@graffiticode/l0175 0.2.0 → 0.3.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (96) hide show
  1. package/dist/compiler.d.ts.map +1 -1
  2. package/dist/compiler.js +94 -130
  3. package/dist/compiler.js.map +1 -1
  4. package/dist/embedding.d.ts +1 -0
  5. package/dist/embedding.d.ts.map +1 -1
  6. package/dist/embedding.js +105 -11
  7. package/dist/embedding.js.map +1 -1
  8. package/dist/index.d.ts +4 -0
  9. package/dist/index.d.ts.map +1 -1
  10. package/dist/index.js +2 -0
  11. package/dist/index.js.map +1 -1
  12. package/dist/lexicon.d.ts +7 -0
  13. package/dist/lexicon.d.ts.map +1 -1
  14. package/dist/lexicon.js +16 -8
  15. package/dist/lexicon.js.map +1 -1
  16. package/dist/static/examples.md +105 -0
  17. package/dist/static/instructions.md +397 -47
  18. package/dist/static/language-info.json +19 -4
  19. package/dist/static/lexicon.json +112 -0
  20. package/dist/static/scope.json +9 -8
  21. package/dist/static/spec.html +81 -15
  22. package/dist/static/stems.md +181 -5
  23. package/dist/static/targets.json +279 -0
  24. package/dist/static/template.gc +7 -67
  25. package/dist/static/unparse-hints.json +3 -0
  26. package/dist/static/usage-guide.md +48 -5
  27. package/dist/targets.d.ts +27 -0
  28. package/dist/targets.d.ts.map +1 -0
  29. package/dist/targets.js +250 -0
  30. package/dist/targets.js.map +1 -0
  31. package/dist/verify-example.d.ts +27 -0
  32. package/dist/verify-example.d.ts.map +1 -0
  33. package/dist/verify-example.js +82 -0
  34. package/dist/verify-example.js.map +1 -0
  35. package/package.json +2 -2
  36. package/spec/#template.gc# +20 -0
  37. package/spec/docs.md +51 -16
  38. package/spec/examples/c1-t1-tm1-multiplechoice.expect.json +1 -0
  39. package/spec/examples/c1-t1-tm1-multiplechoice.gc +27 -0
  40. package/spec/examples/c1-t1-tm2-multiselect.expect.json +1 -0
  41. package/spec/examples/c1-t1-tm2-multiselect.gc +27 -0
  42. package/spec/examples/c1-t1-tm3-hottext.expect.json +1 -0
  43. package/spec/examples/c1-t1-tm3-hottext.gc +27 -0
  44. package/spec/examples/c1-t10-tm1-multiplechoice.expect.json +1 -0
  45. package/spec/examples/c1-t10-tm1-multiplechoice.gc +15 -0
  46. package/spec/examples/c1-t10-tm2-multiselect.expect.json +1 -0
  47. package/spec/examples/c1-t10-tm2-multiselect.gc +15 -0
  48. package/spec/examples/c1-t10-tm3-hottext.expect.json +1 -0
  49. package/spec/examples/c1-t10-tm3-hottext.gc +13 -0
  50. package/spec/examples/c1-t11-tm1-ebsr.expect.json +4 -0
  51. package/spec/examples/c1-t11-tm1-ebsr.gc +30 -0
  52. package/spec/examples/c1-t11-tm2-hottext.expect.json +4 -0
  53. package/spec/examples/c1-t11-tm2-hottext.gc +30 -0
  54. package/spec/examples/c1-t11-tm3-shorttext.expect.json +4 -0
  55. package/spec/examples/c1-t11-tm3-shorttext.gc +30 -0
  56. package/spec/examples/c1-t2-tm1-multiplechoice.expect.json +1 -0
  57. package/spec/examples/c1-t2-tm1-multiplechoice.gc +29 -0
  58. package/spec/examples/c1-t2-tm2-multiselect.expect.json +1 -0
  59. package/spec/examples/c1-t2-tm2-multiselect.gc +28 -0
