{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YCQKR7EWCQXKPPQH2Q3TVLR3OR","short_pith_number":"pith:YCQKR7EW","schema_version":"1.0","canonical_sha256":"c0a0a8fc96142ea7be07d4373aae3b744ce932d85e737c86b744c3a081b9538f","source":{"kind":"arxiv","id":"2606.22778","version":1},"attestation_state":"computed","paper":{"title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Yuichi Tateno","submitted_at":"2026-06-22T02:42:06Z","abstract_excerpt":"With the rapid spread of retrieval-augmented generation and semantic search, choosing the right embedding and retrieval configuration is increasingly hard. Large retrieval benchmarks are comprehensive but too heavy to rerun during development, and there is little infrastructure for comparing production settings--dimensionality reduction, quantization, reranking--across many models under identical conditions. We present HAKARI-Bench, a lightweight benchmark that reconstructs existing retrieval suites into small datasets (Nano-sets): 35 benchmarks and 551 tasks across 43 languages in a unified f"},"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":"2606.22778","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-22T02:42:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fcf72f63cdf35cc9c0df3938d773977b3ef1128069e2733f5e5cbda13adec3dc","abstract_canon_sha256":"a1b3a17d0b81b7ef937869d216ac7647388691e5a907b8c870a71631cbaad0b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:54.316149Z","signature_b64":"6Sf550AiFyFfAnhqHcMmRh5TLcCe69wQ7G/lWuQfGE1DZRiMZ42wsh013oVjG5R5p3oW0X38OQaiRL8yPUcrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0a0a8fc96142ea7be07d4373aae3b744ce932d85e737c86b744c3a081b9538f","last_reissued_at":"2026-06-23T02:13:54.315782Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:54.315782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Yuichi Tateno","submitted_at":"2026-06-22T02:42:06Z","abstract_excerpt":"With the rapid spread of retrieval-augmented generation and semantic search, choosing the right embedding and retrieval configuration is increasingly hard. Large retrieval benchmarks are comprehensive but too heavy to rerun during development, and there is little infrastructure for comparing production settings--dimensionality reduction, quantization, reranking--across many models under identical conditions. We present HAKARI-Bench, a lightweight benchmark that reconstructs existing retrieval suites into small datasets (Nano-sets): 35 benchmarks and 551 tasks across 43 languages in a unified f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22778","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/2606.22778/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":"2606.22778","created_at":"2026-06-23T02:13:54.315846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22778v1","created_at":"2026-06-23T02:13:54.315846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22778","created_at":"2026-06-23T02:13:54.315846+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCQKR7EWCQXK","created_at":"2026-06-23T02:13:54.315846+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCQKR7EWCQXKPPQH","created_at":"2026-06-23T02:13:54.315846+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCQKR7EW","created_at":"2026-06-23T02:13:54.315846+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/YCQKR7EWCQXKPPQH2Q3TVLR3OR","json":"https://pith.science/pith/YCQKR7EWCQXKPPQH2Q3TVLR3OR.json","graph_json":"https://pith.science/api/pith-number/YCQKR7EWCQXKPPQH2Q3TVLR3OR/graph.json","events_json":"https://pith.science/api/pith-number/YCQKR7EWCQXKPPQH2Q3TVLR3OR/events.json","paper":"https://pith.science/paper/YCQKR7EW"},"agent_actions":{"view_html":"https://pith.science/pith/YCQKR7EWCQXKPPQH2Q3TVLR3OR","download_json":"https://pith.science/pith/YCQKR7EWCQXKPPQH2Q3TVLR3OR.json","view_paper":"https://pith.science/paper/YCQKR7EW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22778&json=true","fetch_graph":"https://pith.science/api/pith-number/YCQKR7EWCQXKPPQH2Q3TVLR3OR/graph.json","fetch_events":"https://pith.science/api/pith-number/YCQKR7EWCQXKPPQH2Q3TVLR3OR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCQKR7EWCQXKPPQH2Q3TVLR3OR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCQKR7EWCQXKPPQH2Q3TVLR3OR/action/storage_attestation","attest_author":"https://pith.science/pith/YCQKR7EWCQXKPPQH2Q3TVLR3OR/action/author_attestation","sign_citation":"https://pith.science/pith/YCQKR7EWCQXKPPQH2Q3TVLR3OR/action/citation_signature","submit_replication":"https://pith.science/pith/YCQKR7EWCQXKPPQH2Q3TVLR3OR/action/replication_record"}},"created_at":"2026-06-23T02:13:54.315846+00:00","updated_at":"2026-06-23T02:13:54.315846+00:00"}