{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LOS4FBTJSC3N3FV6VKQ7MWCIW5","short_pith_number":"pith:LOS4FBTJ","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"},"canonical_sha256":"5ba5c2866990b6dd96beaaa1f65848b7723e233fd57c4f0333be7d4061e61839","source":{"kind":"arxiv","id":"2509.02558","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02558","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02558v2","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02558","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"LOS4FBTJSC3N","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"LOS4FBTJSC3N3FV6","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"LOS4FBTJ","created_at":"2026-06-02T02:04:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LOS4FBTJSC3N3FV6VKQ7MWCIW5","target":"record","payload":{"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"},"canonical_sha256":"5ba5c2866990b6dd96beaaa1f65848b7723e233fd57c4f0333be7d4061e61839","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"},"source_kind":"arxiv","source_id":"2509.02558","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6jlAe/dWeerfmXqLxVUsxk8yfi4KZAoA4wJELIJiQmm6SpaHMcueMSWMOJdYurzGylk8KPNR4e6EJQ1wGdbLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:56:18.484012Z"},"content_sha256":"6c4883cd957266c9d0fa253a0fe234c0864498b00df7c337314e67577b4f0793","schema_version":"1.0","event_id":"sha256:6c4883cd957266c9d0fa253a0fe234c0864498b00df7c337314e67577b4f0793"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LOS4FBTJSC3N3FV6VKQ7MWCIW5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cHFvCSWJRhNgF+t33prLoJNZ1YFDlSg82iDl/nJmlJDd1in2rEVA+CCk3LFa8kfoJ/RIpTF7kCjmdee+oH2PBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:56:18.484405Z"},"content_sha256":"916054a5e74ea04c359045a62678215ced5ef7e90ec9138a5f1841df437c1a0b","schema_version":"1.0","event_id":"sha256:916054a5e74ea04c359045a62678215ced5ef7e90ec9138a5f1841df437c1a0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/bundle.json","state_url":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/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":"2026-06-03T22:56:18Z","links":{"resolver":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5","bundle":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/bundle.json","state":"https://pith.science/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LOS4FBTJSC3N3FV6VKQ7MWCIW5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LOS4FBTJSC3N3FV6VKQ7MWCIW5","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":"d5b09b85d2f4b8009390d4705918937cd1b8e7ebd1f86badacf3404ef37f60f3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-02T17:53:57Z","title_canon_sha256":"79b2cf884802767f391f981a2299f22fb10751d0faa672844a91a475d8413eb9"},"schema_version":"1.0","source":{"id":"2509.02558","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02558","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02558v2","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02558","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"LOS4FBTJSC3N","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"LOS4FBTJSC3N3FV6","created_at":"2026-06-02T02:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"LOS4FBTJ","created_at":"2026-06-02T02:04:08Z"}],"graph_snapshots":[{"event_id":"sha256:916054a5e74ea04c359045a62678215ced5ef7e90ec9138a5f1841df437c1a0b","target":"graph","created_at":"2026-06-02T02:04:08Z","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/2509.02558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jimmy Lin, Sahel Sharifymoghaddam, Yijun Ge","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-02T17:53:57Z","title":"Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02558","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":"sha256:6c4883cd957266c9d0fa253a0fe234c0864498b00df7c337314e67577b4f0793","target":"record","created_at":"2026-06-02T02:04:08Z","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":"d5b09b85d2f4b8009390d4705918937cd1b8e7ebd1f86badacf3404ef37f60f3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-02T17:53:57Z","title_canon_sha256":"79b2cf884802767f391f981a2299f22fb10751d0faa672844a91a475d8413eb9"},"schema_version":"1.0","source":{"id":"2509.02558","kind":"arxiv","version":2}},"canonical_sha256":"5ba5c2866990b6dd96beaaa1f65848b7723e233fd57c4f0333be7d4061e61839","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ba5c2866990b6dd96beaaa1f65848b7723e233fd57c4f0333be7d4061e61839","first_computed_at":"2026-06-02T02:04:08.549737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:08.549737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UGTkBcgWVwdtkMgOh85t4w5mujXYnMuWpMPgnWbi0cZoE8gHaFM1uCH799+Rz1AmfdebXsZxajGstd7f8z85Cw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:08.550550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02558","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c4883cd957266c9d0fa253a0fe234c0864498b00df7c337314e67577b4f0793","sha256:916054a5e74ea04c359045a62678215ced5ef7e90ec9138a5f1841df437c1a0b"],"state_sha256":"f11964f453b06f578fc32a600b51213f4e306ac75f440591b35eb841e29da50d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VdzYp126FNzSvZclxwOwRJL1CQC70EYgkrj8CAMGPOQjo2fsqO2MTvUZX83WKLIuvrC5dMFUxhRMaT1m45qnCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T22:56:18.486424Z","bundle_sha256":"cd44024d44c70b440fe29eca62572b0af4b8d43ef0485eb5e5e349f2c6d0c578"}}