  60. package/spec/examples/c1-t2-tm3-ebsr.expect.json +1 -0
  61. package/spec/examples/c1-t2-tm3-ebsr.gc +29 -0
  62. package/spec/examples/c1-t2-tm4-hottext.expect.json +1 -0
  63. package/spec/examples/c1-t2-tm4-hottext.gc +19 -0
  64. package/spec/examples/c1-t2-tm5-shorttext.expect.json +1 -0
  65. package/spec/examples/c1-t2-tm5-shorttext.gc +20 -0
  66. package/spec/examples/c1-t4-tm1-ebsr.expect.json +4 -0
  67. package/spec/examples/c1-t4-tm1-ebsr.gc +30 -0
  68. package/spec/examples/c1-t4-tm2-hottext.expect.json +4 -0
  69. package/spec/examples/c1-t4-tm2-hottext.gc +30 -0
  70. package/spec/examples/c1-t4-tm3-shorttext.expect.json +4 -0
  71. package/spec/examples/c1-t4-tm3-shorttext.gc +30 -0
  72. package/spec/examples/c1-t8-tm1-multiplechoice.expect.json +1 -0
  73. package/spec/examples/c1-t8-tm1-multiplechoice.gc +25 -0
  74. package/spec/examples/c1-t8-tm2-multiselect.expect.json +1 -0
  75. package/spec/examples/c1-t8-tm2-multiselect.gc +25 -0
  76. package/spec/examples/c1-t8-tm3-hottext.expect.json +1 -0
  77. package/spec/examples/c1-t8-tm3-hottext.gc +25 -0
  78. package/spec/examples/c1-t9-tm1-multiplechoice.expect.json +1 -0
  79. package/spec/examples/c1-t9-tm1-multiplechoice.gc +23 -0
  80. package/spec/examples/c1-t9-tm2-multiselect.expect.json +1 -0
  81. package/spec/examples/c1-t9-tm2-multiselect.gc +24 -0
  82. package/spec/examples/c1-t9-tm3-ebsr.expect.json +10 -0
  83. package/spec/examples/c1-t9-tm3-ebsr.gc +30 -0
  84. package/spec/examples/c1-t9-tm4-hottext.expect.json +10 -0
  85. package/spec/examples/c1-t9-tm4-hottext.gc +20 -0
  86. package/spec/examples/c1-t9-tm5-shorttext.expect.json +10 -0
  87. package/spec/examples/c1-t9-tm5-shorttext.gc +20 -0
  88. package/spec/examples.md +100 -86
  89. package/spec/instructions.md +367 -44
  90. package/spec/language-info.json +18 -3
  91. package/spec/rag-examples-design.md +74 -0
  92. package/spec/scope.json +9 -8
  93. package/spec/spec.md +90 -15
  94. package/spec/stems.md +181 -5
  95. package/spec/template.gc +7 -67
  96. package/spec/usage-guide.md +48 -5
package/spec/examples.md CHANGED
@@ -1,91 +1,105 @@
1
1
  <!-- SPDX-License-Identifier: CC-BY-4.0 -->
2
2
  # L0175 RAG Training Examples
3
3
 
4
- _Revised: 2026-06-24_
4
+ _Revised: 2026-08-28_
5
5
 
6
6
  Natural-language prompts for training a RAG model on L0175 — composing 5th-grade ELA
7
- assessment items (Smarter Balanced · Grade 5 · Claim 1) for learning targets **T4**
8
- (`target c1-t4`, Reasoning & Evidence, literary), **T11** (`target c1-t11`, Reasoning & Evidence,
9
- informational), **T9** (`target c1-t9`, Central Ideas, informational), **T8** (`target c1-t8`,
10
- Key Details, informational), and **T10** (`target c1-t10`, Word Meanings, informational). Each
11
- program declares its `target` first. Categories 1–6 below are literary (T4); Category 7 is
12
- informational R&E (T11); Category 8 is Central Ideas (T9); Category 9 is Key Details (T8);
13
- Category 10 is Word Meanings (T10).
