eval-harness

catalog

Every evaluation, at a glance

Pages the harness builds from this project's committed runs: what each goal concludes so far, when the work happened and what it cost, what each dataset covers, and everything recorded. Every name is a link: goals, datasets, arms, models, reference sets and metrics each have a page, and the inspector tests any arms against a baseline, item by item.

This is eval-harness's catalog, live on its six worked examples. Every run behind the numbers on the findings: each goal is one eval, and the inspector tests any of its arms here, without installing anything.

Ask it from your agent, too. The same catalog answers over MCP at https://evals.humancopilot.eu/mcp: its views as read-only tools (datasets and what is inside them, goals, arms, references, metrics, the inspector's comparisons), for Claude, ChatGPT and the OpenAI API, Gemini, or any MCP client. No sign-in; nothing it does writes or spends. How to connect.

Your own project gets the same pages over its runs: evh catalog, then evh catalog-serve (tutorial 5), and the same tools with evh mcp.

all time, 2026-09-25 to 2026-11-02

goalsdataarmswork and spend

01goals at a glance

The leader is the best arm the goal may recommend (not flagged, over a limit or retired), scored against the gold group's reference; the test is the leader against the baseline alone (threshold 0.05). The goal page tests every arm, Holm across them. recommended is what the goal's strategy picks once limits and the tie-break on cost and speed are applied; its ratios are against the baseline (0.5× costs half).

02activity and spend

activity

293 measured runs (repeats counted one by one), by day and dataset.

0501002026-09-25 · cnn_dailymail_200: 4 runs2026-09-26 · cnn_dailymail_20: 2 runs2026-09-26 · cnn_dailymail_200: 22 runs2026-09-27 · ag_news_200: 28 runs2026-09-27 · dbpedia_280: 27 runs2026-09-28 · few_nerd_280: 27 runs2026-09-28 · scifact_200: 23 runs2026-09-29 · scifact_200: 3 runs2026-09-30 · ag_news_200: 5 runs2026-09-30 · cnn_dailymail_200: 9 runs2026-09-30 · dbpedia_280: 2 runs2026-10-01 · few_nerd_280: 1 runs2026-10-14 · cnn_dailymail_dm200: 4 runs2026-10-15 · cnn_dailymail_dm200: 1 runs2026-10-15 · summeval_100: 7 runs2026-10-18 · summeval_100: 26 runs2026-10-19 · summeval_100: 2 runs2026-10-23 · smoke_v1: 1 runs2026-10-30 · fleet_dedup_v1: 2 runs2026-10-30 · orrery_triage_v1_labelled: 51 runs2026-10-31 · orrery_triage_v1_labelled: 39 runs2026-11-01 · orrery_triage_v1_labelled: 1 runs2026-11-02 · summeval_100: 6 runs09-2510-1411-02

ag_news_200cnn_dailymail_20cnn_dailymail_200cnn_dailymail_dm200dbpedia_280few_nerd_280fleet_dedup_v1orrery_triage_v1_labelledscifact_200smoke_v1summeval_100

spend

systems under test $32.15 · judges $13.50 · total $45.66

$0.0000$25.00$50.00systems under test: $32.15 by 2026-11-022026-09-25 · systems under test: $0.2569 so far2026-09-26 · systems under test: $5.74 so far2026-09-27 · systems under test: $7.49 so far2026-09-28 · systems under test: $12.61 so far2026-09-29 · systems under test: $13.04 so far2026-10-01 · systems under test: $13.08 so far2026-10-18 · systems under test: $20.10 so far2026-10-19 · systems under test: $20.23 so far2026-10-30 · systems under test: $30.15 so far2026-10-31 · systems under test: $31.97 so far2026-11-02 · systems under test: $32.15 so farjudges: $13.50 by 2026-11-022026-10-20 · judges: $0.4106 so far2026-10-21 · judges: $13.33 so far2026-11-02 · judges: $13.50 so far09-2510-1411-02

systems under testjudges

every dataset, arm and kind of spend in the period

03coverage

datasetitemsarms scored againstreference setsmetricsgoalslast run
orrery_triage_v1_labelled65gold 336gold/orrery_triage_v1_labelled, silver/orrery_triage_v1_labelled_hand, silver/orrery_triage_v1_labelled_outcomes
20correct, cost_usd, deferred, escalated, false_alarm, false_dismiss, latency_ms, model_correct, model_escalated, model_false_alarm, model_false_dismiss, model_triage_cost, n_probes, no_decision, table_miss, tokens_in, tokens_out, triage_cost, triage_cost_p10, triage_cost_p3
Triage decisions on Orrery's error signals2026-11-02
cnn_dailymail_200200gold 35 · silver 29 · judged 89gold/cnn_dailymail_200, silver/cnn_dailymail_200
31compression, concision, cost_usd, coverage, fmt_bullets, fmt_label, fmt_markdown, fmt_narration, fmt_overlong, fmt_paragraphs, grounding, input_truncated, judge_anthropic_l, judge_gemma_l, judge_gemma_l_unvalidated, judge_openai_l, judge_qwen_s, judge_qwen_s_unvalidated, judge_score, judge_score_unvalidated, judge_won, latency_ms, length_vs_reference, reasoning_tokens, reference_words, rouge1, rougeLsum, summary_words, tokens_in, tokens_out, truncated
Short news summaries (CNN)2026-11-02
ag_news_200200gold 63gold/ag_news_200, gold/ag_news_200_adj1
13answer_words, confidence, correct, correct_after_repair, cost_usd, fmt_markdown, fmt_verbose, latency_ms, parsed, reasoning_tokens, tokens_in, tokens_out, truncated
News topic classification (AG News)2026-10-25
summeval_100100gold 41gold/summeval_100
23cost_usd, input_truncated, latency_ms, n_pairs, pair_agreement, parsed, reasoning_tokens, rho, rho_coherence, rho_consistency, rho_fluency, rho_relevance, tau, tau_coherence, tau_consistency, tau_fluency, tau_relevance, tie_rate, tokens_in, tokens_out, top1, top1_chance, truncated
A scorer that agrees with experts on summaries (SummEval)2026-11-02
dbpedia_280280gold 29gold/dbpedia_280
13answer_words, confidence, correct, correct_after_repair, cost_usd, fmt_markdown, fmt_verbose, latency_ms, parsed, reasoning_tokens, tokens_in, tokens_out, truncated
Encyclopedia topic classification (DBpedia)2026-09-30
few_nerd_280280gold 28gold/few_nerd_280
20cost_usd, f1, fn, fp, latency_ms, n_gold, n_predicted, parsed, precision, reasoning_tokens, recall, tokens_in, tokens_out, tp, truncated, type_penalty, untyped_f1, untyped_fn, untyped_fp, untyped_tp
Named-entity extraction (Few-NERD)2026-10-01
scifact_200200gold 26gold/scifact_200
19cost_usd, duplicate_ids, found_any, latency_ms, llm_named_unknown, llm_parsed, mrr_10, n_relevant, n_returned, ndcg_10, parsed, rank_of_first, reasoning_tokens, recall_10, recall_100, tokens_in, tokens_out, truncated, unknown_ids
Evidence retrieval for scientific claims (SciFact)2026-09-29
cnn_dailymail_dm200200gold 5gold/cnn_dailymail_dm200
20compression, concision, cost_usd, coverage, fmt_bullets, fmt_label, fmt_markdown, fmt_narration, fmt_overlong, fmt_paragraphs, grounding, input_truncated, latency_ms, length_vs_reference, reference_words, rouge1, rougeLsum, summary_words, tokens_in, tokens_out
Short news summaries (CNN)2026-10-15
cnn_dailymail_2020gold 2gold/cnn_dailymail_20
20compression, concision, cost_usd, coverage, fmt_bullets, fmt_label, fmt_markdown, fmt_narration, fmt_overlong, fmt_paragraphs, grounding, input_truncated, latency_ms, length_vs_reference, reference_words, rouge1, rougeLsum, summary_words, tokens_in, tokens_out
Short news summaries (CNN)2026-09-26
fleet_dedup_v1100silver 1 · none 1silver/fleet_dedup_v1
3class_match, key_match, latency_ms
—2026-10-30
smoke_v15silver 1silver/smoke_v1
4cost_usd, latency_ms, output_words, overlap_f1
—2026-10-23
ag_news_2020—gold/ag_news_20—News topic classification (AG News)—
dbpedia_5656—gold/dbpedia_56—Encyclopedia topic classification (DBpedia)—
few_nerd_5656—gold/few_nerd_56—Named-entity extraction (Few-NERD)—
orrery_triage_smoke2—gold/orrery_triage_smoke———
scifact_4040—gold/scifact_40—Evidence retrieval for scientific claims (SciFact)—

