{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UYV4HIS62QZ3V2ZORIBLOX56TA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"96e32cda302bd4f4c818c808146c0da97d0025b59edbb48fdfff8038778a488d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T17:54:58Z","title_canon_sha256":"7f8336369be8aaabe3568c438cf97f40b8f4f596e45196c70422f34d3b23fbb9"},"schema_version":"1.0","source":{"id":"2310.06825","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06825","created_at":"2026-07-05T06:59:24Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06825v1","created_at":"2026-07-05T06:59:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06825","created_at":"2026-07-05T06:59:24Z"},{"alias_kind":"pith_short_12","alias_value":"UYV4HIS62QZ3","created_at":"2026-07-05T06:59:24Z"},{"alias_kind":"pith_short_16","alias_value":"UYV4HIS62QZ3V2ZO","created_at":"2026-07-05T06:59:24Z"},{"alias_kind":"pith_short_8","alias_value":"UYV4HIS6","created_at":"2026-07-05T06:59:24Z"}],"graph_snapshots":[{"event_id":"sha256:3bd4ea9731ed0c2b0e3db9a4549156e24ddc11a4ab1cb634f2a93c017cf4938b","target":"graph","created_at":"2026-07-05T06:59:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The chosen evaluation benchmarks and test sets are representative of downstream usefulness and contain no data leakage from the training corpus."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A 7-billion-parameter model outperforms Llama 2 13B on every benchmark and Llama 1 34B on reasoning, mathematics, and code generation."}],"snapshot_sha256":"a254c6d86f39e2ac32174c4b17c307c7ca802e3fdc325d332906e09648ca7f04"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.06825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.LG"],"headline":"A 7-billion-parameter model outperforms Llama 2 13B on every benchmark and Llama 1 34B on reasoning, mathematics, and code generation.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B"},"references":{"count":29,"internal_anchors":21,"resolved_work":29,"sample":[{"cited_arxiv_id":"2305.13245","doi":"","is_internal_anchor":true,"ref_index":1,"title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","work_id":"b73ad5b2-e553-4c71-b0c9-67e67ba7b158","year":2023},{"cited_arxiv_id":"2108.07732","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","year":2021},{"cited_arxiv_id":"2004.05150","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Longformer: The Long-Document Transformer","work_id":"abea7a44-6668-4de7-aab6-f53a6e5aa088","year":2004},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Piqa: Reasoning about phys- ical commonsense in natural language","work_id":"7cb4a126-31c8-4ff4-bf34-12bd8bdc74fe","year":2020},{"cited_arxiv_id":"2107.03374","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","year":2021}],"snapshot_sha256":"af5cbfc51579651f8062a6608da657e25ecbc7e32801994732e526a7da1cf952"},"source":{"id":"2310.06825","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-24T06:09:42.492805Z","id":"60e91080-3564-4839-bf6a-55d1d74e61e6","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation.","weakest_assumption":"The chosen evaluation benchmarks and test sets are representative of downstream usefulness and contain no data leakage from the training corpus."}},"verdict_id":"60e91080-3564-4839-bf6a-55d1d74e61e6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc76153794084788a1f78c7fc36e275b6e55f11df2a6fbaa473a22931df01e4a","target":"record","created_at":"2026-07-05T06:59:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"96e32cda302bd4f4c818c808146c0da97d0025b59edbb48fdfff8038778a488d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T17:54:58Z","title_canon_sha256":"7f8336369be8aaabe3568c438cf97f40b8f4f596e45196c70422f34d3b23fbb9"},"schema_version":"1.0","source":{"id":"2310.06825","kind":"arxiv","version":1}},"canonical_sha256":"a62bc3a25ed433baeb2e8a02b75fbe9801ea22b68648adaaa87b7e9049ffd391","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a62bc3a25ed433baeb2e8a02b75fbe9801ea22b68648adaaa87b7e9049ffd391","first_computed_at":"2026-07-05T06:59:24.626993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:24.626993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EAPFeXDgQAZY+nj/zXC4YShVXfIVIRtdLOAPeOuxlbToLbC49BYLzVT5AVDrnc6cYLVJGIXcPtttVlBdEtAnBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:24.627496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06825","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc76153794084788a1f78c7fc36e275b6e55f11df2a6fbaa473a22931df01e4a","sha256:3bd4ea9731ed0c2b0e3db9a4549156e24ddc11a4ab1cb634f2a93c017cf4938b"],"state_sha256":"3d8b04c69480bd5f243758eec62713ab181924de33af8f0cbf73a1f9e5fd293a"}