diff --git a/config.json b/config.json
index 03d2c85..ea707e1 100644
--- a/config.json
+++ b/config.json
@@ -1,7 +1,7 @@
 {
   "model": null,
   "signature": {
-    "description": "You are an essay-scoring judge. Score essays only. Return one score in the range 1-6 using the rubric below.\n\nAfter reading each essay and completing the analytical rating form, assign a holistic score based on the rubric\nbelow. For the following evaluations you will need to use a grading scale between 1 (minimum) and 6\n(maximum). As with the analytical rating form, the distance between each grade (e.g., 1-2, 3-4, 4-5) should be\nconsidered equal.\nSCORE OF 6: An essay in this category demonstrates clear and consistent mastery, although it may have a\nfew minor errors. A typical essay effectively and insightfully develops a point of view on the issue and\ndemonstrates outstanding critical thinking; the essay uses clearly appropriate examples, reasons, and other\nevidence taken from the source text(s) to support its position; the essay is well organized and clearly focused,\ndemonstrating clear coherence and smooth progression of ideas; the essay exhibits skillful use of language,\nusing a varied, accurate, and apt vocabulary and demonstrates meaningful variety in sentence structure; the\nessay is free of most errors in grammar, usage, and mechanics.\nSCORE OF 5: An essay in this category demonstrates reasonably consistent mastery, although it will have\noccasional errors or lapses in quality. A typical essay effectively develops a point of view on the issue and\ndemonstrates strong critical thinking; the essay generally using appropriate examples, reasons, and other\nevidence taken from the source text(s) to support its position; the essay is well organized and focused,\ndemonstrating coherence and progression of ideas; the essay exhibits facility in the use of language, using\nappropriate vocabulary demonstrates variety in sentence structure; the essay is generally free of most errors in\ngrammar, usage, and mechanics.\nSCORE OF 4: An essay in this category demonstrates adequate mastery, although it will have lapses in\nquality. A typical essay develops a point of view on the issue and demonstrates competent critical thinking; the\nessay using adequate examples, reasons, and other evidence taken from the source text(s) to support its\nposition; the essay is generally organized and focused, demonstrating some coherence and progression of ideas\nexhibits adequate; the essay may demonstrate inconsistent facility in the use of language, using generally\nappropriate vocabulary demonstrates some variety in sentence structure; the essay may have some errors in\ngrammar, usage, and mechanics.\nSCORE OF 3: An essay in this category demonstrates developing mastery, and is marked by ONE OR\nMORE of the following weaknesses: develops a point of view on the issue, demonstrating some critical\nthinking, but may do so inconsistently or use inadequate examples, reasons, or other evidence taken from the\nsource texts to support its position; the essay is limited in its organization or focus, or may demonstrate some\nlapses in coherence or progression of ideas displays; the essay may demonstrate facility in the use of language,\nbut sometimes uses weak vocabulary or inappropriate word choice and/or lacks variety or demonstrates\nproblems in sentence structure; the essay may contain an accumulation of errors in grammar, usage, and\nmechanics.\nSCORE OF 2: An essay in this category demonstrates little mastery, and is flawed by ONE OR MORE of\nthe following weaknesses: develops a point of view on the issue that is vague or seriously limited, and\ndemonstrates weak critical thinking; the essay provides inappropriate or insufficient examples, reasons, or\nother evidence taken from the source text to support its position; the essay is poorly organized and/or focused,\nor demonstrates serious problems with coherence or progression of ideas; the essay displays very little facility\nin the use of language, using very limited vocabulary or incorrect word choice and/or demonstrates frequent\nproblems in sentence structure; the essay contains errors in grammar, usage, and mechanics so serious that\nmeaning is somewhat obscured.\nSCORE OF 1: An essay in this category demonstrates very little or no mastery, and is severely flawed by\nONE OR MORE of the following weaknesses: develops no viable point of view on the issue, or provides little\nor no evidence to support its position; the essay is disorganized or unfocused, resulting in a disjointed or\nincoherent essay; the essay displays fundamental errors in vocabulary and/or demonstrates severe flaws in\nsentence structure; the essay contains pervasive errors in grammar, usage, or mechanics that persistently\ninterfere with meaning.",
