{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:22U2OFP5G6EWN5WHT2UQOV5WLN","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":"15dfff12f71c943e91133af1c1cea5bbbba99f643d47aa6a0caa26d171c1e0a9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T06:33:51Z","title_canon_sha256":"cb8ed6e19a167ebc6b3d9e8ebd9b519098d68d2d745fa9b5b2f51f0b1a1f757b"},"schema_version":"1.0","source":{"id":"2402.15132","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15132","created_at":"2026-07-05T08:51:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15132v2","created_at":"2026-07-05T08:51:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15132","created_at":"2026-07-05T08:51:13Z"},{"alias_kind":"pith_short_12","alias_value":"22U2OFP5G6EW","created_at":"2026-07-05T08:51:13Z"},{"alias_kind":"pith_short_16","alias_value":"22U2OFP5G6EWN5WH","created_at":"2026-07-05T08:51:13Z"},{"alias_kind":"pith_short_8","alias_value":"22U2OFP5","created_at":"2026-07-05T08:51:13Z"}],"graph_snapshots":[{"event_id":"sha256:94d68e8b8a7399f351285e6c04cdd359bb1947d2e0e3185788827a42ad2e2a33","target":"graph","created_at":"2026-07-05T08:51:13Z","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/2402.15132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decoder-based large language models (LLMs) have shown high performance on many tasks in natural language processing. This is also true for sentence embedding learning, where a decoder-based model, PromptEOL, has achieved the best performance on semantic textual similarity (STS) tasks. However, PromptEOL requires a manually annotated natural language inference (NLI) dataset for fine-tuning. We aim to improve sentence embeddings without using large manually annotated datasets by automatically generating an NLI dataset with an LLM and using it for fine-tuning of PromptEOL. To achieve this, we exp","authors_text":"Hayato Tsukagoshi, Koichi Takeda, Ryohei Sasano, Soma Sato","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T06:33:51Z","title":"Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15132","kind":"arxiv","version":2},"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":"sha256:2e3cb811a3250234586a3d532eacdfbe419cdcf4dae2dc31e8869422f9126b71","target":"record","created_at":"2026-07-05T08:51:13Z","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":"15dfff12f71c943e91133af1c1cea5bbbba99f643d47aa6a0caa26d171c1e0a9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T06:33:51Z","title_canon_sha256":"cb8ed6e19a167ebc6b3d9e8ebd9b519098d68d2d745fa9b5b2f51f0b1a1f757b"},"schema_version":"1.0","source":{"id":"2402.15132","kind":"arxiv","version":2}},"canonical_sha256":"d6a9a715fd378966f6c79ea90757b65b43c88620950346723a4d891c6bfd636f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6a9a715fd378966f6c79ea90757b65b43c88620950346723a4d891c6bfd636f","first_computed_at":"2026-07-05T08:51:13.989426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:13.989426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lusOz7plR2G0Kn+tpSAeTmw75DWydGV6cn6wMGMlYGspNl2UGAh+tx7SSaNlqovazbVnSPSNUDtQTT1XE/DDAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:13.989861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15132","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e3cb811a3250234586a3d532eacdfbe419cdcf4dae2dc31e8869422f9126b71","sha256:94d68e8b8a7399f351285e6c04cdd359bb1947d2e0e3185788827a42ad2e2a33"],"state_sha256":"50e8d59b1426d5273ba50165e365300f98294910fad615834f1c064ba7e6ce90"}