{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OKMICM2ZGGY2C2L4XG7KN75CPG","short_pith_number":"pith:OKMICM2Z","schema_version":"1.0","canonical_sha256":"729881335931b1a1697cb9bea6ffa2799aee1ebdce53a6eec29178e6a19ade2c","source":{"kind":"arxiv","id":"2508.21085","version":1},"attestation_state":"computed","paper":{"title":"Granite Embedding R2 Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Aashka Trivedi, Abraham Daniels, Bhavani Iyer, David Cox, Jaydeep Sen, Ken Barker, Luis Lastras, Madison Lee, Martin Franz, Meet Doshi, Parul Awasthy, Radu Florian, Riyaz Bhat, Rudra Murthy, Salim Roukos, Todd Ward, Vignesh P, Vishwajeet Kumar, Yulong Li, Yushu Yang","submitted_at":"2025-08-26T19:06:29Z","abstract_excerpt":"We introduce the Granite Embedding R2 models, a comprehensive family of high-performance English encoder-based embedding models engineered for enterprise-scale dense retrieval applications. Building upon our first-generation release, these models deliver substantial improvements, including 16x expanded context length (8,192 tokens), state-of-the-art performance across diverse retrieval domains - text, code, long-document search, multi-turn conversational, and tabular data - and measurable speed advantages of 19-44\\% over leading competitors while maintaining superior accuracy. Our release enco"},"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":"2508.21085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-26T19:06:29Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"013718d928f2357f83d11e157616ef0290e149b7cdaf08be4a23fbb5da39bc2c","abstract_canon_sha256":"24e57dc178f5940204a1df463c7c1bb552ef69702b046da96981fe8298500a28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:27.649025Z","signature_b64":"3Bm9O/mUjkmQe7ojjwZQzT/VubIZva0ihrzowYmMQPnikmVUBmda8nSnNEA+qFyeZpbiriS6veHuQarlAaU5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"729881335931b1a1697cb9bea6ffa2799aee1ebdce53a6eec29178e6a19ade2c","last_reissued_at":"2026-07-05T12:01:27.648526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:27.648526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Granite Embedding R2 Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Aashka Trivedi, Abraham Daniels, Bhavani Iyer, David Cox, Jaydeep Sen, Ken Barker, Luis Lastras, Madison Lee, Martin Franz, Meet Doshi, Parul Awasthy, Radu Florian, Riyaz Bhat, Rudra Murthy, Salim Roukos, Todd Ward, Vignesh P, Vishwajeet Kumar, Yulong Li, Yushu Yang","submitted_at":"2025-08-26T19:06:29Z","abstract_excerpt":"We introduce the Granite Embedding R2 models, a comprehensive family of high-performance English encoder-based embedding models engineered for enterprise-scale dense retrieval applications. Building upon our first-generation release, these models deliver substantial improvements, including 16x expanded context length (8,192 tokens), state-of-the-art performance across diverse retrieval domains - text, code, long-document search, multi-turn conversational, and tabular data - and measurable speed advantages of 19-44\\% over leading competitors while maintaining superior accuracy. Our release enco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21085","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/2508.21085/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":"2508.21085","created_at":"2026-07-05T12:01:27.648589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21085v1","created_at":"2026-07-05T12:01:27.648589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21085","created_at":"2026-07-05T12:01:27.648589+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKMICM2ZGGY2","created_at":"2026-07-05T12:01:27.648589+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKMICM2ZGGY2C2L4","created_at":"2026-07-05T12:01:27.648589+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKMICM2Z","created_at":"2026-07-05T12:01:27.648589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18811","citing_title":"Rescaling MLM-Head for Neural Sparse Retrieval","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12028","citing_title":"Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09251","citing_title":"DRBENCHER: Can Your Agent Identify the Entity, Retrieve Its Properties and Do the Math?","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17943","citing_title":"A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21696","citing_title":"Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKMICM2ZGGY2C2L4XG7KN75CPG","json":"https://pith.science/pith/OKMICM2ZGGY2C2L4XG7KN75CPG.json","graph_json":"https://pith.science/api/pith-number/OKMICM2ZGGY2C2L4XG7KN75CPG/graph.json","events_json":"https://pith.science/api/pith-number/OKMICM2ZGGY2C2L4XG7KN75CPG/events.json","paper":"https://pith.science/paper/OKMICM2Z"},"agent_actions":{"view_html":"https://pith.science/pith/OKMICM2ZGGY2C2L4XG7KN75CPG","download_json":"https://pith.science/pith/OKMICM2ZGGY2C2L4XG7KN75CPG.json","view_paper":"https://pith.science/paper/OKMICM2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21085&json=true","fetch_graph":"https://pith.science/api/pith-number/OKMICM2ZGGY2C2L4XG7KN75CPG/graph.json","fetch_events":"https://pith.science/api/pith-number/OKMICM2ZGGY2C2L4XG7KN75CPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKMICM2ZGGY2C2L4XG7KN75CPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKMICM2ZGGY2C2L4XG7KN75CPG/action/storage_attestation","attest_author":"https://pith.science/pith/OKMICM2ZGGY2C2L4XG7KN75CPG/action/author_attestation","sign_citation":"https://pith.science/pith/OKMICM2ZGGY2C2L4XG7KN75CPG/action/citation_signature","submit_replication":"https://pith.science/pith/OKMICM2ZGGY2C2L4XG7KN75CPG/action/replication_record"}},"created_at":"2026-07-05T12:01:27.648589+00:00","updated_at":"2026-07-05T12:01:27.648589+00:00"}