{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7MQHA7X3HPVJJIUAZ2F7KTXNER","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":"0897d5de2d6f90003bcfd9e5abfa812b00ba9506b5b71f89b1738b313ee32fa6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T11:18:32Z","title_canon_sha256":"f7ce2e7fb7356d5f17c5bab44af3242a90b7dbf8b3bd54e4612bf0ac75387fcf"},"schema_version":"1.0","source":{"id":"2412.03223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03223","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03223v1","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03223","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"pith_short_12","alias_value":"7MQHA7X3HPVJ","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"pith_short_16","alias_value":"7MQHA7X3HPVJJIUA","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"pith_short_8","alias_value":"7MQHA7X3","created_at":"2026-07-05T09:44:26Z"}],"graph_snapshots":[{"event_id":"sha256:9c7e5f6c209d1b8684da67eaf1afd499fb934b426081661e8e75650a266f797b","target":"graph","created_at":"2026-07-05T09:44:26Z","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/2412.03223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This report explores the enhancement of text retrieval performance using advanced data refinement techniques. We develop Linq-Embed-Mistral\\footnote{\\url{https://huggingface.co/Linq-AI-Research/Linq-Embed-Mistral}} by building on the E5-mistral and Mistral-7B-v0.1 models, focusing on sophisticated data crafting, data filtering, and negative mining methods, which are highly tailored to each task, applied to both existing benchmark dataset and highly tailored synthetic dataset generated via large language models (LLMs). Linq-Embed-Mistral excels in the MTEB benchmarks (as of May 29, 2024), achie","authors_text":"Chanyeol Choi, Jihoon Kwon, Junseong Kim, Jy-yong Sohn, MinKyung Cho, Sangmo Gu, Seolhwa Lee, Yejin Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T11:18:32Z","title":"Linq-Embed-Mistral Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03223","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":"sha256:31334c48ebe4741140698355635c096a740172dbee3feab431386ca49bde6199","target":"record","created_at":"2026-07-05T09:44:26Z","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":"0897d5de2d6f90003bcfd9e5abfa812b00ba9506b5b71f89b1738b313ee32fa6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T11:18:32Z","title_canon_sha256":"f7ce2e7fb7356d5f17c5bab44af3242a90b7dbf8b3bd54e4612bf0ac75387fcf"},"schema_version":"1.0","source":{"id":"2412.03223","kind":"arxiv","version":1}},"canonical_sha256":"fb20707efb3bea94a280ce8bf54eed2451cb895a9615e245fc5db03694ffd564","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb20707efb3bea94a280ce8bf54eed2451cb895a9615e245fc5db03694ffd564","first_computed_at":"2026-07-05T09:44:26.692094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:26.692094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e5YmXyt71iOiTgPLgVedA7pyCtb0YvNxTgwpK6cddtDGVpB4TDSSPd/NNJCEwywe/8zGRlbK0mxVm8o1M1sxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:26.692562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31334c48ebe4741140698355635c096a740172dbee3feab431386ca49bde6199","sha256:9c7e5f6c209d1b8684da67eaf1afd499fb934b426081661e8e75650a266f797b"],"state_sha256":"bae12083701da6a2f87e2342feefa8fd441831a4b42cdfdd1e063de5450017a9"}