha256":"c7c9cb838427bef2"}},{"arxiv_id":"2308.03449","paper":"/paper/knowledge-preserving-pruning-for-pre-trained","title":"Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models","date":"2023-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snudm-starlab/k-prune","path":"src/utils/arch.py","file_url":"https://github.com/snudm-starlab/k-prune/blob/HEAD/src/utils/arch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e710f0bc27cebd18","mcp_get_code":{"code_sha256":"e710f0bc27cebd18"}},{"arxiv_id":"2205.11380","paper":"/paper/outliers-dimensions-that-disrupt-transformers","title":"Outliers Dimensions that Disrupt Transformers Are Driven by Frequency","date":"2022-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpucce/outliersvsfreq","path":"outliersvsfreq/parameter_access.py","file_url":"https://github.com/gpucce/outliersvsfreq/blob/HEAD/outliersvsfreq/parameter_access.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":"2349f1f44cdb663a","mcp_get_code":{"code_sha256":"2349f1f44cdb663a"}},{"arxiv_id":"2101.04108","paper":"/paper/controllable-guarantees-for-fair-outcomes-via","title":"Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation","date":"2021-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-sri/fnf","path":"generative/flow.py","file_url":"https://github.com/eth-sri/fnf/blob/HEAD/generative/flow.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2f44b49a20c9cd67","mcp_get_code":{"code_sha256":"2f44b49a20c9cd67"}},{"arxiv_id":"2002.09576","paper":"/paper/unmask-adversarial-detection-and-defense","title":"UnMask: Adversarial Detection and Defense Through Robust Feature Alignment","date":"2020-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"safreita1/unmask","path":"utils.py","file_url":"https://github.com/safreita1/unmask/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"068d3d6699b81f75","mcp_get_code":{"code_sha256":"068d3d6699b81f75"}},{"arxiv_id":"1904.02323","paper":"/paper/summit-scaling-deep-learning-interpretability","title":"Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations","date":"2019-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fredhohman/summit-notebooks","path":"influence.py","file_url":"https://github.com/fredhohman/summit-notebooks/blob/HEAD/influence.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c545c01301a1eed","mcp_get_code":{"code_sha256":"7c545c01301a1eed"}},{"arxiv_id":"1811.10597","paper":"/paper/gan-dissection-visualizing-and-understanding","title":"GAN Dissection: Visualizing and Understanding Generative Adversarial Networks","date":"2018-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedombenLiu/gandissect","path":"netdissect/server.py","file_url":"https://github.com/freedombenLiu/gandissect/blob/HEAD/netdissect/server.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7ff4317d03c4c34","mcp_get_code":{"code_sha256":"a7ff4317d03c4c34"}},{"arxiv_id":"1508.06576","paper":"/paper/a-neural-algorithm-of-artistic-style","title":"A Neural Algorithm of Artistic Style","date":"2015-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arvind1998/Neural-Style-Transfer","path":"model.py","file_url":"https://github.com/arvind1998/Neural-Style-Transfer/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11905b0b5a3383e5","mcp_get_code":{"code_sha256":"11905b0b5a3383e5"}},{"arxiv_id":"aaai_26027","paper":null,"title":"arXiv:aaai_26027","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"UCAS-LCH/Twin-Rep","path":"model_utils.py","file_url":"https://github.com/UCAS-LCH/Twin-Rep/blob/HEAD/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1898431b4546fe6c","mcp_get_code":{"code_sha256":"1898431b4546fe6c"}},{"arxiv_id":"Prach_1-Lipschitz_Layers_Compared_Memory_Speed_and_Certifiable_Robustness_CVPR_2024_paper","paper":null,"title":"arXiv:Prach_1-Lipschitz_Layers_Compared_Memory_Speed_and_Certifiable_Robustness_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"berndprach/1LipschitzLayersCompared","path":"models/simplified_conv_net.py","file_url":"https://github.com/berndprach/1LipschitzLayersCompared/blob/HEAD/models/simplified_conv_net.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c7c9cb838427bef2","mcp_get_code":{"code_sha256":"c7c9cb838427bef2"}},{"arxiv_id":"2025.acl-long.175","paper":null,"title":"arXiv:2025.acl-long.175","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jinghan1he/VHR","path":"utils.py","file_url":"https://github.com/jinghan1he/VHR/blob/HEAD/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":"31736c6b695804ef","mcp_get_code":{"code_sha256":"31736c6b695804ef"}}]}