{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y4H43MTS4EWUMDYJEGBB74GU5X","short_pith_number":"pith:Y4H43MTS","canonical_record":{"source":{"id":"2507.20059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-26T20:57:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1695fb4b8fff0ed5c5f6333ee8fc156a12be287199fe41bbe5df7a8f3a9dca2e","abstract_canon_sha256":"44b6f8c93db4c6225b16a1fb3bf8bfdf0e310e8105512fee4f019b651af0665a"},"schema_version":"1.0"},"canonical_sha256":"c70fcdb272e12d460f0921821ff0d4edf2eea2f71672d1b09a1fed94ea893bca","source":{"kind":"arxiv","id":"2507.20059","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20059","created_at":"2026-07-05T11:44:12Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20059v1","created_at":"2026-07-05T11:44:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20059","created_at":"2026-07-05T11:44:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y4H43MTS4EWU","created_at":"2026-07-05T11:44:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y4H43MTS4EWUMDYJ","created_at":"2026-07-05T11:44:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y4H43MTS","created_at":"2026-07-05T11:44:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y4H43MTS4EWUMDYJEGBB74GU5X","target":"record","payload":{"canonical_record":{"source":{"id":"2507.20059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-26T20:57:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1695fb4b8fff0ed5c5f6333ee8fc156a12be287199fe41bbe5df7a8f3a9dca2e","abstract_canon_sha256":"44b6f8c93db4c6225b16a1fb3bf8bfdf0e310e8105512fee4f019b651af0665a"},"schema_version":"1.0"},"canonical_sha256":"c70fcdb272e12d460f0921821ff0d4edf2eea2f71672d1b09a1fed94ea893bca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:12.668682Z","signature_b64":"bP7pUfAj1htB/A5/KgGM8mvYJmQXCk7Mp6tJ918ytke3qZ/Q/EJQLIRM93StO50LLttWVJw3LuocZH1500pSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c70fcdb272e12d460f0921821ff0d4edf2eea2f71672d1b09a1fed94ea893bca","last_reissued_at":"2026-07-05T11:44:12.668190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:12.668190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.20059","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":"2026-07-05T11:44:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gK+PUxRhKJunDlRxjfccUf5JwzWUeE3Hzwue9PORVGfqyYPjwaVEI6YCF0u40/txTlCSjX9yC1FRRhJSZ8jCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:50:38.397312Z"},"content_sha256":"669f48ff6da8d5177f10bb3e33c571285785ca305963d324f10f4a4631ba5431","schema_version":"1.0","event_id":"sha256:669f48ff6da8d5177f10bb3e33c571285785ca305963d324f10f4a4631ba5431"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y4H43MTS4EWUMDYJEGBB74GU5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Haoyu Wang, Ran Xu, Wenqi Shi, Yuchen Zhuang, Yue Yu","submitted_at":"2025-07-26T20:57:24Z","abstract_excerpt":"Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved at inference time. While RAG demonstrates strong performance on benchmarks largely derived from general-domain corpora like Wikipedia, its effectiveness under realistic, diverse retrieval scenarios remains underexplored. We evaluated RAG systems using MassiveDS, a large-scale datastore with mixture of knowledge, and identified critical limitations: retrieval mainly benefits smaller models, rerankers add minimal value, and no single retrieval source consistently excels. Moreove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20059","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/2507.20059/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":"2026-07-05T11:44:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIh4TNCGApgf65zvpa639vpFQnXiSTZxA7wBmWyizINa7iCDjrPcq36FETnQje9BT85V2kAabnZgXdigffi0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:50:38.397813Z"},"content_sha256":"5900a70bccd2165e91c624c23327ec801b9cb86f9f7d7d486b7a44a597930a6d","schema_version":"1.0","event_id":"sha256:5900a70bccd2165e91c624c23327ec801b9cb86f9f7d7d486b7a44a597930a6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/bundle.json","state_url":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/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":"2026-08-04T13:50:38Z","links":{"resolver":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X","bundle":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/bundle.json","state":"https://pith.science/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y4H43MTS4EWUMDYJEGBB74GU5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y4H43MTS4EWUMDYJEGBB74GU5X","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":"44b6f8c93db4c6225b16a1fb3bf8bfdf0e310e8105512fee4f019b651af0665a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-26T20:57:24Z","title_canon_sha256":"1695fb4b8fff0ed5c5f6333ee8fc156a12be287199fe41bbe5df7a8f3a9dca2e"},"schema_version":"1.0","source":{"id":"2507.20059","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20059","created_at":"2026-07-05T11:44:12Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20059v1","created_at":"2026-07-05T11:44:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20059","created_at":"2026-07-05T11:44:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y4H43MTS4EWU","created_at":"2026-07-05T11:44:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y4H43MTS4EWUMDYJ","created_at":"2026-07-05T11:44:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y4H43MTS","created_at":"2026-07-05T11:44:12Z"}],"graph_snapshots":[{"event_id":"sha256:5900a70bccd2165e91c624c23327ec801b9cb86f9f7d7d486b7a44a597930a6d","target":"graph","created_at":"2026-07-05T11:44:12Z","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/2507.20059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved at inference time. While RAG demonstrates strong performance on benchmarks largely derived from general-domain corpora like Wikipedia, its effectiveness under realistic, diverse retrieval scenarios remains underexplored. We evaluated RAG systems using MassiveDS, a large-scale datastore with mixture of knowledge, and identified critical limitations: retrieval mainly benefits smaller models, rerankers add minimal value, and no single retrieval source consistently excels. Moreove","authors_text":"Carl Yang, Haoyu Wang, Ran Xu, Wenqi Shi, Yuchen Zhuang, Yue Yu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-26T20:57:24Z","title":"RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20059","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":"sha256:669f48ff6da8d5177f10bb3e33c571285785ca305963d324f10f4a4631ba5431","target":"record","created_at":"2026-07-05T11:44:12Z","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":"44b6f8c93db4c6225b16a1fb3bf8bfdf0e310e8105512fee4f019b651af0665a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-26T20:57:24Z","title_canon_sha256":"1695fb4b8fff0ed5c5f6333ee8fc156a12be287199fe41bbe5df7a8f3a9dca2e"},"schema_version":"1.0","source":{"id":"2507.20059","kind":"arxiv","version":1}},"canonical_sha256":"c70fcdb272e12d460f0921821ff0d4edf2eea2f71672d1b09a1fed94ea893bca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c70fcdb272e12d460f0921821ff0d4edf2eea2f71672d1b09a1fed94ea893bca","first_computed_at":"2026-07-05T11:44:12.668190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:12.668190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bP7pUfAj1htB/A5/KgGM8mvYJmQXCk7Mp6tJ918ytke3qZ/Q/EJQLIRM93StO50LLttWVJw3LuocZH1500pSBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:12.668682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20059","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:669f48ff6da8d5177f10bb3e33c571285785ca305963d324f10f4a4631ba5431","sha256:5900a70bccd2165e91c624c23327ec801b9cb86f9f7d7d486b7a44a597930a6d"],"state_sha256":"00ba9ea79e876ba8a13bcdf9cac2451a4fc2d57cebd25f76f20601f2595cb6f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UEpZBeNOGe6aK6UTNiFafgbeexy4zQaAgrmC1+3GK0XMdLsv3pZMF2mP5ib1sV0SAm5wTNzJHz2B6E2XWoonDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:50:38.402705Z","bundle_sha256":"ca85a8e3d698a7cbdfb292782e2da2cdebe73fbab783d0f5e0da9eae784c5890"}}