14
-
15
- ## Category 1: EBSR items (two-part selected response)
16
-
17
- 1. Write an EBSR item about the main character's motivation in a story about a girl at a tide pool.
18
- 2. Compose a two-part item: Part A asks what can be inferred about the narrator's feelings; Part B asks for the supporting line.
19
- 3. Make an EBSR item about the setting and how it shapes the mood of the scene.
20
- 4. Build an EBSR item about an event and why the character reacts the way she does.
21
- 5. Write an EBSR item about the relationship between two characters, standard rl-3.
22
- 6. Compose an EBSR item about the author's point of view, standard rl-6.
23
- 7. Make an EBSR item about the theme of the passage.
24
-
25
- ## Category 2: Hot Text items (select text)
26
-
27
- 8. Make a hot-text item where students click the statement that best describes the character, then click the supporting sentences.
28
- 9. Compose a hot-text item where Part B asks students to highlight every sentence that shows the character's focus.
29
- 10. Write a hot-text item about the narrator's feelings toward another character.
30
-
31
- ## Category 3: Short Text items (constructed response)
32
-
33
- 11. Write a short-text item asking what inference can be made about the character, with evidence.
34
- 12. Compose a short-text constructed-response item about the theme, hand-scored 0–2.
35
- 13. Make a short-text item about how the setting affects the character, with a custom rubric.
36
-
37
- ## Category 4: Authoring the inference graph
38
-
39
- 14. Add a supported claim, that the character cares more about the tide pool than the picnic, and point question q1's focus at it.
40
- 15. Add a second supported claim about the brother and build a separate question q2 around it.
41
- 16. Tag line 1 and line 3 as directly supporting the main inference.
42
- 17. Mark line 2 as evidence that supports a wrong claim, tied to both the correct claim and the 'anger' distractor.
43
- 18. Mark the last two lines as irrelevant so they can serve as Part B foils.
44
-
45
- ## Category 5: Distractors by error type
46
-
47
- 19. Add a misreads-detail distractor for question q1 that takes the character's silence as anger.
48
- 20. Add an erroneous-inference distractor for q1 that the character dislikes being outdoors.
49
- 21. Add a faulty-reasoning distractor for q1 that mistakes the character's whisper for fear.
50
- 22. Give each distractor a rationale explaining the student error it targets, and tag it with the question id(s) it foils.
51
-
52
- ## Category 6: Item-first composition
53
-
54
- 23. Compose the questions first: write an EBSR question, a short-text question, and a hot-text question, each with its stem from the guideline catalog, then author foils targeting each.
55
- 24. Compose one question per inference dimension the passage supports, then author a targeted foil set for each.
56
- 25. Set a question's focus to a specific correct claim and write its stem, then author the distractors that target it.
57
-
58
- ## Category 7: Informational items (target c1-t11)
59
-
60
- 26. From an informational article about the history of bridge design, write an EBSR item about the relationships between the successive designs (dimension relationships-interactions, standard ri-3).
61
- 27. Make an item about how the author uses evidence to support a point in a science article (dimension author-use-of-information, standard ri-8).
62
- 28. Compose an EBSR item about the author's point of view in an informational passage about city planning (dimension point-of-view, standard ri-6).
63
- 29. Write a short-text item asking what conclusion can be drawn about the author's opinion of renewable energy, with key evidence (dimension authors-opinion).
64
- 30. Make a hot-text item about the author's purpose in an informational passage (dimension purpose).
65
-
66
- ## Category 8: Central Ideas items (target c1-t9)
67
-
68
- A DIFFERENT skill from Reasoning & Evidence the main idea, the key details that build it, and summary (DOK 2; standards ri-1+ri-2). Distractors are usually TRUE statements that just aren't central: too-narrow (a supporting detail), too-broad (an overgeneralization), insignificant (a minor detail), or misreads-detail.