04recorded

whenwhatkind
2026-11-02 16:17judged cnn_mistral_m_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_mistral_s_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_openai_l_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_openai_m_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_openai_s_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_qwen_l_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_qwen_m_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_qwen_s_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_anthropic_l_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_anthropic_m_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_anthropic_s_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_bart_l_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_bart_l_xsum_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_bart_m_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_bart_s_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_deepseek_l_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_deepseek_m_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_deepseek_s_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_gemma_l_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_gemma_m_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_gemma_s_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_glm_l_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_glm_m_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_glm_s_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_lead3_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_llama_l_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_llama_m_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_llama_s_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:17judged cnn_mistral_l_n200_v1 · judged/judge-summ-pick-v1 on cnn_dailymail_200judge
2026-11-02 16:01ran se_qwen_s_n100_pairwise_v1 on summeval_100run
2026-11-02 15:28ran se_gemma_l_n100_pairwise_v1 on summeval_100run
2026-11-02 15:16ran se_qwen_s_n100_pick_v1 on summeval_100run
2026-11-02 15:13ran se_gemma_l_n100_pick_v1 on summeval_100run
2026-11-02 14:14ran se_random_n100_pairwise_v1 on summeval_100run
2026-11-02 14:14ran se_random_n100_pick_v1 on summeval_100run
2026-11-02 08:17rescored triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_phi4_14b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_qwen38_27b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_qwen3_30b_a3b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_gemma4_31b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_gpt_oss_20b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_llama31_8b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_ministral_3_14b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_phi4_14b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_qwen38_27b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_qwen3_30b_a3b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_mistral_large_4_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_sonnet_55_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_stub_dismiss_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_stub_escalate_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c, repeats on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_deepseek_41flash_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_gemini_35_flash_lite_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_gemini_4_argon_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_gpt_61_sol_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_gpt_6_luna_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_haiku_55_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_hosted_gemma4_31b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_hosted_gpt_oss_120b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_hosted_mistral_medium_35_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_hosted_qwen35_122b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_hosted_qwen3_30b_a3b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_kimi_k31_pro_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_gemma4_12b_noreason_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_gemma4_31b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_gpt_oss_120b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_gpt_oss_20b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_llama31_8b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_llama4_scout_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_ministral_3_14b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_mistral_medium_35_128b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_nemotron_35_super_120b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_phi4_14b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_qwen38_27b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_qwen3_30b_a3b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_gemma4_12b_noreason_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_gemma4_31b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_gpt_oss_20b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_llama31_8b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_ministral_3_14b_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_baseline_pro_v1 · rescored 5f2c057c, repeats ×3 on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_gpt_61_sol_v1 · rescored 5f2c057c, repeats ×3 on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3 on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_haiku_55_v1 · rescored 5f2c057c, repeats ×3 on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_baseline_pro_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_hosted_gemma4_31b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_hosted_gpt_oss_120b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_hosted_qwen35_122b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_kimi_k31_pro_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_gemma4_31b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_gpt_oss_120b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_gpt_oss_20b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_nemotron_35_super_120b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_dgx_qwen38_27b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_gemma4_31b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_gpt_oss_20b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_mac_qwen38_27b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_gemma4_31b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_gpt_oss_20b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_local_x3_qwen38_27b_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_mistral_large_4_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_baseline_pro_noreason_v1 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_deepseek_41flash_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17rescored triage_gpt_6_luna_v2 · rescored 5f2c057c on orrery_triage_v1_labelledrescore
2026-11-02 08:17silver reference silver/orrery_triage_v1_labelled_outcomesreference
2026-11-01 08:15closed round r3 of Triage decisions on Orrery's error signalsround
