{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F627W5S6MYZXPBYNO2575U2M6H","short_pith_number":"pith:F627W5S6","schema_version":"1.0","canonical_sha256":"2fb5fb765e663377870d76bbfed34cf1e63cd5c515cc17ed0647fbf96f0dc92a","source":{"kind":"arxiv","id":"2506.10802","version":1},"attestation_state":"computed","paper":{"title":"Constructing and Evaluating Declarative RAG Pipelines in PyTerrier","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Parry, Craig Macdonald, Jinyuan Fang, Zaiqiao Meng","submitted_at":"2025-06-12T15:16:34Z","abstract_excerpt":"Search engines often follow a pipeline architecture, where complex but effective reranking components are used to refine the results of an initial retrieval. Retrieval augmented generation (RAG) is an exciting application of the pipeline architecture, where the final component generates a coherent answer for the users from the retrieved documents. In this demo paper, we describe how such RAG pipelines can be formulated in the declarative PyTerrier architecture, and the advantages of doing so. Our PyTerrier-RAG extension for PyTerrier provides easy access to standard RAG datasets and evaluation"},"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":"2506.10802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-12T15:16:34Z","cross_cats_sorted":[],"title_canon_sha256":"f5e75fce93b97ac75d05757c6be9acc87b4a1b47d21ed11b40fa259308b6ac2a","abstract_canon_sha256":"a05804dfaac8e8d652f339a35c41e2e31a6b9725de3896058faa8ed9b8479f5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:30.767075Z","signature_b64":"lwIK3tMB1Pb+Jw8GsHsGsFS5VhVjCzIX1PXAsDjpJaL46oBIM+K9VZzNe0Iz+CNoVcEpxfSDtNDI5iIFEdVHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fb5fb765e663377870d76bbfed34cf1e63cd5c515cc17ed0647fbf96f0dc92a","last_reissued_at":"2026-07-05T11:20:30.766516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:30.766516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constructing and Evaluating Declarative RAG Pipelines in PyTerrier","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Parry, Craig Macdonald, Jinyuan Fang, Zaiqiao Meng","submitted_at":"2025-06-12T15:16:34Z","abstract_excerpt":"Search engines often follow a pipeline architecture, where complex but effective reranking components are used to refine the results of an initial retrieval. Retrieval augmented generation (RAG) is an exciting application of the pipeline architecture, where the final component generates a coherent answer for the users from the retrieved documents. In this demo paper, we describe how such RAG pipelines can be formulated in the declarative PyTerrier architecture, and the advantages of doing so. Our PyTerrier-RAG extension for PyTerrier provides easy access to standard RAG datasets and evaluation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10802","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/2506.10802/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":"2506.10802","created_at":"2026-07-05T11:20:30.766576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10802v1","created_at":"2026-07-05T11:20:30.766576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10802","created_at":"2026-07-05T11:20:30.766576+00:00"},{"alias_kind":"pith_short_12","alias_value":"F627W5S6MYZX","created_at":"2026-07-05T11:20:30.766576+00:00"},{"alias_kind":"pith_short_16","alias_value":"F627W5S6MYZXPBYN","created_at":"2026-07-05T11:20:30.766576+00:00"},{"alias_kind":"pith_short_8","alias_value":"F627W5S6","created_at":"2026-07-05T11:20:30.766576+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/F627W5S6MYZXPBYNO2575U2M6H","json":"https://pith.science/pith/F627W5S6MYZXPBYNO2575U2M6H.json","graph_json":"https://pith.science/api/pith-number/F627W5S6MYZXPBYNO2575U2M6H/graph.json","events_json":"https://pith.science/api/pith-number/F627W5S6MYZXPBYNO2575U2M6H/events.json","paper":"https://pith.science/paper/F627W5S6"},"agent_actions":{"view_html":"https://pith.science/pith/F627W5S6MYZXPBYNO2575U2M6H","download_json":"https://pith.science/pith/F627W5S6MYZXPBYNO2575U2M6H.json","view_paper":"https://pith.science/paper/F627W5S6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10802&json=true","fetch_graph":"https://pith.science/api/pith-number/F627W5S6MYZXPBYNO2575U2M6H/graph.json","fetch_events":"https://pith.science/api/pith-number/F627W5S6MYZXPBYNO2575U2M6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F627W5S6MYZXPBYNO2575U2M6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F627W5S6MYZXPBYNO2575U2M6H/action/storage_attestation","attest_author":"https://pith.science/pith/F627W5S6MYZXPBYNO2575U2M6H/action/author_attestation","sign_citation":"https://pith.science/pith/F627W5S6MYZXPBYNO2575U2M6H/action/citation_signature","submit_replication":"https://pith.science/pith/F627W5S6MYZXPBYNO2575U2M6H/action/replication_record"}},"created_at":"2026-07-05T11:20:30.766576+00:00","updated_at":"2026-07-05T11:20:30.766576+00:00"}