Datasets:
task_id stringlengths 3 3 | sample int32 0 3 | status stringclasses 3
values | score float64 0 1 | task_mean_score float64 0 1 | task_done_rate float64 0.5 1 | n_turns int32 2 20 | n_tool_calls int32 0 20 | task stringlengths 243 864 | final stringlengths 0 21.5k | final_unwrapped stringclasses 45
values | transcript stringlengths 5.73k 203k | messages listlengths 5 42 | action_only_trajectories listlengths 4 41 | full_trajectories listlengths 4 41 | condition stringclasses 1
value | run_id stringclasses 1
value | eval_job_id stringclasses 1
value | base_model stringclasses 1
value | base_model_revision stringclasses 1
value | loss_tokens int64 30M 30M | notes_loss_tokens int64 21M 21M | recall_loss_tokens int64 9M 9M | epochs int32 2 2 | turn_budget int32 20 20 | error stringclasses 0
values | judge_score float64 0 1 | graded_response stringlengths 0 6k | judge_criteria listlengths 1 85 | judge_responses listlengths | judge_response_status stringclasses 2
values | judge_model stringclasses 1
value | judge_model_revision stringclasses 1
value |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
001 | 0 | done | 0.429 | 0.3571 | 1 | 5 | 4 | "I'm assembling a bank of our antitrust practice's deals that drew regulatory scrutiny — pull ever(...TRUNCATED) | "Based on my comprehensive search of the Calderwood & Harkness LLP DMS, I have identified **one matt(...TRUNCATED) | "=== SYSTEM PROMPT ===\nYou are an agent exploring the document management system (DMS) of the law f(...TRUNCATED) | [{"role":"system","content":"You are an agent exploring the document management system (DMS) of the (...TRUNCATED) | [{"role":"user","content":"I'm assembling a bank of our antitrust practice's deals that drew regulat(...TRUNCATED) | [{"role":"user","content":"I'm assembling a bank of our antitrust practice's deals that drew regulat(...TRUNCATED) | scale70-30m | scale70-30m-20t-think | 115167 | Qwen/Qwen3.5-9B | c202236235762e1c871ad0ccb60c8ee5ba337b9a | 30,004,389 | 21,003,132 | 9,001,257 | 2 | 20 | null | 0.429 | "Based on my comprehensive search of the Calderwood & Harkness LLP DMS, I have identified **one matt(...TRUNCATED) | ["Identifies matter 1003-00001 (Harrowgate PE) as a qualifying matter.","Identifies matter 1038-0000(...TRUNCATED) | null | not_saved_by_harness | zai-org/GLM-4-32B-0414 | 077b5c2f5c43bd3239fd605a0600229e8facbd4a | |
001 | 1 | done | 0.286 | 0.3571 | 1 | 4 | 3 | "I'm assembling a bank of our antitrust practice's deals that drew regulatory scrutiny — pull ever(...TRUNCATED) | "Based on my search through the DMS, I identified **three antitrust matters** where C&H drew an HSR (...TRUNCATED) | "=== SYSTEM PROMPT ===\nYou are an agent exploring the document management system (DMS) of the law f(...TRUNCATED) | [{"role":"system","content":"You are an agent exploring the document management system (DMS) of the (...TRUNCATED) | [{"role":"user","content":"I'm assembling a bank of our antitrust practice's deals that drew regulat(...TRUNCATED) | [{"role":"user","content":"I'm assembling a bank of our antitrust practice's deals that drew regulat(...TRUNCATED) | scale70-30m | scale70-30m-20t-think | 115167 | Qwen/Qwen3.5-9B | c202236235762e1c871ad0ccb60c8ee5ba337b9a | 30,004,389 | 21,003,132 | 9,001,257 | 2 | 20 | null | 0.286 | "Based on my search through the DMS, I identified **three antitrust matters** where C&H drew an HSR (...TRUNCATED) | ["Identifies matter 1003-00001 (Harrowgate PE) as a qualifying matter.","Identifies matter 1038-0000(...TRUNCATED) | null | not_saved_by_harness | zai-org/GLM-4-32B-0414 | 077b5c2f5c43bd3239fd605a0600229e8facbd4a | |
