Unverified50% confidenceBenchmarkExact time
Horizontal layouts perform excellently: 97.3% exact on the test set and 99.0% on unseen horizontal layouts; vertical writing is the weak point: 40.0% on the test set, mainly due to Latin text printed sideways (registration number 62.7%, date 82.7%), while the table portion is normal; in unseen fully vertical layouts the table is rotated, at only 4%.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn manually proofread samples, the character error rate was only 0.68% when the text was clearly legible, but approximately 45% of sampled passages were completely uncorrectable due to source quality issues.75% similarUnverifiedAn evaluation suite with 1,800 test cases has long maintained a stable aggregate pass rate of 97%, but the 64-case multilingual slice within it has a pass rate of only 61%74% similarUnverifiedJev achieved 98.5% accuracy on English comments and 93.4% on the other seven languages, a gap of about 5 percentage points; the probabilities of the nine missed detections all ranged from 0.16 to 0.49, and it correctly identified the language in all 520 cases.71% similarUnverifiedAblation analysis shows that fine-tuning on the segment paradigm yields a +5.29-point improvement on the test set, while replacing the first 4,500 transcript words with 2,000 retrieved words yields only a +1.55-point improvement.68% similarUnverifiedOn a test set of 600 synthetic invoices, the QLoRA fine-tuned model achieved a full-invoice exact rate of 83.0%, an auto-approval rate of 86.8%, and 0 out of 461 validation-coverage field errors in approved invoices (upper bound 0.8%).68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036989API
curl https://kongchang.com/api/v1/knowledge/claims/1036989MCP
get_claim(id=1036989)