2026-11-01 08:14rescored triage_hosted_gpt_oss_120b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_hosted_mistral_medium_35_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_hosted_qwen35_122b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_hosted_qwen3_30b_a3b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_kimi_k31_pro_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_gemma4_12b_noreason_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_gemma4_31b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_gpt_oss_120b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_gpt_oss_20b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_llama31_8b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_llama4_scout_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_ministral_3_14b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_mistral_medium_35_128b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_nemotron_35_super_120b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_phi4_14b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_qwen35_122b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_qwen38_27b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_qwen3_30b_a3b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_mac_gemma4_12b_noreason_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_mac_gemma4_31b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_mac_gpt_oss_20b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_mac_llama31_8b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_mac_ministral_3_14b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_mac_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_mac_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_mac_phi4_14b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_mac_qwen38_27b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_mac_qwen3_30b_a3b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_x3_gemma4_31b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_x3_gpt_oss_20b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_x3_llama31_8b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_x3_ministral_3_14b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_x3_nemotron_35_bolt_e4b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_x3_nemotron_35_lightning_30b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_x3_phi4_14b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_x3_qwen38_27b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_local_x3_qwen3_30b_a3b_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_mistral_large_4_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_sonnet_55_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_stub_dismiss_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_stub_escalate_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_baseline_pro_noreason_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_baseline_pro_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_deepseek_41flash_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_gemini_35_flash_lite_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_gemini_4_argon_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_gpt_61_sol_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_gpt_6_luna_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_haiku_55_v1 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_hosted_gemma4_31b_v2 · rescored 3d3a6afd on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_baseline_pro_v1 · rescored 3d3a6afd, repeats ×3 on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_gpt_61_sol_v1 · rescored 3d3a6afd, repeats ×3 on orrery_triage_v1_labelledrescore
2026-11-01 08:14rescored triage_haiku_55_v1 · rescored 3d3a6afd, repeats ×3 on orrery_triage_v1_labelledrescore
2026-11-01 08:13ran triage_local_mac_gemma4_31b_v2 on orrery_triage_v1_labelledrun
2026-10-31 17:31ran triage_local_mac_qwen38_27b_v2 on orrery_triage_v1_labelledrun
2026-10-31 16:54ran triage_local_mac_nemotron_35_lightning_30b_v2 on orrery_triage_v1_labelledrun
2026-10-31 16:42ran triage_local_mac_gpt_oss_20b_v2 on orrery_triage_v1_labelledrun
2026-10-31 16:36ran triage_local_mac_nemotron_35_bolt_e4b_v2 on orrery_triage_v1_labelledrun
2026-10-31 16:23ran triage_baseline_pro_noreason_v1 on orrery_triage_v1_labelledrun
2026-10-31 16:14ran triage_mistral_large_4_v2 on orrery_triage_v1_labelledrun
2026-10-31 16:05ran triage_local_dgx_gpt_oss_20b_v2 on orrery_triage_v1_labelledrun
2026-10-31 16:00ran triage_local_dgx_gpt_oss_120b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:51ran triage_kimi_k31_pro_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:51ran triage_local_dgx_nemotron_35_super_120b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:49ran triage_local_x3_qwen38_27b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:32ran triage_local_dgx_qwen35_122b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:28ran triage_hosted_qwen35_122b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:26ran triage_local_x3_nemotron_35_lightning_30b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:21ran triage_hosted_gpt_oss_120b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:18ran triage_local_x3_nemotron_35_bolt_e4b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:16ran triage_local_dgx_nemotron_35_lightning_30b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:14ran triage_hosted_gemma4_31b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:12ran triage_local_x3_gpt_oss_20b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:08ran triage_local_dgx_nemotron_35_bolt_e4b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:05ran triage_local_x3_gemma4_31b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:03ran triage_local_dgx_qwen38_27b_v2 on orrery_triage_v1_labelledrun
2026-10-31 15:02ran triage_gpt_6_luna_v2 on orrery_triage_v1_labelledrun
2026-10-31 14:53ran triage_deepseek_41flash_v2 on orrery_triage_v1_labelledrun
2026-10-31 14:44ran triage_local_dgx_gemma4_31b_v2 on orrery_triage_v1_labelledrun
2026-10-31 14:22closed round r2 of Triage decisions on Orrery's error signalsround
2026-10-31 14:22opened round r3 of Triage decisions on Orrery's error signalsround
