{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZYBTSGAO62EBLPGS4BPNRE7WX5","short_pith_number":"pith:ZYBTSGAO","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"},"canonical_sha256":"ce0339180ef68815bcd2e05ed893f6bf72fa5bc56c609e27b426d514c8323a73","source":{"kind":"arxiv","id":"2605.30790","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30790","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30790v1","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30790","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZYBTSGAO62EB","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZYBTSGAO62EBLPGS","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZYBTSGAO","created_at":"2026-06-01T01:03:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZYBTSGAO62EBLPGS4BPNRE7WX5","target":"record","payload":{"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"},"canonical_sha256":"ce0339180ef68815bcd2e05ed893f6bf72fa5bc56c609e27b426d514c8323a73","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"},"source_kind":"arxiv","source_id":"2605.30790","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:03:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xzV2c0KxoWQxk3Aunq9E3omNNruFj+/tIcaM47iBLvV6yARAGJuL5WrEwxJfyVtvtXucDPM48WNonArdXAirAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:01:06.695555Z"},"content_sha256":"81108c29f4073140049b41e3ed438f47c405ed783a1e56fe181dffee195c4fd5","schema_version":"1.0","event_id":"sha256:81108c29f4073140049b41e3ed438f47c405ed783a1e56fe181dffee195c4fd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZYBTSGAO62EBLPGS4BPNRE7WX5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:03:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mU9/PpoQzmbfpus5CaWbc91siJd9VUm1pWxitU5sH9wZHO1WfS59v22a2MkD8VwLo765OX6Z+MLTYUdVhvw3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:01:06.695928Z"},"content_sha256":"d04ac0ef97ae5179d8d84ce03ed5c18785fe8e91d59fca5f9f51526853db17d9","schema_version":"1.0","event_id":"sha256:d04ac0ef97ae5179d8d84ce03ed5c18785fe8e91d59fca5f9f51526853db17d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/bundle.json","state_url":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T07:01:06Z","links":{"resolver":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5","bundle":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/bundle.json","state":"https://pith.science/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYBTSGAO62EBLPGS4BPNRE7WX5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZYBTSGAO62EBLPGS4BPNRE7WX5","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":"bb827f44c32b7d3dc7af953feb624b928d5ae1597c72a5e14db35f81935c4002","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-29T03:26:41Z","title_canon_sha256":"2a74df3b9c5d850aeff370415a28d1583316b95e83e9ff272a2f5e3f41d46eb1"},"schema_version":"1.0","source":{"id":"2605.30790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30790","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30790v1","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30790","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZYBTSGAO62EB","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZYBTSGAO62EBLPGS","created_at":"2026-06-01T01:03:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZYBTSGAO","created_at":"2026-06-01T01:03:16Z"}],"graph_snapshots":[{"event_id":"sha256:d04ac0ef97ae5179d8d84ce03ed5c18785fe8e91d59fca5f9f51526853db17d9","target":"graph","created_at":"2026-06-01T01:03:16Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.30790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anton van der Vegt, Bevan Koopman, Guido Zuccon, Jonathan J Ross","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-29T03:26:41Z","title":"On the impact of retrieved content representations in RAG Pipelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30790","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:81108c29f4073140049b41e3ed438f47c405ed783a1e56fe181dffee195c4fd5","target":"record","created_at":"2026-06-01T01:03:16Z","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":"bb827f44c32b7d3dc7af953feb624b928d5ae1597c72a5e14db35f81935c4002","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-29T03:26:41Z","title_canon_sha256":"2a74df3b9c5d850aeff370415a28d1583316b95e83e9ff272a2f5e3f41d46eb1"},"schema_version":"1.0","source":{"id":"2605.30790","kind":"arxiv","version":1}},"canonical_sha256":"ce0339180ef68815bcd2e05ed893f6bf72fa5bc56c609e27b426d514c8323a73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce0339180ef68815bcd2e05ed893f6bf72fa5bc56c609e27b426d514c8323a73","first_computed_at":"2026-06-01T01:03:16.803854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:16.803854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dMz1xVhb2ibEcQcaiBWS0unZBGGbhsYeoS/syvF/lJ5J06nvRVC3TSb8wS+64zlNFTxmukUmGZN38I0Iyv0EDQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:16.804629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81108c29f4073140049b41e3ed438f47c405ed783a1e56fe181dffee195c4fd5","sha256:d04ac0ef97ae5179d8d84ce03ed5c18785fe8e91d59fca5f9f51526853db17d9"],"state_sha256":"3f30f692f6dc713f4085863cce81c61918500d14e62dd1edd7f7dda1f12e250a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2nvnh1VPDrNKda4aVEsHErASMx+erfFbQYfra4W9nein4tfcSRHfbtPWwahc8ETOEhSYaxqKTqZp8lPR4ruyDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T07:01:06.697915Z","bundle_sha256":"44be149b4a6f4d84cfbb1c02af3175901c127b7abfcf739025c832763ef26240"}}