{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OFLWBQIJK6CR44E5KACTURL34G","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":"3933d84e3ebf6fa4b780076677e59e82059375c141bd00e779df461ba7c1769e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-22T17:50:31Z","title_canon_sha256":"4f00e2e655e6ac25e7dc764f17d9c7fec2f5e612b4cc2b7fcabf7fd2b1fcf87b"},"schema_version":"1.0","source":{"id":"2407.15831","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15831","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15831v2","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15831","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"OFLWBQIJK6CR","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"pith_short_16","alias_value":"OFLWBQIJK6CR44E5","created_at":"2026-07-05T10:10:42Z"},{"alias_kind":"pith_short_8","alias_value":"OFLWBQIJ","created_at":"2026-07-05T10:10:42Z"}],"graph_snapshots":[{"event_id":"sha256:b40baaaa3e2b68e270967bf8bdb485edbb4b2dd629f10c3ebd0633cfbf53a521","target":"graph","created_at":"2026-07-05T10:10:42Z","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/2407.15831/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text embedding models have been popular for information retrieval applications such as semantic search and Question-Answering systems based on Retrieval-Augmented Generation (RAG). Those models are typically Transformer models that are fine-tuned with contrastive learning objectives. One of the challenging aspects of fine-tuning embedding models is the selection of high quality hard-negative passages for contrastive learning. In this paper we introduce a family of positive-aware mining methods that use the positive relevance score as an anchor for effective false negative removal, leading to f","authors_text":"Benedikt Schifferer, Even Oldridge, Gabriel de Souza P. Moreira, Mengyao Xu, Radek Osmulski, Ronay Ak","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-22T17:50:31Z","title":"NV-Retriever: Improving text embedding models with effective hard-negative mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15831","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":"sha256:4fba80c672901f60cb476de7038e836b9a797d152e2ce384970bc6ae595369e0","target":"record","created_at":"2026-07-05T10:10:42Z","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":"3933d84e3ebf6fa4b780076677e59e82059375c141bd00e779df461ba7c1769e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2024-07-22T17:50:31Z","title_canon_sha256":"4f00e2e655e6ac25e7dc764f17d9c7fec2f5e612b4cc2b7fcabf7fd2b1fcf87b"},"schema_version":"1.0","source":{"id":"2407.15831","kind":"arxiv","version":2}},"canonical_sha256":"715760c10957851e709d50053a457be1a84896a106f2a7819127f934eeb44505","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"715760c10957851e709d50053a457be1a84896a106f2a7819127f934eeb44505","first_computed_at":"2026-07-05T10:10:42.084850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:42.084850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C9LrZmZqGPoo7FGRe+WxHhFDUC6eJofUUxTP+yMsjYssFQF5FXhop5W83lx0dUcxMsUnuFsty+v6XOwUlCxDDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:42.085363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15831","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fba80c672901f60cb476de7038e836b9a797d152e2ce384970bc6ae595369e0","sha256:b40baaaa3e2b68e270967bf8bdb485edbb4b2dd629f10c3ebd0633cfbf53a521"],"state_sha256":"b69fadd44aafbca0a869a61ff322841ff7e62ee43fa7c4ae3fd70c3886107457"}