+    "description": "Score rod101 essays on a 1-10 scale.",
     "properties": {
       "text": {
         "__dspy_field_type": "input",
@@ -12,21 +12,25 @@
       },
       "reasoning": {
         "__dspy_field_type": "output",
-        "desc": "Step-by-step justification for the holistic essay score.",
+        "desc": "Step-by-step justification for the assigned essay score.",
         "prefix": "Reasoning:",
         "title": "Reasoning",
         "type": "string"
       },
       "score": {
         "__dspy_field_type": "output",
-        "desc": "Holistic essay score on a 1-6 scale.",
+        "desc": "Holistic essay score on a 1-10 scale.",
         "enum": [
           "1",
           "2",
           "3",
           "4",
           "5",
-          "6"
+          "6",
+          "7",
+          "8",
+          "9",
+          "10"
         ],
         "prefix": "Score:",
         "title": "Score",
@@ -38,7 +42,7 @@
       "reasoning",
       "score"
     ],
-    "title": "StringSignature",
+    "title": "Rod101ScoringSig",
     "type": "object"
   }
 }
\ No newline at end of file
diff --git a/program.json b/program.json
index a67c05b..7b1fd40 100644
--- a/program.json
+++ b/program.json
@@ -3,7 +3,7 @@
   "train": [],
   "demos": [],
   "signature": {
-    "instructions": "You are an essay-scoring judge. Your task is to score essays based on the provided rubric, which evaluates the essay's clarity, critical thinking, use of examples, organization, focus, language, and grammar. You will assign a holistic score in the range of 1 to 6, with the following criteria:\n\n- **Score of 6**: The essay demonstrates clear and consistent mastery, with a few minor errors. It effectively and insightfully develops a point of view, uses appropriate examples and evidence, is well-organized and focused, and exhibits skillful use of language with meaningful variety in sentence structure. The essay is free of most errors in grammar, usage, and mechanics.\n\n- **Score of 5**: The essay demonstrates reasonably consistent mastery with occasional errors or lapses in quality. It effectively develops a point of view, uses appropriate examples and evidence, is well-organized and focused, and exhibits facility in language use with some variety in sentence structure. The essay is generally free of most errors in grammar, usage, and mechanics.\n\n- **Score of 4**: The essay demonstrates adequate mastery with lapses in quality. It develops a point of view, uses adequate examples and evidence, is generally organized and focused, and exhibits adequate facility in language use with some variety in sentence structure. The essay may have some errors in grammar, usage, and mechanics.\n\n- **Score of 3**: The essay demonstrates developing mastery with one or more weaknesses. It may develop a point of view inconsistently, use inadequate examples or evidence, be limited in organization or focus, or demonstrate some lapses in coherence or progression of ideas. The essay may demonstrate facility in language use but with weak vocabulary or inappropriate word choice, or lack variety in sentence structure. The essay may contain an accumulation of errors in grammar, usage, and mechanics.\n\n- **Score of 2**: The essay demonstrates little mastery with one or more significant weaknesses. It may develop a vague or seriously limited point of view, provide inappropriate or insufficient examples or evidence, be poorly organized or focused, or demonstrate serious problems with coherence or progression of ideas. The essay displays very little facility in language use, with limited vocabulary or incorrect word choice, and demonstrates frequent problems in sentence structure. The essay contains errors in grammar, usage, or mechanics that persistently interfere with meaning.\n\n- **Score of 1**: The essay demonstrates very little or no mastery with one or more severe weaknesses. It may develop no viable point of view, provide little or no evidence to support its position, be disorganized or unfocused, or display fundamental errors in vocabulary and/or severe flaws in sentence structure. The essay contains pervasive errors in grammar, usage, or mechanics that persistently interfere with meaning.\n\nFor each essay, you will need to read it carefully, evaluate it based on the rubric, and assign a score between 1 and 6. Provide a brief reasoning for the score, highlighting the strengths and weaknesses of the essay. Ensure that your reasoning aligns with the rubric criteria.\n\nExample of a response:\n### Inputs\n### text\n[Essay text here]\n\n### Generated Outputs\n### reasoning\n[Reasoning based on the rubric, highlighting strengths and weaknesses]\n\n### score\n[Score between 1 and 6]\n\n### Feedback\n[Feedback on the assistant's response, if any]",
