{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UYV4HIS62QZ3V2ZORIBLOX56TA","short_pith_number":"pith:UYV4HIS6","schema_version":"1.0","canonical_sha256":"a62bc3a25ed433baeb2e8a02b75fbe9801ea22b68648adaaa87b7e9049ffd391","source":{"kind":"arxiv","id":"2310.06825","version":1},"attestation_state":"computed","paper":{"title":"Mistral 7B","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A 7-billion-parameter model outperforms Llama 2 13B on every benchmark and Llama 1 34B on reasoning, mathematics, and code generation.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, L\\'elio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timoth\\'ee Lacroix, William El Sayed","submitted_at":"2023-10-10T17:54:58Z","abstract_excerpt":"We introduce Mistral 7B v0.1, a 7-billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation. Our model leverages grouped-query attention (GQA) for faster inference, coupled with sliding window attention (SWA) to effectively handle sequences of arbitrary length with a reduced inference cost. We also provide a model fine-tuned to follow instructions, Mistral 7B -- Instruct, that surpasses the Llama 2 13B -- Chat model both on human and auto"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.06825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T17:54:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7f8336369be8aaabe3568c438cf97f40b8f4f596e45196c70422f34d3b23fbb9","abstract_canon_sha256":"96e32cda302bd4f4c818c808146c0da97d0025b59edbb48fdfff8038778a488d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:24.627496Z","signature_b64":"EAPFeXDgQAZY+nj/zXC4YShVXfIVIRtdLOAPeOuxlbToLbC49BYLzVT5AVDrnc6cYLVJGIXcPtttVlBdEtAnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a62bc3a25ed433baeb2e8a02b75fbe9801ea22b68648adaaa87b7e9049ffd391","last_reissued_at":"2026-07-05T06:59:24.626993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:24.626993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mistral 7B","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A 7-billion-parameter model outperforms Llama 2 13B on every benchmark and Llama 1 34B on reasoning, mathematics, and code generation.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, L\\'elio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timoth\\'ee Lacroix, William El Sayed","submitted_at":"2023-10-10T17:54:58Z","abstract_excerpt":"We introduce Mistral 7B v0.1, a 7-billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation. Our model leverages grouped-query attention (GQA) for faster inference, coupled with sliding window attention (SWA) to effectively handle sequences of arbitrary length with a reduced inference cost. We also provide a model fine-tuned to follow instructions, Mistral 7B -- Instruct, that surpasses the Llama 2 13B -- Chat model both on human and auto"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The chosen evaluation benchmarks and test sets are representative of downstream usefulness and contain no data leakage from the training corpus.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Mistral 7B is a 7B-parameter LLM that outperforms Llama 2 13B across benchmarks via grouped-query attention and sliding-window attention while remaining efficient.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A 7-billion-parameter model outperforms Llama 2 13B on every benchmark and Llama 1 34B on reasoning, mathematics, and code generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a254c6d86f39e2ac32174c4b17c307c7ca802e3fdc325d332906e09648ca7f04"},"source":{"id":"2310.06825","kind":"arxiv","version":1},"verdict":{"id":"60e91080-3564-4839-bf6a-55d1d74e61e6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-24T06:09:42.492805Z","strongest_claim":"Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation.","one_line_summary":"Mistral 7B is a 7B-parameter LLM that outperforms Llama 2 13B across benchmarks via grouped-query attention and sliding-window attention while remaining efficient.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The chosen evaluation benchmarks and test sets are representative of downstream usefulness and contain no data leakage from the training corpus.","pith_extraction_headline":"A 7-billion-parameter model outperforms Llama 2 13B on every benchmark and Llama 1 34B on reasoning, mathematics, and code generation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.06825/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":29,"sample":[{"doi":"","year":2023,"title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","work_id":"b73ad5b2-e553-4c71-b0c9-67e67ba7b158","ref_index":1,"cited_arxiv_id":"2305.13245","is_internal_anchor":true},{"doi":"","year":2021,"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","ref_index":2,"cited_arxiv_id":"2108.07732","is_internal_anchor":true},{"doi":"","year":2004,"title":"Longformer: The Long-Document Transformer","work_id":"abea7a44-6668-4de7-aab6-f53a6e5aa088","ref_index":3,"cited_arxiv_id":"2004.05150","is_internal_anchor":true},{"doi":"","year":2020,"title":"Piqa: Reasoning about phys- ical commonsense in natural