replicationbench
v1.0ReplicationBench - A benchmark for evaluating AI agents on reproducing computational results from astrophysics research papers. Adapted from Christine8888/replicationbench-release.
harbor run -d replicationbench@1.0Tasks (90)
abacus__ewald_force_accuracy
harbor run -d replicationbench@1.0 -t abacus__ewald_force_accuracyf0afc88
abacus__ewald_force_comparison
harbor run -d replicationbench@1.0 -t abacus__ewald_force_comparisonf0afc88
abacus__lattice_force_error
harbor run -d replicationbench@1.0 -t abacus__lattice_force_errorf0afc88
abacus__lcdm_total_force_accuracy
harbor run -d replicationbench@1.0 -t abacus__lcdm_total_force_accuracyf0afc88
astm3__cross_modal_photometry_to_spectra_search
harbor run -d replicationbench@1.0 -t astm3__cross_modal_photometry_to_spectra_searchf0afc88
astm3__modality_importance_rot_class_accuracy
harbor run -d replicationbench@1.0 -t astm3__modality_importance_rot_class_accuracyf0afc88
astm3__multimodal_classification_clip
harbor run -d replicationbench@1.0 -t astm3__multimodal_classification_clipf0afc88
astm3__photometry_classification_accuracy_no_clip
harbor run -d replicationbench@1.0 -t astm3__photometry_classification_accuracy_no_clipf0afc88
astm3__photometry_classification_accuracy_with_clip
harbor run -d replicationbench@1.0 -t astm3__photometry_classification_accuracy_with_clipf0afc88
astm3__spectra_classification_accuracy_limited_data_10_percent
harbor run -d replicationbench@1.0 -t astm3__spectra_classification_accuracy_limited_data_10_percentf0afc88
astm3__spectral_similarity_search
harbor run -d replicationbench@1.0 -t astm3__spectral_similarity_searchf0afc88
bayes_cal__cold_hot_tandem
harbor run -d replicationbench@1.0 -t bayes_cal__cold_hot_tandemf0afc88
bayes_cal__cold_temp
harbor run -d replicationbench@1.0 -t bayes_cal__cold_tempf0afc88
bayes_cal__evidence
harbor run -d replicationbench@1.0 -t bayes_cal__evidencef0afc88
bayes_cal__hot_temp
harbor run -d replicationbench@1.0 -t bayes_cal__hot_tempf0afc88
bayes_cal__load_cal
harbor run -d replicationbench@1.0 -t bayes_cal__load_calf0afc88
bayes_cal__nwp_set
harbor run -d replicationbench@1.0 -t bayes_cal__nwp_setf0afc88
chandra_representation__2dae_embedding
harbor run -d replicationbench@1.0 -t chandra_representation__2dae_embeddingf0afc88
chandra_representation__2dpca_embedding
harbor run -d replicationbench@1.0 -t chandra_representation__2dpca_embeddingf0afc88
chandra_representation__blackbody_spectral_fit
harbor run -d replicationbench@1.0 -t chandra_representation__blackbody_spectral_fitf0afc88
chandra_representation__powerlaw_spectral_fit
harbor run -d replicationbench@1.0 -t chandra_representation__powerlaw_spectral_fitf0afc88
disk_ridges__gaia_dr2_all
harbor run -d replicationbench@1.0 -t disk_ridges__gaia_dr2_allf0afc88
disk_ridges__gaia_dr2_rvs
harbor run -d replicationbench@1.0 -t disk_ridges__gaia_dr2_rvsf0afc88
disk_ridges__peak_mean_vz_all
harbor run -d replicationbench@1.0 -t disk_ridges__peak_mean_vz_allf0afc88
disk_ridges__ridge_slope
harbor run -d replicationbench@1.0 -t disk_ridges__ridge_slopef0afc88
disk_ridges__ridges_in_all
harbor run -d replicationbench@1.0 -t disk_ridges__ridges_in_allf0afc88
eht_resolve__eht_reconstruction
harbor run -d replicationbench@1.0 -t eht_resolve__eht_reconstructionf0afc88
eht_resolve__eht_ring_orientation_angle
harbor run -d replicationbench@1.0 -t eht_resolve__eht_ring_orientation_anglef0afc88
