{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LOS4FBTJSC3N3FV6VKQ7MWCIW5","short_pith_number":"pith:LOS4FBTJ","schema_version":"1.0","canonical_sha256":"5ba5c2866990b6dd96beaaa1f65848b7723e233fd57c4f0333be7d4061e61839","source":{"kind":"arxiv","id":"2509.02558","version":2},"attestation_state":"computed","paper":{"title":"Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jimmy Lin, Sahel Sharifymoghaddam, Yijun Ge","submitted_at":"2025-09-02T17:53:57Z","abstract_excerpt":"Retrieval benchmarks for large language models (LLMs) should reflect the long, reasoning-intensive queries typical of retrieval-augmented generation (RAG). We present a systematic study of BRIGHT, a reasoning-focused retrieval benchmark, along with strong, reproducible reference methods integrated into Anserini, Pyserini, and RankLLM. We evaluate lexical, sparse, dense, and fusion-based retrievers, as well as LLM rerankers, under long-query settings. In reproducing BRIGHT's lexical baseline, we identify a key under-documented detail: query-side BM25 (BM25Q), which applies BM25 weighting to the"},"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":"2509.02558","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-02T17:53:57Z","cross_cats_sorted":[],"title_canon_sha256":"79b2cf884802767f391f981a2299f22fb10751d0faa672844a91a475d8413eb9","abstract_canon_sha256":"d5b09b85d2f4b8009390d4705918937cd1b8e7ebd1f86badacf3404ef37f60f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:08.550550Z","signature_b64":"UGTkBcgWVwdtkMgOh85t4w5mujXYnMuWpMPgnWbi0cZoE8gHaFM1uCH799+Rz1AmfdebXsZxajGstd7f8z85Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ba5c2866990b6dd96beaaa1f65848b7723e233fd57c4f0333be7d4061e61839","last_reissued_at":"2026-06-02T02:04:08.549737Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:08.549737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jimmy Lin, Sahel Sharifymoghaddam, Yijun Ge","submitted_at":"2025-09-02T17:53:57Z","abstract_excerpt":"Retrieval benchmarks for large language models (LLMs) should reflect the long, reasoning-intensive queries typical of retrieval-augmented generation (RAG). We present a systematic study of BRIGHT, a reasoning-focused retrieval benchmark, along with strong, reproducible reference methods integrated into Anserini, Pyserini, and RankLLM. We evaluate lexical, sparse, dense, and fusion-based retrievers, as well as LLM rerankers, under long-query settings. In reproducing BRIGHT's lexical baseline, we identify a key under-documented detail: query-side BM25 (BM25Q), which applies BM25 weighting to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02558","kind":"arxiv","version":2},"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/2509.02558/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":"2509.02558","created_at":"2026-06-02T02:04:08.549848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02558v2","created_at":"2026-06-02T02:04:08.549848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02558","created_at":"2026-06-02T02:04:08.549848+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOS4FBTJSC3N","created_at":"2026-06-02T02:04:08.549848+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOS4FBTJSC3N3FV6","created_at":"2026-06-02T02:04:08.549848+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOS4FBTJ","created_at":"2026-06-02T02:04:08.549848+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/LOS4FBTJSC3N3FV6VKQ7MWCIW5","json":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5.json","graph_json":"https://pith.science/api/pith-number/LOS4FBTJSC3N3FV6VKQ7MWCIW5/graph.json","events_json":"https://pith.science/api/pith-number/LOS4FBTJSC3N3FV6VKQ7MWCIW5/events.json","paper":"https://pith.science/paper/LOS4FBTJ"},"agent_actions":{"view_html":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5","download_json":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5.json","view_paper":"https://pith.science/paper/LOS4FBTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02558&json=true","fetch_graph":"https://pith.science/api/pith-number/LOS4FBTJSC3N3FV6VKQ7MWCIW5/graph.json","fetch_events":"https://pith.science/api/pith-number/LOS4FBTJSC3N3FV6VKQ7MWCIW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/action/storage_attestation","attest_author":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/action/author_attestation","sign_citation":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/action/citation_signature","submit_replication":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/action/replication_record"}},"created_at":"2026-06-02T02:04:08.549848+00:00","updated_at":"2026-06-02T02:04:08.549848+00:00"}