{"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/powerset","entry":"powerset","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":23,"n_papers_ran":16,"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":23,"n_samples_ran":16,"n_samples_fingerprinted":1,"n_places":26,"n_places_pointer_only":12,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":8,"ran_fixture":1,"ran":7,"unverified":7},"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":"2604.18352","paper":"/paper/arxiv-2604-18352","title":"Tight Auditing of Differential Privacy in MST and AIM","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"sassoftware/dpmm","path":"src/dpmm/models/aim.py","file_url":"https://github.com/sassoftware/dpmm/blob/HEAD/src/dpmm/models/aim.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":"611f287567bbaa87","mcp_get_code":{"code_sha256":"611f287567bbaa87"}},{"arxiv_id":"2505.20278","paper":"/paper/the-coverage-principle-a-framework-for","title":"The Coverage Principle: A Framework for Understanding Compositional Generalization","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaistai/coverage-principle","path":"determine_coverage.py","file_url":"https://github.com/kaistai/coverage-principle/blob/HEAD/determine_coverage.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f57f77a1a37531dc","mcp_get_code":{"code_sha256":"f57f77a1a37531dc"}},{"arxiv_id":"2503.22674","paper":"/paper/questbench-can-llms-ask-the-right-question-to","title":"QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?","date":"2025-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-deepmind/questbench","path":"Planning/backtrace_utils.py","file_url":"https://github.com/google-deepmind/questbench/blob/HEAD/Planning/backtrace_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":"e661cb08acaf5994","mcp_get_code":{"code_sha256":"e661cb08acaf5994"}},{"arxiv_id":"2502.13870","paper":"/paper/spex-scaling-feature-interaction-explanations","title":"SPEX: Scaling Feature Interaction Explanations for LLMs","date":"2025-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"basics-lab/spectral-explain","path":"src/spectralexplain/utils.py","file_url":"https://github.com/basics-lab/spectral-explain/blob/HEAD/src/spectralexplain/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b1f0be90b2b91abd","mcp_get_code":{"code_sha256":"b1f0be90b2b91abd"}},{"arxiv_id":"2501.16944","paper":"/paper/exact-computation-of-any-order-shapley","title":"Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks","date":"2025-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FFmgll/GraphSHAP-IQ","path":"shapiq/exact.py","file_url":"https://github.com/FFmgll/GraphSHAP-IQ/blob/HEAD/shapiq/exact.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f21e14f8bd8bb9c3","mcp_get_code":{"code_sha256":"f21e14f8bd8bb9c3"}},{"arxiv_id":"2412.02646","paper":"/paper/interpretable-generalized-additive-models-for","title":"Interpretable Generalized Additive Models for Datasets with Missing Values","date":"2024-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jdonnelly36/M-GAM","path":"visualization_utils.py","file_url":"https://github.com/jdonnelly36/M-GAM/blob/HEAD/visualization_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"70a2f7a8dd235c5f","mcp_get_code":{"code_sha256":"70a2f7a8dd235c5f"}},{"arxiv_id":"2412.02482","paper":"/paper/what-should-a-neuron-aim-for-designing-local","title":"What should a neuron aim for? Designing local objective functions based on information theory","date":"2024-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"priesemann-group/infomorphic_networks","path":"im_net/im_model.py","file_url":"https://github.com/priesemann-group/infomorphic_networks/blob/HEAD/im_net/im_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"2964b884853dfa1a","mcp_get_code":{"code_sha256":"2964b884853dfa1a"}},{"arxiv_id":"2410.11964","paper":"/paper/a-complete-decomposition-of-kl-error-using","title":"A Complete Decomposition of KL Error using Refined Information and Mode Interaction Selection","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EnouenJ/mode-attributing-hierarchy","path":"models.py","file_url":"https://github.com/EnouenJ/mode-attributing-hierarchy/blob/HEAD/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fb9020626aee2101","mcp_get_code":{"code_sha256":"fb9020626aee2101"}},{"arxiv_id":"2410.11964","paper":"/paper/a-complete-decomposition-of-kl-error-using","title":"A