{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U6635Z6CXJ6MNKKBZB5V45XVXZ","short_pith_number":"pith:U6635Z6C","schema_version":"1.0","canonical_sha256":"a7bdbee7c2ba7cc6a941c87b5e76f5be491a4dc304a6d3eb6eea71a95bf8dc63","source":{"kind":"arxiv","id":"2504.13587","version":1},"attestation_state":"computed","paper":{"title":"RAG Without the Lag: Interactive Debugging for Retrieval-Augmented Generation Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Aditya Parameswaran, Quentin Romero Lauro, Sepanta Zeighami, Shreya Shankar","submitted_at":"2025-04-18T09:38:49Z","abstract_excerpt":"Retrieval-augmented generation (RAG) pipelines have become the de-facto approach for building AI assistants with access to external, domain-specific knowledge. Given a user query, RAG pipelines typically first retrieve (R) relevant information from external sources, before invoking a Large Language Model (LLM), augmented (A) with this information, to generate (G) responses. Modern RAG pipelines frequently chain multiple retrieval and generation components, in any order. However, developing effective RAG pipelines is challenging because retrieval and generation components are intertwined, makin"},"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":"2504.13587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-18T09:38:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"068c1ca4e77b5cc927fdeac8388adfbd0d089537b89d48451c6c6272c4a36a34","abstract_canon_sha256":"d50ac60c62ce6465fc2bdd30b0204aaa6cec3747508cb96218bc614e8d6ecaa9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:58.589115Z","signature_b64":"IHvfM6l5NqyZQwRuofdUjld44tagtxIZbTK/EVgp/Vt5WrHlohpJASwIoveUBeeeyI7x6y0N4zblP3EONLDtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7bdbee7c2ba7cc6a941c87b5e76f5be491a4dc304a6d3eb6eea71a95bf8dc63","last_reissued_at":"2026-07-05T10:50:58.588602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:58.588602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAG Without the Lag: Interactive Debugging for Retrieval-Augmented Generation Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Aditya Parameswaran, Quentin Romero Lauro, Sepanta Zeighami, Shreya Shankar","submitted_at":"2025-04-18T09:38:49Z","abstract_excerpt":"Retrieval-augmented generation (RAG) pipelines have become the de-facto approach for building AI assistants with access to external, domain-specific knowledge. Given a user query, RAG pipelines typically first retrieve (R) relevant information from external sources, before invoking a Large Language Model (LLM), augmented (A) with this information, to generate (G) responses. Modern RAG pipelines frequently chain multiple retrieval and generation components, in any order. However, developing effective RAG pipelines is challenging because retrieval and generation components are intertwined, makin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13587","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/2504.13587/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":"2504.13587","created_at":"2026-07-05T10:50:58.588677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13587v1","created_at":"2026-07-05T10:50:58.588677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13587","created_at":"2026-07-05T10:50:58.588677+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6635Z6CXJ6M","created_at":"2026-07-05T10:50:58.588677+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6635Z6CXJ6MNKKB","created_at":"2026-07-05T10:50:58.588677+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6635Z6C","created_at":"2026-07-05T10:50:58.588677+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/U6635Z6CXJ6MNKKBZB5V45XVXZ","json":"https://pith.science/pith/U6635Z6CXJ6MNKKBZB5V45XVXZ.json","graph_json":"https://pith.science/api/pith-number/U6635Z6CXJ6MNKKBZB5V45XVXZ/graph.json","events_json":"https://pith.science/api/pith-number/U6635Z6CXJ6MNKKBZB5V45XVXZ/events.json","paper":"https://pith.science/paper/U6635Z6C"},"agent_actions":{"view_html":"https://pith.science/pith/U6635Z6CXJ6MNKKBZB5V45XVXZ","download_json":"https://pith.science/pith/U6635Z6CXJ6MNKKBZB5V45XVXZ.json","view_paper":"https://pith.science/paper/U6635Z6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13587&json=true","fetch_graph":"https://pith.science/api/pith-number/U6635Z6CXJ6MNKKBZB5V45XVXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/U6635Z6CXJ6MNKKBZB5V45XVXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6635Z6CXJ6MNKKBZB5V45XVXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6635Z6CXJ6MNKKBZB5V45XVXZ/action/storage_attestation","attest_author":"https://pith.science/pith/U6635Z6CXJ6MNKKBZB5V45XVXZ/action/author_attestation","sign_citation":"https://pith.science/pith/U6635Z6CXJ6MNKKBZB5V45XVXZ/action/citation_signature","submit_replication":"https://pith.science/pith/U6635Z6CXJ6MNKKBZB5V45XVXZ/action/replication_record"}},"created_at":"2026-07-05T10:50:58.588677+00:00","updated_at":"2026-07-05T10:50:58.588677+00:00"}