001 | 2 | done | 0.429 | 0.3571 | 1 | 4 | 3 | "I'm assembling a bank of our antitrust practice's deals that drew regulatory scrutiny — pull ever(...TRUNCATED) | "# Antitrust Matters with HSR Second Requests — Calderwood & Harkness LLP\n\n## Summary\n\nBased o(...TRUNCATED) | "=== SYSTEM PROMPT ===\nYou are an agent exploring the document management system (DMS) of the law f(...TRUNCATED) | [{"role":"system","content":"You are an agent exploring the document management system (DMS) of the (...TRUNCATED) | [{"role":"user","content":"I'm assembling a bank of our antitrust practice's deals that drew regulat(...TRUNCATED) | [{"role":"user","content":"I'm assembling a bank of our antitrust practice's deals that drew regulat(...TRUNCATED) | scale70-30m | scale70-30m-20t-think | 115167 | Qwen/Qwen3.5-9B | c202236235762e1c871ad0ccb60c8ee5ba337b9a | 30,004,389 | 21,003,132 | 9,001,257 | 2 | 20 | null | 0.429 | "# Antitrust Matters with HSR Second Requests — Calderwood & Harkness LLP\n\n## Summary\n\nBased o(...TRUNCATED) | ["Identifies matter 1003-00001 (Harrowgate PE) as a qualifying matter.","Identifies matter 1038-0000(...TRUNCATED) | null | not_saved_by_harness | zai-org/GLM-4-32B-0414 | 077b5c2f5c43bd3239fd605a0600229e8facbd4a | |
001 | 3 | done | 0.286 | 0.3571 | 1 | 4 | 3 | "I'm assembling a bank of our antitrust practice's deals that drew regulatory scrutiny — pull ever(...TRUNCATED) | "**Summary of Antitrust Matters with HSR Second Requests at C&H**\n\n**Matter 1003-00001** (Harrowga(...TRUNCATED) | "=== SYSTEM PROMPT ===\nYou are an agent exploring the document management system (DMS) of the law f(...TRUNCATED) | [{"role":"system","content":"You are an agent exploring the document management system (DMS) of the (...TRUNCATED) | [{"role":"user","content":"I'm assembling a bank of our antitrust practice's deals that drew regulat(...TRUNCATED) | [{"role":"user","content":"I'm assembling a bank of our antitrust practice's deals that drew regulat(...TRUNCATED) | scale70-30m | scale70-30m-20t-think | 115167 | Qwen/Qwen3.5-9B | c202236235762e1c871ad0ccb60c8ee5ba337b9a | 30,004,389 | 21,003,132 | 9,001,257 | 2 | 20 | null | 0.286 | "**Summary of Antitrust Matters with HSR Second Requests at C&H**\n\n**Matter 1003-00001** (Harrowga(...TRUNCATED) | ["Identifies matter 1003-00001 (Harrowgate PE) as a qualifying matter.","Identifies matter 1038-0000(...TRUNCATED) | null | not_saved_by_harness | zai-org/GLM-4-32B-0414 | 077b5c2f5c43bd3239fd605a0600229e8facbd4a | |
002 | 0 | done | 0.5 | 0.3125 | 1 | 4 | 3 | "A merger client is asking about clearance timeline risk and I want to ground my advice in our own t(...TRUNCATED) | "Based on my review of the firm's antitrust work product in the DMS, only **one merger review** in o(...TRUNCATED) | "=== SYSTEM PROMPT ===\nYou are an agent exploring the document management system (DMS) of the law f(...TRUNCATED) | [{"role":"system","content":"You are an agent exploring the document management system (DMS) of the (...TRUNCATED) | [{"role":"user","content":"A merger client is asking about clearance timeline risk and I want to gro(...TRUNCATED) | [{"role":"user","content":"A merger client is asking about clearance timeline risk and I want to gro(...TRUNCATED) | scale70-30m | scale70-30m-20t-think | 115167 | Qwen/Qwen3.5-9B | c202236235762e1c871ad0ccb60c8ee5ba337b9a | 30,004,389 | 21,003,132 | 9,001,257 | 2 | 20 | null | 0.5 | "Based on my review of the firm's antitrust work product in the DMS, only **one merger review** in o(...TRUNCATED) | ["Identifies matter 1003-00001 (Harrowgate PE) as a qualifying matter.","Identifies matter 1038-0000(...TRUNCATED) | null | not_saved_by_harness | zai-org/GLM-4-32B-0414 | 077b5c2f5c43bd3239fd605a0600229e8facbd4a | |
