mirror of
https://github.com/allaunthefox/SilverSight.git
synced 2026-07-31 01:25:21 +00:00
allaun
4490dc28a7
- Move canonical FixedPoint to Core/SilverSight/FixedPoint.lean - Add SilverSightRRC library: RRC logogram gates, receipt bridge, AVM ISA - Add AVMIsa.Emit as the sole top-level JSON output boundary - Add rrc-emit-fixture executable and Python I/O shims - Update AGENTS.md, glossary, project map, and build baseline Build: 2981 jobs, 0 errors (lake build)
86 lines
2.8 KiB
Python
86 lines
2.8 KiB
Python
#!/usr/bin/env python3
|
||
"""PIST 8×8 strand adjacency matrix builder.
|
||
|
||
This is a raw-feature shim: it carries no admissibility logic. It tokenizes
|
||
input text, assigns each token to a strand by vocab_index % 8, and counts
|
||
bigram adjacencies projected onto strands.
|
||
|
||
Output schema matches `rrc_pist_predictions_250_v1.json` (matrix-only).
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import argparse
|
||
import hashlib
|
||
import json
|
||
import re
|
||
from typing import Any
|
||
|
||
|
||
def tokenize(text: str) -> list[str]:
|
||
"""Split text into normalized tokens."""
|
||
text = text.lower()
|
||
# Keep letters, digits, and a small set of math symbols
|
||
tokens = re.findall(r"[a-z0-9]+|[+\-*/=^(){}\[\]]", text)
|
||
return tokens
|
||
|
||
|
||
def strand(token: str, vocab: list[str]) -> int:
|
||
return vocab.index(token) % 8
|
||
|
||
|
||
def build_matrix(tokens: list[str]) -> list[list[int]]:
|
||
"""Build 8×8 strand adjacency matrix from token bigrams."""
|
||
vocab = sorted(set(tokens))
|
||
matrix = [[0 for _ in range(8)] for _ in range(8)]
|
||
for t_i, t_j in zip(tokens, tokens[1:]):
|
||
matrix[strand(t_i, vocab)][strand(t_j, vocab)] += 1
|
||
return matrix
|
||
|
||
|
||
def canonical_json_matrix(matrix: list[list[int]]) -> str:
|
||
"""Canonical row-major JSON with no whitespace for hashing."""
|
||
return json.dumps(matrix, separators=(",", ":"))
|
||
|
||
|
||
def build_record(text: str, equation_id: str, name: str) -> dict[str, Any]:
|
||
tokens = tokenize(text)
|
||
vocab = sorted(set(tokens))
|
||
matrix = build_matrix(tokens)
|
||
matrix_json = canonical_json_matrix(matrix)
|
||
return {
|
||
"equation_id": equation_id,
|
||
"name": name,
|
||
"schema": "rrc_pist_predictions_250_v1",
|
||
"claim_boundary": "matrix-only;no-classifier;no-lean-spectral",
|
||
"matrix_schema": "token_strand_adjacency_8x8_v1",
|
||
"matrix_8x8": matrix,
|
||
"matrix_hash": hashlib.sha256(matrix_json.encode("utf-8")).hexdigest(),
|
||
"global_vocab_hash": hashlib.sha256(
|
||
json.dumps(vocab, separators=(",", ":")).encode("utf-8")
|
||
).hexdigest(),
|
||
"proxy_pred": None,
|
||
"exact_pred": None,
|
||
"source_records": [{"equation_record_id": equation_id, "name": name}],
|
||
}
|
||
|
||
|
||
def main() -> None:
|
||
parser = argparse.ArgumentParser(description="Build PIST 8×8 adjacency matrix")
|
||
parser.add_argument("--text", required=True, help="input equation text")
|
||
parser.add_argument("--equation-id", default="rrc_eq_unknown")
|
||
parser.add_argument("--name", default="unknown")
|
||
parser.add_argument("--output", help="write JSON record to file")
|
||
args = parser.parse_args()
|
||
|
||
record = build_record(args.text, args.equation_id, args.name)
|
||
out = json.dumps(record, indent=2)
|
||
if args.output:
|
||
with open(args.output, "w", encoding="utf-8") as f:
|
||
f.write(out + "\n")
|
||
else:
|
||
print(out)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|