2026-10-31 13:23rescored triage_local_dgx_gpt_oss_20b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_llama31_8b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_llama4_scout_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_ministral_3_14b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_mistral_medium_35_128b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_nemotron_35_super_120b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_phi4_14b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_qwen35_122b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_qwen38_27b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_qwen3_30b_a3b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_mac_gemma4_12b_noreason_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_mac_gemma4_31b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_mac_gpt_oss_20b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_mac_llama31_8b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_mac_ministral_3_14b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_mac_nemotron_35_lightning_30b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_mac_phi4_14b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_mac_qwen38_27b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_mac_qwen3_30b_a3b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_x3_gemma4_31b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_x3_gpt_oss_20b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_x3_llama31_8b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_x3_ministral_3_14b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_x3_nemotron_35_lightning_30b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_x3_phi4_14b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_x3_qwen38_27b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_x3_qwen3_30b_a3b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_mistral_large_4_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_sonnet_55_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_stub_dismiss_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_stub_escalate_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored 77adc97b, repeats on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_baseline_pro_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_deepseek_41flash_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_gemini_35_flash_lite_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_gemini_4_argon_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_gpt_61_sol_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_gpt_6_luna_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_haiku_55_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_hosted_gemma4_31b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_hosted_gpt_oss_120b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_hosted_mistral_medium_35_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_hosted_qwen35_122b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_hosted_qwen3_30b_a3b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_kimi_k31_pro_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_gemma4_12b_noreason_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_gemma4_31b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_local_dgx_gpt_oss_120b_v1 · rescored 77adc97b on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_baseline_pro_v1 · rescored 77adc97b, repeats ×3 on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_gpt_61_sol_v1 · rescored 77adc97b, repeats ×3 on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_gpt_6_luna_v1 · rescored 77adc97b, repeats ×3 on orrery_triage_v1_labelledrescore
2026-10-31 13:23rescored triage_haiku_55_v1 · rescored 77adc97b, repeats ×3 on orrery_triage_v1_labelledrescore
2026-10-31 13:23opened round r2 of Triage decisions on Orrery's error signalsround
2026-10-31 13:19promoted triage_baseline_pro_v1 as the baseline on orrery_triage_v1_labelledbaseline
2026-10-31 13:19closed round r1 of Triage decisions on Orrery's error signalsround
2026-10-31 13:18opened round r1 of Triage decisions on Orrery's error signalsround
2026-10-31 11:30rescored triage_baseline_pro_v1 · rescored cd35dc1f, repeats ×3 on orrery_triage_v1_labelledrescore
2026-10-31 11:30rescored triage_gpt_61_sol_v1 · rescored cd35dc1f, repeats ×3 on orrery_triage_v1_labelledrescore
2026-10-31 11:30rescored triage_gpt_6_luna_v1 · rescored cd35dc1f, repeats ×3 on orrery_triage_v1_labelledrescore
2026-10-31 11:30rescored triage_haiku_55_v1 · rescored cd35dc1f, repeats ×3 on orrery_triage_v1_labelledrescore
2026-10-31 11:30rescored triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f, repeats on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_gpt_oss_20b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_llama31_8b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_llama4_scout_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_ministral_3_14b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_mistral_medium_35_128b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_nemotron_35_lightning_30b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_nemotron_35_super_120b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_phi4_14b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_qwen35_122b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_qwen38_27b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_qwen3_30b_a3b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_mac_gemma4_12b_noreason_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_mac_gemma4_31b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_mac_gpt_oss_20b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_mac_llama31_8b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_mac_ministral_3_14b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_mac_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_mac_nemotron_35_lightning_30b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_mac_phi4_14b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_mac_qwen38_27b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_mac_qwen3_30b_a3b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_x3_gemma4_31b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_x3_gpt_oss_20b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_x3_llama31_8b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_x3_ministral_3_14b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_x3_nemotron_35_bolt_e4b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_x3_nemotron_35_lightning_30b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_x3_phi4_14b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_x3_qwen38_27b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_x3_qwen3_30b_a3b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_mistral_large_4_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_sonnet_55_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_stub_dismiss_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_stub_escalate_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_baseline_pro_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_deepseek_41flash_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_gemini_35_flash_lite_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_gemini_4_argon_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_gpt_61_sol_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_gpt_6_luna_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_haiku_55_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_hosted_gemma4_31b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_hosted_gpt_oss_120b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_hosted_mistral_medium_35_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_hosted_qwen35_122b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_hosted_qwen3_30b_a3b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_kimi_k31_pro_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_gemma4_12b_noreason_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_gemma4_31b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 11:08rescored triage_local_dgx_gpt_oss_120b_v1 · rescored cd35dc1f on orrery_triage_v1_labelledrescore