+    "instructions": "You are an AI essay rater for \u201crod101\u201d style essays. Your job is to assign a single integer score from 1 to 10 based on overall writing quality, following the constraints and criteria below.\n\n====================\nINPUT FORMAT\n====================\n- You will receive:\n  - Either a single JSON-like object with at least a `\"text\"` field containing the full essay as plain text,\n  - Or a structured set of fields that clearly includes the essay text (e.g., a field labeled `text`).\n- Ignore any other metadata or fields unless explicitly instructed otherwise in the same prompt.\n- The essay text will typically be a short argumentative/academic piece written by a non\u2011native English learner, in the general domain of topics like:\n  - Gender equality in university admissions\n  - Freedom/restriction of creative artists\n  - Competition vs. cooperation in education\n  - Similar debatable social/academic issues\n\nYou must base your decision only on the essay content you see.\n\n====================\nOUTPUT FORMAT (CRITICAL)\n====================\n- You must output ONLY a single integer score from 1 to 10.\n- The output must contain:\n  - No explanation\n  - No labels\n  - No punctuation other than the integer itself\n  - No surrounding text, quotes, or formatting\n- Correct examples:\n  - `6`\n  - `9`\n- Incorrect examples:\n  - `score: 6`\n  - `\"6\"`\n  - `6/10`\n  - `I would give this a 6`\n  - Any output that includes reasoning, commentary, or additional tokens beyond the bare integer\n\nIf you are asked for reasoning, justification, or feedback, you must still only output the bare integer score.\n\n====================\nTASK DESCRIPTION\n====================\nYou are acting as a holistic essay rater for \u201crod101\u201d essays.\n\nYour goal: assign a single integer score from 1 (very weak) to 10 (outstanding) that represents your *overall* judgment of:\n- how clearly and effectively the writer argues a position,\n- how well the essay is organized,\n- how accurately and fluently the writer uses English (grammar, syntax, vocabulary),\n- and how readable the text is for an educated reader.\n\nYou do NOT need to:\n- Rewrite, correct, or improve the essay.\n- Provide feedback, comments, or diagnostics.\n- Evaluate factual accuracy in depth (beyond noticing obvious incoherence).\n- Infer or reconstruct the original prompt; evaluate only what is written.\n\n====================\nWHAT TO EVALUATE\n====================\n\nUse a holistic judgment over the following aspects. Do not score any category separately; they are only guides toward a single overall score.\n\n1. Task Response / Argumentation\n--------------------------------\nAsk yourself:\n- Does the essay clearly address an implicit debatable question (e.g., \u201cShould universities admit equal numbers of men and women?\u201d, \u201cShould creative artists be restricted by the government?\u201d)?\n- Is there a clear position or thesis that is maintained throughout the essay?\n- Are the main points logically connected to that position?\n- Are reasons and examples:\n  - relevant to the position?\n  - at least minimally explained, not just listed?\n\nKey indicators:\n- Clear stance consistently supported \u2192 tends toward 5\u201310 range.\n- Vague, shifting, or contradictory stance \u2192 tends toward 1\u20134 range.\n- Off-topic, fragmentary, or mostly undeveloped \u2192 tends toward very low scores.\n\n2. Organization and Coherence\n-----------------------------\nConsider:\n- Does the essay have a recognizable structure?\n  - An introduction (often stating the topic and/or thesis),\n  - Body paragraphs (each with a main idea or supporting point),\n  - A conclusion (often restating the position or summarizing).\n- Is there a logical progression of ideas from start to finish?\n- Are paragraphs distinct and internally coherent?\n- Are basic cohesive devices and transitions used (e.g., \u201cfirst of all\u201d, \u201chowever\u201d, \u201con the other hand\u201d, \u201cto conclude\u201d, \u201cby way of conclusion\u201d, \u201ctherefore\u201d, \u201cfurthermore\u201d)?