Complete Decomposition of KL Error using Refined Information and Mode Interaction Selection","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EnouenJ/mode-attributing-hierarchy","path":"utils/utils.py","file_url":"https://github.com/EnouenJ/mode-attributing-hierarchy/blob/HEAD/utils/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"70a2f7a8dd235c5f","mcp_get_code":{"code_sha256":"70a2f7a8dd235c5f"}},{"arxiv_id":"2410.01091","paper":"/paper/efficient-and-private-marginal-reconstruction","title":"Efficient and Private Marginal Reconstruction with Local Non-Negativity","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bcmullins/efficient-marginal-reconstruction","path":"src/rem/reconstruction.py","file_url":"https://github.com/bcmullins/efficient-marginal-reconstruction/blob/HEAD/src/rem/reconstruction.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3058e1adeee40c17","mcp_get_code":{"code_sha256":"3058e1adeee40c17"}},{"arxiv_id":"2406.16749","paper":"/paper/inferring-stochastic-low-rank-recurrent","title":"Inferring stochastic low-rank recurrent neural networks from neural data","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mackelab/smc_rnns","path":"fixed_points/constrained_scify.py","file_url":"https://github.com/mackelab/smc_rnns/blob/HEAD/fixed_points/constrained_scify.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":"07159a7ad120cadd","mcp_get_code":{"code_sha256":"07159a7ad120cadd"}},{"arxiv_id":"2406.16749","paper":"/paper/inferring-stochastic-low-rank-recurrent","title":"Inferring stochastic low-rank recurrent neural networks from neural data","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mackelab/smc_rnns","path":"fixed_points/find_fixed_points_analytic.py","file_url":"https://github.com/mackelab/smc_rnns/blob/HEAD/fixed_points/find_fixed_points_analytic.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":"5803a5532384606b","mcp_get_code":{"code_sha256":"5803a5532384606b"}},{"arxiv_id":"2406.04606","paper":"/paper/helpful-or-harmful-data-fine-tuning-free","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JTWang2000/FreeShap","path":"vinfo/dvutils/utils.py","file_url":"https://github.com/JTWang2000/FreeShap/blob/HEAD/vinfo/dvutils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fb9020626aee2101","mcp_get_code":{"code_sha256":"fb9020626aee2101"}},{"arxiv_id":"2403.07797","paper":"/paper/joint-selection-adaptively-incorporating","title":"Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miguel-fuentes/jam_aistats","path":"code/mechanisms/adaptive_grid.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/adaptive_grid.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ab9a745dded1630","mcp_get_code":{"code_sha256":"7ab9a745dded1630"}},{"arxiv_id":"2403.07797","paper":"/paper/joint-selection-adaptively-incorporating","title":"Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miguel-fuentes/jam_aistats","path":"code/mechanisms/aim.py","file_url":"https://github.com/miguel-fuentes/jam_aistats/blob/HEAD/code/mechanisms/aim.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"802df9e4d1beab55","mcp_get_code":{"code_sha256":"802df9e4d1beab55"}},{"arxiv_id":"2402.03985","paper":"/paper/a-bias-variance-decomposition-for-ensembles","title":"A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dpbayes/generative-ensemble-bias-variance-decomposition","path":"lib/aim/aim.py","file_url":"https://github.com/dpbayes/generative-ensemble-bias-variance-decomposition/blob/HEAD/lib/aim/aim.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"802df9e4d1beab55","mcp_get_code":{"code_sha256":"802df9e4d1beab55"}},{"arxiv_id":"2311.04056","paper":"/paper/multi-view-causal-representation-learning","title":"Multi-View Causal Representation Learning with Partial Observability","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"causallearningai/multiview-crl","path":"utils.py","file_url":"https://github.com/causallearningai/multiview-crl/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"99a88e5f37a92f0d","mcp_get_code":{"code_sha256":"99a88e5f37a92f0d"}},{"arxiv_id":"2308.05588","paper":"/paper/banzhaf-values-for-facts-in-query-answering","title":"Banzhaf Values for Facts in Query Answering","date":null,"month_inferred_from_arxiv_id":"2023-08","title_source":"archive","repo":"omer-abramovich/adaban","path":"src/Helper_functions.py","file_url":"https://github.com/omer-abramovich/adaban/blob/HEAD/src/Helper_functions.