KnowLine-9B-Gen1 / TRAINING_SOURCES.json
PEScn's picture
Document retained mixU source-family exposure for S1MB
4083a79 verified
Raw History Blame Contribute Delete
59 kB
{
"model": "PelaAI/KnowLine-9B-Gen1",
"weight_revision": "a421fc438cebe28e95de6951bc8bc440119db969",
"training_rows": 1143656,
"training_sha256": "9e01ff4882d28fdc350b08ebb7b70b5cb26e79c6d4d6438a43d7bdbb589ce7cd",
"parts": {
"or1d": 873134,
"Kf_unseen": 241781,
"additional_injection": 16824,
"paired_convention_pilots": 11917
},
"inherited_source_declaration": "https://huggingface.co/PelaAI/KnowLine-31B-Gen1/blob/986803e4037f7778d24623184729a31202e3d302/README.md",
"basis": "Retained mixU channel counts checked against prior source-family declarations; this is not a new record-level overlap audit. No prior models overlap counts reused. Source revisions and any undeclared families remain unknown. Pretraining exposure is unknown.",
"training_data_public": false,
"channels": {
"gapo_gsm_tmpl": 38000,
"gapb_sata_more": 26906,
"gapb_hard_nli_35b": 17666,
"gapb_absa_quad": 17501,
"r_mmlu_aux": 28793,
"gapb_clinical_nli": 14899,
"gapo_severity": 14630,
"cand_agent_gui": 14569,
"gapo_answer_resp": 14157,
"gapb_ragtruth_more": 13793,
"r_medmcqa": 17150,
"k_winogrande": 15679,
"gapo_gsm_var": 8303,
"r_aqua": 14183,
"gapb_clinical_tmpl": 7855,
"gapo_bbh_geometric_shapes": 7000,
"gapo_bbh_logical_deduction": 7000,
"fix7_chess_lichess": 7000,
"cand_router_hazard": 5500,
"cand_router_safety": 5500,
"cand_router_pii": 5499,
"openjevdata_commonsense_context": 10221,
"cand_router_tool_need": 5493,
"cand_router_hallucination": 5490,
"k_acos": 9428,
"openjevdata_knowledge_qa": 9510,
"cand_rules_threshold": 5000,
"cand_rules_pointer": 5000,
"cand_rules_compound": 5000,
"cand_rules_form": 5000,
"cand_rules_membership": 5000,
"cand_rules_presence": 5000,
"cand_rules_contains": 5000,
"cand_rules_precedence": 5000,
"cand_rules_boolean": 5000,
"cand_rules_select": 5000,
"openjevdata_deductive_reasoning": 9314,
"t_pol3_equiphours": 4937,
"fix7_toolret_apisguru": 4783,
"cand_router_jailbreak": 4668,
"gapo_bbh_web_of_lies": 4500,
"gapo_bbh_navigate": 4500,
"gapo_bbh_formal_fallacies": 4500,
"gapo_bbh_table": 4500,
"gapo_bbh_date": 4500,
"k_gsm8k": 7309,
"synth_workflow_docs@v1": 7314,
"gapo_bbh_bool": 4000,
"fix7_wino_knowref": 4000,
"r_sciq": 6811,
"r_logiqa": 6811,
"z_humicroedit": 6816,
"kd_synth_workflow_docs@v1": 3817,
"kd_synth_policy_exception@v1": 3765,
"z_cfcolor": 6760,
"fix7_w2c_gen": 3501,
"nd2_social_needs": 3354,
"nd2_critical_path": 3300,
"nd2_colregs": 3300,
"nd2_crop_diagnosis": 3300,
"nd2_volunteer_match": 3300,
"nd2_wildlife_sign": 3300,
"nd2_insurance_coverage": 3300,
"nd2_order_dialogue_state": 3300,
"nd2_soil_texture": 3300,
"nd2_manifest_anomaly": 3300,
"nd2_museum_dating": 3300,
"nd2_sports_officiating": 3300,
"nd2_supply_attribution": 3300,
"nd2_recipe_tags": 3300,
"nd2_hs_section": 3300,
"nd2_league_standings": 3300,
"nd2_ad_compliance": 3300,
"nd2_machine_failure": 3300,
"nd2_meter_anomaly": 3300,
"nd2_nova_group": 3300,
"nd2_metar_flight_category": 3300,
"nd2_math_misconception": 3300,
"nd2_reconciliation": 3300,
"nd2_cuisine": 3300,
"nd2_listing_consistency": 3300,
"nd2_nutrition_claims": 3300,
"nd2_shelter_outcome": 3300,
"nd2_plan_select": 3300,
"nd2_job_seniority": 3300,
"nd2_nutriscore": 3300,
"nd2_house_price_pair": 3300,
"nd2_ntsb_occurrence": 3300,
"nd2_storm_event_type": 3300,
"nd2_stellar_class": 3300,
"nd2_telecom_rca": 3300,
"nd2_electrical_fault": 3300,
"nd2_zoning_check": 3300,
"nd2_incoterms": 3300,
"nd2_mtg_color": 3300,
"nd2_revenue_attribution": 3300,
"nd2_beer_style": 3300,
"nd2_telecom_standards": 3300,
"nd2_ab_test": 3300,
"nd2_worldbank_sector": 3299,
"nd2_readability_pair": 3298,
"nd2_aqi": 3297,
"nd2_mrb_disposition": 3249,
"z_bpomp": 5591,
"esci_v2": 5626,
"nd2_museum_department": 3160,
"nd2_monster_cr": 3109,
"fix7_wino_twins": 3038,
"kd_synth_record_requirements@v1": 2962,
"openjevdata_probabilistic_reasoning": 5036,
"synth_record_requirements@v1": 4643,
"digap_home": 4273,
"synth_quantitative@v1": 4420,
"cand_agent_tool": 2306,
"fix7_toolret_hermes": 2282,
"kd_kn_cmb": 2094,
"z_sata": 3608,
"k_winogrande_fmt": 2834,
"kd_kn_medmcqa": 2060,
"kd_g_cail": 2059,
"kd_kn_race": 2027,
"kd_g_lcqmc": 2027,
"gapo_bbh_colored_objects": 2000,
"gapo_bbh_arith": 2000,
