{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HDGIX6VV72TWA6CSIHNKUTCX7C","short_pith_number":"pith:HDGIX6VV","schema_version":"1.0","canonical_sha256":"38cc8bfab5fea760785241daaa4c57f88e855896a0d8f57bc99d13177083e936","source":{"kind":"arxiv","id":"2608.02112","version":1},"attestation_state":"computed","paper":{"title":"Do Static Embeddings Add Value to Hybrid Dutch Retrieval?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Ant\\'onio Pereira Barata","submitted_at":"2026-08-03T12:10:51Z","abstract_excerpt":"Embedding benchmarks measure standalone model quality, but they do not establish whether a low-cost retriever contributes complementary ranking information once lexical and transformer-based retrieval are already combined. We present a controlled evaluation of this question across Dutch retrieval tasks from the Massive Text Embedding Benchmark for Dutch (MTEB-NL). Weighted reciprocal rank fusion (RRF) combines Best Matching 25 (BM25), Qwen/Qwen3-Embedding-0.6B (Qwen), and two multilingual static embedding models. Five datasets comprising 14,500 queries and 786,573 documents are scored exhausti"},"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":"2608.02112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T12:10:51Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c2ea95a9db396ea3108d75f63428343bfb8f637373907e57c66507a2a429e89d","abstract_canon_sha256":"b637cc56af3d685ffbbe05a715eb3ee40c5ca150c5a829ccc111d0c8e5c60db2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:10:55.144729Z","signature_b64":"QP/ODbPuAeLzZykangKEHmjOOOA1PwvJPkK0NpP+Oa0LQxtbI7OaJAfkgslejLTZGpJUDRaXsPMJCHDwUOn3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38cc8bfab5fea760785241daaa4c57f88e855896a0d8f57bc99d13177083e936","last_reissued_at":"2026-08-04T02:10:55.142812Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:10:55.142812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Static Embeddings Add Value to Hybrid Dutch Retrieval?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Ant\\'onio Pereira Barata","submitted_at":"2026-08-03T12:10:51Z","abstract_excerpt":"Embedding benchmarks measure standalone model quality, but they do not establish whether a low-cost retriever contributes complementary ranking information once lexical and transformer-based retrieval are already combined. We present a controlled evaluation of this question across Dutch retrieval tasks from the Massive Text Embedding Benchmark for Dutch (MTEB-NL). Weighted reciprocal rank fusion (RRF) combines Best Matching 25 (BM25), Qwen/Qwen3-Embedding-0.6B (Qwen), and two multilingual static embedding models. Five datasets comprising 14,500 queries and 786,573 documents are scored exhausti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02112","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/2608.02112/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":"2608.02112","created_at":"2026-08-04T02:10:55.144691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02112v1","created_at":"2026-08-04T02:10:55.144691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02112","created_at":"2026-08-04T02:10:55.144691+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDGIX6VV72TW","created_at":"2026-08-04T02:10:55.144691+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDGIX6VV72TWA6CS","created_at":"2026-08-04T02:10:55.144691+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDGIX6VV","created_at":"2026-08-04T02:10:55.144691+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/HDGIX6VV72TWA6CSIHNKUTCX7C","json":"https://pith.science/pith/HDGIX6VV72TWA6CSIHNKUTCX7C.json","graph_json":"https://pith.science/api/pith-number/HDGIX6VV72TWA6CSIHNKUTCX7C/graph.json","events_json":"https://pith.science/api/pith-number/HDGIX6VV72TWA6CSIHNKUTCX7C/events.json","paper":"https://pith.science/paper/HDGIX6VV"},"agent_actions":{"view_html":"https://pith.science/pith/HDGIX6VV72TWA6CSIHNKUTCX7C","download_json":"https://pith.science/pith/HDGIX6VV72TWA6CSIHNKUTCX7C.json","view_paper":"https://pith.science/paper/HDGIX6VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02112&json=true","fetch_graph":"https://pith.science/api/pith-number/HDGIX6VV72TWA6CSIHNKUTCX7C/graph.json","fetch_events":"https://pith.science/api/pith-number/HDGIX6VV72TWA6CSIHNKUTCX7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDGIX6VV72TWA6CSIHNKUTCX7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDGIX6VV72TWA6CSIHNKUTCX7C/action/storage_attestation","attest_author":"https://pith.science/pith/HDGIX6VV72TWA6CSIHNKUTCX7C/action/author_attestation","sign_citation":"https://pith.science/pith/HDGIX6VV72TWA6CSIHNKUTCX7C/action/citation_signature","submit_replication":"https://pith.science/pith/HDGIX6VV72TWA6CSIHNKUTCX7C/action/replication_record"}},"created_at":"2026-08-04T02:10:55.144691+00:00","updated_at":"2026-08-04T02:10:55.144691+00:00"}