69
-
70
- 31. From an informational article about honeybees, write a multiple-choice item asking which sentence best states the main idea (dimension central-idea). Make the distractors a true supporting detail (too-narrow), an overgeneralization (too-broad), and a misread (misreads-detail).
71
- 32. Make a multi-select item: choose the two sentences that should be included in a summary of the passage (dimension summary); `focus` lists the two correct claims, distractors are insignificant or too-broad statements.
72
- 33. Compose an EBSR item where Part A asks for the main idea and Part B asks which detail best supports it (dimension central-idea, standard ri-2).
73
- 34. Write a short-text item: "Determine the main idea of the passage. Explain using key details…" (dimension central-idea, DOK r-dok3).
74
- 35. Write a multiple-choice "missing key detail" item: present a short summary in the stem and ask which key detail is missing; the focus claim is the missing detail.
75
-
76
- ## Category 9: Key Details items (target c1-t8)
77
-
78
- A DIFFERENT model — the inference/conclusion is GIVEN in the stem and the student selects the supporting EVIDENCE (DOK 1–2; standards ri-1+ri-7; dimension supporting-evidence). Author ONE supported claim = the given inference (its `focus`), state it in the stem, and author `source`s as the options: directly-supports = correct evidence (with a `quote`), supports-wrong-claim/irrelevant = distractor evidence. No distractor claims.
79
-
80
- 36. From an informational article about Roman aqueducts, write a multiple-choice item that states the conclusion "aqueducts brought water to distant cities" and asks which detail from the passage best supports it (dimension supporting-evidence).
81
- 37. Make a multi-select item: which two details best support the stated conclusion? Select two answers (two directly-supports sources are the correct set).
82
- 38. Make a single-part hot-text item: state the inference, then have students click the sentence(s) in the passage that support it (dimension supporting-evidence).
83
-
84
- ## Category 10: Word Meanings items (target c1-t10)
85
-
86
- A DIFFERENT model the question asks for the MEANING of a targeted word/phrase in context, so the options are meanings (DOK 1–2; standard ri-4 + the L-4 family). Author a top-level `words` list: a `word` (the targeted word, with line/quote for context) holding `meanings` — `status correct` (the answer) + `status distractor` (error-type other-meaning/misinterprets/wrong-context + rationale). The outcome's `focus` names the word; state the word + its sentence in the stem.
87
-
88
- 39. From an informational article, write a multiple-choice item asking what the word "aqueduct" most likely means as used in the passage (dimension word-meaning, standard l-4a — context). Distractors: another meaning that ignores context (other-meaning), a misread (misinterprets), and a wrong-context meaning.
89
- 40. Make a multi-select item: "What does the word 'channel' most likely mean? Choose two answers." (two correct meanings, dimension word-meaning).
90
- 41. Write a roots/affixes item: ask what the root in a word means, standard l-4b (dimension word-meaning).
91
- 42. Make a click-the-word item (hot-text): "Read the dictionary entry … Click the word in the paragraph that matches this definition." Author the candidate `word`s the correct one is the outcome's `focus` with the `line` of its paragraph, plus a few distractor candidate words from that same paragraph (`text` only, no `meanings`). The compiler shows the paragraph and makes those authored candidates clickable; the focus word is correct. (Author only the correct word and every content word in the paragraph becomes a choice.) Keep the passage out of the stem.
7
+ assessment items (Smarter Balanced · Grade 5 · Claim 1). They are written the way a fifth-grade
8
+ teacher would ask for an item, and they stay away from specific passage content so the model
9
+ learns the task shape, not a topic. Each program declares its `target` first.
