{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4SLLHLCGJ23LVNL3J3LCLPJU7P","short_pith_number":"pith:4SLLHLCG","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"},"canonical_sha256":"e496b3ac464eb6bab57b4ed625bd34fbfab4f8e2f897446d380ea8397ead3cf4","source":{"kind":"arxiv","id":"2310.19349","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19349","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19349v1","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19349","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"4SLLHLCGJ23L","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"4SLLHLCGJ23LVNL3","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"4SLLHLCG","created_at":"2026-07-05T07:06:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4SLLHLCGJ23LVNL3J3LCLPJU7P","target":"record","payload":{"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"},"canonical_sha256":"e496b3ac464eb6bab57b4ed625bd34fbfab4f8e2f897446d380ea8397ead3cf4","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"},"source_kind":"arxiv","source_id":"2310.19349","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:06:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hV/PhfePzk9s904S3yP2DxQCidba0rUfJTPSpgTY7g1JdctYrF2FEtkhC5jp0iCGLwn04II2JvfqyJ+86p2sCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T06:42:25.134060Z"},"content_sha256":"da013add546df4e2abc273275f62eca90841920e8d76d93f992dba887d963ba1","schema_version":"1.0","event_id":"sha256:da013add546df4e2abc273275f62eca90841920e8d76d93f992dba887d963ba1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4SLLHLCGJ23LVNL3J3LCLPJU7P","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:06:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WC6sj+blUgnCvJwq89/yiv2WFo+Te4/q9n8MNM1WRq325egm6y2i8jgxc1k4FViZ9yttJ3g+3208dITMdhxxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T06:42:25.134451Z"},"content_sha256":"53340ba0a4d0c988c7e295069c90d8d2d2f32de9ef2279537101c53effdad28d","schema_version":"1.0","event_id":"sha256:53340ba0a4d0c988c7e295069c90d8d2d2f32de9ef2279537101c53effdad28d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/bundle.json","state_url":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/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":"2026-07-19T06:42:25Z","links":{"resolver":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P","bundle":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/bundle.json","state":"https://pith.science/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4SLLHLCGJ23LVNL3J3LCLPJU7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4SLLHLCGJ23LVNL3J3LCLPJU7P","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":"b0830cca298b4a78e040a6630adbe78742b8e7840cc1f828c9e44d6c6ad1f51b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T08:43:26Z","title_canon_sha256":"a56d66e6a7c3e9fc33bb8a843d6d9b38b78dd880515bffed5ef40eabcccc656a"},"schema_version":"1.0","source":{"id":"2310.19349","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19349","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19349v1","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19349","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"4SLLHLCGJ23L","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"4SLLHLCGJ23LVNL3","created_at":"2026-07-05T07:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"4SLLHLCG","created_at":"2026-07-05T07:06:49Z"}],"graph_snapshots":[{"event_id":"sha256:53340ba0a4d0c988c7e295069c90d8d2d2f32de9ef2279537101c53effdad28d","target":"graph","created_at":"2026-07-05T07:06:49Z","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/2310.19349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Hayato Tsukagoshi, Koichi Takeda, Ryohei Sasano","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T08:43:26Z","title":"Japanese SimCSE Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19349","kind":"arxiv","version":1},"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:da013add546df4e2abc273275f62eca90841920e8d76d93f992dba887d963ba1","target":"record","created_at":"2026-07-05T07:06:49Z","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":"b0830cca298b4a78e040a6630adbe78742b8e7840cc1f828c9e44d6c6ad1f51b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T08:43:26Z","title_canon_sha256":"a56d66e6a7c3e9fc33bb8a843d6d9b38b78dd880515bffed5ef40eabcccc656a"},"schema_version":"1.0","source":{"id":"2310.19349","kind":"arxiv","version":1}},"canonical_sha256":"e496b3ac464eb6bab57b4ed625bd34fbfab4f8e2f897446d380ea8397ead3cf4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e496b3ac464eb6bab57b4ed625bd34fbfab4f8e2f897446d380ea8397ead3cf4","first_computed_at":"2026-07-05T07:06:49.824275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:49.824275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tdujm1utfX8FYv/+mY3d0ARv443yOenTdCDsYgvveXXU7YHQaVwjgSxtW55wd16/BJFKeHpkpP9f7Dn6wHfWDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:49.824781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19349","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da013add546df4e2abc273275f62eca90841920e8d76d93f992dba887d963ba1","sha256:53340ba0a4d0c988c7e295069c90d8d2d2f32de9ef2279537101c53effdad28d"],"state_sha256":"4f0e6e9788e0be38afaefed64319837f6539cd5fde9a18c0dc32ef427786c7b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r2YbXpu0ro7eds5rzlUEUdx79QSGX8aabMIsQSo3Pj1TMaiph5SMpV1OuErRYTet/P7AcF3hW7au1qgS9smrAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T06:42:25.136720Z","bundle_sha256":"cbc9bfa0529d1cf6c958f89a05df9500a32fe4f29f59939338696b03572cc242"}}