"kd_g_clinc": 1999,
"cand_agent_swe": 1988,
"kd_g_ocnli": 1960,
"oj11_replay": 2187,
"t_time_billing": 1796,
"hf_g_clinc": 2941,
"oj11_community": 1944,
"t_tab_count_exec": 1692,
"synth_policy_exception@v1": 3344,
"kd_mj_news_huffpost": 1676,
"kd_g_kuake_qtr": 1675,
"hf_g_ocnli": 2826,
"kd_code_contests": 1620,
"fix7_finentity_contrast": 1611,
"fix7_apibank_args": 1527,
"z_toolret": 2665,
"gapo_bbh_object_counting": 1500,
"gapo_bbh_word_sorting": 1500,
"gapo_bbh_dyck": 1500,
"gapo_bbh_hyperbaton": 1500,
"kd_g_anli": 1493,
"z_bright": 2501,
"fix7_w2c_hermes": 1370,
"kd_kn_cmmlu": 1363,
"digap_pop909real": 2394,
"digap_chess": 2332,
"h_crux": 2306,
"h_anli_nli": 2322,
"digap_pop909": 2314,
"kd_g_yelp": 1314,
"k_acos_fmt": 1714,
"t_tab_count_claim": 1296,
"kd_kn_cflue": 1294,
"kd_g_qbqtc": 1293,
"digap_cladder": 2155,
"kd_gen_mnli_train": 1271,
"kd_gen_snli": 1267,
"kd_fix_cfever_claim": 1248,
"kd_g_yahoo": 1247,
"fix7_apibank_next": 1240,
"kd_synth_deductive@v1": 1236,
"kd_kn_medqa": 1235,
"kd_g_cofacts": 1233,
"kd_synth_quantitative@v1": 1230,
"kd_gen_code_docstring": 1226,
"kd_gen_fever": 1226,
"kd_synth_evidence_validation@v1": 1226,
"kd_g_chinesesafe": 1225,
"kd_gen_squad2": 1223,
"kd_kn_cosmosqa": 1221,
"kd_gen_glaive_tool_choice": 1219,
"kd_kn_medqa_zh": 1213,
"kd_d_amz_zh": 1206,
"gapo_bbh_temporal": 1200,
"kd_kn_sciq": 1192,
"openjevdata_intent_routing": 2242,
"kd_g_liar2": 1181,
"kd_gen_helpsteer3": 1181,
"kd_kn_aqua": 1178,
"kd_mj_intent_contrast": 1175,
"hf_g_anli": 2107,
"j_tool_hardsel": 2042,
"kd_gen_goemotions": 1164,
"openjevdata_quantitative_reasoning": 2201,
"kd_kn_piqa": 1151,
"kd_kn_logiqa_zh": 1131,
"kd_cuad": 1112,
"kd_gen_civil_more": 1103,
"t_pol3_library": 1100,
"kd_kn_logiqa_en": 1097,
"t_pol3_carrental": 1096,
"kd_d_mtop": 1077,
"hf_nd_climate_disclosure": 1077,
"inj2_synth_policy_exception@v1": 1500,
"hf_nd_situation_emotion": 1060,
"kd_kn_art": 1057,
"hf_nd_causal_choice": 1052,
"kd_di_isarcasm": 1051,
"hf_nd_zh_idiom_cloze": 1048,
"kd_g_offenseval": 1047,
"hf_nd_issue_type": 1046,
"hf_nd_moral_action": 1042,
"kd_kn_qasc": 1035,
"h_isarcasm": 1808,
"kd_d_se_topic": 1028,
"hf_nd_employer_review": 1019,
"hf_nd_wine_review": 1012,
"hf_nd_action_judgment": 1009,
"hf_nd_table_fact": 1008,
"kd_di_when2call": 1008,
"kd_di_hover": 1004,
"hf_nd_dialogue_emotion": 1001,
"hf_nd_dialogue_act": 1001,
"hf_g_yahoo": 1737,
"hf_nd_zh_shopping_review": 991,
"inj2_synth_quantitative@v1": 1400,
"cand_agent_research": 986,
"kd_d_mclwic_en": 985,
"fix7_musr_fault": 983,
"kd_di_esci": 974,
"kd_gen_cfever": 971,
"hf_nd_zh_poem_match": 967,
"kd_di_sgd": 961,
"kd_gen_dureader_yesno": 958,
"cand_agent_tau": 935,
"h_phish_construct": 1671,
"kd_kn_boolq": 931,
"openjevdata_multi_hop": 1810,
"kof_oracle_v3_paraphrase": 1523,
"kof_oracle_v3": 1543,
"z_humicroedit_fmt": 1276,
"hf_d_se_topic": 1499,
"kd_gen_shp": 883,
"kof_hist_v3": 1527,
"hf_nd_clothing_review": 861,
"hf_g_tmmluplus": 1466,
"kd_fix_fever_claim": 858,
"kd_gen_webgpt": 855,
"hf_nd_airline_tweet": 852,
"hf_nd_code_comment": 852,
"hf_nd_pubhealth_claim": 851,
"kd_gen_chip_sts": 850,
"kd_gen_hatexplain": 850,
"hf_di_banking77": 1462,
"fix7_finentity_news": 846,
"hf_nd_ade_report": 843,
"hf_nd_idiom_usage": 842,
"hf_nd_covid_misinfo": 841,
"hf_nd_drug_review_rating": 839,
"hf_nd_chemprot_relation": 837,
"hf_nd_sdg_topic": 835,
"kd_synth_score_rubric@v1": 834,
"kd_gen_iflytek": 833,
"kd_gen_qqp_train": 832,
"kd_gen_toxigen": 831,
"hf_d_mtop": 1433,
"kd_gen_aegis_prompt": 826,
"kd_gen_thucnews": 825,
"hf_g_wic": 1447,
"hf_i_tw_exam": 1428,
"hf_nd_answer_grading": 823,
"z_cfcolor_fmt": 1139,
"kd_d_xnli_zh": 822,
"arena_oracle_v3_paraphrase": 1395,
"kd_gen_devign": 821,
"hf_nd_paper_field": 821,
"hf_g_cail": 1440,
"hf_di_vast": 1457,
"arena_hist_v3": 1388,
"hf_nd_ddi_relation": 813,
"kd_kn_proofwriter": 812,
"hf_nd_drug_review_condition": 808,
"hf_nd_hate_offensive": 808,
"hf_nd_metaphor_word": 804,
"hf_g_lcqmc": 1348,
"hf_nd_rct_sentence_role": 803,
"hf_g_sst5": 1434,
"kd_kn_dream": 800,
"hf_nd_med_abstract_topic": 799,
"hf_di_hellaswag": 1405,
"z_toolret_x": 1417,
"openjevdata_answer_preference": 1465,
"hf_nd_patent_section": 776,
"arena_oracle_v3": 1360,
"z_finentity": 1371,
"kd_gen_glaive_call_needed": 762,
"kd_g_beavertails": 761,
"k_gsm8k_fmt": 1027,
"hf_di_when2call": 1308,