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd577d42a4ebc364","mcp_get_code":{"code_sha256":"dd577d42a4ebc364"}},{"arxiv_id":"2308.00221","paper":"/paper/advancing-beyond-identification-multi-bit","title":"Advancing Beyond Identification: Multi-bit Watermark for Large Language Models","date":"2023-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bangawayoo/mb-lm-watermarking","path":"watermark_reliability_release/mb_watermark_processor.py","file_url":"https://github.com/bangawayoo/mb-lm-watermarking/blob/HEAD/watermark_reliability_release/mb_watermark_processor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ef28b9c2c6fbab3c","mcp_get_code":{"code_sha256":"ef28b9c2c6fbab3c"}},{"arxiv_id":"2202.00913","paper":"/paper/invariant-ancestry-search","title":"Invariant Ancestry Search","date":"2022-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"phillipmogensen/invariantancestrysearch","path":"InvariantAncestrySearch/IASfunctions.py","file_url":"https://github.com/phillipmogensen/invariantancestrysearch/blob/HEAD/InvariantAncestrySearch/IASfunctions.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"09081dcf6b856d7e","mcp_get_code":{"code_sha256":"09081dcf6b856d7e"}},{"arxiv_id":"2106.12543","paper":"/paper/synthetic-benchmarks-for-scientific-research","title":"Synthetic Benchmarks for Scientific Research in Explainable Machine Learning","date":"2021-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abacusai/xai-bench","path":"custom_explainers/ground_truth_shap.py","file_url":"https://github.com/abacusai/xai-bench/blob/HEAD/custom_explainers/ground_truth_shap.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":"59aef8f3c1a54ec8","mcp_get_code":{"code_sha256":"59aef8f3c1a54ec8"}},{"arxiv_id":"2012.10203","paper":"/paper/classification-with-strategically-withheld","title":"Classification with Strategically Withheld Data","date":"2020-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoming-codes/str-withheld","path":"credit.py","file_url":"https://github.com/haoming-codes/str-withheld/blob/HEAD/credit.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"ed13995bc898b48b","mcp_get_code":{"code_sha256":"ed13995bc898b48b"}},{"arxiv_id":"2011.01444","paper":"/paper/a-score-and-search-approach-to-learning","title":"A Score-and-Search Approach to Learning Bayesian Networks with Noisy-OR Relations","date":"2020-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CharupriyaSharma/eBNSLNoisyOR","path":"NoisyORScore.py","file_url":"https://github.com/CharupriyaSharma/eBNSLNoisyOR/blob/HEAD/NoisyORScore.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"26d6862177db6349","mcp_get_code":{"code_sha256":"26d6862177db6349"}},{"arxiv_id":"2007.02863","paper":"/paper/counterfactual-data-augmentation-using","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","date":"2020-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"spitis/mrl","path":"experiments/coda/coda_generic.py","file_url":"https://github.com/spitis/mrl/blob/HEAD/experiments/coda/coda_generic.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04039e3271a013fe","mcp_get_code":{"code_sha256":"04039e3271a013fe"}},{"arxiv_id":"1810.05739","paper":"/paper/meansum-a-neural-model-for-unsupervised-multi","title":"MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization","date":"2018-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"megagonlabs/coop","path":"coop/util.py","file_url":"https://github.com/megagonlabs/coop/blob/HEAD/coop/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"2c46661b0f3477eb","mcp_get_code":{"code_sha256":"2c46661b0f3477eb"}},{"arxiv_id":"2021.acl-long.288","paper":null,"title":"arXiv:2021.acl-long.288","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"coryshain/cdr","path":"cdr/config.py","file_url":"https://github.com/coryshain/cdr/blob/HEAD/cdr/config.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eceedaf4a4ffc6e9","mcp_get_code":{"code_sha256":"eceedaf4a4ffc6e9"}}]}