aaron/aaronAI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
main
aaronAI/experiments/frame_distribution_2026-05-03.json
T
aaron ed2d090afc experiments/frame_distribution_report: Stage 2 frame analysis (Track 1 Improvement #3) 
Read-only inspection of the frame data Mistral produces in Stage 2, in
service of Track 2 substrate design (Step 2.4 operation set spec).

Artifacts:
- New SQL view `stage2_frames_v` over `stage_3_queue.stage2_metadata`
  (CREATE OR REPLACE; idempotent; raw JSONB exposed alongside structured
  fields so worker-version drift is inspectable).
- Analysis script: frequency, label-hygiene collisions, per-doc count,
  co-occurrence (top-K), file-type \u00d7 frame cross-tab, worker-version split,
  data-gap accounting, corpus-wide coverage.
- JSON sidecar for diff-across-runs reproducibility.
- Markdown report with explicit Track 2 viability section.

Headline findings:
- Frames cluster meaningfully on the framed-doc subset (subject to
  validation on larger samples for the file-type cross-tab).
- Only 56% of corpus has frame coverage. 198 conversation sources bypass
  Stage 2 by design (`ingest_conversations.py` writes directly to
  embeddings); 339 short docs (<2000 chars) skip Mistral by char-gate;
  12 Stage 2 failures.
- All 14 voice notes and all 39 dream outputs are in the data gap.
  Primary capture and self-reflection channels are silent to the frame
  system. Dreamer cannot frame-condition on its own output.
- 54 normalized label collisions (`Professional Experience` vs
  `Professional_Experience`, etc.) — any router must normalize first.
- "Education" is a near-universal frame (36% of frame-extracted docs);
  cheap 20-doc hand-inspection diagnostic in report \u00a78 to distinguish
  prompt artifact from corpus shape.
- File-type \u00d7 frame stratification is concrete signal that ties to
  Improvement #2 (`embeddings.type` backfill); currently NULL for 71% of
  rows.

No production code touched. View is droppable; script is read-only.
2026-05-03 20:32:37 +00:00