"hf_di_hover": 1297,
"hf_nd_math_difficulty": 728,
"hf_di_contractnli": 1340,
"h_sgd": 1290,
"hf_nd_math_subject": 711,
"inj2_k_acos": 900,
"z_bpomp_fmt": 905,
"openjevdata_reading_comprehension": 1287,
"hf_d_xnli_zh": 1186,
"digap_habermas": 1178,
"kd_gen_tweet_sentiment": 675,
"fix7_toolret_glaive": 670,
"hf_g_kuake_qtr": 1154,
"kd_aes2": 657,
"kd_gen_tweet_hate": 656,
"blackjack": 1104,
"kd_jigsaw_severity": 651,
"kd_asap_sas": 647,
"hf_nd_tab_bank_marketing": 645,
"kd_amazon": 641,
"hf_di_arc": 1103,
"kd_d_cdial_bias": 639,
"hf_di_newyorker": 1113,
"kd_di_phish_url": 636,
"web_element": 1054,
"fix7_musr_ledger": 629,
"kd_gen_app_reviews": 628,
"kd_mj_scitail": 624,
"hf_nd_stress_post": 624,
"kd_cmexam": 619,
"hf_di_commonsenseqa": 1089,
"inj2_z_toolret": 900,
"kd_mhs": 617,
"kd_di_phish_email": 616,
"kd_gen_amazon_polarity": 615,
"hf_mj_news_huffpost": 1087,
"chess_move": 1033,
"fix7_musr_trip": 612,
"kd_mj_scicite": 612,
"kd_gen_nlpcc14_sc": 612,
"kd_mj_fin_topic": 611,
"kd_mj_argq_stance": 610,
"kd_mj_tab_adult": 609,
"hf_i_drcd_choice": 1038,
"kd_mj_wdc_match": 607,
"kd_d_xlwic_zh": 605,
"fix7_musr_alibi": 603,
"chess_theme": 1016,
"kd_gen_swsr": 602,
"arcade_2048": 1037,
"kd_d_amz_en": 596,
"kd_helpsteer": 596,
"kd_gen_climate_fever": 594,
"inj2_k_gsm8k": 781,
"kd_gen_imdb": 592,
"kd_d_bq_dev": 589,
"synth_deductive@v1": 1142,
"arcade_sudoku": 1052,
"kd_gen_healthver": 587,
"kd_patent": 587,
"kd_arena140k": 585,
"kd_gen_chnsenticorp": 581,
"kd_d_lingnli": 578,
"kd_mnli": 575,
"fix7_musr_ballot": 571,
"synth_evidence_validation@v1": 1162,
"kd_clone": 569,
"arcade_dino": 993,
"hf_kn_cmmlu": 950,
"inj2_z_bpomp": 700,
"kd_di_enron_spam": 556,
"kd_gen_snips": 553,
"kd_mj_humaid": 553,
"toolace": 894,
"hf_kn_medmcqa": 966,
"hf_kn_cmb": 940,
"hf_g_qbqtc": 885,
"openjevdata_option_logic": 989,
"kd_d_prosocial": 528,
"fix7_musr_author": 525,
"h_apibank": 880,
"hf_g_liar2": 874,
"openjevdata_temporal_numeric": 1151,
"hf_kn_race": 896,
"hf_d_amz_zh": 890,
"kd_gen_chip_ctc": 510,
"hf_i_drcd_sentence": 882,
"kd_d_sohu": 506,
"kd_mj_tab_churn": 504,
"kd_fakenews_zh": 502,
"kd_d_diasafety": 502,
"hf_g_cofacts": 893,
"inj3_synth_policy_exception@v1": 700,
"inj2_z_bright": 697,
"kd_mj_clickbait": 493,
"kd_afqmc": 491,
"hf_g_offenseval": 866,
"kd_d_casehold": 490,
"kd_cold": 489,
"hf_nd_counterfactual_review": 488,
"hf_g_chinesesafe": 832,
"kd_d_atec": 485,
"kd_dbpedia": 484,
"kd_d_ledgar": 484,
"h_phish_url": 867,
"hf_d_lingnli": 832,
"hf_di_bfcl_w2c": 863,
"hf_g_yelp": 899,
"hf_di_openbookqa": 801,
"hf_di_commonsenseqa_fmt": 602,
"h_oj11_wanli_bal": 837,
"kd_d_risawoz": 469,
"hf_fix_cfever_claim": 855,
"kd_bq": 465,
"z_sata_fmt": 625,
"hf_g_beavertails": 803,
"arcade_flappy": 861,
"chess_harness_rich": 773,
"hf_di_phish_email": 822,
"hf_kn_medqa": 806,
"kd_d_scotus": 442,
"hf_g_kuake_qic": 712,
"hf_gen_fever": 769,
"hf_gen_mnli_train": 739,
"hf_gen_snli": 750,
"kd_di_bfcl_w2c": 436,
"hf_kn_aqua": 732,
"hf_kn_logiqa_zh": 751,
"h_anli_nli_fmt": 693,
"chess_harness_ascii": 756,
"web_op": 756,
"hf_d_casehold": 691,
"hf_i_rt_critics": 727,
"chess_harness_fen": 678,
"hf_d_mclwic_en": 734,
"hf_kn_sciq": 744,
"hf_kn_medqa_zh": 751,
"kd_d_newsgroups_test": 416,
"kd_gen_tweet_emotion": 415,
"kd_sick": 415,
"kd_kn_ruletaker": 415,
"shell_exit": 730,
"hf_j_ops_itsm": 696,
"patch_resolves": 701,
"hf_kn_mmlu_aux": 666,
"hf_d_ledgar": 686,
"kd_qqp": 406,
"openjevdata_evidence_validation": 808,
"hf_gen_chip_ctc": 664,
"hf_kn_cosmosqa": 725,
"synth_score_rubric@v1": 821,
"typed_customer_service": 659,
"hf_gen_civil_more": 688,
"hf_kn_cflue": 706,
"kd_socialiqa": 398,
"hf_i_amazon_cn": 710,
"hf_di_arc_fmt": 540,
"kd_civil_comments": 393,
"kd_tripadvisor": 391,
"typed_agent_trace_observability": 703,
"hf_gen_cfever": 664,
"inj2_z_finentity": 500,
"hf_gen_goemotions": 675,
"hf_kn_gaokao": 655,
"hf_kn_qasc": 643,
"hf_kn_piqa": 712,
"typed_invoice_processing": 663,
"kd_cefr": 374,
"hf_gen_dureader_yesno": 643,
"hf_i_semeval_tweet": 570,
"hf_gen_helpsteer3": 668,
"hf_gen_nlpcc_stance": 627,
"typed_security_incidents": 652,
"hf_gen_iflytek": 601,
"hf_kn_logiqa_en": 609,
"hf_gen_hatexplain": 633,
"kd_d_ecthr": 348,
"hf_code_contests": 616,
"kd_mj_medqpairs": 345,
"hf_j_aftersales_cfpb_route": 609,
"hf_kn_art": 623,
"hf_j_aftersales_abcd_action": 586,
"hf_gen_tweet_stance": 604,
