{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JTLOVPWAYZQSGAUDX5JIDUVXAW","short_pith_number":"pith:JTLOVPWA","schema_version":"1.0","canonical_sha256":"4cd6eabec0c661230283bf5281d2b705b64376be83106f8fc7e223f3aca205b1","source":{"kind":"arxiv","id":"2406.01607","version":2},"attestation_state":"computed","paper":{"title":"Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Hongliu Cao","submitted_at":"2024-05-27T09:52:54Z","abstract_excerpt":"Text embedding methods have become increasingly popular in both industrial and academic fields due to their critical role in a variety of natural language processing tasks. The significance of universal text embeddings has been further highlighted with the rise of Large Language Models (LLMs) applications such as Retrieval-Augmented Systems (RAGs). While previous models have attempted to be general-purpose, they often struggle to generalize across tasks and domains. However, recent advancements in training data quantity, quality and diversity; synthetic data generation from LLMs as well as usi"},"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":"2406.01607","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T09:52:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"729ba752e09e4c3a1f8278f63bb7d8344244568e5e53112787284b9184ba780f","abstract_canon_sha256":"155c0fb0b3ed7aff7285ab6f7170d627b9e8a976e644db8f738ff88e44096a93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:20.059004Z","signature_b64":"r22Wz0vsJuOXtB6RSqW2uQnpSJO3hh+VERB7PI4m0UqNOLtAIOUyRApJEMfDLVofmT1d5UBfMTuZSn5/Wj7NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cd6eabec0c661230283bf5281d2b705b64376be83106f8fc7e223f3aca205b1","last_reissued_at":"2026-07-05T08:34:20.058556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:20.058556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Hongliu Cao","submitted_at":"2024-05-27T09:52:54Z","abstract_excerpt":"Text embedding methods have become increasingly popular in both industrial and academic fields due to their critical role in a variety of natural language processing tasks. The significance of universal text embeddings has been further highlighted with the rise of Large Language Models (LLMs) applications such as Retrieval-Augmented Systems (RAGs). While previous models have attempted to be general-purpose, they often struggle to generalize across tasks and domains. However, recent advancements in training data quantity, quality and diversity; synthetic data generation from LLMs as well as usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01607","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/2406.01607/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":"2406.01607","created_at":"2026-07-05T08:34:20.058612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01607v2","created_at":"2026-07-05T08:34:20.058612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01607","created_at":"2026-07-05T08:34:20.058612+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTLOVPWAYZQS","created_at":"2026-07-05T08:34:20.058612+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTLOVPWAYZQSGAUD","created_at":"2026-07-05T08:34:20.058612+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTLOVPWA","created_at":"2026-07-05T08:34:20.058612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26483","citing_title":"Efficient Listwise Reranking with Compressed Document Representations","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW","json":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW.json","graph_json":"https://pith.science/api/pith-number/JTLOVPWAYZQSGAUDX5JIDUVXAW/graph.json","events_json":"https://pith.science/api/pith-number/JTLOVPWAYZQSGAUDX5JIDUVXAW/events.json","paper":"https://pith.science/paper/JTLOVPWA"},"agent_actions":{"view_html":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW","download_json":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW.json","view_paper":"https://pith.science/paper/JTLOVPWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01607&json=true","fetch_graph":"https://pith.science/api/pith-number/JTLOVPWAYZQSGAUDX5JIDUVXAW/graph.json","fetch_events":"https://pith.science/api/pith-number/JTLOVPWAYZQSGAUDX5JIDUVXAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/action/storage_attestation","attest_author":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/action/author_attestation","sign_citation":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/action/citation_signature","submit_replication":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/action/replication_record"}},"created_at":"2026-07-05T08:34:20.058612+00:00","updated_at":"2026-07-05T08:34:20.058612+00:00"}