{"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/load-features","entry":"load_features","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":14,"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":15,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":15,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":12},"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":"2603.11940","paper":"/paper/arxiv-2603-11940","title":"Exhaustive Circuit Mapping of a Single-Cell Foundation Model Reveals Massive Redundancy, Heavy-Tailed Hub Architecture, and Layer-Dependent Differentiation Control","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Biodyn-AI/sae-biological-map","path":"src/revision/make_figures.py","file_url":"https://github.com/Biodyn-AI/sae-biological-map/blob/HEAD/src/revision/make_figures.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4d8ed6301a3c8094","mcp_get_code":{"code_sha256":"4d8ed6301a3c8094"}},{"arxiv_id":"2601.22359","paper":"/paper/arxiv-2601-22359","title":"The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Graph-COM/Langevin_unlearning","path":"utils.py","file_url":"https://github.com/Graph-COM/Langevin_unlearning/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b149132fab16d2fd","mcp_get_code":{"code_sha256":"b149132fab16d2fd"}},{"arxiv_id":"2502.11748","paper":"/paper/ilias-instance-level-image-retrieval-at-scale","title":"ILIAS: Instance-Level Image retrieval At Scale","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ilias-vrg/ilias","path":"knn_search/src/utils.py","file_url":"https://github.com/ilias-vrg/ilias/blob/HEAD/knn_search/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"798a08952de685c1","mcp_get_code":{"code_sha256":"798a08952de685c1"}},{"arxiv_id":"2408.02859","paper":"/paper/2408-02859","title":"Multistain Pretraining for Slide Representation Learning in Pathology","date":"2024-08-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mahmoodlab/madeleine","path":"madeleine/datasets/wsi_dataset.py","file_url":"https://github.com/mahmoodlab/madeleine/blob/HEAD/madeleine/datasets/wsi_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d276dd72565d8b15","mcp_get_code":{"code_sha256":"d276dd72565d8b15"}},{"arxiv_id":"2312.17742","paper":"/paper/learning-vision-from-models-rivals-learning","title":"Learning Vision from Models Rivals Learning Vision from Data","date":"2023-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/syn-rep-learn","path":"SynCLR/eval/main_downstream_linear.py","file_url":"https://github.com/google-research/syn-rep-learn/blob/HEAD/SynCLR/eval/main_downstream_linear.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fe2674b28e128309","mcp_get_code":{"code_sha256":"fe2674b28e128309"}},{"arxiv_id":"2311.09939","paper":"/paper/red-dot-multimodal-fact-checking-via-relevant","title":"RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stevejpapad/relevant-evidence-detection","path":"src/utils.py","file_url":"https://github.com/stevejpapad/relevant-evidence-detection/blob/HEAD/src/utils.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":"ad59ff90af89c577","mcp_get_code":{"code_sha256":"ad59ff90af89c577"}},{"arxiv_id":"2305.15393","paper":"/paper/layoutgpt-compositional-visual-planning-and","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weixi-feng/layoutgpt","path":"run_layoutgpt_2d.py","file_url":"https://github.com/weixi-feng/layoutgpt/blob/HEAD/run_layoutgpt_2d.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0b66d7eb2f18c94","mcp_get_code":{"code_sha256":"c0b66d7eb2f18c94"}},{"arxiv_id":"2305.15393","paper":"/paper/layoutgpt-compositional-visual-planning-and","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weixi-feng/layoutgpt","path":"run_layoutgpt_3d.py","file_url":"https://github.com/weixi-feng/layoutgpt/blob/HEAD/run_layoutgpt_3d.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3af0b42145b07f7f","mcp_get_code":{"code_sha256":"3af0b42145b07f7f"}},{"arxiv_id":"2203.13838","paper":"/paper/analyzing-generalization-of-vision-and","title":"Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas","date":"2022-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raphael-sch/map2seq_vln","path":"vln/env.py","file_url":"https://github.com/raphael-sch/map2seq_vln/blob/HEAD/vln/env.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":"010f3141fcd0a2a7","mcp_get_code":{"code_sha256":"010f3141fcd0a2a7"}},{"arxiv_id":"2005.07959","paper":"/paper/characteristic-functions-on-graphs-birds-of-a","title":"Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models","date":"2020-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"benedekrozemberczki/FEATHER","path":"src/utils.py","file_url":"https://github.com/benedekrozemberczki/FEATHER/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23b06215419ec8a3","mcp_get_code":{"code_sha256":"23b06215419ec8a3"}},{"arxiv_id":"2001.03671","paper":"/paper/retouchdown-adding-touchdown-to-streetlearn","title":"Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View","date":"2020-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VegB/VLN-Transformer","path":"touchdown/env.py","file_url":"https://github.com/VegB/VLN-Transformer/blob/HEAD/touchdown/env.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":"51021c67dc837367","mcp_get_code":{"code_sha256":"51021c67dc837367"}},{"arxiv_id":"1910.00324","paper":"/paper/graph-convolutional-networks-for-learning","title":"Graph convolutional networks for learning with few clean and many noisy labels","date":"2019-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/noisy-fewshot-learning","path":"utils.py","file_url":"https://github.com/google-research/noisy-fewshot-learning/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":"a3fd5332294feb14","mcp_get_code":{"code_sha256":"a3fd5332294feb14"}},{"arxiv_id":"1904.01561","paper":"/paper/are-learned-molecular-representations-ready","title":"Analyzing Learned Molecular Representations for Property Prediction","date":"2019-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","path":"chemprop/features/utils.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/features/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5045ed0a87b443be","mcp_get_code":{"code_sha256":"5045ed0a87b443be"}},{"arxiv_id":"1710.10891","paper":"/paper/open-set-logo-detection-and-retrieval","title":"Open Set Logo Detection and Retrieval","date":"2017-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ilmonteux/logohunter","path":"src/utils.py","file_url":"https://github.com/ilmonteux/logohunter/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9ac92e9508c68b0a","mcp_get_code":{"code_sha256":"9ac92e9508c68b0a"}},{"arxiv_id":"1310.1531","paper":"/paper/decaf-a-deep-convolutional-activation-feature","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","date":"2013-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"starfoe/Eye-bnb","path":"eyebnb_ec2/web_query.py","file_url":"https://github.com/starfoe/Eye-bnb/blob/HEAD/eyebnb_ec2/web_query.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":"d6f6e154c5f165d4","mcp_get_code":{"code_sha256":"d6f6e154c5f165d4"}}]}