2026-10-31 09:08ran triage_local_dgx_gemma4_12b_noreason_v1 on orrery_triage_v1_labelledrun
2026-10-31 09:06ran triage_local_mac_gemma4_12b_noreason_v1 on orrery_triage_v1_labelledrun
2026-10-31 09:01ran triage_local_dgx_gpt_oss_120b_v1 on orrery_triage_v1_labelledrun
2026-10-31 08:45ran triage_local_mac_ministral_3_14b_v1 on orrery_triage_v1_labelledrun
2026-10-31 08:45ran triage_local_dgx_qwen3_30b_a3b_v1 on orrery_triage_v1_labelledrun
2026-10-31 08:39ran triage_local_dgx_llama31_8b_v1 on orrery_triage_v1_labelledrun
2026-10-31 08:33ran triage_local_dgx_phi4_14b_v1 on orrery_triage_v1_labelledrun
2026-10-31 08:14ran triage_local_dgx_ministral_3_14b_v1 on orrery_triage_v1_labelledrun
2026-10-31 08:08ran triage_local_mac_qwen3_30b_a3b_v1 on orrery_triage_v1_labelledrun
2026-10-31 07:52ran triage_local_dgx_gemma4_31b_v1 on orrery_triage_v1_labelledrun
2026-10-31 07:24ran triage_stub_escalate_v1 on orrery_triage_v1_labelledrun
2026-10-31 07:24ran triage_stub_dismiss_v1 on orrery_triage_v1_labelledrun
2026-10-31 04:22ran triage_local_dgx_vllm_qwen3_30b_a3b_nvfp4_v1 on orrery_triage_v1_labelledrun
2026-10-31 00:37ran triage_local_x3_qwen3_30b_a3b_v1 on orrery_triage_v1_labelledrun
2026-10-30 23:46ran triage_hosted_qwen3_30b_a3b_v1 on orrery_triage_v1_labelledrun
2026-10-30 23:07ran triage_local_mac_qwen38_27b_v1 on orrery_triage_v1_labelledrun
2026-10-30 21:52ran triage_local_mac_phi4_14b_v1 on orrery_triage_v1_labelledrun
2026-10-30 21:28ran triage_local_mac_nemotron_35_lightning_30b_v1 on orrery_triage_v1_labelledrun
2026-10-30 21:06ran triage_local_dgx_qwen38_27b_v1 on orrery_triage_v1_labelledrun
2026-10-30 20:40ran triage_local_x3_nemotron_35_bolt_e4b_v1 · repeats on orrery_triage_v1_labelledrun
2026-10-30 20:25ran triage_local_dgx_gpt_oss_20b_v1 on orrery_triage_v1_labelledrun
2026-10-30 20:11ran triage_local_x3_gpt_oss_20b_v1 on orrery_triage_v1_labelledrun
2026-10-30 20:11ran triage_local_dgx_nemotron_35_lightning_30b_v1 on orrery_triage_v1_labelledrun
2026-10-30 19:57ran triage_local_mac_llama31_8b_v1 on orrery_triage_v1_labelledrun
2026-10-30 19:53ran triage_local_x3_nemotron_35_bolt_e4b_v1 on orrery_triage_v1_labelledrun
2026-10-30 19:49ran triage_local_mac_nemotron_35_bolt_e4b_v1 on orrery_triage_v1_labelledrun
2026-10-30 19:29ran triage_local_x3_nemotron_35_lightning_30b_v1 on orrery_triage_v1_labelledrun
2026-10-30 19:27ran triage_local_dgx_nemotron_35_bolt_e4b_v1 on orrery_triage_v1_labelledrun
2026-10-30 19:23ran triage_local_mac_gemma4_31b_v1 on orrery_triage_v1_labelledrun
2026-10-30 19:11ran triage_local_dgx_nemotron_35_super_120b_v1 on orrery_triage_v1_labelledrun
2026-10-30 18:46ran triage_local_x3_gemma4_31b_v1 on orrery_triage_v1_labelledrun
2026-10-30 18:26ran triage_local_dgx_mistral_medium_35_128b_v1 on orrery_triage_v1_labelledrun
2026-10-30 17:34ran triage_local_mac_gpt_oss_20b_v1 on orrery_triage_v1_labelledrun
2026-10-30 17:28ran triage_local_x3_qwen38_27b_v1 on orrery_triage_v1_labelledrun
2026-10-30 16:33ran triage_local_x3_phi4_14b_v1 on orrery_triage_v1_labelledrun
2026-10-30 16:19ran triage_local_dgx_llama4_scout_v1 on orrery_triage_v1_labelledrun
2026-10-30 16:14ran triage_local_x3_ministral_3_14b_v1 on orrery_triage_v1_labelledrun
2026-10-30 16:04ran triage_local_dgx_qwen35_122b_v1 on orrery_triage_v1_labelledrun
2026-10-30 15:25ran triage_baseline_pro_v1 · repeats ×3 on orrery_triage_v1_labelledrun
2026-10-30 15:07ran triage_local_x3_llama31_8b_v1 on orrery_triage_v1_labelledrun
2026-10-30 14:51ran triage_hosted_gpt_oss_120b_v1 on orrery_triage_v1_labelledrun
2026-10-30 14:37ran triage_gpt_61_sol_v1 · repeats ×3 on orrery_triage_v1_labelledrun
2026-10-30 14:36ran triage_gpt_6_luna_v1 · repeats ×3 on orrery_triage_v1_labelledrun
2026-10-30 14:31ran dedup_pinned_f07efa9_v1 on fleet_dedup_v1run
2026-10-30 14:31silver reference silver/fleet_dedup_v1 written by dedup_pinned_f07efa9_v1reference
2026-10-30 14:30ran dedup_guard_v1 on fleet_dedup_v1run
2026-10-30 14:30ran triage_hosted_qwen35_122b_v1 on orrery_triage_v1_labelledrun
2026-10-30 14:24ran triage_haiku_55_v1 · repeats ×3 on orrery_triage_v1_labelledrun
2026-10-30 14:22ran triage_hosted_gemma4_31b_v1 on orrery_triage_v1_labelledrun
2026-10-30 14:17ran triage_hosted_mistral_medium_35_v1 on orrery_triage_v1_labelledrun
2026-10-30 13:51ran triage_kimi_k31_pro_v1 on orrery_triage_v1_labelledrun
2026-10-30 13:33ran triage_gemini_4_argon_v1 on orrery_triage_v1_labelledrun
2026-10-30 13:25ran triage_baseline_pro_v1 on orrery_triage_v1_labelledrun
2026-10-30 13:15ran triage_mistral_large_4_v1 on orrery_triage_v1_labelledrun
2026-10-30 13:09ran triage_gpt_61_sol_v1 on orrery_triage_v1_labelledrun
2026-10-30 13:09ran triage_gpt_6_luna_v1 on orrery_triage_v1_labelledrun
2026-10-30 13:09ran triage_sonnet_55_v1 on orrery_triage_v1_labelledrun
2026-10-30 13:07ran triage_deepseek_41flash_v1 on orrery_triage_v1_labelledrun
2026-10-30 13:04ran triage_haiku_55_v1 on orrery_triage_v1_labelledrun
2026-10-30 13:00ran triage_gemini_35_flash_lite_v1 on orrery_triage_v1_labelledrun
2026-10-30 12:33gold reference gold/orrery_triage_smokereference
2026-10-30 12:24gold reference gold/orrery_triage_v1_labelledreference
2026-10-30 12:24silver reference silver/orrery_triage_v1_labelled_handreference
2026-10-25 16:49rescored cnn_qwen_m_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_qwen_s_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_qwen_l_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_openai_m_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_openai_s_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_mistral_s_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_openai_l_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_mistral_m_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_llama_s_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_mistral_l_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_llama_m_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_lead3_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_llama_l_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_glm_m_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_glm_s_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_glm_l_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_gemma_m_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_gemma_s_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_gemma_l_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_deepseek_m_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_deepseek_s_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_deepseek_l_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_bart_m_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_bart_s_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_bart_l_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_bart_l_xsum_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_anthropic_s_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_anthropic_l_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:49rescored cnn_anthropic_m_n200_v1 · silver on cnn_dailymail_200rescore
2026-10-25 16:22silver reference silver/cnn_dailymail_200 written by cnn_anthropic_l_n200_v1reference