002 | 1 | done | 0.5 | 0.3125 | 1 | 4 | 3 | "A merger client is asking about clearance timeline risk and I want to ground my advice in our own t(...TRUNCATED) | "Based on my search of the Calderwood & Harkness LLP DMS, I found **one merger review matter** that (...TRUNCATED) | "=== SYSTEM PROMPT ===\nYou are an agent exploring the document management system (DMS) of the law f(...TRUNCATED) | [{"role":"system","content":"You are an agent exploring the document management system (DMS) of the (...TRUNCATED) | [{"role":"user","content":"A merger client is asking about clearance timeline risk and I want to gro(...TRUNCATED) | [{"role":"user","content":"A merger client is asking about clearance timeline risk and I want to gro(...TRUNCATED) | scale70-30m | scale70-30m-20t-think | 115167 | Qwen/Qwen3.5-9B | c202236235762e1c871ad0ccb60c8ee5ba337b9a | 30,004,389 | 21,003,132 | 9,001,257 | 2 | 20 | null | 0.5 | "Based on my search of the Calderwood & Harkness LLP DMS, I found **one merger review matter** that (...TRUNCATED) | ["Identifies matter 1003-00001 (Harrowgate PE) as a qualifying matter.","Identifies matter 1038-0000(...TRUNCATED) | null | not_saved_by_harness | zai-org/GLM-4-32B-0414 | 077b5c2f5c43bd3239fd605a0600229e8facbd4a | |
002 | 2 | done | 0.25 | 0.3125 | 1 | 8 | 7 | "A merger client is asking about clearance timeline risk and I want to ground my advice in our own t(...TRUNCATED) | "Based on my search of the Calderwood & Harkness LLP DMS, here are the findings regarding merger rev(...TRUNCATED) | "=== SYSTEM PROMPT ===\nYou are an agent exploring the document management system (DMS) of the law f(...TRUNCATED) | [{"role":"system","content":"You are an agent exploring the document management system (DMS) of the (...TRUNCATED) | [{"role":"user","content":"A merger client is asking about clearance timeline risk and I want to gro(...TRUNCATED) | [{"role":"user","content":"A merger client is asking about clearance timeline risk and I want to gro(...TRUNCATED) | scale70-30m | scale70-30m-20t-think | 115167 | Qwen/Qwen3.5-9B | c202236235762e1c871ad0ccb60c8ee5ba337b9a | 30,004,389 | 21,003,132 | 9,001,257 | 2 | 20 | null | 0.25 | "Based on my search of the Calderwood & Harkness LLP DMS, here are the findings regarding merger rev(...TRUNCATED) | ["Identifies matter 1003-00001 (Harrowgate PE) as a qualifying matter.","Identifies matter 1038-0000(...TRUNCATED) | null | not_saved_by_harness | zai-org/GLM-4-32B-0414 | 077b5c2f5c43bd3239fd605a0600229e8facbd4a | |