"hf_gen_healthver": 587,
"hf_d_risawoz": 563,
"inj3_synth_quantitative@v1": 500,
"hf_gen_code_docstring": 548,
"hf_gen_thucnews": 564,
"hf_kn_dream": 613,
"kd_d_atis": 336,
"kd_formality": 335,
"hf_kn_proofwriter": 593,
"kd_cola": 331,
"hf_d_newsgroups_test": 549,
"kd_newsgroups": 328,
"kd_humicroedit": 327,
"hf_d_scotus": 576,
"hf_kn_quail": 578,
"hf_gen_shp": 573,
"hf_arena140k": 510,
"hf_nd_fake_job_post": 325,
"hf_gen_webgpt": 593,
"openjevdata_constraint_planning": 628,
"h_crux_fmt": 416,
"hf_fix_fever_claim": 586,
"kd_d_afqmc_dev": 318,
"hf_di_nli4ct": 544,
"hf_j_aftersales_abcd_case": 580,
"hf_j_agentsafe_tab": 580,
"kd_gen_averitec": 310,
"inj2_h_crux": 400,
"openjevdata_code_database": 566,
"kd_g_sst5": 308,
"hf_j_aftersales_bitext": 512,
"hf_di_openbookqa_fmt": 403,
"openjevdata_emotion_recognition": 506,
"hf_gen_toxigen": 500,
"hf_cuad": 509,
"inj2_openjevdata_deductive_reasoning": 414,
"hf_gen_squad2": 527,
"hf_j_aftersales_cfpb_outcome": 554,
"openjevdata_policy_exception": 781,
"hf_gen_tweet_sentiment": 510,
"hf_d_prosocial": 509,
"hf_jigsaw_severity": 486,
"hf_mnli": 513,
"kd_kn_cflue_tf": 284,
"hf_kn_strategyqa": 467,
"kd_multirc": 283,
"hf_gen_climate_fever": 495,
"hf_gen_averitec": 512,
"hf_d_amz_en": 470,
"hf_d_bq_dev": 454,
"hf_gen_snips": 461,
"hf_dbpedia": 460,
"hf_mj_fin_topic": 445,
"inj2_openjevdata_commonsense_context": 379,
"kd_gen_tweet_irony": 265,
"hf_mj_tab_churn": 444,
"inj2_openjevdata_knowledge_qa": 378,
"synth_musr@v1": 264,
"hf_j_ops_statuspage": 442,
"hf_d_cdial_bias": 467,
"hf_cmexam": 477,
"inj2_synth_evidence_validation@v1": 350,
"kd_d_unfair_tos": 259,
"hf_gen_glaive_tool_choice": 437,
"hf_mj_tab_adult": 450,
"kd_quest": 255,
"hf_j_agentsafe_llmail": 447,
"hf_d_atis": 451,
"hf_mj_humaid": 417,
"hf_mj_argq_stance": 459,
"hf_kn_boolq": 473,
"hf_kn_jecqa": 413,
"hf_mj_scitail": 443,
"hf_jigsaw_rules": 401,
"hf_mj_medqpairs": 447,
"hf_folio": 411,
"hf_d_toxicchat": 437,
"h_sgd_fmt": 376,
"inj2_synth_score_rubric@v1": 350,
"kd_phrasebank": 242,
"hf_j_ops_bgl": 413,
"hf_gen_swsr": 418,
"hf_mhs": 403,
"hf_d_mclwic_zh": 434,
"inj2_synth_deductive@v1": 349,
"hf_ellipse": 413,
"hf_d_xlwic_zh": 428,
"hf_mj_argq_pair": 424,
"hf_sick": 423,
"kd_ellipse": 237,
"hf_gen_chip_sts": 397,
"hf_quest": 376,
"hf_gen_app_reviews": 369,
"hf_gen_amazon_polarity": 362,
"hf_asap_sas": 381,
"openjevdata_score_quality": 401,
"hf_gen_qqp_train": 411,
"hf_mj_scicite": 417,
"hf_gen_devign": 398,
"hf_kn_pubmedqa": 412,
"blackjack_count": 391,
"inj2_h_apibank": 300,
"inj3_k_acos": 300,
"hf_mj_wdc_match": 431,
"hf_fakenews_zh": 426,
"hf_gen_glaive_call_needed": 415,
"hf_civil_comments": 408,
"hf_d_ecthr": 406,
"hf_helpsteer": 371,
"hf_afqmc": 349,
"hf_gen_tweet_emotion": 409,
"hf_gen_chnsenticorp": 392,
"hf_clone": 363,
"hf_socialiqa": 402,
"h_isarcasm_fmt": 419,
"hf_j_aftersales_multidogo": 360,
"hf_aes2": 352,
"hf_d_afqmc_dev": 363,
"inj3_z_toolret": 300,
"inj2_hf_di_bfcl_w2c": 282,
"hf_j_agentsafe_jb_wild": 322,
"inj3_hf_mj_news_huffpost": 300,
"hf_di_ragtruth": 381,
"hf_gen_imdb": 363,
"hf_d_sohu": 334,
"hf_gen_nlpcc14_sc": 370,
"hf_patent": 366,
"hf_gen_tweet_hate": 353,
"inj3_openjevdata_commonsense_context": 300,
"hf_newsgroups": 367,
"hf_kn_cflue_tf": 366,
"hf_gen_tweet_irony": 357,
"hf_amazon": 351,
"h_phish_construct_fmt": 355,
"inj3_openjevdata_knowledge_qa": 292,
"hf_formality": 354,
"inj3_k_gsm8k": 266,
"hf_cefr": 341,
"hf_humicroedit": 339,
"hf_gen_fiqa_sentiment": 349,
"hf_mj_tab_wine": 321,
"kd_gen_nlpcc_stance": 190,
"hf_mj_clickbait": 353,
"z_finentity_fmt": 221,
"hf_d_diasafety": 339,
"hf_phrasebank": 320,
"hf_j_ops_synth_tickets": 326,
"inj2_h_sgd": 281,
"inj3_z_bpomp": 250,
"hf_di_when2call_fmt": 323,
"hf_tripadvisor": 307,
"hf_qqp": 294,
"hf_di_hellaswag_fmt": 240,
"inj3_openjevdata_deductive_reasoning": 258,
"hf_d_atec": 333,
"hf_d_moderation": 299,
"hf_di_hover_fmt": 316,
"hf_kn_ruletaker": 276,
"hf_mj_news_bbc": 302,
"inj3_hf_di_hover": 213,
"hf_di_contractnli_fmt": 225,
"hf_di_vast_fmt": 229,
"hf_kn_eeval": 283,
"hf_j_ops_hdfs": 276,
"hf_bq": 292,
"inj2_z_cfcolor": 200,
"inj3_z_finentity": 200,
"hf_di_newyorker_fmt": 218,
"inj3_hf_di_contractnli": 191,
"hf_j_agentsafe_pi_gandalf": 241,
"hf_d_unfair_tos": 281,
"kd_di_newyorker": 145,
"hf_j_agentsafe_creddata": 271,
"kd_gen_tweet_stance": 143,
