{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YENANHR4AIWZ4TXAWDTE4OUFUL","short_pith_number":"pith:YENANHR4","schema_version":"1.0","canonical_sha256":"c11a069e3c022d9e4ee0b0e64e3a85a2f2ac3d79fb38f77adad5e5204af58fc4","source":{"kind":"arxiv","id":"2402.01613","version":2},"attestation_state":"computed","paper":{"title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andriy Mulyar, Brandon Duderstadt, John X. Morris, Zach Nussbaum","submitted_at":"2024-02-02T18:23:18Z","abstract_excerpt":"This technical report describes the training of nomic-embed-text-v1, the first fully reproducible, open-source, open-weights, open-data, 8192 context length English text embedding model that outperforms both OpenAI Ada-002 and OpenAI text-embedding-3-small on the short-context MTEB benchmark and the long context LoCo benchmark. We release the training code and model weights under an Apache 2.0 license. In contrast with other open-source models, we release the full curated training data and code that allows for full replication of nomic-embed-text-v1. You can find code and data to replicate the"},"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":"2402.01613","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T18:23:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5078e01958947bdafeafc2534defbc5622802935ef6fdb1806bb4a73ece2d769","abstract_canon_sha256":"dcbe79f403641e164a2f430654bc7f0e1f024041db5a71cff266e71081b5882e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T14:48:33.907845Z","signature_b64":"pu5x6+WtU2YaBYBlRs3RrvKmJmqlHXewtkMu0gbAHZ4geOI/8su/rqsgBIcMKXYfIrIHklCql+LM6XUWscnZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c11a069e3c022d9e4ee0b0e64e3a85a2f2ac3d79fb38f77adad5e5204af58fc4","last_reissued_at":"2026-05-21T14:48:33.905059Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T14:48:33.905059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andriy Mulyar, Brandon Duderstadt, John X. Morris, Zach Nussbaum","submitted_at":"2024-02-02T18:23:18Z","abstract_excerpt":"This technical report describes the training of nomic-embed-text-v1, the first fully reproducible, open-source, open-weights, open-data, 8192 context length English text embedding model that outperforms both OpenAI Ada-002 and OpenAI text-embedding-3-small on the short-context MTEB benchmark and the long context LoCo benchmark. We release the training code and model weights under an Apache 2.0 license. In contrast with other open-source models, we release the full curated training data and code that allows for full replication of nomic-embed-text-v1. You can find code and data to replicate the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01613","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/2402.01613/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":"2402.01613","created_at":"2026-05-21T14:48:33.905173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01613v2","created_at":"2026-05-21T14:48:33.905173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01613","created_at":"2026-05-21T14:48:33.905173+00:00"},{"alias_kind":"pith_short_12","alias_value":"YENANHR4AIWZ","created_at":"2026-05-21T14:48:33.905173+00:00"},{"alias_kind":"pith_short_16","alias_value":"YENANHR4AIWZ4TXA","created_at":"2026-05-21T14:48:33.905173+00:00"},{"alias_kind":"pith_short_8","alias_value":"YENANHR4","created_at":"2026-05-21T14:48:33.905173+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":21,"sample":[{"citing_arxiv_id":"2605.20815","citing_title":"GraphRAG on Consumer Hardware: Benchmarking Local LLMs for Healthcare EHR Schema Retrieval","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2412.13663","citing_title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","ref_index":170,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17524","citing_title":"Coordinate Heterogeneity Governs Binary Quantization: From InfoNCE to Recall","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2506.00077","citing_title":"Gaussian mixture models as a proxy for interacting language models","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2508.01959","citing_title":"SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09321","citing_title":"OpenIIR: An Open Simulation Platform for Information Retrieval Research","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12714","citing_title":"Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28816","citing_title":"ASTRA: Mapping Art-Technology Institutions via Conceptual Axes, Text Embeddings, and Unsupervised Clustering","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11135","citing_title":"Control Charts for Multi-agent Systems","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09321","citing_title":"OpenIIR: An Open Simulation Platform for Information Retrieval Research","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10782","citing_title":"TrajPrism: A Multi-Task Benchmark for Language-Grounded Urban Trajectory Understanding","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24623","citing_title":"XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00618","citing_title":"Is Textual Similarity Invariant under Machine Translation? Evidence Based on the Political Manifesto Corpus","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20711","citing_title":"Participatory provenance as representational auditing for AI-mediated public consultation","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12133","citing_title":"Towards Platonic Representation for Table Reasoning: A Foundation for Permutation-Invariant Retrieval","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07201","citing_title":"BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07079","citing_title":"MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07249","citing_title":"MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07878","citing_title":"Black-box model classification under the discriminative factorization","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15597","citing_title":"LLMs Corrupt Your Documents When You Delegate","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25605","citing_title":"Health System Scale Semantic Search Across Unstructured Clinical Notes","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YENANHR4AIWZ4TXAWDTE4OUFUL","json":"https://pith.science/pith/YENANHR4AIWZ4TXAWDTE4OUFUL.json","graph_json":"https://pith.science/api/pith-number/YENANHR4AIWZ4TXAWDTE4OUFUL/graph.json","events_json":"https://pith.science/api/pith-number/YENANHR4AIWZ4TXAWDTE4OUFUL/events.json","paper":"https://pith.science/paper/YENANHR4"},"agent_actions":{"view_html":"https://pith.science/pith/YENANHR4AIWZ4TXAWDTE4OUFUL","download_json":"https://pith.science/pith/YENANHR4AIWZ4TXAWDTE4OUFUL.json","view_paper":"https://pith.science/paper/YENANHR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01613&json=true","fetch_graph":"https://pith.science/api/pith-number/YENANHR4AIWZ4TXAWDTE4OUFUL/graph.json","fetch_events":"https://pith.science/api/pith-number/YENANHR4AIWZ4TXAWDTE4OUFUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YENANHR4AIWZ4TXAWDTE4OUFUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YENANHR4AIWZ4TXAWDTE4OUFUL/action/storage_attestation","attest_author":"https://pith.science/pith/YENANHR4AIWZ4TXAWDTE4OUFUL/action/author_attestation","sign_citation":"https://pith.science/pith/YENANHR4AIWZ4TXAWDTE4OUFUL/action/citation_signature","submit_replication":"https://pith.science/pith/YENANHR4AIWZ4TXAWDTE4OUFUL/action/replication_record"}},"created_at":"2026-05-21T14:48:33.905173+00:00","updated_at":"2026-05-21T14:48:33.905173+00:00"}