Initialize v0.0.3

[haonan-li]

Chang log:

1. Add restore_claims function to decomposer, to restore the decomposed claims to the original user input.
2. Add utils/data_class.py which defines the data structure for several intermedia processing function and final output.
3. Parallel the restore_claims, identify_checkworthiness and query_generation functions to speed up.
4. Add the token count for all steps.
5. Change the verification logic from input all evidence together within a single LLM call, to verify the claim by each evidence for each LLM call.
6. Remove the deterministic output, change the factuality to a number in [0,1], calculated by the judgement with each simple evidence.
7. Redesign the webpage.