002 | 3 | done | 0 | 0.3125 | 1 | 4 | 3 | "A merger client is asking about clearance timeline risk and I want to ground my advice in our own t(...TRUNCATED) | "Based on my search of the C&H DMS, I found only one merger review in the antitrust practice: **Matt(...TRUNCATED) | "=== SYSTEM PROMPT ===\nYou are an agent exploring the document management system (DMS) of the law f(...TRUNCATED) | [{"role":"system","content":"You are an agent exploring the document management system (DMS) of the (...TRUNCATED) | [{"role":"user","content":"A merger client is asking about clearance timeline risk and I want to gro(...TRUNCATED) | [{"role":"user","content":"A merger client is asking about clearance timeline risk and I want to gro(...TRUNCATED) | scale70-30m | scale70-30m-20t-think | 115167 | Qwen/Qwen3.5-9B | c202236235762e1c871ad0ccb60c8ee5ba337b9a | 30,004,389 | 21,003,132 | 9,001,257 | 2 | 20 | null | 0 | "Based on my search of the C&H DMS, I found only one merger review in the antitrust practice: **Matt(...TRUNCATED) | ["Identifies matter 1003-00001 (Harrowgate PE) as a qualifying matter.","Identifies matter 1038-0000(...TRUNCATED) | null | not_saved_by_harness | zai-org/GLM-4-32B-0414 | 077b5c2f5c43bd3239fd605a0600229e8facbd4a | |
003 | 0 | done | 0.333 | 0.25 | 0.75 | 5 | 4 | "I'm prepping talking points on our antitrust track record and want examples from our antitrust prac(...TRUNCATED) | "## Antitrust Practice: Second Request to Clearance Success Stories\n\nBased on my search of the C&H(...TRUNCATED) | "=== SYSTEM PROMPT ===\nYou are an agent exploring the document management system (DMS) of the law f(...TRUNCATED) | [{"role":"system","content":"You are an agent exploring the document management system (DMS) of the (...TRUNCATED) | [{"role":"user","content":"I'm prepping talking points on our antitrust track record and want exampl(...TRUNCATED) | [{"role":"user","content":"I'm prepping talking points on our antitrust track record and want exampl(...TRUNCATED) | scale70-30m | scale70-30m-20t-think | 115167 | Qwen/Qwen3.5-9B | c202236235762e1c871ad0ccb60c8ee5ba337b9a | 30,004,389 | 21,003,132 | 9,001,257 | 2 | 20 | null | 0.333 | "## Antitrust Practice: Second Request to Clearance Success Stories\n\nBased on my search of the C&H(...TRUNCATED) | ["Identifies matter 1041-00001 (Solara Digital) as a qualifying matter.","Provides or identifies pos(...TRUNCATED) | null | not_saved_by_harness | zai-org/GLM-4-32B-0414 | 077b5c2f5c43bd3239fd605a0600229e8facbd4a | |
003 | 1 | done | 0.333 | 0.25 | 0.75 | 5 | 4 | "I'm prepping talking points on our antitrust track record and want examples from our antitrust prac(...TRUNCATED) | "# Antitrust Practice: Second Request to Clearance Success Patterns\n\n## Executive Summary\n\nBased(...TRUNCATED) | "=== SYSTEM PROMPT ===\nYou are an agent exploring the document management system (DMS) of the law f(...TRUNCATED) | [{"role":"system","content":"You are an agent exploring the document management system (DMS) of the (...TRUNCATED) | [{"role":"user","content":"I'm prepping talking points on our antitrust track record and want exampl(...TRUNCATED) | [{"role":"user","content":"I'm prepping talking points on our antitrust track record and want exampl(...TRUNCATED) | scale70-30m | scale70-30m-20t-think | 115167 | Qwen/Qwen3.5-9B | c202236235762e1c871ad0ccb60c8ee5ba337b9a | 30,004,389 | 21,003,132 | 9,001,257 | 2 | 20 | null | 0.333 | "# Antitrust Practice: Second Request to Clearance Success Patterns\n\n## Executive Summary\n\nBased(...TRUNCATED) | ["Identifies matter 1041-00001 (Solara Digital) as a qualifying matter.","Provides or identifies pos(...TRUNCATED) | null | not_saved_by_harness | zai-org/GLM-4-32B-0414 | 077b5c2f5c43bd3239fd605a0600229e8facbd4a |
scale70-30m Agentic evaluation, 20 turns, thinking enabled
1,000 saved evaluation attempts: 250 C&H firm-knowledge tasks × four samples.