2026-10-25 15:10rescored ag_anthropic_l_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_anthropic_m_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_anthropic_s_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_bart_mnli_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_bert_base_fy_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_bert_base_ta_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_bert_mini_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_constant_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_deepseek_l_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_deepseek_m_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_deepseek_s_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_gemma_l_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_gemma_m_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_gemma_s_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_glm_l_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_glm_m_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_glm_s_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_keyword_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_llama_l_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_llama_m_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_llama_s_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_mistral_l_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_mistral_m_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_mistral_s_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_openai_l_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_openai_m_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_openai_s_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_qwen_l_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_qwen_m_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 15:10rescored ag_qwen_s_n200_v1 · adjudicated on ag_news_200rescore
2026-10-25 14:08promoted fn_span_marker_n200_v1 as the baseline on few_nerd_280baseline
2026-10-25 14:08promoted ag_bert_mini_n200_v1 as the baseline on ag_news_200baseline
2026-10-25 14:08promoted cnn_bart_l_n200_v1 as the baseline on cnn_dailymail_200baseline
2026-10-25 14:08promoted db_bert_base_fy_n200_v1 as the baseline on dbpedia_280baseline
2026-10-25 14:08promoted se_gemma_l_n100_v1 as the baseline on summeval_100baseline
2026-10-25 14:08promoted sf_e5_base_n200_v1 as the baseline on scifact_200baseline
2026-10-25 13:39judged cnn_bart_l_n200_v1 · judged/judge-summ-pointwise-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_deepseek_m_n200_v1 · judged/judge-summ-pointwise-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_anthropic_l_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_anthropic_m_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_anthropic_s_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_bart_l_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_bart_l_xsum_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_bart_m_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_bart_s_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_deepseek_l_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_deepseek_m_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_deepseek_s_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_gemma_l_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_gemma_m_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_gemma_s_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_glm_l_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_glm_m_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_glm_s_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_lead3_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_llama_l_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_llama_m_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_llama_s_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_mistral_l_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_mistral_m_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_mistral_s_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_openai_l_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_openai_m_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_openai_s_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_qwen_l_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_qwen_m_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_qwen_s_n200_v1 · judged/judge-summ-v2 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_anthropic_l_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_anthropic_m_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_anthropic_s_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_bart_l_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_bart_l_xsum_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_bart_m_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_bart_s_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_deepseek_l_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_deepseek_m_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_deepseek_s_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_gemma_l_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_gemma_m_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_gemma_s_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_glm_l_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_glm_m_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_glm_s_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_lead3_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_llama_l_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_llama_m_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_llama_s_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_mistral_l_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_mistral_m_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_mistral_s_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_openai_l_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_openai_m_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_openai_s_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_qwen_l_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_qwen_m_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-25 13:39judged cnn_qwen_s_n200_v1 · judged/judge-summ-v1 on cnn_dailymail_200judge
2026-10-23 14:23promoted demo_v1 as the baseline on smoke_v1baseline
2026-10-23 14:23ran demo_v1 on smoke_v1run
2026-10-19 15:20gold reference gold/ag_news_200_adj1reference
2026-10-19 07:22ran se_gemma_l_pubtextcw_n100_v1 · pair on summeval_100run
2026-10-19 07:22closed round r2 of A scorer that agrees with experts on summaries (SummEval)round
2026-10-19 07:08ran se_gemma_l_pubtext_n100_v1 · pair on summeval_100run
2026-10-19 07:08opened round r2 of A scorer that agrees with experts on summaries (SummEval)round
2026-10-18 23:26ran se_unievalpub_n100_v1 on summeval_100run
2026-10-18 23:26closed round r1 of A scorer that agrees with experts on summaries (SummEval)round
2026-10-18 22:11ran se_unieval_n100_v1 on summeval_100run
2026-10-18 13:07ran se_qwen37max_n100_v1 on summeval_100run
2026-10-18 12:02ran se_anthropic_l_n100_v1 on summeval_100run
