{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PT4GLVP27C5MU2SRT2K52RJYRP","short_pith_number":"pith:PT4GLVP2","schema_version":"1.0","canonical_sha256":"7cf865d5faf8baca6a519e95dd45388bd7f2b692341af34a3197faa8dc43f06f","source":{"kind":"arxiv","id":"2401.05856","version":1},"attestation_state":"computed","paper":{"title":"Seven Failure Points When Engineering a Retrieval Augmented Generation System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Mohamed Abdelrazek, Scott Barnett, Srikanth Thudumu, Stefanus Kurniawan, Zach Brannelly","submitted_at":"2024-01-11T12:04:11Z","abstract_excerpt":"Software engineers are increasingly adding semantic search capabilities to applications using a strategy known as Retrieval Augmented Generation (RAG). A RAG system involves finding documents that semantically match a query and then passing the documents to a large language model (LLM) such as ChatGPT to extract the right answer using an LLM. RAG systems aim to: a) reduce the problem of hallucinated responses from LLMs, b) link sources/references to generated responses, and c) remove the need for annotating documents with meta-data. However, RAG systems suffer from limitations inherent to info"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.05856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-01-11T12:04:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70e1b9920e5a7360c725b41b7690952bf885ff2d54e0e8adeff0cc968c1cd77e","abstract_canon_sha256":"96c042402397ec5b7be33e2b576ac012d75476855561c90fd398b5e82aa64174"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:43.316924Z","signature_b64":"4Vit37aL3KD8cZDvs4YgRcE7GiibwMyd1i2aybW7HLiqm6s4L+dj7R9l+2weC8X/cGA9yF2XJpnU6Xvww3ehDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf865d5faf8baca6a519e95dd45388bd7f2b692341af34a3197faa8dc43f06f","last_reissued_at":"2026-07-05T07:40:43.316490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:43.316490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seven Failure Points When Engineering a Retrieval Augmented Generation System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Mohamed Abdelrazek, Scott Barnett, Srikanth Thudumu, Stefanus Kurniawan, Zach Brannelly","submitted_at":"2024-01-11T12:04:11Z","abstract_excerpt":"Software engineers are increasingly adding semantic search capabilities to applications using a strategy known as Retrieval Augmented Generation (RAG). A RAG system involves finding documents that semantically match a query and then passing the documents to a large language model (LLM) such as ChatGPT to extract the right answer using an LLM. RAG systems aim to: a) reduce the problem of hallucinated responses from LLMs, b) link sources/references to generated responses, and c) remove the need for annotating documents with meta-data. However, RAG systems suffer from limitations inherent to info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05856","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.05856/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":"2401.05856","created_at":"2026-07-05T07:40:43.316557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05856v1","created_at":"2026-07-05T07:40:43.316557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05856","created_at":"2026-07-05T07:40:43.316557+00:00"},{"alias_kind":"pith_short_12","alias_value":"PT4GLVP27C5M","created_at":"2026-07-05T07:40:43.316557+00:00"},{"alias_kind":"pith_short_16","alias_value":"PT4GLVP27C5MU2SR","created_at":"2026-07-05T07:40:43.316557+00:00"},{"alias_kind":"pith_short_8","alias_value":"PT4GLVP2","created_at":"2026-07-05T07:40:43.316557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17721","citing_title":"Understanding and Debugging Failures in N-Gram-Based Generative Retrieval","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06003","citing_title":"Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge Graphs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23697","citing_title":"SemChunk-C: Semantic Segmentation for C Code","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27294","citing_title":"Separating Semantic Competition from Context Length in RAG Reading","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2505.00017","citing_title":"ReCellTy: Domain-Specific Knowledge Graph Retrieval-Augmented LLMs Reasoning Workflow for Single-Cell Annotation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02398","citing_title":"Improving MPI Error Detection and Repair with Large Language Models and Bug References","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25313","citing_title":"Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14488","citing_title":"Controlling Authority Retrieval: A Missing Retrieval Objective for Authority-Governed Knowledge","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02010","citing_title":"Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PT4GLVP27C5MU2SRT2K52RJYRP","json":"https://pith.science/pith/PT4GLVP27C5MU2SRT2K52RJYRP.json","graph_json":"https://pith.science/api/pith-number/PT4GLVP27C5MU2SRT2K52RJYRP/graph.json","events_json":"https://pith.science/api/pith-number/PT4GLVP27C5MU2SRT2K52RJYRP/events.json","paper":"https://pith.science/paper/PT4GLVP2"},"agent_actions":{"view_html":"https://pith.science/pith/PT4GLVP27C5MU2SRT2K52RJYRP","download_json":"https://pith.science/pith/PT4GLVP27C5MU2SRT2K52RJYRP.json","view_paper":"https://pith.science/paper/PT4GLVP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05856&json=true","fetch_graph":"https://pith.science/api/pith-number/PT4GLVP27C5MU2SRT2K52RJYRP/graph.json","fetch_events":"https://pith.science/api/pith-number/PT4GLVP27C5MU2SRT2K52RJYRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PT4GLVP27C5MU2SRT2K52RJYRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PT4GLVP27C5MU2SRT2K52RJYRP/action/storage_attestation","attest_author":"https://pith.science/pith/PT4GLVP27C5MU2SRT2K52RJYRP/action/author_attestation","sign_citation":"https://pith.science/pith/PT4GLVP27C5MU2SRT2K52RJYRP/action/citation_signature","submit_replication":"https://pith.science/pith/PT4GLVP27C5MU2SRT2K52RJYRP/action/replication_record"}},"created_at":"2026-07-05T07:40:43.316557+00:00","updated_at":"2026-07-05T07:40:43.316557+00:00"}