10
+
11
+ This is a covering set: every task model of every target appears at least once, and across the
12
+ task models each target's dimensions are each covered at least once. Standard is a function of
13
+ dimension, so covering dimensions covers the standards too — except in Word Meanings, where the
14
+ one dimension spans four L-4 strategies (context, roots and affixes, dictionary, word
15
+ relationships), which are covered instead. The dimension is carried by the skill the prompt
16
+ describes, not a tag.
17
+
18
+ Item type maps to a task-model number within each target, and the numbers collide across targets
19
+ a short-text item is tm3 in T4/T11 but tm5 in T2/T9; a hot-text item is tm2 in T4/T11, tm4 in T2/T9, and
20
+ tm3 in T1/T8/T10 so each prompt names its target and task model.
21
+
22
+ ## Target 4 (`c1-t4`) Reasoning & Evidence, literary
23
+
24
+ Students read a story and reason about it — a character's feelings or motives, how two characters
25
+ relate, the setting, an event, the narrator's point of view or feelings, the theme, or the topic —
26
+ and back it up with evidence from the text.
27
+
28
+ 1. c1-t4 tm1 — Make a two-part item for a story: in Part A students figure out what the main character is feeling or why they act the way they do, and in Part B they pick the line that best backs it up.
29
+ 2. c1-t4 tm1 — Make a two-part item for a story about an important event: in Part A students figure out why it happens or how a character reacts to it, and in Part B they pick the line that best supports their answer.
30
+ 3. c1-t4 tm1 — Make a two-part item for a story about two characters: in Part A students figure out how the two feel about each other, and in Part B they pick the line that best shows it.
31
+ 4. c1-t4 tm2 Make an item for a story where students first click the sentence that best tells the narrator's point of view, then click the sentence or two that support it.
32
+ 5. c1-t4 tm2 — Make an item for a story where students first click the sentence that best shows how the setting shapes the mood, then click the sentences that support it.
33
+ 6. c1-t4 tm2 Make an item for a story where students first click the sentence that best shows how the narrator feels about another character, then click the sentences that support it.
34
+ 7. c1-t4 tm3 — Make a written-response item for a story: ask students what the theme is and have them explain it using details from the text.
35
+ 8. c1-t4 tm3 — Make a written-response item for a story: ask students what the story is mostly about and have them support it with details from the text.
36
+
37
+ ## Target 11 (`c1-t11`) Reasoning & Evidence, informational
38
+
39
+ The same kind of reasoning as Target 4, but for an informational passage how ideas or events
40
+ connect, how the author uses information to support a point, the author's point of view or
41
+ purpose, or the author's opinion always supported with evidence.
42
+
43
+ 9. c1-t11 tm1 Make a two-part item for an informational passage: in Part A students figure out how two ideas or events are connected, and in Part B they choose the detail that best supports it.
44
+ 10. c1-t11 tm1 — Make a two-part item for an informational passage: in Part A students figure out the author's point of view, and in Part B they choose the detail that best supports it.
45
+ 11. c1-t11 tm2 Make an item for an informational passage where students click the sentence that best states the author's purpose, then click the sentences that support it.
46
+ 12. c1-t11 tm2 — Make an item for an informational passage where students click the sentence that best shows how the author uses facts to support a point, then click the sentences that support it.
47
+ 13. c1-t11 tm3 — Make a written-response item for an informational passage: ask students what conclusion they can draw about the author's opinion and have them back it up with evidence from the text.
48
+
49
+ ## Target 2 (`c1-t2`) Central Ideas, literary
50
+
51
+ Students find the theme of a story or poem, the key details and events that build it, or summarize
52
+ part of it. The theme is a lesson or message, not a plot event. Wrong answers are usually true but
53
+ not central. Summaries here always cover a section or a key event, never the whole story.
54
+
55
+ 14. c1-t2 tm1 Make an item for a story that asks which sentence best tells the theme.
56
+ 15. c1-t2 tm2 Make an item for a story where students choose the two sentences that belong in a summary of it.