The base model is Qwen/Qwen3.5-9B at revision c202236235762e1c871ad0ccb60c8ee5ba337b9a, trained for two
epochs on a 70% notes / 30% recall mixture. This dataset has
30,004,389 total loss-bearing training-data tokens
(21,003,132 notes + 9,001,257 recall).
The token count describes the dataset before its two training exposures.
Run: scale70-30m-20t-think; evaluation job: 115167.
Mean stored rubric score: 18.59%.
Status counts: {"done": 949, "max_turns": 6, "protocol_failure": 45}.
All errors and unanswered attempts remain in the export. Scores are the original
rounded per-attempt rubric fractions, not a binary success rate. A non-done
attempt can have a nonzero score if the grader used its unwrapped answer.
The 10M / 20-turn evaluation includes one context-limit attempt retained as zero.
Format
The first 13 columns and their Arrow types match the published
base 5-turn
and base 20-turn
exports: task_id, sample, status, score, task_mean_score, task_done_rate,
n_turns, n_tool_calls, task, final, final_unwrapped, transcript, messages.
messages preserves every original system/user/assistant message and its exact
content, including saved thinking. transcript uses the same readable rendering
as the base exports. Row order follows the original JSONL; task_id and sample
are the stable attempt key. No failed rows are dropped or resampled.
Additional full_trajectories and action_only_trajectories contain chronological
lists of objects with exactly role and content (user/assistant only). The full
view preserves all non-system messages. In the action-only view, user messages
and observations remain exact; assistant content is JSON containing parsed
commands and a task_complete boolean. A valid final block with no tool call
sets task_complete; it does not mean the answer was correct. Malformed calls
have no parsed commands; their original text remains in messages. Unsupported
but parseable tool requests remain commands. SYSTEM is retained in messages
and transcript, without inventing a user turn for it.
Structured metadata columns identify condition, run, evaluation job, base model
and revision, note/recall/total loss tokens, epochs, and turn budget. As in the
base exports, the HF split is named train for compatibility; these are held-out
evaluation attempts, not training examples.
Judge outputs
judge_score is an explicit alias of the original per-attempt score.
graded_response is the exact answer slice used by the grader (first 6,000
characters of the final answer or unwrapped fallback); judge_criteria lists
the rubric criteria in their original order. Judge model and revision are
structured columns. error retains any saved rollout error message.
The original grader converted each judge reply to a boolean in memory and saved
only aggregate scores. It did not persist the individual judge replies or
per-criterion decisions. judge_responses is therefore null, with
judge_response_status=not_saved_by_harness for graded answers and
not_invoked_no_answer for empty answers. These missing responses have not been
reconstructed or regenerated. The original judge_errors.json is also included;
all eight completed evaluations recorded zero judge API errors.
Files and reproduction
data/train-00000-of-00001.parquet: the Dataset Viewer table.raw/scale70-30m-20t-think.jsonl: byte-for-byte original rollout JSONL.scores.json: original aggregate and per-task/per-sample scores.completion.json: the evaluation completion receipt.judge_errors.json: original judge API error record.audit_inputs.tar.gz: frozen task JSONs, task list, protocol/grader source, and this condition's training metadata, with paths relative to the scaling root.manifest.json: source and artifact hashes, schema, and validation results.
The exporter is recipe/internalization/reports/export_agentic_eval_hf.py in the
research repository. It validates all rows after Parquet round-trip and checks
the rendering against both base exports. The failure-analysis report and its
input-restoration instructions live under
recipe/internalization/reports/internalization-agentic-failures/.
Provenance
The environment is Harvey AI's synthetic legal benchmark,
revision c2488cfa24fd01ee88016a121479a2f86b394bd4, licensed MIT.
The frozen benchmark has 250 firm-knowledge tasks and a mirror of 9,288 documents.
The agent tools are glob, grep, and read. Grading used
zai-org/GLM-4-32B-0414, revision 077b5c2f5c43bd3239fd605a0600229e8facbd4a.
No new inference or grading was performed for this export.
- Downloads last month
- -