{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NMNRHNFRF5J3BSAHVQTPDEIEG2","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":"b1a2d8685417495dc9910a0982c8cfb65acee2827a159a43aae4a29e682c9d71","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T02:35:47Z","title_canon_sha256":"658fa7752fd3945baa8bd0a2a6c945a1f8b60ad3e7a40b5efb1eac8f59c49b4d"},"schema_version":"1.0","source":{"id":"2507.01297","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01297","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01297v2","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01297","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"pith_short_12","alias_value":"NMNRHNFRF5J3","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"NMNRHNFRF5J3BSAH","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"NMNRHNFR","created_at":"2026-07-05T11:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:7dd3734bd4f09c8b3030e0e812f565f91d3a96564d091cbf0d06bc31dabda01a","target":"graph","created_at":"2026-07-05T11:32:33Z","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/2507.01297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented Generation (RAG) has primarily been studied in limited settings, such as factoid question answering; more challenging, reasoning-intensive benchmarks have seen limited success from minimal RAG. In this work, we challenge this prevailing view on established, reasoning-intensive benchmarks: MMLU, MMLU Pro, AGI Eval, GPQA, and MATH. We identify a key missing component in prior work: a usable, web-scale datastore aligned with the breadth of pretraining data. To this end, we introduce CompactDS: a diverse, high-quality, web-scale datastore that achieves high retrieval accuracy a","authors_text":"Michael Duan, Pang Wei Koh, Rulin Shao, Sewon Min, Xinxi Lyu","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T02:35:47Z","title":"Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01297","kind":"arxiv","version":2},"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":"sha256:902350a52bde76293da3277808a8a4bc44c27da70952b3b88e808884a8c1c44d","target":"record","created_at":"2026-07-05T11:32:33Z","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":"b1a2d8685417495dc9910a0982c8cfb65acee2827a159a43aae4a29e682c9d71","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T02:35:47Z","title_canon_sha256":"658fa7752fd3945baa8bd0a2a6c945a1f8b60ad3e7a40b5efb1eac8f59c49b4d"},"schema_version":"1.0","source":{"id":"2507.01297","kind":"arxiv","version":2}},"canonical_sha256":"6b1b13b4b12f53b0c807ac26f1910436ac2d82a9be5ad9f0dc09463df60cccda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b1b13b4b12f53b0c807ac26f1910436ac2d82a9be5ad9f0dc09463df60cccda","first_computed_at":"2026-07-05T11:32:33.234504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:33.234504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tb307YnuaZm6f++PVdcsTg6H6GulZMYEJ52lEc5RlkAGlFIxLzv+pffrW0XdXLxxlzgDFErYeWWMVKGswBczCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:33.234965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01297","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:902350a52bde76293da3277808a8a4bc44c27da70952b3b88e808884a8c1c44d","sha256:7dd3734bd4f09c8b3030e0e812f565f91d3a96564d091cbf0d06bc31dabda01a"],"state_sha256":"8c42b1426ad9236d7aea473063996f03b868fb106a6c054c0dc82cbdd187a69b"}