Evaluation report

Evaluation report — rag

Customer

biblioteca

Suite

rag

This run

staging — 2026-08-27T09:52:49.239043+00:00

Reference

staging — 2026-08-27T09:52:41.183791+00:00

Code version

b5870a655c776d75f8be518796bad8acf02fb08a-dirty — uncommitted changes were present, so this run cannot be reproduced from the repository

Did it get worse? Yes

6 checks got worse compared with the reference. Every case could be judged. No case is suspended. The configuration is the same as the reference.

What got worse (6)

Case	Check	What happened	Why
`borrowing`	`faithfulness`	Went from passing to failing (1.000000 → 0.500000).	1 of 2 claims appear in the passages
`joining`	`faithfulness`	Went from passing to failing (1.000000 → 0.500000).	1 of 2 claims appear in the passages
`late-return`	`faithfulness`	Went from passing to failing (1.000000 → 0.500000).	1 of 2 claims appear in the passages
`opening-hours`	`faithfulness`	Went from passing to failing (1.000000 → 0.500000).	1 of 2 claims appear in the passages
`study-room`	`faithfulness`	Went from passing to failing (1.000000 → 0.500000).	1 of 2 claims appear in the passages
`wifi`	`faithfulness`	Went from passing to failing (1.000000 → 0.500000).	1 of 2 claims appear in the passages

What could not be judged (0)

Nothing in this section.

What is set aside (0)

Nothing in this section.

What was added or removed (0)

Nothing in this section.

What got better (0)

Nothing in this section.

What stayed the same (12)

Case	Check	What happened	Why
`borrowing`	`pii_absent`	Score unchanged at 1.000000.	no identifier found (checked: codice_fiscale, email, iban, partita_iva, phone_it)
`borrowing`	`cost_budget`	Score unchanged at 0.754148.	0.000652 USD against a 0.002000 cap (within budget)
`joining`	`pii_absent`	Score unchanged at 1.000000.	no identifier found (checked: codice_fiscale, email, iban, partita_iva, phone_it)
`joining`	`cost_budget`	Score unchanged at 0.755287.	0.000648 USD against a 0.002000 cap (within budget)
`late-return`	`pii_absent`	Score unchanged at 1.000000.	no identifier found (checked: codice_fiscale, email, iban, partita_iva, phone_it)
`late-return`	`cost_budget`	Score unchanged at 0.757863.	0.000639 USD against a 0.002000 cap (within budget)
`opening-hours`	`pii_absent`	Score unchanged at 1.000000.	no identifier found (checked: codice_fiscale, email, iban, partita_iva, phone_it)
`opening-hours`	`cost_budget`	Score unchanged at 0.754717.	0.000650 USD against a 0.002000 cap (within budget)
`study-room`	`pii_absent`	Score unchanged at 1.000000.	no identifier found (checked: codice_fiscale, email, iban, partita_iva, phone_it)
`study-room`	`cost_budget`	Score unchanged at 0.757002.	0.000642 USD against a 0.002000 cap (within budget)
`wifi`	`pii_absent`	Score unchanged at 1.000000.	no identifier found (checked: codice_fiscale, email, iban, partita_iva, phone_it)
`wifi`	`cost_budget`	Score unchanged at 0.757576.	0.000640 USD against a 0.002000 cap (within budget)