{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:INFD73OGFCUGVWSPGCDJ6CWNGU","short_pith_number":"pith:INFD73OG","schema_version":"1.0","canonical_sha256":"434a3fedc628a86ada4f30869f0acd353421537189cb38d920258ec3f97d4116","source":{"kind":"arxiv","id":"2605.14488","version":1},"attestation_state":"computed","paper":{"title":"Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Deepchecks introduces a comprehensive framework for evaluating Retrieval-Augmented Generation systems through multi-faceted analysis, root cause identification, and production monitoring.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alex Zaikman, Assaf Gerner, Jonatan Liberman, Lior Rokach, Liron Hamra, Nadav Barak, Neal Harow, Netta Madvil, Noam Bresler, Philip Tannor, Rotem Brazilay, Shay Tsadok, Shir Chorev, Yaron Friedman","submitted_at":"2026-05-14T07:27:50Z","abstract_excerpt":"Large Language Models (LLMs) augmented with Retrieval-Augmented Generation (RAG) techniques are revolutionizing applications across multiple domains, such as healthcare, finance, and customer service. Despite their potential, evaluating RAG systems remains a complex challenge due to the stochastic nature of generated outputs and the intricate interplay between retrieval and generation components. This paper introduces Deepchecks, a comprehensive framework tailored for evaluating RAG applications. Deepchecks' evaluation framework addresses RAG applications evaluation through a multi-faceted app"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:27:50Z","cross_cats_sorted":[],"title_canon_sha256":"b7d93b94fffaca55c4ac9b2ecc75b8588349264d59ee05655590375d86ffad7f","abstract_canon_sha256":"045acd3ced2cb19e760e1b2a377ae413ebbfd901e825b4b8f89d645bf5b13bf2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:06.464591Z","signature_b64":"Bsc0AOnBCLsqA3mp5ky1eXZ9QBU6nZ1JARJCeTOKkF1TxhNJxM4vT3VtSj+qXkFtn/La4LdDUuN3vstxF8QIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"434a3fedc628a86ada4f30869f0acd353421537189cb38d920258ec3f97d4116","last_reissued_at":"2026-05-17T23:39:06.463862Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:06.463862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Deepchecks introduces a comprehensive framework for evaluating Retrieval-Augmented Generation systems through multi-faceted analysis, root cause identification, and production monitoring.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alex Zaikman, Assaf Gerner, Jonatan Liberman, Lior Rokach, Liron Hamra, Nadav Barak, Neal Harow, Netta Madvil, Noam Bresler, Philip Tannor, Rotem Brazilay, Shay Tsadok, Shir Chorev, Yaron Friedman","submitted_at":"2026-05-14T07:27:50Z","abstract_excerpt":"Large Language Models (LLMs) augmented with Retrieval-Augmented Generation (RAG) techniques are revolutionizing applications across multiple domains, such as healthcare, finance, and customer service. Despite their potential, evaluating RAG systems remains a complex challenge due to the stochastic nature of generated outputs and the intricate interplay between retrieval and generation components. This paper introduces Deepchecks, a comprehensive framework tailored for evaluating RAG applications. Deepchecks' evaluation framework addresses RAG applications evaluation through a multi-faceted app"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Deepchecks' evaluation framework addresses RAG applications evaluation through a multi-faceted approach, root cause analysis and production monitoring. By ensuring alignment with application-specific requirements, Deepchecks framework provides a robust foundation for assessing reliability, relevance, and user satisfaction in RAG systems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a multi-faceted approach with root cause analysis and production monitoring can effectively handle the stochastic nature of outputs and the interplay between retrieval and generation components to provide robust, aligned evaluations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Deepchecks is a new multi-faceted evaluation framework for RAG that incorporates root cause analysis and production monitoring to assess reliability, relevance, and user satisfaction.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Deepchecks introduces a comprehensive framework for evaluating Retrieval-Augmented Generation systems through multi-faceted analysis, root cause identification, and production monitoring.