eht_resolve__eht_ring_size
harbor run -d replicationbench@1.0 -t eht_resolve__eht_ring_sizef0afc88
eht_resolve__eht_ring_width
harbor run -d replicationbench@1.0 -t eht_resolve__eht_ring_widthf0afc88
galaxy_manifold__data_preparation
harbor run -d replicationbench@1.0 -t galaxy_manifold__data_preparationf0afc88
galaxy_manifold__evolution_tracks
harbor run -d replicationbench@1.0 -t galaxy_manifold__evolution_tracksf0afc88
galaxy_manifold__gas_mass_estimation
harbor run -d replicationbench@1.0 -t galaxy_manifold__gas_mass_estimationf0afc88
galaxy_manifold__manifold_plane
harbor run -d replicationbench@1.0 -t galaxy_manifold__manifold_planef0afc88
galaxy_manifold__manifold_recovery
harbor run -d replicationbench@1.0 -t galaxy_manifold__manifold_recoveryf0afc88
galaxy_manifold__morphological_classification
harbor run -d replicationbench@1.0 -t galaxy_manifold__morphological_classificationf0afc88
galaxy_manifold__physical_properties
harbor run -d replicationbench@1.0 -t galaxy_manifold__physical_propertiesf0afc88
galaxy_manifold__property_prediction
harbor run -d replicationbench@1.0 -t galaxy_manifold__property_predictionf0afc88
galaxy_manifold__svd_analysis
harbor run -d replicationbench@1.0 -t galaxy_manifold__svd_analysisf0afc88
galaxy_manifold__transformation_matrix
harbor run -d replicationbench@1.0 -t galaxy_manifold__transformation_matrixf0afc88
galaxy_soptics__bcg_identification
harbor run -d replicationbench@1.0 -t galaxy_soptics__bcg_identificationf0afc88
galaxy_soptics__clustering_hyperparameter_optimization
harbor run -d replicationbench@1.0 -t galaxy_soptics__clustering_hyperparameter_optimizationf0afc88
galaxy_soptics__fof_optimization_sdss
harbor run -d replicationbench@1.0 -t galaxy_soptics__fof_optimization_sdssf0afc88
galaxy_soptics__millennium_data_extraction
harbor run -d replicationbench@1.0 -t galaxy_soptics__millennium_data_extractionf0afc88
galaxy_soptics__nyu_vagc_processing
harbor run -d replicationbench@1.0 -t galaxy_soptics__nyu_vagc_processingf0afc88
galaxy_soptics__shi_catalog_acquisition
harbor run -d replicationbench@1.0 -t galaxy_soptics__shi_catalog_acquisitionf0afc88
galaxy_soptics__soptics_implementation
harbor run -d replicationbench@1.0 -t galaxy_soptics__soptics_implementationf0afc88
galaxy_soptics__soptics_validation_shi
harbor run -d replicationbench@1.0 -t galaxy_soptics__soptics_validation_shif0afc88
gw_cosmo__dark_energy
harbor run -d replicationbench@1.0 -t gw_cosmo__dark_energyf0afc88
gw_cosmo__h0_scaling
harbor run -d replicationbench@1.0 -t gw_cosmo__h0_scalingf0afc88
gw_cosmo__measure_combo
harbor run -d replicationbench@1.0 -t gw_cosmo__measure_combof0afc88
gw_cosmo__modified_gravity
harbor run -d replicationbench@1.0 -t gw_cosmo__modified_gravityf0afc88
gw_nsbh__default_mbh
harbor run -d replicationbench@1.0 -t gw_nsbh__default_mbhf0afc88
gw_nsbh__default_mtov
harbor run -d replicationbench@1.0 -t gw_nsbh__default_mtovf0afc88
gw_nsbh__equal_mass_slope
harbor run -d replicationbench@1.0 -t gw_nsbh__equal_mass_slopef0afc88
gw_nsbh__load_data
harbor run -d replicationbench@1.0 -t gw_nsbh__load_dataf0afc88
gw_nsbh__mass_gap
harbor run -d replicationbench@1.0 -t gw_nsbh__mass_gapf0afc88
gw_nsbh__mass_gap_constraint
harbor run -d replicationbench@1.0 -t gw_nsbh__mass_gap_constraintf0afc88
gw_nsbh__mtov_spin
harbor run -d replicationbench@1.0 -t gw_nsbh__mtov_spinf0afc88
gw_nsbh__mtov_spin_2