"inj3_synth_evidence_validation@v1": 200,
"kd_di_contractnli": 139,
"hf_d_dna_response": 229,
"hf_gen_scifact": 246,
"inj3_synth_score_rubric@v1": 200,
"inj3_synth_deductive@v1": 198,
"hf_cola": 224,
"hf_kn_m3ke": 191,
"hf_di_phish_email_fmt": 184,
"h_apibank_fmt": 132,
"h_phish_url_fmt": 187,
"kd_d_mclwic_zh": 109,
"inj3_hf_mj_humaid": 150,
"hf_di_bfcl_w2c_fmt": 210,
"inj3_hf_mj_scitail": 150,
"kd_g_kuake_qic": 97,
"hf_j_agentsafe_pi_deepset": 143,
"hf_j_agentsafe_ai4privacy": 146,
"hf_di_banking77_fmt": 123,
"h_crux_input": 138,
"typed_customer_service_decisive": 129,
"hf_di_nli4ct_fmt": 96,
"inj2_openjevdata_intent_routing": 92,
"hf_j_agentsafe_jb_jackhhao": 111,
"inj2_openjevdata_temporal_numeric": 85,
"inj3_openjevdata_quantitative_reasoning": 78,
"hf_multirc": 104,
"kd_g_wic": 59,
"typed_invoice_processing_decisive": 112,
"inj3_openjevdata_intent_routing": 69,
"typed_security_incidents_decisive": 100,
"kd_mj_tab_wine": 56,
"inj2_openjevdata_evidence_validation": 63,
"inj2_openjevdata_quantitative_reasoning": 76,
"inj2_openjevdata_reading_comprehension": 58,
"openjevdata_score_rubric": 101,
"kd_kn_gaokao": 45,
"inj2_openjevdata_multi_hop": 81,
"inj3_openjevdata_temporal_numeric": 64,
"kd_kn_quail": 44,
"hf_di_ragtruth_fmt": 62,
"inj3_openjevdata_multi_hop": 57,
"inj2_openjevdata_answer_preference": 57,
"inj2_openjevdata_option_logic": 55,
"kd_kn_strategyqa": 37,
"typed_agent_trace_observability_decisive": 73,
"inj3_openjevdata_answer_preference": 39,
"inj2_openjevdata_policy_exception": 31,
"inj3_openjevdata_evidence_validation": 29,
"inj3_openjevdata_reading_comprehension": 35,
"kd_di_acos": 19,
"kd_mj_news_bbc": 19,
"inj2_openjevdata_constraint_planning": 24,
"inj3_openjevdata_option_logic": 33,
"inj3_openjevdata_policy_exception": 26,
"hf_j_ops_hadoop": 21,
"kd_kn_mmlu_aux": 14,
"openjevdata_score_intensity": 19,
"inj2_openjevdata_emotion_recognition": 22,
"inj3_openjevdata_constraint_planning": 16,
"inj3_openjevdata_code_database": 13,
"inj2_openjevdata_code_database": 15,
"inj3_openjevdata_emotion_recognition": 7,
"inj2_openjevdata_score_rubric": 7,
"inj2_openjevdata_probabilistic_reasoning": 6,
"inj3_openjevdata_score_rubric": 2,
"inj2_openjevdata_score_quality": 3,
"inj2_openjevdata_score_intensity": 1,
"inj3_openjevdata_probabilistic_reasoning": 2,
"inj3_openjevdata_score_quality": 1
},
"s1mb_source_declarations": [
{
"benchmark_id": "aqua-rat-choice-test-v1",
"relationship": "same_source_family",
"source_description": "AQuA-RAT (deepmind/aqua_rat) train split.",
"retained_support_channels": {
"r_aqua": 14183,
"kd_kn_aqua": 1178,
"hf_kn_aqua": 732
},
"support_channel_rows": 16093,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "arc-choice-test-v1",
"relationship": "same_source_family",
"source_description": "ARC (allenai/ai2_arc) train split.",
"retained_support_channels": {
"hf_di_arc": 1103,
"hf_di_arc_fmt": 540
},
"support_channel_rows": 1643,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "banking77-choice-test-v1",
"relationship": "same_source_family",
"source_description": "BANKING77 (PolyAI/banking77) train split.",
"retained_support_channels": {
"hf_di_banking77": 1462,
"hf_di_banking77_fmt": 123
},
"support_channel_rows": 1585,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "civil-comments-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Civil Comments (google/civil_comments) train split.",
"retained_support_channels": {
"kd_gen_civil_more": 1103,
"hf_gen_civil_more": 688,
"kd_civil_comments": 393,
"hf_civil_comments": 408
},
"support_channel_rows": 2592,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "cladder-noul-test-v1",
"relationship": "related_domain",
"source_description": "generated CLadder-style causal questions (not drawn from the CLadder release); shared source identity with CLadder is not claimed.",
"retained_support_channels": {
"digap_cladder": 2155
},
"support_channel_rows": 2155,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": null
},
{
"benchmark_id": "clinc-choice-test-v1",
"relationship": "same_source_family",
"source_description": "CLINC150 (clinc_oos) train split.",
"retained_support_channels": {
"kd_g_clinc": 1999,
"hf_g_clinc": 2941
},
"support_channel_rows": 4940,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "contract-nli-choice-test-v1",