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3ad0ef882df57348c575b2f79731c7a1ad931f51ba8600980b66f8a3c4cd89dd"},"source":{"id":"2605.14488","kind":"arxiv","version":1},"verdict":{"id":"69021ba9-3b65-4619-b7e1-29a69ef8f18d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:05:30.492507Z","strongest_claim":"Deepchecks' evaluation framework addresses RAG applications evaluation through a multi-faceted approach, root cause analysis and production monitoring. By ensuring alignment with application-specific requirements, Deepchecks framework provides a robust foundation for assessing reliability, relevance, and user satisfaction in RAG systems.","one_line_summary":"Deepchecks is a new multi-faceted evaluation framework for RAG that incorporates root cause analysis and production monitoring to assess reliability, relevance, and user satisfaction.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a multi-faceted approach with root cause analysis and production monitoring can effectively handle the stochastic nature of outputs and the interplay between retrieval and generation components to provide robust, aligned evaluations.","pith_extraction_headline":"Deepchecks introduces a comprehensive framework for evaluating Retrieval-Augmented Generation systems through multi-faceted analysis, root cause identification, and production monitoring."},"references":{"count":20,"sample":[{"doi":"","year":2025,"title":"Amazon Web Services: New RAG evaluation and llm-as-a-judge ca- pabilities in Amazon Bedrock.AWS Blog(2025), retrieved from https://aws.amazon.com/blogs/aws/new-rag-evaluation-and-llm-as-a- judge-capab","work_id":"2a0dd696-e7a4-44d9-8141-d6cc7b43266c","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Arize AI: Llms as judges: A comprehensive survey on LLM-based evaluation methods.Arize AI Blog(2025), retrieved from https://arize.com/blog/llm- as-judge-survey-paper/","work_id":"a74514ba-500a-400b-b27c-89cb1d0286f9","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"arXiv preprint arXiv:2407.00072 (2024)","work_id":"fcf6f100-76b9-4df9-8485-ffdc9f152440","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Proceedings of the 2015 Con- ference on Empirical Methods in Natural Language Processing pp","work_id":"61902027-6e92-400e-b24e-98c2483c6f45","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Con- fident AI Blog (2024), https://www.confident-ai.com/blog/why-llm-as-a- judge-is-the-best-llm-evaluation-method","work_id":"fbcfd867-0e8e-4d82-b589-45be8fea046f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":20,"snapshot_sha256":"0a1a6f088c841a316110469cce24b6ebcea9592fb48e49c11ddaede437fb743a","internal_anchors":1},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.14488","created_at":"2026-05-17T23:39:06.463979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14488v1","created_at":"2026-05-17T23:39:06.463979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14488","created_at":"2026-05-17T23:39:06.463979+00:00"},{"alias_kind":"pith_short_12","alias_value":"INFD73OGFCUG","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"INFD73OGFCUGVWSP","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"INFD73OG","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INFD73OGFCUGVWSPGCDJ6CWNGU","json":"https://pith.science/pith/INFD73OGFCUGVWSPGCDJ6CWNGU.json","graph_json":"https://pith.science/api/pith-number/INFD73OGFCUGVWSPGCDJ6CWNGU/graph.json","events_json":"https://pith.science/api/pith-number/INFD73OGFCUGVWSPGCDJ6CWNGU/events.json","paper":"https://pith.science/paper/INFD73OG"},"agent_actions":{"view_html":"https://pith.science/pith/INFD73OGFCUGVWSPGCDJ6CWNGU","download_json":"https://pith.science/pith/INFD73OGFCUGVWSPGCDJ6CWNGU.json","view_paper":"https://pith.science/paper/INFD73OG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14488&json=true","fetch_graph":"https://pith.science/api/pith-number/INFD73OGFCUGVWSPGCDJ6CWNGU/graph.json","fetch_events":"https://pith.science/api/pith-number/INFD73OGFCUGVWSPGCDJ6CWNGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INFD73OGFCUGVWSPGCDJ6CWNGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INFD73OGFCUGVWSPGCDJ6CWNGU/action/storage_attestation","attest_author":"https://pith.science/pith/INFD73OGFCUGVWSPGCDJ6CWNGU/action/author_attestation","sign_citation":"https://pith.science/pith/INFD73OGFCUGVWSPGCDJ6CWNGU/action/citation_signature","submit_replication":"https://pith.science/pith/INFD73OGFCUGVWSPGCDJ6CWNGU/action/replication_record"}},"created_at":"2026-05-17T23:39:06.463979+00:00","updated_at":"2026-05-17T23:39:06.463979+00:00"}