harbor run -d replicationbench@1.0 -t gw_nsbh__mtov_spin_2f0afc88
gw_nsbh__spin_constraint
harbor run -d replicationbench@1.0 -t gw_nsbh__spin_constraintf0afc88
hubble_trails__classifier_performance
harbor run -d replicationbench@1.0 -t hubble_trails__classifier_performancef0afc88
hubble_trails__satellite_chance_post2020_acis
harbor run -d replicationbench@1.0 -t hubble_trails__satellite_chance_post2020_acisf0afc88
hubble_trails__satellite_chance_post2020_uvis
harbor run -d replicationbench@1.0 -t hubble_trails__satellite_chance_post2020_uvisf0afc88
hubble_trails__satellite_chance_pre2020_acis
harbor run -d replicationbench@1.0 -t hubble_trails__satellite_chance_pre2020_acisf0afc88
hubble_trails__satellite_chance_pre2020_uvis
harbor run -d replicationbench@1.0 -t hubble_trails__satellite_chance_pre2020_uvisf0afc88
hubble_trails__satellite_fractions
harbor run -d replicationbench@1.0 -t hubble_trails__satellite_fractionsf0afc88
hubble_trails__satellite_fractions_increase
harbor run -d replicationbench@1.0 -t hubble_trails__satellite_fractions_increasef0afc88
lensing_dr6_growth__alens
harbor run -d replicationbench@1.0 -t lensing_dr6_growth__alensf0afc88
lensing_dr6_growth__params
harbor run -d replicationbench@1.0 -t lensing_dr6_growth__paramsf0afc88
ls_cal__antenna_temp
harbor run -d replicationbench@1.0 -t ls_cal__antenna_tempf0afc88
ls_cal__cab_temp
harbor run -d replicationbench@1.0 -t ls_cal__cab_tempf0afc88
ls_cal__cold_sparam
harbor run -d replicationbench@1.0 -t ls_cal__cold_sparamf0afc88
ls_cal__hot_temp
harbor run -d replicationbench@1.0 -t ls_cal__hot_tempf0afc88
ls_cal__nwp
harbor run -d replicationbench@1.0 -t ls_cal__nwpf0afc88
mars_clouds__dbscan_optimization
harbor run -d replicationbench@1.0 -t mars_clouds__dbscan_optimizationf0afc88
mars_clouds__dbscan_test
harbor run -d replicationbench@1.0 -t mars_clouds__dbscan_testf0afc88
muse_outflows__dust_reddening
harbor run -d replicationbench@1.0 -t muse_outflows__dust_reddeningf0afc88
muse_outflows__electron_density
harbor run -d replicationbench@1.0 -t muse_outflows__electron_densityf0afc88
muse_outflows__narrow_and_broad_line_decomposition_for_j080427
harbor run -d replicationbench@1.0 -t muse_outflows__narrow_and_broad_line_decomposition_for_j080427f0afc88
muse_outflows__outflow_energetics
harbor run -d replicationbench@1.0 -t muse_outflows__outflow_energeticsf0afc88
muse_outflows__voronoi_binning_for_emission_lines_j080427
harbor run -d replicationbench@1.0 -t muse_outflows__voronoi_binning_for_emission_lines_j080427f0afc88
trgb_std_candle__aseq_bseq_trgb
harbor run -d replicationbench@1.0 -t trgb_std_candle__aseq_bseq_trgbf0afc88
trgb_std_candle__fit_aseq_bseq
harbor run -d replicationbench@1.0 -t trgb_std_candle__fit_aseq_bseqf0afc88
trgb_std_candle__gaia_synthetic_i_trgb
harbor run -d replicationbench@1.0 -t trgb_std_candle__gaia_synthetic_i_trgbf0afc88
trgb_std_candle__med_color_amp
harbor run -d replicationbench@1.0 -t trgb_std_candle__med_color_ampf0afc88
ver_waves__gaia_breathing_typical
harbor run -d replicationbench@1.0 -t ver_waves__gaia_breathing_typicalf0afc88
ver_waves__gaia_rv_sample_size
harbor run -d replicationbench@1.0 -t ver_waves__gaia_rv_sample_sizef0afc88
ver_waves__solar_height_from_gaia_dr2
harbor run -d replicationbench@1.0 -t ver_waves__solar_height_from_gaia_dr2f0afc88
ver_waves__sun_height_corrected
harbor run -d replicationbench@1.0 -t ver_waves__sun_height_correctedf0afc88