"relationship": "same_source_family",
"source_description": "ContractNLI train split.",
"retained_support_channels": {
"hf_di_contractnli": 1340,
"hf_di_contractnli_fmt": 225,
"inj3_hf_di_contractnli": 191,
"kd_di_contractnli": 139
},
"support_channel_rows": 1895,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "dbpedia-choice-test-v1",
"relationship": "same_source_family",
"source_description": "DBpedia-14 (fancyzhx/dbpedia_14) train split.",
"retained_support_channels": {
"kd_dbpedia": 484,
"hf_dbpedia": 460
},
"support_channel_rows": 944,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "esci-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Amazon ESCI train split.",
"retained_support_channels": {
"esci_v2": 5626,
"kd_di_esci": 974
},
"support_channel_rows": 6600,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "go-emotions-noul-test-v1",
"relationship": "same_source_family",
"source_description": "GoEmotions (google-research-datasets/go_emotions) train split.",
"retained_support_channels": {
"kd_gen_goemotions": 1164,
"hf_gen_goemotions": 675
},
"support_channel_rows": 1839,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "gsm8k-choice-test-v1",
"relationship": "same_source_family",
"source_description": "GSM8K (openai/gsm8k) train split.",
"retained_support_channels": {
"k_gsm8k": 7309,
"k_gsm8k_fmt": 1027,
"inj2_k_gsm8k": 781,
"inj3_k_gsm8k": 266
},
"support_channel_rows": 9383,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "laya--typed-decisions-choice-test-v1",
"relationship": "same_source_family",
"source_description": "LocalLLaMA/typed-decisions train data (its four workflows).",
"retained_support_channels": {
"typed_customer_service": 659,
"typed_agent_trace_observability": 703,
"typed_invoice_processing": 663,
"typed_security_incidents": 652,
"typed_customer_service_decisive": 129,
"typed_invoice_processing_decisive": 112,
"typed_security_incidents_decisive": 100,
"typed_agent_trace_observability_decisive": 73
},
"support_channel_rows": 3091,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "laya--typed-decisions-noul-test-v1",
"relationship": "same_source_family",
"source_description": "LocalLLaMA/typed-decisions train data (its four workflows).",
"retained_support_channels": {
"typed_customer_service": 659,
"typed_agent_trace_observability": 703,
"typed_invoice_processing": 663,
"typed_security_incidents": 652,
"typed_customer_service_decisive": 129,
"typed_invoice_processing_decisive": 112,
"typed_security_incidents_decisive": 100,
"typed_agent_trace_observability_decisive": 73
},
"support_channel_rows": 3091,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "laya--typed-decisions-score-test-v1",
"relationship": "same_source_family",
"source_description": "LocalLLaMA/typed-decisions train data (its four workflows).",
"retained_support_channels": {
"typed_customer_service": 659,
"typed_agent_trace_observability": 703,
"typed_invoice_processing": 663,
"typed_security_incidents": 652,
"typed_customer_service_decisive": 129,
"typed_invoice_processing_decisive": 112,
"typed_security_incidents_decisive": 100,
"typed_agent_trace_observability_decisive": 73
},
"support_channel_rows": 3091,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "mtop-choice-test-v1",
"relationship": "same_source_family",
"source_description": "MTOP (tasksource/mtop) train split.",
"retained_support_channels": {
"kd_d_mtop": 1077,
"hf_d_mtop": 1433
},
"support_channel_rows": 2510,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--amount-extraction-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--amount-extraction-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--browser-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--citation-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--context-retention-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--customer-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--customer-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--customer-control-v1-score-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--drone-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--drone-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--drone-control-v1-score-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--email-selection-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