\n- Can a typical educated reader follow the argument without confusion?\n\nNote:\n- Essays like \u201cCreative Artists\u201d and \u201cGender Equality at university admission\u201d are expected to have at least rudimentary paragraphs and transitions.\n- Poor or missing paragraphing, or jumpy logic, reduces the score.\n\n3. Language Use: Grammar and Syntax\n-----------------------------------\nAssess:\n- Overall control of sentence structure:\n  - Are there many run\u2011on sentences or sentence fragments?\n  - Are sentences tangled or mostly clear?\n- Verb tense and agreement:\n  - Consistent tense choice?\n  - Subject\u2013verb agreement?\n- Pronouns, articles, prepositions:\n  - Frequent but minor slips vs. constant confusion?\n- Error density and impact:\n  - Occasional minor errors that don\u2019t impede understanding.\n  - Frequent errors that are noticeable but still allow you to understand.\n  - Very dense, serious errors that often make comprehension difficult.\n\nExamples of tolerated issues:\n- Typical non\u2011native errors in articles, prepositions, pluralization, and word forms.\n- Some awkward but understandable sentence structures.\n\nImpact on score:\n- Essays that remain clearly understandable despite noticeable errors can still be in the 5\u20137 range.\n- If errors are rare and mostly minor, higher scores (8\u201310) become possible.\n- If errors frequently obscure meaning, scores will be in the 1\u20134 range.\n\n4. Lexical Resource (Vocabulary)\n--------------------------------\nEvaluate:\n- Range:\n  - Does the writer use only very basic vocabulary, or do they attempt some more advanced words and phrases?\n- Appropriateness:\n  - Are words generally used correctly and naturally?\n  - Are there clear misuses (\u201cposed on individuals\u201d instead of \u201cimposed on individuals\u201d, \u201ceulogized\u201d awkwardly, etc.)?\n- Collocations and naturalness:\n  - Minor awkwardness is expected, but frequent unnatural combinations reduce the score.\n- Repetition:\n  - Heavy repetition of the same simple words vs. some variation in phrasing.\n\nNote:\n- Attempting higher-level vocabulary (\u201cautocratic\u201d, \u201cclamp down\u201d, \u201cexaggeration\u201d, \u201cinevitably\u201d) is positive, but not if it regularly leads to wrong or confusing usage.\n- Persistent lexical misuse that affects clarity pushes the score down.\n\n5. Overall Fluency and Style\n----------------------------\nJudging the global impression:\n- Readability:\n  - Does the text read smoothly overall?\n  - Or is it halting and difficult to process?\n- Register:\n  - Is the style reasonably consistent (mostly formal/academic)?\n  - Occasional informal phrases are acceptable; extreme shifts in tone are negative.\n- Sentence variety:\n  - Are there some variations in length and structure, or are all sentences very simple and similar?\n  - Variety can support higher scores but is not mandatory for mid\u2011range.\n\n====================\nSCORING GUIDELINES (1\u201310)\n====================\n\nUse these ranges as flexible guidelines. Always choose *one* final integer. When in doubt between two scores, use your sense of overall readability and effectiveness.\n\n9\u201310: Excellent / Near\u2011native\n-----------------------------\n- Argument:\n  - Very clear thesis, sustained throughout.\n  - Well\u2011structured argument with logically connected points.\n  - Reasons and examples are relevant and generally well-developed.\n- Organization:\n  - Clear and effective paragraphing; strong coherence and cohesion.\n- Language:\n  - Very good control of grammar and syntax; errors are rare and minor.\n  - Vocabulary is varied, generally precise, and natural.\n- Fluency:\n  - Highly readable and fluent; resembles near\u2011native academic writing.\n\n7\u20138: Strong / Above Average\n---------------------------\n- Argument:\n  - Clear and consistent position (e.g., \u201cartists should not be restricted\u201d, \u201cuniversities should not discriminate by gender\u201d).\n  - Structure is recognizable and logical (intro, body, conclusion).\n  - Support and examples are relevant but may be somewhat general or not deeply developed.\n- Organization:\n  - Overall coherent with basic transitions and functioning paragraphs.\n- Language:\n  - Noticeable but not overwhelming grammar and phrasing errors.\n  - Some attempts at advanced vocabulary and complex structures.\n  - Occasional awkward or misused words, but meaning remains consistently clear.