language","work_id":"7cb4a126-31c8-4ff4-bf34-12bd8bdc74fe","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":5,"cited_arxiv_id":"2107.03374","is_internal_anchor":true}],"resolved_work":29,"snapshot_sha256":"af5cbfc51579651f8062a6608da657e25ecbc7e32801994732e526a7da1cf952","internal_anchors":21},"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":"2310.06825","created_at":"2026-07-05T06:59:24.627057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.06825v1","created_at":"2026-07-05T06:59:24.627057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06825","created_at":"2026-07-05T06:59:24.627057+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYV4HIS62QZ3","created_at":"2026-07-05T06:59:24.627057+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYV4HIS62QZ3V2ZO","created_at":"2026-07-05T06:59:24.627057+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYV4HIS6","created_at":"2026-07-05T06:59:24.627057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":713,"internal_anchor_count":704,"sample":[{"citing_arxiv_id":"2607.07964","citing_title":"KronQ: LLM Quantization via Kronecker-Factored Hessian","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2607.08374","citing_title":"Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06913","citing_title":"Evaluating LLM Robustness Under Domain-Specific Prompt Perturbations in Public Health Applications","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05992","citing_title":"PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18752","citing_title":"A Scientific Human-Agent Reproduction Pipeline","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26036","citing_title":"Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25761","citing_title":"Bridging Spherical Black-Box Optimizers","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24320","citing_title":"ZONOS2 Technical Report","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24644","citing_title":"Measuring User's Mental Models of Speech Translation in Human-AI Collaboration","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24163","citing_title":"CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24331","citing_title":"Transformer-Based Language Models Across Domain Verticals: Architectures, Applications and Critical Assessment","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24964","citing_title":"Evidence for feature-specific error correction in LLMs","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24970","citing_title":"Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26454","citing_title":"Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning -- The Limit of the Scaling Law","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26290","citing_title":"SSM Adapters via Hankel Reduced-order Modeling: Injection Site Determines Task Suitability in Long-Context Fine-Tuning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27205","citing_title":"Smaller Models, Unexpected Costs: Trade-offs in LLM Quantization for Automated Program Repair","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26660","citing_title":"Generating Special Triangulations with Transformers","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26749","citing_title":"Structure Before Collapse: Transient semantic geometry in next-token prediction","ref_index":95,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23313","citing_title":"Uncertainty-based Debiasing and Unlearning for Decontamination","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24937","citing_title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22817","citing_title":"SelPE: Progressive Selection for Private Structured Text Synthesis","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23590","citing_title":"The Topology of Ill-Posed Questions: Persistent Homology for Detection and Steering in LLMs","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22826","citing_title":"MINCE: Shrinking LLM Evaluation Datasets via Few-Model Monte Carlo Calibration","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":249,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22496","citing_title":"Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYV4HIS62QZ3V2ZORIBLOX56TA","json":"https://pith.science/pith/UYV4HIS62QZ3V2ZORIBLOX56TA.json","graph_json":"https://pith.science/api/pith-number/UYV4HIS62QZ3V2ZORIBLOX56TA/graph.json","events_json":"https://pith.science/api/pith-number/UYV4HIS62QZ3V2ZORIBLOX56TA/events.json","paper":"https://pith.science/paper/UYV4HIS6"},"agent_actions":{"view_html":"https://pith.science/pith/UYV4HIS62QZ3V2ZORIBLOX56TA","download_json":"https://pith.science/pith/UYV4HIS62QZ3V2ZORIBLOX56TA.json","view_paper":"https://pith.science/paper/UYV4HIS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.06825&json=true","fetch_graph":"https://pith.science/api/pith-number/UYV4HIS62QZ3V2ZORIBLOX56TA/graph.json","fetch_events":"https://pith.science/api/pith-number/UYV4HIS62QZ3V2ZORIBLOX56TA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYV4HIS62QZ3V2ZORIBLOX56TA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYV4HIS62QZ3V2ZORIBLOX56TA/action/storage_attestation","attest_author":"https://pith.science/pith/UYV4HIS62QZ3V2ZORIBLOX56TA/action/author_attestation","sign_citation":"https://pith.science/pith/UYV4HIS62QZ3V2ZORIBLOX56TA/action/citation_signature","submit_replication":"https://pith.science/pith/UYV4HIS62QZ3V2ZORIBLOX56TA/action/replication_record"}},"created_at":"2026-07-05T06:59:24.627057+00:00","updated_at":"2026-07-05T06:59:24.627057+00:00"}