57
+ 16. c1-t2 tm3 — Make a two-part item for a story: in Part A students pick the theme, and in Part B they choose the sentence that best supports it.
58
+ 17. c1-t2 tm4 Make an item for a story where students click the one or two sentences that best show the theme.
59
+ 18. c1-t2 tm5 — Make a written-response item for a story: ask students to summarize what happens after a key moment, using details from the text.
60
+
61
+ ## Target 9 (`c1-t9`) Central Ideas, informational
62
+
63
+ Students find the main idea of an informational passage, the key details that build it, or a
64
+ summary. Wrong answers are usually true but not central a small supporting detail, an
65
+ overgeneralization, or a misread. T2 is its literary twin; the two are the only targets that use all five task models.
66
+
67
+ 19. c1-t9 tm1 — Make an item for an informational passage that asks which sentence best states the main idea.
68
+ 20. c1-t9 tm1Make an item that shows students a short summary of an informational passage with one key detail left out and asks which detail is missing.
69
+ 21. c1-t9 tm2 — Make an item for an informational passage where students choose the two sentences that belong in a summary.
70
+ 22. c1-t9 tm3 Make a two-part item for an informational passage: in Part A students pick the main idea, and in Part B they choose the key detail that best supports it.
71
+ 23. c1-t9 tm4 Make an item for an informational passage where students click the sentence or two that best show the main idea.
72
+ 24. c1-t9 tm5 Make a written-response item for an informational passage: ask students to figure out the main idea and explain it using key details from the text.
73
+
74
+ ## Target 1 (`c1-t1`) Key Details, literary
75
+
76
+ The same job as Target 8, but on a story instead of an article. Give students a conclusion about
77
+ the story and have them find the line or lines that support it. Wrong answers are other lines that
78
+ tell about the story without backing up that particular conclusion.
79
+
80
+ 25. c1-t1 tm1 Give students a conclusion about a story and make an item asking which line from the story best supports it.
81
+ 26. c1-t1 tm2 Give students a conclusion about a story and make an item asking which two lines best support it.
82
+ 27. c1-t1 tm3 — Give students a conclusion about a story and make an item where they click the sentence or two that support it.
83
+
84
+ ## Target 8 (`c1-t8`) Key Details, informational
85
+
86
+ The conclusion is handed to the students; their job is to find the evidence. Give them an
87
+ inference about an informational passage and have them pick the detail(s) that support it. The
88
+ wrong answers are other details that don't actually support it.
89
+
90
+ 28. c1-t8 tm1 — Give students a conclusion about an informational passage and make an item asking which detail from the passage best supports it.
91
+ 29. c1-t8 tm2Give students a conclusion about an informational passage and make an item asking which two details best support it.
92
+ 30. c1-t8 tm3 — Give students a conclusion about an informational passage and make an item where they click the sentence or two that support it.
93
+
94
+ ## Target 10 (`c1-t10`) — Word Meanings, informational
95
+
96
+ Students figure out what a word or phrase means the way it is used in an informational passage.
97
+ The answer choices are meanings; wrong ones come from another meaning of the word, a misread, or
98
+ the wrong context. Items lean on context, but can also use a word's roots and affixes, a dictionary
99
+ entry, or word relationships like synonyms and antonyms.
100
+
101
+ 31. c1-t10 tm1 — Make an item that asks what a key word most likely means the way it is used in an informational passage.
102
+ 32. c1-t10 tm1 — Make an item that asks what a word means by using its Greek or Latin root or prefix.
103
+ 33. c1-t10 tm2 — Make an item that asks students to choose the two answers that best give the meaning of a key word as it is used in an informational passage.
104
+ 34. c1-t10 tm2 — Make an item that asks students to choose the two words that mean about the same as a key word from the passage.
105
+ 35. c1-t10 tm3 — Give students a short dictionary definition and make an item where they click the word in the paragraph that matches it.