{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:INFD73OGFCUGVWSPGCDJ6CWNGU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"045acd3ced2cb19e760e1b2a377ae413ebbfd901e825b4b8f89d645bf5b13bf2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:27:50Z","title_canon_sha256":"b7d93b94fffaca55c4ac9b2ecc75b8588349264d59ee05655590375d86ffad7f"},"schema_version":"1.0","source":{"id":"2605.14488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14488","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14488v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14488","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"INFD73OGFCUG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"INFD73OGFCUGVWSP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"INFD73OG","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:621c1a4beae394ba8f6633cce1b5633b4f88e184026786df7f7660390e9a4c60","target":"graph","created_at":"2026-05-17T23:39:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Deepchecks introduces a comprehensive framework for evaluating Retrieval-Augmented Generation systems through multi-faceted analysis, root cause identification, and production monitoring."}],"snapshot_sha256":"3ad0ef882df57348c575b2f79731c7a1ad931f51ba8600980b66f8a3c4cd89dd"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","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","cross_cats":[],"headline":"Deepchecks introduces a comprehensive framework for evaluating Retrieval-Augmented Generation systems through multi-faceted analysis, root cause identification, and production monitoring.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:27:50Z","title":"Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)"},"references":{"count":20,"internal_anchors":1,"resolved_work":20,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"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","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"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","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"arXiv preprint arXiv:2407.00072 (2024)","work_id":"fcf6f100-76b9-4df9-8485-ffdc9f152440","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Proceedings of the 2015 Con- ference on Empirical Methods in Natural Language Processing pp","work_id":"61902027-6e92-400e-b24e-98c2483c6f45","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"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","year":2024}],"snapshot_sha256":"0a1a6f088c841a316110469cce24b6ebcea9592fb48e49c11ddaede437fb743a"},"source":{"id":"2605.14488","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:05:30.492507Z","id":"69021ba9-3b65-4619-b7e1-29a69ef8f18d","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Deepchecks introduces a comprehensive framework for evaluating Retrieval-Augmented Generation systems through multi-faceted analysis, root cause identification, and production monitoring.","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.","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."}},"verdict_id":"69021ba9-3b65-4619-b7e1-29a69ef8f18d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:96f1ac22c205f168beb8dbf790dd8f6f2937d2fde9b0721d2e9abe0f60151fc6","target":"record","created_at":"2026-05-17T23:39:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"045acd3ced2cb19e760e1b2a377ae413ebbfd901e825b4b8f89d645bf5b13bf2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:27:50Z","title_canon_sha256":"b7d93b94fffaca55c4ac9b2ecc75b8588349264d59ee05655590375d86ffad7f"},"schema_version":"1.0","source":{"id":"2605.14488","kind":"arxiv","version":1}},"canonical_sha256":"434a3fedc628a86ada4f30869f0acd353421537189cb38d920258ec3f97d4116","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"434a3fedc628a86ada4f30869f0acd353421537189cb38d920258ec3f97d4116","first_computed_at":"2026-05-17T23:39:06.463862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:06.463862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bsc0AOnBCLsqA3mp5ky1eXZ9QBU6nZ1JARJCeTOKkF1TxhNJxM4vT3VtSj+qXkFtn/La4LdDUuN3vstxF8QIAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:06.464591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96f1ac22c205f168beb8dbf790dd8f6f2937d2fde9b0721d2e9abe0f60151fc6","sha256:621c1a4beae394ba8f6633cce1b5633b4f88e184026786df7f7660390e9a4c60"],"state_sha256":"41fb079fc2df19968cb6bbba4c23eb4e0df32b25dacbf0e065073a81a93cab05"}