{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6LKHVFJ7SYNNEBBEMWM5SHBXOJ","short_pith_number":"pith:6LKHVFJ7","schema_version":"1.0","canonical_sha256":"f2d47a953f961ad204246599d91c37727f0204b0a4e7dd0dd5648c5bfbec1c75","source":{"kind":"arxiv","id":"2405.05374","version":1},"attestation_state":"computed","paper":{"title":"Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Daniel Campos, Danmei Xu, Gaurav Nuti, Luke Merrick","submitted_at":"2024-05-08T19:05:18Z","abstract_excerpt":"This report describes the training dataset creation and recipe behind the family of \\texttt{arctic-embed} text embedding models (a set of five models ranging from 22 to 334 million parameters with weights open-sourced under an Apache-2 license). At the time of their release, each model achieved state-of-the-art retrieval accuracy for models of their size on the MTEB Retrieval leaderboard, with the largest model, arctic-embed-l outperforming closed source embedding models such as Cohere's embed-v3 and Open AI's text-embed-3-large. In addition to the details of our training recipe, we have provi"},"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":"2405.05374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T19:05:18Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"1aa8382fc392496f2ba924a6e0e92b4f7486daedb09559d816c51b300017d9de","abstract_canon_sha256":"cb29da0ccd56d19e2147c8c891ff023ffb9bfa500a8a84f5b88a2d601145e27d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:17.625388Z","signature_b64":"OEhiil22qtWIdrUvTh1k6eSyQhbozys4njdidTpdEUAPjwERWsOskQst7czx3AS4alY9vAtUEbK1k2aoGhjACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2d47a953f961ad204246599d91c37727f0204b0a4e7dd0dd5648c5bfbec1c75","last_reissued_at":"2026-07-05T08:17:17.624963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:17.624963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Daniel Campos, Danmei Xu, Gaurav Nuti, Luke Merrick","submitted_at":"2024-05-08T19:05:18Z","abstract_excerpt":"This report describes the training dataset creation and recipe behind the family of \\texttt{arctic-embed} text embedding models (a set of five models ranging from 22 to 334 million parameters with weights open-sourced under an Apache-2 license). At the time of their release, each model achieved state-of-the-art retrieval accuracy for models of their size on the MTEB Retrieval leaderboard, with the largest model, arctic-embed-l outperforming closed source embedding models such as Cohere's embed-v3 and Open AI's text-embed-3-large. In addition to the details of our training recipe, we have provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05374","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/2405.05374/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":"2405.05374","created_at":"2026-07-05T08:17:17.625017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.05374v1","created_at":"2026-07-05T08:17:17.625017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05374","created_at":"2026-07-05T08:17:17.625017+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LKHVFJ7SYNN","created_at":"2026-07-05T08:17:17.625017+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LKHVFJ7SYNNEBBE","created_at":"2026-07-05T08:17:17.625017+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LKHVFJ7","created_at":"2026-07-05T08:17:17.625017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12332","citing_title":"Measuring Semantic Progress in Multi-turn Dialogue via Information Gain","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31142","citing_title":"On the Robustness of Multilingual Text Embedding Rankings Across Learning Tasks, Languages, and Benchmark Datasets","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25030","citing_title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12539","citing_title":"LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12714","citing_title":"Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2406.17557","citing_title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05726","citing_title":"SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ","json":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ.json","graph_json":"https://pith.science/api/pith-number/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/graph.json","events_json":"https://pith.science/api/pith-number/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/events.json","paper":"https://pith.science/paper/6LKHVFJ7"},"agent_actions":{"view_html":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ","download_json":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ.json","view_paper":"https://pith.science/paper/6LKHVFJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.05374&json=true","fetch_graph":"https://pith.science/api/pith-number/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/action/storage_attestation","attest_author":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/action/author_attestation","sign_citation":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/action/citation_signature","submit_replication":"https://pith.science/pith/6LKHVFJ7SYNNEBBEMWM5SHBXOJ/action/replication_record"}},"created_at":"2026-07-05T08:17:17.625017+00:00","updated_at":"2026-07-05T08:17:17.625017+00:00"}