{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZYBTSGAO62EBLPGS4BPNRE7WX5","short_pith_number":"pith:ZYBTSGAO","schema_version":"1.0","canonical_sha256":"ce0339180ef68815bcd2e05ed893f6bf72fa5bc56c609e27b426d514c8323a73","source":{"kind":"arxiv","id":"2605.30790","version":1},"attestation_state":"computed","paper":{"title":"On the impact of retrieved content representations in RAG Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Anton van der Vegt, Bevan Koopman, Guido Zuccon, Jonathan J Ross","submitted_at":"2026-05-29T03:26:41Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) supplements a language model's input with retrieved documents, yet most RAG pipelines inherit retrieval components designed for human readers. How retrieved content should be represented when the consumer is a large language model (LLM) rather than a human is less well understood. Recent work has proposed transformations of retrieved content and identified properties that affect generation, but each examines a single transformation or property in isolation, leaving open which features of a document's representation matter most. We address this with a contro"},"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":"2605.30790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-29T03:26:41Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2a74df3b9c5d850aeff370415a28d1583316b95e83e9ff272a2f5e3f41d46eb1","abstract_canon_sha256":"bb827f44c32b7d3dc7af953feb624b928d5ae1597c72a5e14db35f81935c4002"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:16.804629Z","signature_b64":"dMz1xVhb2ibEcQcaiBWS0unZBGGbhsYeoS/syvF/lJ5J06nvRVC3TSb8wS+64zlNFTxmukUmGZN38I0Iyv0EDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce0339180ef68815bcd2e05ed893f6bf72fa5bc56c609e27b426d514c8323a73","last_reissued_at":"2026-06-01T01:03:16.803854Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:16.803854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the impact of retrieved content representations in RAG Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Anton van der Vegt, Bevan Koopman, Guido Zuccon, Jonathan J Ross","submitted_at":"2026-05-29T03:26:41Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) supplements a language model's input with retrieved documents, yet most RAG pipelines inherit retrieval components designed for human readers. How retrieved content should be represented when the consumer is a large language model (LLM) rather than a human is less well understood. Recent work has proposed transformations of retrieved content and identified properties that affect generation, but each examines a single transformation or property in isolation, leaving open which features of a document's representation matter most. We address this with a contro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30790","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/2605.30790/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":"2605.30790","created_at":"2026-06-01T01:03:16.803984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30790v1","created_at":"2026-06-01T01:03:16.803984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30790","created_at":"2026-06-01T01:03:16.803984+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYBTSGAO62EB","created_at":"2026-06-01T01:03:16.803984+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYBTSGAO62EBLPGS","created_at":"2026-06-01T01:03:16.803984+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYBTSGAO","created_at":"2026-06-01T01:03:16.803984+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/ZYBTSGAO62EBLPGS4BPNRE7WX5","json":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5.json","graph_json":"https://pith.science/api/pith-number/ZYBTSGAO62EBLPGS4BPNRE7WX5/graph.json","events_json":"https://pith.science/api/pith-number/ZYBTSGAO62EBLPGS4BPNRE7WX5/events.json","paper":"https://pith.science/paper/ZYBTSGAO"},"agent_actions":{"view_html":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5","download_json":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5.json","view_paper":"https://pith.science/paper/ZYBTSGAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30790&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYBTSGAO62EBLPGS4BPNRE7WX5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYBTSGAO62EBLPGS4BPNRE7WX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/action/storage_attestation","attest_author":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/action/author_attestation","sign_citation":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/action/citation_signature","submit_replication":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/action/replication_record"}},"created_at":"2026-06-01T01:03:16.803984+00:00","updated_at":"2026-06-01T01:03:16.803984+00:00"}