987 lines
14 KiB
JSON
Raw Permalink Blame History

{
"generated_at": "2026-05-03T20:21:33.558462",
"n_docs_with_frames": 668,
"n_distinct_labels": 1374,
"top_30_frames": [
[
"Education",
238
],
[
"Course",
58
],
[
"Programming",
43
],
[
"Design",
32
],
[
"Professional Experience",
24
],
[
"Employment",
24
],
[
"Research",
23
],
[
"3D Printing",
22
],
[
"Project",
21
],
[
"Grading",
21
],
[
"Art",
21
],
[
"Budget",
21
],
[
"Academic Integrity",
20
],
[
"Teaching",
19
],
[
"Technology",
18
],
[
"Attendance",
17
],
[
"Application",
15
],
[
"Accommodation",
13
],
[
"Manufacturing",
13
],
[
"Coursework",
11
],
[
"Recommendation",
10
],
[
"Manufacturing Process",
10
],
[
"Additive Manufacturing",
10
],
[
"Job Application",
10
],
[
"Exhibitions",
10
],
[
"Academic Administration",
9
],
[
"Communication",
9
],
[
"Course Design",
9
],
[
"Veteran and Military Services",
9
],
[
"Career",
9
]
],
"label_collisions": {
"conversational": [
[
"Conversational",
1
],
[
"conversational",
1
]
],
"content": [
[
"Content",
1
],
[
"content",
1
]
],
"cascade": [
[
"Cascade",
1
],
[
"cascade",
1
]
],
"education": [
[
"Education",
238
],
[
"education",
1
]
],
"academic record": [
[
"Academic_Record",
1
],
[
"Academic Record",
1
]
],
"independent study": [
[
"Independent Study",
5
],
[
"Independent_Study",
2
]
],
"project management": [
[
"Project Management",
7
],
[
"Project_Management",
1
]
],
"digital fabrication": [
[
"Digital Fabrication",
6
],
[
"digital_fabrication",
1
],
[
"digital fabrication",
1
]
],
"project proposal": [
[
"Project_Proposal",
2
],
[
"Project Proposal",
2
]
],
"academic integrity": [
[
"Academic Integrity",
20
],
[
"Academic_Integrity",
2
]
],
"3d printing": [
[
"3D Printing",
22
],
[
"3D_Printing",
7
]
],
"technical skills": [
[
"Technical Skills",
2
],
[
"Technical_Skills",
1
]
],
"course structure": [
[
"Course Structure",
7
],
[
"Course_Structure",
1
]
],
"course design": [
[
"Course Design",
9
],
[
"Course_Design",
1
]
],
"product design": [
[
"Product Design",
6
],
[
"Product_Design",
1
]
],
"professional experience": [
[
"Professional Experience",
24
],
[
"Professional_Experience",
6
]
],
"disability accommodations": [
[
"Disability Accommodations",
4
],
[
"Disability_Accommodations",
1
]
],
"material science": [
[
"Material_Science",
2
],
[
"Material Science",
4
]
],
"computational design": [
[
"Computational Design",
7
],
[
"Computational_Design",
1
]
],
"computer services policy": [
[
"Computer Services Policy",
6
],
[
"Computer_Services_Policy",
1
]
],
"work experience": [
[
"Work_Experience",
1
],
[
"Work Experience",
3
]
],
"academic program": [
[
"Academic Program",
7
],
[
"Academic_Program",
1
]
],
"project-based learning": [
[
"Project-Based Learning",
5
],
[
"Project-Based_Learning",
1
],
[
"Project-based Learning",
2
]
],
"art and design": [
[
"Art and Design",
6
],
[
"Art_and_Design",
1
]
],
"fdm technology": [
[
"FDM_Technology",
2
],
[
"FDM Technology",
1
]
],
"material selection": [
[
"Material_Selection",
1
],
[
"Material Selection",
1
]
],
"product development": [
[
"Product Development",
6
],
[
"Product_Development",
2
]
],
"market research": [
[
"Market_Research",
1
],
[
"Market Research",
2
]
],
"computer services": [
[
"Computer Services",
2
],
[
"Computer_Services",
1
]
],
"student evaluation of instruction": [
[
"Student Evaluation of Instruction",
1
],
[
"Student_Evaluation_of_Instruction",
1
]
],
"course management": [
[
"Course_Management",
1
],
[
"Course Management",
1
]
],
"grade policy": [
[
"Grade_Policy",
1
],
[
"Grade Policy",
1
]
],
"academic transcript": [
[
"Academic_Transcript",
1
],
[
"Academic Transcript",
1
]
],
"evaluation criteria": [
[
"Evaluation Criteria",
1
],
[
"Evaluation_Criteria",
1
]
],
"computer science": [
[
"Computer Science",
2
],
[
"Computer_Science",
1
]
],
"electrical circuit": [
[
"Electrical Circuit",
2
],
[
"Electrical_Circuit",
1
]
],
"digital logic": [
[
"Digital Logic",
1
],
[
"Digital_Logic",
1
]
],
"course description": [
[
"Course Description",
3
],
[
"Course_Description",
1
]
],
"organizational structure": [
[
"Organizational_Structure",
1
],
[
"Organizational Structure",
1
]
],
"digital design": [
[
"Digital_Design",
1
],
[
"Digital Design",
4
]
],
"contact information": [
[
"Contact Information",
2
],
[
"Contact_Information",
1
]
],
"professional career": [
[
"Professional_Career",
2
],
[
"Professional Career",
1
]
],
"personal projects": [
[
"Personal_Projects",
1
],
[
"Personal Projects",
2
]
],
"ai development": [
[
"AI_Development",
1
],
[
"AI Development",
1
]
],
"university service": [
[
"University Service",
2
],
[
"University_Service",
1
]
],
"professional exhibitions and publications": [
