{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:22U2OFP5G6EWN5WHT2UQOV5WLN","short_pith_number":"pith:22U2OFP5","schema_version":"1.0","canonical_sha256":"d6a9a715fd378966f6c79ea90757b65b43c88620950346723a4d891c6bfd636f","source":{"kind":"arxiv","id":"2402.15132","version":2},"attestation_state":"computed","paper":{"title":"Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Koichi Takeda, Ryohei Sasano, Soma Sato","submitted_at":"2024-02-23T06:33:51Z","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"},"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":"2402.15132","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T06:33:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb8ed6e19a167ebc6b3d9e8ebd9b519098d68d2d745fa9b5b2f51f0b1a1f757b","abstract_canon_sha256":"15dfff12f71c943e91133af1c1cea5bbbba99f643d47aa6a0caa26d171c1e0a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:13.989861Z","signature_b64":"lusOz7plR2G0Kn+tpSAeTmw75DWydGV6cn6wMGMlYGspNl2UGAh+tx7SSaNlqovazbVnSPSNUDtQTT1XE/DDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6a9a715fd378966f6c79ea90757b65b43c88620950346723a4d891c6bfd636f","last_reissued_at":"2026-07-05T08:51:13.989426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:13.989426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Koichi Takeda, Ryohei Sasano, Soma Sato","submitted_at":"2024-02-23T06:33:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15132","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/2402.15132/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":"2402.15132","created_at":"2026-07-05T08:51:13.989483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15132v2","created_at":"2026-07-05T08:51:13.989483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15132","created_at":"2026-07-05T08:51:13.989483+00:00"},{"alias_kind":"pith_short_12","alias_value":"22U2OFP5G6EW","created_at":"2026-07-05T08:51:13.989483+00:00"},{"alias_kind":"pith_short_16","alias_value":"22U2OFP5G6EWN5WH","created_at":"2026-07-05T08:51:13.989483+00:00"},{"alias_kind":"pith_short_8","alias_value":"22U2OFP5","created_at":"2026-07-05T08:51:13.989483+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/22U2OFP5G6EWN5WHT2UQOV5WLN","json":"https://pith.science/pith/22U2OFP5G6EWN5WHT2UQOV5WLN.json","graph_json":"https://pith.science/api/pith-number/22U2OFP5G6EWN5WHT2UQOV5WLN/graph.json","events_json":"https://pith.science/api/pith-number/22U2OFP5G6EWN5WHT2UQOV5WLN/events.json","paper":"https://pith.science/paper/22U2OFP5"},"agent_actions":{"view_html":"https://pith.science/pith/22U2OFP5G6EWN5WHT2UQOV5WLN","download_json":"https://pith.science/pith/22U2OFP5G6EWN5WHT2UQOV5WLN.json","view_paper":"https://pith.science/paper/22U2OFP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15132&json=true","fetch_graph":"https://pith.science/api/pith-number/22U2OFP5G6EWN5WHT2UQOV5WLN/graph.json","fetch_events":"https://pith.science/api/pith-number/22U2OFP5G6EWN5WHT2UQOV5WLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22U2OFP5G6EWN5WHT2UQOV5WLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22U2OFP5G6EWN5WHT2UQOV5WLN/action/storage_attestation","attest_author":"https://pith.science/pith/22U2OFP5G6EWN5WHT2UQOV5WLN/action/author_attestation","sign_citation":"https://pith.science/pith/22U2OFP5G6EWN5WHT2UQOV5WLN/action/citation_signature","submit_replication":"https://pith.science/pith/22U2OFP5G6EWN5WHT2UQOV5WLN/action/replication_record"}},"created_at":"2026-07-05T08:51:13.989483+00:00","updated_at":"2026-07-05T08:51:13.989483+00:00"}