--email-selection-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--entity-alignment-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--entity-alignment-control-v1-score-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--ir-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--ir-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--ir-control-v1-score-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--mailroom-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--mailroom-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--painting-geometry-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--painting-geometry-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--painting-geometry-v1-score-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--phone-extraction-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--phone-extraction-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--reasoning-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--reasoning-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--reasoning-control-v1-score-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--silent-failure-control-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--snake-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--snake-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--sponsor-segment-control-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--tic-tac-toe-v1-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--vizdoom-basic-v1-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--vizdoom-basic-v1-score-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--workflow-controls-v1--customer-service-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--workflow-controls-v1--invoice-processing-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "open-jev--workflow-controls-v1--security-incidents-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Open-Jev 1.1 training data (the Open-Jev control families).",
"retained_support_channels": {
"oj11_replay": 2187,
"oj11_community": 1944
},
"support_channel_rows": 4131,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "openbookqa-choice-test-v1",
"relationship": "same_source_family",
"source_description": "OpenBookQA (allenai/openbookqa) train split.",
"retained_support_channels": {
"hf_di_openbookqa": 801,
"hf_di_openbookqa_fmt": 403
},
"support_channel_rows": 1204,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "ruletaker-noul-test-v1",
"relationship": "same_source_family",
"source_description": "RuleTaker / ProofWriter (tasksource/ruletaker, tasksource/proofwriter) train splits.",
"retained_support_channels": {
"kd_kn_proofwriter": 812,
"kd_kn_ruletaker": 415,
"hf_kn_proofwriter": 593,
"hf_kn_ruletaker": 276
},
"support_channel_rows": 2096,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "sgd-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Schema-Guided Dialogue (dstc8-schema-guided-dialogue) train split.",
"retained_support_channels": {
"kd_di_sgd": 961,
"h_sgd": 1290,
"h_sgd_fmt": 376,
"inj2_h_sgd": 281
},
"support_channel_rows": 2908,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "snli-choice-test-v1",
"relationship": "same_source_family",
"source_description": "SNLI (stanfordnlp/snli) train split.",
"retained_support_channels": {
"kd_gen_snli": 1267,
"hf_gen_snli": 750
},
"support_channel_rows": 2017,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "argument-quality-choice-test-v1",
"relationship": "same_source_family",
"source_description": "IBM-ArgQ-Rank-30k (ibm-research/argument_quality_ranking_30k) train split.",
"retained_support_channels": {
"kd_mj_argq_stance": 610,
"hf_mj_argq_stance": 459,
"hf_mj_argq_pair": 424
},
"support_channel_rows": 1493,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "argument-quality-noul-test-v1",
"relationship": "same_source_family",
"source_description": "IBM-ArgQ-Rank-30k (ibm-research/argument_quality_ranking_30k) train split.",
"retained_support_channels": {
"kd_mj_argq_stance": 610,
"hf_mj_argq_stance": 459,
"hf_mj_argq_pair": 424
},
"support_channel_rows": 1493,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "scicite-choice-test-v1",
"relationship": "same_source_family",
"source_description": "SciCite (allenai/scicite) train split.",
"retained_support_channels": {
