Unverified50% confidenceFactExact time
Footnote's retrieval layer uses handwritten BM25 plus local bge-small vectors, fuses them with weighted reciprocal rank fusion, and has been tuned on a 59-question evaluation set.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedUnder an 18k character budget, anchored hybrid retrieval achieved 36.18% accuracy, BM25 achieved 35.98%, while the best direct planner-guided method reached only 34.19%.60% similarVerifiedBM25 (Best Matching 25) is a probabilistic ranking algorithm proposed by Stephen Robertson and others in the 1990s, scoring relevance based on three factors: term frequency, inverse document frequency, and document length normalization.58% similarUnverifiedBGS's Black Label grade requires all four sub-scores to be perfect 10s; statistically, only approximately 0.5% of submitted cards can achieve this grade.57% similarUnverifiedThe author's fine-tuning used the QLoRA method, with LoRA rank/alpha of 32/64, a learning rate of 1e-4, batch size 1 with gradient accumulation of 16, AdamW 8-bit optimizer, and training for 1 epoch.55% similarUnverifiedIn a needle-in-a-haystack experiment with a 128K Token context and about 16,000 key-value pairs, changing the position of just one key-value pair produced a maximum accuracy gap of 40.2% for DeepSeek-V4-Flash-Base, 34.8% for DeepSeek-V4-Pro-Base, and still 19.1% and 14.8% respectively after post-training optimization.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1045095API
curl https://kongchang.com/api/v1/knowledge/claims/1045095MCP
get_claim(id=1045095)