2026-10-18 11:56ran se_anthropic_m_n100_v1 on summeval_100run
2026-10-18 11:51ran se_openai_l_n100_v1 on summeval_100run
2026-10-18 11:48ran se_openai_m_n100_v1 on summeval_100run
2026-10-18 11:43ran se_anthropic_s_n100_v1 on summeval_100run
2026-10-18 11:39ran se_mistral_l_n100_v1 on summeval_100run
2026-10-18 11:21ran se_mistral_m_n100_v1 on summeval_100run
2026-10-18 11:17ran se_openai_s_n100_v1 on summeval_100run
2026-10-18 11:15ran se_glm_l_n100_v1 on summeval_100run
2026-10-18 11:09ran se_deepseek_l_n100_v1 on summeval_100run
2026-10-18 10:59ran se_qwen_m_n100_v1 on summeval_100run
2026-10-18 10:48ran se_llama_l_n100_v1 on summeval_100run
2026-10-18 10:27ran se_glm_m_n100_v1 on summeval_100run
2026-10-18 10:21ran se_deepseek_m_n100_v1 on summeval_100run
2026-10-18 10:19ran se_deepseek_s_n100_v1 on summeval_100run
2026-10-18 10:13ran se_llama_m_n100_v1 on summeval_100run
2026-10-18 10:04ran se_llama_s_n100_v1 on summeval_100run
2026-10-18 09:52ran se_gemma_l_n100_v1 on summeval_100run
2026-10-18 09:41ran se_glm_s_n100_v1 on summeval_100run
2026-10-18 09:32ran se_qwen_s_n100_v1 on summeval_100run
2026-10-18 09:25ran se_gemma_s_n100_v1 on summeval_100run
2026-10-18 09:06ran se_gemma_m_n100_v1 on summeval_100run
2026-10-18 08:58ran se_mistral_s_n100_v1 on summeval_100run
2026-10-15 13:42ran se_bartscore_n100_v1 on summeval_100run
2026-10-15 13:07ran se_coverage_n100_v1 on summeval_100run
2026-10-15 13:05ran se_length_n100_v1 on summeval_100run
2026-10-15 13:05ran se_random_n100_v1 on summeval_100run
2026-10-15 13:05ran se_rougeL_n100_v1 on summeval_100run
2026-10-15 13:04ran se_rouge2_n100_v1 on summeval_100run
2026-10-15 13:04ran se_rouge1_n100_v1 on summeval_100run
2026-10-15 13:04opened round r1 of A scorer that agrees with experts on summaries (SummEval)round
2026-10-15 13:03gold reference gold/summeval_100reference
2026-10-15 04:37ran cnn_bart_s_dm200_v1 on cnn_dailymail_dm200run
2026-10-14 15:38ran cnn_bart_l_dm200_v1 on cnn_dailymail_dm200run
2026-10-14 15:00ran cnn_bart_l_xsum_dm200_v1 on cnn_dailymail_dm200run
2026-10-14 14:40ran cnn_bart_m_dm200_v1 on cnn_dailymail_dm200run
2026-10-14 13:41ran cnn_lead3_dm200_v1 on cnn_dailymail_dm200run
2026-10-14 13:39gold reference gold/cnn_dailymail_dm200reference
2026-10-01 14:21closed round r1 of Named-entity extraction (Few-NERD)round
2026-10-01 13:08rescored fn_mistral_l_n200_v1 on few_nerd_280rescore
2026-09-30 15:48ran cnn_bart_l_n200_v1 · linux on cnn_dailymail_200run
2026-09-30 15:48closed round r2 of Short news summaries (CNN)round
2026-09-30 15:26ran cnn_bart_l_xsum_n200_v1 · linux on cnn_dailymail_200run
2026-09-30 15:09ran cnn_bart_m_n200_v1 · linux on cnn_dailymail_200run
2026-09-30 14:53ran cnn_bart_s_n200_v1 · linux on cnn_dailymail_200run
2026-09-30 14:41ran cnn_lead3_n200_v1 · linux on cnn_dailymail_200run
2026-09-30 14:41opened round r2 of Short news summaries (CNN)round
2026-09-30 14:41ran db_bert_base_fy_n200_v1 · linux on dbpedia_280run
2026-09-30 14:41opened round r2 of Encyclopedia topic classification (DBpedia)round
2026-09-30 14:41closed round r2 of Encyclopedia topic classification (DBpedia)round
2026-09-30 14:40ran ag_bert_base_fy_n200_v1 · linux on ag_news_200run
2026-09-30 14:40closed round r2 of News topic classification (AG News)round
2026-09-30 14:39ran ag_bert_base_ta_n200_v1 · linux on ag_news_200run
2026-09-30 14:38ran ag_bert_mini_n200_v1 · linux on ag_news_200run
2026-09-30 14:38opened round r2 of News topic classification (AG News)round
2026-09-30 09:46ran ag_bert_base_ta_n200_v1 on ag_news_200run
2026-09-30 09:46closed round r1 of News topic classification (AG News)round
2026-09-30 09:45ran ag_bert_base_fy_n200_v1 on ag_news_200run
2026-09-30 09:45ran cnn_bart_l_xsum_n200_v1 on cnn_dailymail_200run
2026-09-30 09:45closed round r1 of Short news summaries (CNN)round
2026-09-30 09:29ran cnn_bart_s_n200_v1 on cnn_dailymail_200run
2026-09-30 09:12ran cnn_bart_s_n200_v1 · repeats on cnn_dailymail_200run
2026-09-30 09:12opened round r3 of Short news summaries (CNN)round
2026-09-30 09:12closed round r3 of Short news summaries (CNN)round
2026-09-30 09:10ran db_bert_base_fy_n200_v1 on dbpedia_280run
2026-09-30 09:10closed round r1 of Encyclopedia topic classification (DBpedia)round
2026-09-30 08:57ran cnn_bart_m_n200_v1 on cnn_dailymail_200run
2026-09-29 18:04closed round r3 of Evidence retrieval for scientific claims (SciFact)round
2026-09-29 17:44re-parsed sf_qwen_s_n200_v1 · repeats on scifact_200reparse
2026-09-29 17:27re-parsed sf_llama_s_n200_v1 · repeats on scifact_200reparse
2026-09-29 17:27opened round r3 of Evidence retrieval for scientific claims (SciFact)round
2026-09-29 16:49re-parsed sf_llama_l_n200_v1 · repeats on scifact_200reparse
2026-09-28 23:15closed round r2 of Evidence retrieval for scientific claims (SciFact)round
2026-09-28 22:54re-parsed sf_qwen_s_e5first_n200_v1 · pair on scifact_200reparse
2026-09-28 22:33re-parsed sf_qwen_s_bm25first_n200_v1 · pair on scifact_200reparse
2026-09-28 22:23re-parsed sf_glm_s_e5first_n200_v1 · pair on scifact_200reparse
2026-09-28 22:23opened round r2 of Evidence retrieval for scientific claims (SciFact)round
2026-09-28 22:13re-parsed sf_glm_s_bm25first_n200_v1 · pair on scifact_200reparse
2026-09-28 22:01closed round r1 of Evidence retrieval for scientific claims (SciFact)round
2026-09-28 21:46re-parsed sf_llama_l_n200_v1 on scifact_200reparse
2026-09-28 21:23re-parsed sf_glm_m_n200_v1 on scifact_200reparse
2026-09-28 21:19re-parsed sf_deepseek_m_n200_v1 on scifact_200reparse
2026-09-28 21:05re-parsed sf_llama_m_n200_v1 on scifact_200reparse
2026-09-28 20:54re-parsed sf_deepseek_s_n200_v1 on scifact_200reparse
2026-09-28 20:21re-parsed sf_gemma_l_n200_v1 on scifact_200reparse
2026-09-28 19:23re-parsed sf_llama_s_n200_v1 on scifact_200reparse
2026-09-28 18:59re-parsed sf_gemma_s_n200_v1 on scifact_200reparse
2026-09-28 18:40re-parsed sf_gemma_m_n200_v1 on scifact_200reparse
2026-09-28 18:30re-parsed sf_glm_s_n200_v1 on scifact_200reparse
2026-09-28 18:06re-parsed sf_mistral_s_n200_v1 on scifact_200reparse
2026-09-28 17:47re-parsed sf_qwen_s_n200_v1 on scifact_200reparse
2026-09-28 17:46re-parsed sf_e5_base_n200_v1 on scifact_200reparse
2026-09-28 17:46re-parsed sf_mpnet_n200_v1 on scifact_200reparse
2026-09-28 17:46re-parsed sf_bge_small_n200_v1 on scifact_200reparse
2026-09-28 17:46re-parsed sf_first_k_n200_v1 on scifact_200reparse
2026-09-28 17:46re-parsed sf_minilm_n200_v1 on scifact_200reparse
2026-09-28 17:46re-parsed sf_random_n200_v1 on scifact_200reparse
2026-09-28 17:46opened round r1 of Evidence retrieval for scientific claims (SciFact)round
2026-09-28 17:46re-parsed sf_bm25_n200_v1 on scifact_200reparse
2026-09-28 14:59gold reference gold/scifact_200reference
2026-09-28 14:59gold reference gold/scifact_40reference
2026-09-28 14:19rescored fn_qwen_s_n200_v1 on few_nerd_280rescore
2026-09-28 14:09rescored fn_qwen_m_n200_v1 on few_nerd_280rescore
2026-09-28 14:01rescored fn_qwen_l_n200_v1 on few_nerd_280rescore
2026-09-28 13:55rescored fn_openai_s_n200_v1 on few_nerd_280rescore
2026-09-28 13:48rescored fn_openai_m_n200_v1 on few_nerd_280rescore
2026-09-28 13:39rescored fn_openai_l_n200_v1 on few_nerd_280rescore