"kd_mj_scicite": 612,
"hf_mj_scicite": 417
},
"support_channel_rows": 1029,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "scitail-noul-test-v1",
"relationship": "same_source_family",
"source_description": "SciTail (allenai/scitail, snli_format) train split.",
"retained_support_channels": {
"kd_mj_scitail": 624,
"hf_mj_scitail": 443,
"inj3_hf_mj_scitail": 150
},
"support_channel_rows": 1217,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "patent-similarity-score-test-v1",
"relationship": "same_source_family",
"source_description": "Google patent phrase similarity train.csv (the source of tasksource/patent-phrase-similarity).",
"retained_support_channels": {
"kd_patent": 587,
"hf_patent": 366
},
"support_channel_rows": 953,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "aegis2-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Aegis 2.0 safety/routing sources inherited through or1d. The earlier source declaration covered train and validation; retained per-split counts have not been reconstructed for mixU.",
"retained_support_channels": {
"cand_router_hazard": 5500,
"cand_router_safety": 5500,
"kd_gen_aegis_prompt": 826
},
"support_channel_rows": 11826,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": null
},
{
"benchmark_id": "laya--enron-spam-noul-test-v1",
"relationship": "same_source_family",
"source_description": "Enron-Spam (SetFit/enron_spam) train split.",
"retained_support_channels": {
"kd_di_enron_spam": 556
},
"support_channel_rows": 556,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "hh-rlhf-choice-test-v1",
"relationship": "same_source_family",
"source_description": "BeaverTails (PKU-Alignment/BeaverTails 30k_train) and Aegis 2.0 train-split prompts, which reuse Anthropic HH-RLHF red-team prompts.",
"retained_support_channels": {
"kd_gen_aegis_prompt": 826,
"kd_g_beavertails": 761,
"hf_g_beavertails": 803
},
"support_channel_rows": 2390,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": "train"
},
{
"benchmark_id": "synthetic-relevance--nanocoir-noul-test-v1",
"relationship": "related_domain",
"source_description": "DeepMind CodeContests training problems; related code-retrieval domain only, not established CoIR source identity.",
"retained_support_channels": {
"kd_code_contests": 1620,
"hf_code_contests": 616
},
"support_channel_rows": 2236,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": null
},
{
"benchmark_id": "synthetic-relevance--nanocoir-score-test-v1",
"relationship": "related_domain",
"source_description": "DeepMind CodeContests training problems; related code-retrieval domain only, not established CoIR source identity.",
"retained_support_channels": {
"kd_code_contests": 1620,
"hf_code_contests": 616
},
"support_channel_rows": 2236,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": null
},
{
"benchmark_id": "few-nerd-choice-test-v1",
"relationship": "same_source_family",
"source_description": "Few-NERD supervised source sentences recast into PII-redaction routing in the inherited or1d component; exact retained upstream split membership not re-audited.",
"retained_support_channels": {
"cand_router_pii": 5499
},
"support_channel_rows": 5499,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": null
},
{
"benchmark_id": "gretel-pii-choice-test-v1",
"relationship": "related_domain",
"source_description": "yes/no PII-redaction questions built from Gretel's synthetic financial documents (gretelai/synthetic_pii_finance_multilingual), a different Gretel dataset from the gretelai/gretel-pii-masking-en-v1 data behind this benchmark; shared source identity is not claimed.",
"retained_support_channels": {
"cand_router_pii": 5499
},
"support_channel_rows": 5499,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": null
},
{
"benchmark_id": "massive-choice-test-v1",
"relationship": "same_source_family",
"source_description": "OpenJevData-140k intent-routing source family; its source notices list MASSIVE. Exact MASSIVE split/locales and retained item identities are unknown.",
"retained_support_channels": {
"openjevdata_intent_routing": 2242,
"inj2_openjevdata_intent_routing": 92,
"inj3_openjevdata_intent_routing": 69
},
"support_channel_rows": 2403,
"support_count_scope": "Rows in supporting mixed channels; not necessarily all from this upstream source",
"split": null
}
]
}