[
"Professional Exhibitions and Publications",
1
],
[
"Professional_Exhibitions_and_Publications",
1
]
],
"selected external consulting and design work": [
[
"Selected External Consulting and Design Work",
1
],
[
"Selected_External_Consulting_and_Design_Work",
2
]
],
"academic career": [
[
"Academic_Career",
1
],
[
"Academic Career",
2
]
],
"technology integration": [
[
"Technology Integration",
2
],
[
"Technology_Integration",
1
]
],
"artistic practice": [
[
"Artistic_Practice",
1
],
[
"Artistic Practice",
1
]
],
"multi-material 3d printing": [
[
"Multi-Material 3D Printing",
1
],
[
"Multi-material 3D Printing",
1
]
],
"community engagement": [
[
"Community Engagement",
3
],
[
"Community_Engagement",
1
]
],
"digitaldesignandfabrication": [
[
"DigitalDesignAndFabrication",
1
],
[
"DigitalDesignandFabrication",
1
]
],
"professional background": [
[
"Professional Background",
3
],
[
"Professional_Background",
1
]
]
},
"per_doc_frame_count": {
"3": 282,
"5": 67,
"4": 195,
"2": 57,
"7": 13,
"11": 5,
"13": 2,
"15": 1,
"12": 4,
"6": 21,
"8": 8,
"10": 4,
"9": 6,
"30": 1,
"14": 1,
"18": 1
},
"top_30_pairs": [
{
"a": "Course",
"b": "Education",
"count": 46
},
{
"a": "Education",
"b": "Project",
"count": 20
},
{
"a": "Design",
"b": "Education",
"count": 20
},
{
"a": "Education",
"b": "Professional Experience",
"count": 20
},
{
"a": "Education",
"b": "Employment",
"count": 20
},
{
"a": "Education",
"b": "Technology",
"count": 18
},
{
"a": "Education",
"b": "Grading",
"count": 17
},
{
"a": "Education",
"b": "Research",
"count": 15
},
{
"a": "Art",
"b": "Education",
"count": 15
},
{
"a": "Attendance",
"b": "Grading",
"count": 14
},
{
"a": "Course",
"b": "Grading",
"count": 13
},
{
"a": "Academic Integrity",
"b": "Education",
"count": 11
},
{
"a": "Attendance",
"b": "Education",
"count": 11
},
{
"a": "Attendance",
"b": "Course",
"count": 11
},
{
"a": "Application",
"b": "Employment",
"count": 11
},
{
"a": "Coursework",
"b": "Education",
"count": 10
},
{
"a": "Course",
"b": "Design",
"count": 10
},
{
"a": "Course",
"b": "Programming",
"count": 10
},
{
"a": "Application",
"b": "Education",
"count": 10
},
{
"a": "Budget",
"b": "Education",
"count": 10
},
{
"a": "Academic Integrity",
"b": "Accommodation",
"count": 9
},
{
"a": "Education",
"b": "Teaching",
"count": 9
},
{
"a": "Education",
"b": "Programming",
"count": 9
},
{
"a": "Academic Integrity",
"b": "Attendance",
"count": 9
},
{
"a": "Course",
"b": "Project",
"count": 8
},
{
"a": "Research",
"b": "Teaching",
"count": 8
},
{
"a": "Grading",
"b": "Project",
"count": 7
},
{
"a": "Art",
"b": "Technology",
"count": 7
},
{
"a": "Academic Integrity",
"b": "Course",
"count": 7
},
{
"a": "Accommodation",
"b": "Course",
"count": 7
}
],
"folder_crosstab": {
"Education": {
"pdf": 116,
"docx": 119,
"pptx": 3
},
"Course": {
"pdf": 29,
"docx": 29
},
"Programming": {
"pptx": 15,
"docx": 10,
"pdf": 12,
"txt": 6
},
"Design": {
"pdf": 13,
"docx": 16,
"pptx": 3
},
"Professional Experience": {
"docx": 13,
"pdf": 11
},
"Employment": {
"pdf": 15,
"docx": 9
},
"Research": {
"pdf": 9,
"docx": 13,
"markdown": 1
},
"3D Printing": {
"docx": 3,
"pdf": 11,
"pptx": 8
},
"Project": {
"pdf": 8,
"docx": 12,
"markdown": 1
},
"Grading": {
"pdf": 10,
"docx": 11
},
"Art": {
"docx": 11,
"pdf": 9,
"pptx": 1
},
"Budget": {
"docx": 6,
"pdf": 15
},
"Academic Integrity": {
"docx": 17,
"pdf": 3
},
"Teaching": {
"pdf": 9,
"docx": 10
},
"Technology": {
"docx": 15,
"pdf": 3
},
"Attendance": {
"docx": 11,
"pdf": 6
},
"Application": {
"pdf": 13,
"docx": 2
},
"Accommodation": {
"docx": 11,
"pdf": 2
},
"Manufacturing": {
"docx": 6,
"pptx": 4,
"pdf": 3
},
"Coursework": {
"pdf": 8,
"docx": 3
}
},
"bin_totals": {
"markdown": 64,
"pdf": 286,
"pptx": 70,
"txt": 28,
"docx": 217,
"dream_output": 3
},
"worker_versions": {
"2.0": 3,
"2.1": 665
},
"data_gap": {
"count": 339,
"by_type_bin": {
"pdf": 110,
"voice_note": 14,
"docx": 110,
"dream_output": 39,
"pptx": 31,
"txt": 28,
"markdown": 7
},
"char_length": {
"min": 6,
"max": 1998,
"median": 1077
},
"sample_sources": [
"Thesis Paper Guidlines.pdf",
"2026-04-30-17-06-voice.md",
"2026-04-30-15-59-voice.md",
"2026-04-30-16-53-voice.md",
"2026-04-30-16-23-voice.md",
"2026-04-29-17-52-voice.md",
"2026-04-30-16-59-voice.md",
"Outline for 3D Printed Materials for Foundry Casting.docx",
"2026-04-26-22-52-voice.md",
"2026-04-30-synthesis.md"
]
},
"corpus_coverage": {
"total_distinct_sources_in_embeddings": 1255,
"conversations_no_frames_by_design": 198,
"files_with_frames": 704,
"files_short_no_frames": 339,
"files_stage2_failed": 12,
"frame_coverage_pct": 56.1
}
}
Reference in New Issue View Git Blame Copy Permalink