2026-09-28 13:29rescored fn_mistral_s_n200_v1 on few_nerd_280rescore
2026-09-28 13:25rescored fn_mistral_m_n200_v1 on few_nerd_280rescore
2026-09-28 12:54rescored fn_llama_s_n200_v1 on few_nerd_280rescore
2026-09-28 12:29rescored fn_llama_m_n200_v1 on few_nerd_280rescore
2026-09-28 12:07rescored fn_llama_l_n200_v1 on few_nerd_280rescore
2026-09-28 11:57rescored fn_glm_s_n200_v1 on few_nerd_280rescore
2026-09-28 11:40rescored fn_glm_m_n200_v1 on few_nerd_280rescore
2026-09-28 10:50rescored fn_glm_l_n200_v1 on few_nerd_280rescore
2026-09-28 10:22rescored fn_gemma_s_n200_v1 on few_nerd_280rescore
2026-09-28 10:08rescored fn_gemma_m_n200_v1 on few_nerd_280rescore
2026-09-28 09:55rescored fn_gemma_l_n200_v1 on few_nerd_280rescore
2026-09-28 09:44rescored fn_deepseek_s_n200_v1 on few_nerd_280rescore
2026-09-28 09:38rescored fn_deepseek_m_n200_v1 on few_nerd_280rescore
2026-09-28 09:21rescored fn_deepseek_l_n200_v1 on few_nerd_280rescore
2026-09-28 09:14rescored fn_anthropic_s_n200_v1 on few_nerd_280rescore
2026-09-28 09:02rescored fn_anthropic_m_n200_v1 on few_nerd_280rescore
2026-09-28 08:49rescored fn_anthropic_l_n200_v1 on few_nerd_280rescore
2026-09-28 07:08rescored fn_span_marker_n200_v1 on few_nerd_280rescore
2026-09-28 07:07rescored fn_gliner_n200_v1 on few_nerd_280rescore
2026-09-28 07:07rescored fn_capitalized_n200_v1 on few_nerd_280rescore
2026-09-28 07:07rescored fn_nothing_n200_v1 on few_nerd_280rescore
2026-09-28 07:07opened round r1 of Named-entity extraction (Few-NERD)round
2026-09-28 05:58gold reference gold/few_nerd_56reference
2026-09-28 05:40gold reference gold/few_nerd_280reference
2026-09-27 18:29ran db_bart_mnli_n200_v1 on dbpedia_280run
2026-09-27 17:56ran db_qwen_s_n200_v1 on dbpedia_280run
2026-09-27 16:58ran db_qwen_m_n200_v1 on dbpedia_280run
2026-09-27 16:54ran db_qwen_l_n200_v1 on dbpedia_280run
2026-09-27 16:46ran db_openai_s_n200_v1 on dbpedia_280run
2026-09-27 16:42ran db_openai_m_n200_v1 on dbpedia_280run
2026-09-27 16:36ran db_openai_l_n200_v1 on dbpedia_280run
2026-09-27 16:30ran db_mistral_s_n200_v1 on dbpedia_280run
2026-09-27 16:26ran db_mistral_m_n200_v1 on dbpedia_280run
2026-09-27 16:24ran db_mistral_l_n200_v1 on dbpedia_280run
2026-09-27 15:28ran db_llama_s_n200_v1 on dbpedia_280run
2026-09-27 15:21ran db_llama_m_n200_v1 on dbpedia_280run
2026-09-27 15:12ran db_llama_l_n200_v1 on dbpedia_280run
2026-09-27 15:09ran db_keyword_n200_v1 on dbpedia_280run
2026-09-27 15:09ran db_glm_s_n200_v1 on dbpedia_280run
2026-09-27 15:03ran db_glm_m_n200_v1 on dbpedia_280run
2026-09-27 14:54ran db_glm_l_n200_v1 on dbpedia_280run
2026-09-27 14:45ran db_gemma_s_n200_v1 on dbpedia_280run
2026-09-27 14:42ran db_gemma_m_n200_v1 on dbpedia_280run
2026-09-27 14:38ran db_gemma_l_n200_v1 on dbpedia_280run
2026-09-27 14:33ran db_deepseek_s_n200_v1 on dbpedia_280run
2026-09-27 14:25ran db_deepseek_m_n200_v1 on dbpedia_280run
2026-09-27 14:21ran db_deepseek_l_n200_v1 on dbpedia_280run
2026-09-27 14:12ran db_constant_n200_v1 on dbpedia_280run
2026-09-27 14:12ran db_anthropic_s_n200_v1 on dbpedia_280run
2026-09-27 14:07ran db_anthropic_m_n200_v1 on dbpedia_280run
2026-09-27 13:57ran db_anthropic_l_n200_v1 on dbpedia_280run
2026-09-27 13:57opened round r1 of Encyclopedia topic classification (DBpedia)round
2026-09-27 11:58gold reference gold/dbpedia_280reference
2026-09-27 11:58gold reference gold/dbpedia_56reference
2026-09-27 10:53ran ag_qwen_s_n200_v1 on ag_news_200run
2026-09-27 10:49ran ag_qwen_m_n200_v1 on ag_news_200run
2026-09-27 10:46ran ag_qwen_l_n200_v1 on ag_news_200run
2026-09-27 10:36ran ag_openai_s_n200_v1 on ag_news_200run
2026-09-27 10:33ran ag_openai_m_n200_v1 on ag_news_200run
2026-09-27 10:30ran ag_openai_l_n200_v1 on ag_news_200run
2026-09-27 10:26ran ag_mistral_s_n200_v1 on ag_news_200run
2026-09-27 10:23ran ag_mistral_m_n200_v1 on ag_news_200run
2026-09-27 10:22ran ag_mistral_l_n200_v1 on ag_news_200run
2026-09-27 09:51ran ag_llama_s_n200_v1 on ag_news_200run
2026-09-27 09:48ran ag_llama_m_n200_v1 on ag_news_200run
2026-09-27 09:44ran ag_llama_l_n200_v1 on ag_news_200run
2026-09-27 09:41ran ag_keyword_n200_v1 on ag_news_200run
2026-09-27 09:41ran ag_glm_s_n200_v1 on ag_news_200run
2026-09-27 09:37ran ag_glm_m_n200_v1 on ag_news_200run
2026-09-27 09:30ran ag_glm_l_n200_v1 on ag_news_200run
2026-09-27 09:23ran ag_gemma_s_n200_v1 on ag_news_200run
2026-09-27 09:21ran ag_gemma_m_n200_v1 on ag_news_200run
2026-09-27 09:19ran ag_gemma_l_n200_v1 on ag_news_200run
2026-09-27 09:16ran ag_deepseek_s_n200_v1 on ag_news_200run
2026-09-27 09:10ran ag_deepseek_m_n200_v1 on ag_news_200run
2026-09-27 09:07ran ag_deepseek_l_n200_v1 on ag_news_200run
2026-09-27 09:03ran ag_constant_n200_v1 on ag_news_200run
2026-09-27 09:03ran ag_bert_mini_n200_v1 on ag_news_200run
2026-09-27 09:03ran ag_bart_mnli_n200_v1 on ag_news_200run
2026-09-27 08:58ran ag_anthropic_s_n200_v1 on ag_news_200run
2026-09-27 08:55ran ag_anthropic_m_n200_v1 on ag_news_200run
2026-09-27 08:48ran ag_anthropic_l_n200_v1 on ag_news_200run
2026-09-27 08:48opened round r1 of News topic classification (AG News)round
2026-09-27 08:02gold reference gold/ag_news_200reference
2026-09-27 08:02gold reference gold/ag_news_20reference
2026-09-26 16:14ran cnn_bart_l_n200_v1 on cnn_dailymail_200run
2026-09-26 15:37ran cnn_bart_l_v1 on cnn_dailymail_20run
2026-09-26 15:33ran cnn_lead3_n200_v1 on cnn_dailymail_200run
2026-09-26 15:33ran cnn_lead3_v1 on cnn_dailymail_20run
2026-09-26 11:28ran cnn_mistral_s_n200_v1 on cnn_dailymail_200run
2026-09-26 11:19ran cnn_mistral_m_n200_v1 on cnn_dailymail_200run
2026-09-26 11:10ran cnn_mistral_l_n200_v1 on cnn_dailymail_200run
2026-09-26 10:29ran cnn_glm_s_n200_v1 on cnn_dailymail_200run
2026-09-26 10:23ran cnn_glm_m_n200_v1 on cnn_dailymail_200run
2026-09-26 10:12ran cnn_glm_l_n200_v1 on cnn_dailymail_200run
2026-09-26 09:53ran cnn_qwen_s_n200_v1 on cnn_dailymail_200run
2026-09-26 08:12ran cnn_qwen_l_n200_v1 on cnn_dailymail_200run
2026-09-26 08:02ran cnn_gemma_s_n200_v1 on cnn_dailymail_200run
2026-09-26 07:39ran cnn_gemma_m_n200_v1 on cnn_dailymail_200run
2026-09-26 07:32ran cnn_gemma_l_n200_v1 on cnn_dailymail_200run
2026-09-26 07:24ran cnn_llama_s_n200_v1 on cnn_dailymail_200run
2026-09-26 07:05ran cnn_openai_s_n200_v1 on cnn_dailymail_200run
2026-09-26 07:00ran cnn_openai_m_n200_v1 on cnn_dailymail_200run
2026-09-26 06:54ran cnn_anthropic_s_n200_v1 on cnn_dailymail_200run
2026-09-26 06:48ran cnn_anthropic_l_n200_v1 on cnn_dailymail_200run
2026-09-26 00:32ran cnn_anthropic_m_n200_v1 on cnn_dailymail_200run
2026-09-26 00:22ran cnn_openai_l_n200_v1 on cnn_dailymail_200run
2026-09-26 00:16ran cnn_llama_l_n200_v1 on cnn_dailymail_200run
2026-09-26 00:04ran cnn_llama_m_n200_v1 on cnn_dailymail_200run
2026-09-25 23:51ran cnn_deepseek_l_n200_v1 on cnn_dailymail_200run
2026-09-25 23:42ran cnn_deepseek_m_n200_v1 on cnn_dailymail_200run
2026-09-25 23:36ran cnn_deepseek_s_n200_v1 on cnn_dailymail_200run
2026-09-25 23:26ran cnn_qwen_m_n200_v1 on cnn_dailymail_200run
2026-09-25 23:26opened round r1 of Short news summaries (CNN)round
2026-09-25 23:19gold reference gold/cnn_dailymail_200reference
2026-09-25 08:00gold reference gold/cnn_dailymail_20reference
2026-09-25 05:53silver reference silver/smoke_v1 written by reference_opus_v1reference