{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UY25E2XLM5E7IHSJ5M74ODGRUJ","short_pith_number":"pith:UY25E2XL","schema_version":"1.0","canonical_sha256":"a635d26aeb6749f41e49eb3fc70cd1a2471a077a4ff5f7b565129bda6ede7710","source":{"kind":"arxiv","id":"2412.17364","version":1},"attestation_state":"computed","paper":{"title":"Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jeongsu Yu","submitted_at":"2024-12-23T07:55:22Z","abstract_excerpt":"Text embedding models play a crucial role in natural language processing, particularly in information retrieval, and their importance is further highlighted with the recent utilization of RAG (Retrieval- Augmented Generation). This study presents an efficient fine-tuning methodology encompassing data selection, loss function, and model architecture to enhance the information retrieval performance of pre-trained text embedding models. In particular, this study proposes a novel Contrastive Learning Penalty function that overcomes the limitations of existing Contrastive Learning. The proposed met"},"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":"2412.17364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-23T07:55:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b00511b39022ddb4ca9864beef980b1cab3c728236d4a866c263eec9f197631a","abstract_canon_sha256":"0f0749d8c785d316600477a8ddfa9ba7cca45cd4096fefb9813fa930dfafebf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:21.458761Z","signature_b64":"uUSGRmCM8YZAYsx7HkcX4OWqJGxgas1ewlYIdEpxZbLZaAEOl2Fg11D9ax+S55yIrTBPSYK4IHkseuTEtAniAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a635d26aeb6749f41e49eb3fc70cd1a2471a077a4ff5f7b565129bda6ede7710","last_reissued_at":"2026-07-05T09:53:21.458283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:21.458283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jeongsu Yu","submitted_at":"2024-12-23T07:55:22Z","abstract_excerpt":"Text embedding models play a crucial role in natural language processing, particularly in information retrieval, and their importance is further highlighted with the recent utilization of RAG (Retrieval- Augmented Generation). This study presents an efficient fine-tuning methodology encompassing data selection, loss function, and model architecture to enhance the information retrieval performance of pre-trained text embedding models. In particular, this study proposes a novel Contrastive Learning Penalty function that overcomes the limitations of existing Contrastive Learning. The proposed met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17364","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/2412.17364/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":"2412.17364","created_at":"2026-07-05T09:53:21.458353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17364v1","created_at":"2026-07-05T09:53:21.458353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17364","created_at":"2026-07-05T09:53:21.458353+00:00"},{"alias_kind":"pith_short_12","alias_value":"UY25E2XLM5E7","created_at":"2026-07-05T09:53:21.458353+00:00"},{"alias_kind":"pith_short_16","alias_value":"UY25E2XLM5E7IHSJ","created_at":"2026-07-05T09:53:21.458353+00:00"},{"alias_kind":"pith_short_8","alias_value":"UY25E2XL","created_at":"2026-07-05T09:53:21.458353+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/UY25E2XLM5E7IHSJ5M74ODGRUJ","json":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ.json","graph_json":"https://pith.science/api/pith-number/UY25E2XLM5E7IHSJ5M74ODGRUJ/graph.json","events_json":"https://pith.science/api/pith-number/UY25E2XLM5E7IHSJ5M74ODGRUJ/events.json","paper":"https://pith.science/paper/UY25E2XL"},"agent_actions":{"view_html":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ","download_json":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ.json","view_paper":"https://pith.science/paper/UY25E2XL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17364&json=true","fetch_graph":"https://pith.science/api/pith-number/UY25E2XLM5E7IHSJ5M74ODGRUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/UY25E2XLM5E7IHSJ5M74ODGRUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/action/storage_attestation","attest_author":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/action/author_attestation","sign_citation":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/action/citation_signature","submit_replication":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/action/replication_record"}},"created_at":"2026-07-05T09:53:21.458353+00:00","updated_at":"2026-07-05T09:53:21.458353+00:00"}