{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QEANPHB5EGF2SNKNF2UMEL6VDD","short_pith_number":"pith:QEANPHB5","schema_version":"1.0","canonical_sha256":"8100d79c3d218ba9354d2ea8c22fd518c3e7b7c43bb929f7c2fe8fa63017579a","source":{"kind":"arxiv","id":"2312.16144","version":2},"attestation_state":"computed","paper":{"title":"Towards Better Monolingual Japanese Retrievers with Multi-Vector Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin Clavi\\'e","submitted_at":"2023-12-26T18:07:05Z","abstract_excerpt":"As language-specific training data tends to be sparsely available compared to English, document retrieval in many languages has been largely relying on multilingual models. In Japanese, the best performing deep-learning based retrieval approaches rely on multilingual dense embedders, with Japanese-only models lagging far behind. However, multilingual models require considerably more compute and data to train and have higher computational and memory requirements while often missing out on culturally-relevant information. In this paper, we introduce JaColBERT, a family of multi-vector retrievers"},"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":"2312.16144","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-26T18:07:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da62f0319253764c98783a5613e568c93bd26cc0c263a1220c02f4092ef0d364","abstract_canon_sha256":"b6cb41a1325b4ec8918dc0d181e5dd242d1341c54cf49ee83cd0bbcd028dd5d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:55.141906Z","signature_b64":"qCGEH4esWNB0WuW3Mv7qOc6N0MMi54SW1vCqN6MDb31x7Q8UOs81HyyBkOdAxUkd4SZK0kXd/w2+10hLQjW8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8100d79c3d218ba9354d2ea8c22fd518c3e7b7c43bb929f7c2fe8fa63017579a","last_reissued_at":"2026-07-05T09:09:55.141425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:55.141425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Better Monolingual Japanese Retrievers with Multi-Vector Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin Clavi\\'e","submitted_at":"2023-12-26T18:07:05Z","abstract_excerpt":"As language-specific training data tends to be sparsely available compared to English, document retrieval in many languages has been largely relying on multilingual models. In Japanese, the best performing deep-learning based retrieval approaches rely on multilingual dense embedders, with Japanese-only models lagging far behind. However, multilingual models require considerably more compute and data to train and have higher computational and memory requirements while often missing out on culturally-relevant information. In this paper, we introduce JaColBERT, a family of multi-vector retrievers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16144","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/2312.16144/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":"2312.16144","created_at":"2026-07-05T09:09:55.141479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16144v2","created_at":"2026-07-05T09:09:55.141479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16144","created_at":"2026-07-05T09:09:55.141479+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEANPHB5EGF2","created_at":"2026-07-05T09:09:55.141479+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEANPHB5EGF2SNKN","created_at":"2026-07-05T09:09:55.141479+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEANPHB5","created_at":"2026-07-05T09:09:55.141479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28190","citing_title":"The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QEANPHB5EGF2SNKNF2UMEL6VDD","json":"https://pith.science/pith/QEANPHB5EGF2SNKNF2UMEL6VDD.json","graph_json":"https://pith.science/api/pith-number/QEANPHB5EGF2SNKNF2UMEL6VDD/graph.json","events_json":"https://pith.science/api/pith-number/QEANPHB5EGF2SNKNF2UMEL6VDD/events.json","paper":"https://pith.science/paper/QEANPHB5"},"agent_actions":{"view_html":"https://pith.science/pith/QEANPHB5EGF2SNKNF2UMEL6VDD","download_json":"https://pith.science/pith/QEANPHB5EGF2SNKNF2UMEL6VDD.json","view_paper":"https://pith.science/paper/QEANPHB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16144&json=true","fetch_graph":"https://pith.science/api/pith-number/QEANPHB5EGF2SNKNF2UMEL6VDD/graph.json","fetch_events":"https://pith.science/api/pith-number/QEANPHB5EGF2SNKNF2UMEL6VDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEANPHB5EGF2SNKNF2UMEL6VDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEANPHB5EGF2SNKNF2UMEL6VDD/action/storage_attestation","attest_author":"https://pith.science/pith/QEANPHB5EGF2SNKNF2UMEL6VDD/action/author_attestation","sign_citation":"https://pith.science/pith/QEANPHB5EGF2SNKNF2UMEL6VDD/action/citation_signature","submit_replication":"https://pith.science/pith/QEANPHB5EGF2SNKNF2UMEL6VDD/action/replication_record"}},"created_at":"2026-07-05T09:09:55.141479+00:00","updated_at":"2026-07-05T09:09:55.141479+00:00"}