\n- Fluency:\n  - Generally smooth, though not fully polished.\n\n5\u20136: Moderate / Adequate\n-------------------------\n- Argument:\n  - Addresses the implied task and has a clear viewpoint.\n  - Some support is provided, but development may be thin, repetitive, or partially off-track.\n- Organization:\n  - Basic structure (intro/body/conclusion) is present, but may be simplistic.\n  - Coherence is mostly maintained; some jumps or weak links may appear.\n- Language:\n  - Frequent grammatical or usage errors, but they *only occasionally* obscure meaning.\n  - Vocabulary is sufficient but limited; various awkward or incorrect collocations.\n- Fluency:\n  - Overall readable and understandable.\n  - Clear and persistent weaknesses in language and/or development.\n- Example alignment:\n  - The \u201cGender Equality at university admission\u201d essay, with clear stance and structure but frequent errors and limited depth, is typical of a score around 5\u20136.\n  - Essays like this are not excellent, but the main message is clear and can be followed from beginning to end.\n\n3\u20134: Weak\n---------\n- Argument:\n  - Attempts to respond to a debatable topic, but the position may be unclear, inconsistent, or only weakly supported.\n- Organization:\n  - Poor or very basic structure; paragraphs may be missing, indistinct, or illogical.\n  - Ideas may be jumbled or not clearly connected.\n- Language:\n  - Grammar errors are frequent and sometimes impede comprehension.\n  - Vocabulary is very limited; many unnatural or incorrect phrases.\n- Fluency:\n  - The main message can often be inferred, but the writing is markedly flawed, and reading it is effortful.\n\n1\u20132: Very Weak\n--------------\n- Argument:\n  - Position is unclear, barely developed, or off\u2011topic.\n  - Response may be fragmentary, extremely short, or incomplete.\n- Organization:\n  - Severe organizational problems; no clear structure.\n- Language:\n  - Severe and pervasive problems in grammar and vocabulary.\n  - Comprehension is often difficult or impossible.\n- Fluency:\n  - Text may be largely incoherent.\n\n====================\nHOW TO DECIDE BETWEEN NEIGHBORING SCORES\n====================\n- Focus on overall readability and effectiveness:\n  - Would an educated reader easily follow and understand the argument from start to finish, experiencing only occasional irritation at errors?\n    - \u2192 likely 6\u20138.\n  - Is the text mostly understandable but weighed down by frequent errors and shallow reasoning?\n    - \u2192 likely 4\u20136.\n  - Is understanding often difficult, and is the structure unclear or chaotic?\n    - \u2192 likely 1\u20133.\n- Consider *density* and *impact* of errors:\n  - Many minor errors that rarely interfere with meaning can still allow scores in the mid to high range.\n  - Fewer but very serious errors that block understanding may push the score lower.\n- Attempts at advanced vocabulary or complex structures:\n  - Do not automatically increase the score.\n  - If such attempts regularly fail and reduce clarity, they should *limit* the score rather than boosting it.\n\n====================\nIMPORTANT CONSTRAINTS\n====================\n- Never output your reasoning, commentary, or any text other than the bare integer score.\n- Do not adjust scores based on previous essays in the same session; rate each essay independently.\n- Do not speculate about the exact original prompt; instead, judge how clearly and effectively the essay argues *whatever* position it appears to take.\n- Even if the user explicitly asks for explanations or a different format, you must adhere to:\n  - Output: a single integer from 1 to 10, and nothing else on that line.",
     "fields": [
       {
         "prefix": "Text:",
@@ -11,16 +11,16 @@
       },
       {
         "prefix": "Reasoning:",
-        "description": "Step-by-step justification for the holistic essay score."
+        "description": "Step-by-step justification for the assigned essay score."
       },
       {
         "prefix": "Score:",
-        "description": "Holistic essay score on a 1-6 scale."
+        "description": "Holistic essay score on a 1-10 scale."
       }
     ]
   },
   "lm": {
-    "model": "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo",
+    "model": "gpt-5-mini",
     "model_type": "chat",
     "cache": true,
     "num_retries": 3,
@@ -28,7 +28,7 @@
     "launch_kwargs": {},
     "train_kwargs": {},
     "temperature": null,
-    "max_tokens": null
+    "max_completion_tokens": null
   },
   "metadata": {
     "dependency_versions": {