{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4SLLHLCGJ23LVNL3J3LCLPJU7P","short_pith_number":"pith:4SLLHLCG","schema_version":"1.0","canonical_sha256":"e496b3ac464eb6bab57b4ed625bd34fbfab4f8e2f897446d380ea8397ead3cf4","source":{"kind":"arxiv","id":"2310.19349","version":1},"attestation_state":"computed","paper":{"title":"Japanese SimCSE Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Koichi Takeda, Ryohei Sasano","submitted_at":"2023-10-30T08:43:26Z","abstract_excerpt":"We report the development of Japanese SimCSE, Japanese sentence embedding models fine-tuned with SimCSE. Since there is a lack of sentence embedding models for Japanese that can be used as a baseline in sentence embedding research, we conducted extensive experiments on Japanese sentence embeddings involving 24 pre-trained Japanese or multilingual language models, five supervised datasets, and four unsupervised datasets. In this report, we provide the detailed training setup for Japanese SimCSE and their evaluation results."},"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":"2310.19349","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T08:43:26Z","cross_cats_sorted":[],"title_canon_sha256":"a56d66e6a7c3e9fc33bb8a843d6d9b38b78dd880515bffed5ef40eabcccc656a","abstract_canon_sha256":"b0830cca298b4a78e040a6630adbe78742b8e7840cc1f828c9e44d6c6ad1f51b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:49.824781Z","signature_b64":"tdujm1utfX8FYv/+mY3d0ARv443yOenTdCDsYgvveXXU7YHQaVwjgSxtW55wd16/BJFKeHpkpP9f7Dn6wHfWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e496b3ac464eb6bab57b4ed625bd34fbfab4f8e2f897446d380ea8397ead3cf4","last_reissued_at":"2026-07-05T07:06:49.824275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:49.824275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Japanese SimCSE Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Koichi Takeda, Ryohei Sasano","submitted_at":"2023-10-30T08:43:26Z","abstract_excerpt":"We report the development of Japanese SimCSE, Japanese sentence embedding models fine-tuned with SimCSE. Since there is a lack of sentence embedding models for Japanese that can be used as a baseline in sentence embedding research, we conducted extensive experiments on Japanese sentence embeddings involving 24 pre-trained Japanese or multilingual language models, five supervised datasets, and four unsupervised datasets. In this report, we provide the detailed training setup for Japanese SimCSE and their evaluation results."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19349","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/2310.19349/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":"2310.19349","created_at":"2026-07-05T07:06:49.824340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19349v1","created_at":"2026-07-05T07:06:49.824340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19349","created_at":"2026-07-05T07:06:49.824340+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SLLHLCGJ23L","created_at":"2026-07-05T07:06:49.824340+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SLLHLCGJ23LVNL3","created_at":"2026-07-05T07:06:49.824340+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SLLHLCG","created_at":"2026-07-05T07:06:49.824340+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/4SLLHLCGJ23LVNL3J3LCLPJU7P","json":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P.json","graph_json":"https://pith.science/api/pith-number/4SLLHLCGJ23LVNL3J3LCLPJU7P/graph.json","events_json":"https://pith.science/api/pith-number/4SLLHLCGJ23LVNL3J3LCLPJU7P/events.json","paper":"https://pith.science/paper/4SLLHLCG"},"agent_actions":{"view_html":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P","download_json":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P.json","view_paper":"https://pith.science/paper/4SLLHLCG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19349&json=true","fetch_graph":"https://pith.science/api/pith-number/4SLLHLCGJ23LVNL3J3LCLPJU7P/graph.json","fetch_events":"https://pith.science/api/pith-number/4SLLHLCGJ23LVNL3J3LCLPJU7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/action/storage_attestation","attest_author":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/action/author_attestation","sign_citation":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/action/citation_signature","submit_replication":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/action/replication_record"}},"created_at":"2026-07-05T07:06:49.824340+00:00","updated_at":"2026-07-05T07:06:49.824340+00:00"}