{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UY25E2XLM5E7IHSJ5M74ODGRUJ","short_pith_number":"pith:UY25E2XL","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"},"canonical_sha256":"a635d26aeb6749f41e49eb3fc70cd1a2471a077a4ff5f7b565129bda6ede7710","source":{"kind":"arxiv","id":"2412.17364","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17364","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17364v1","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17364","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_12","alias_value":"UY25E2XLM5E7","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_16","alias_value":"UY25E2XLM5E7IHSJ","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_8","alias_value":"UY25E2XL","created_at":"2026-07-05T09:53:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UY25E2XLM5E7IHSJ5M74ODGRUJ","target":"record","payload":{"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"},"canonical_sha256":"a635d26aeb6749f41e49eb3fc70cd1a2471a077a4ff5f7b565129bda6ede7710","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"},"source_kind":"arxiv","source_id":"2412.17364","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":"2026-07-05T09:53:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"La4PbgjB38/5DFNmzH2yl9rInHe8bG3MZCq2mG0CTFrYrLuO8aU39eZ2tbspy0QlySJkVZmE486n8Dp5/3kNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:16:10.006245Z"},"content_sha256":"7310242a7f14644cd093e40e8acd614e470c0d76135a8af0b0ba40786d117f22","schema_version":"1.0","event_id":"sha256:7310242a7f14644cd093e40e8acd614e470c0d76135a8af0b0ba40786d117f22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UY25E2XLM5E7IHSJ5M74ODGRUJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:53:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NWpb2fAjRVxgtcsTU8s/8vZbB35Ycw+fOTtrjA2UovglHA27RQ4a10neYcBoMH+5DsPyiiHXCIMtwgliD0jKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:16:10.007782Z"},"content_sha256":"514a1815c79038c6d2069e4339ce14dad49734f75e961539610f1ded2ceb8a70","schema_version":"1.0","event_id":"sha256:514a1815c79038c6d2069e4339ce14dad49734f75e961539610f1ded2ceb8a70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/bundle.json","state_url":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/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":"2026-08-19T20:16:10Z","links":{"resolver":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ","bundle":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/bundle.json","state":"https://pith.science/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UY25E2XLM5E7IHSJ5M74ODGRUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UY25E2XLM5E7IHSJ5M74ODGRUJ","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":"0f0749d8c785d316600477a8ddfa9ba7cca45cd4096fefb9813fa930dfafebf1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-23T07:55:22Z","title_canon_sha256":"b00511b39022ddb4ca9864beef980b1cab3c728236d4a866c263eec9f197631a"},"schema_version":"1.0","source":{"id":"2412.17364","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17364","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17364v1","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17364","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_12","alias_value":"UY25E2XLM5E7","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_16","alias_value":"UY25E2XLM5E7IHSJ","created_at":"2026-07-05T09:53:21Z"},{"alias_kind":"pith_short_8","alias_value":"UY25E2XL","created_at":"2026-07-05T09:53:21Z"}],"graph_snapshots":[{"event_id":"sha256:514a1815c79038c6d2069e4339ce14dad49734f75e961539610f1ded2ceb8a70","target":"graph","created_at":"2026-07-05T09:53:21Z","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/2412.17364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jeongsu Yu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-23T07:55:22Z","title":"Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17364","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":"sha256:7310242a7f14644cd093e40e8acd614e470c0d76135a8af0b0ba40786d117f22","target":"record","created_at":"2026-07-05T09:53:21Z","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":"0f0749d8c785d316600477a8ddfa9ba7cca45cd4096fefb9813fa930dfafebf1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-12-23T07:55:22Z","title_canon_sha256":"b00511b39022ddb4ca9864beef980b1cab3c728236d4a866c263eec9f197631a"},"schema_version":"1.0","source":{"id":"2412.17364","kind":"arxiv","version":1}},"canonical_sha256":"a635d26aeb6749f41e49eb3fc70cd1a2471a077a4ff5f7b565129bda6ede7710","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a635d26aeb6749f41e49eb3fc70cd1a2471a077a4ff5f7b565129bda6ede7710","first_computed_at":"2026-07-05T09:53:21.458283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:21.458283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uUSGRmCM8YZAYsx7HkcX4OWqJGxgas1ewlYIdEpxZbLZaAEOl2Fg11D9ax+S55yIrTBPSYK4IHkseuTEtAniAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:21.458761Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17364","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7310242a7f14644cd093e40e8acd614e470c0d76135a8af0b0ba40786d117f22","sha256:514a1815c79038c6d2069e4339ce14dad49734f75e961539610f1ded2ceb8a70"],"state_sha256":"de1b24d7b949efeb1ae62b8ae931c300fe026ef3e5347879b7f163bc636bfbbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3sufz0ALsLrUY1hfdmaZUvNyyeKz0Q2cSlFYesyR9g2p9uPxF/FAOeA88xKreCZPFkAq5ghNzPJyGU5Ci2qBBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:16:10.013067Z","bundle_sha256":"45d5d092a6c6d0d012bf4b171aba9f8901940eb3383a14c2ffa211f6e80d7532"}}