{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZL63GJPRLMPHJ5HHQZ2CXNA6EA","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":"342919fd21ebca51681577f339817650f22f777abcb6a8f6b53031456303dc3d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-28T15:12:47Z","title_canon_sha256":"f56e343e237f48a5d85c2195861ba0c78226381c90163fceb55741ea3be8ab05"},"schema_version":"1.0","source":{"id":"2311.16867","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16867","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16867v2","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16867","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZL63GJPRLMPH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZL63GJPRLMPHJ5HH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZL63GJPR","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:19d55b342864393158ec51e70a833b8cee0e291c76cd51ffeb7356d10829ea87","target":"graph","created_at":"2026-05-17T23:38:48Z","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":"Falcon-180B significantly outperforms models such as PaLM or Chinchilla, improves upon LLaMA 2 or Inflection-1, and nears the performance of PaLM-2-Large at a reduced pretraining and inference cost, making it one of the three best language models in the world along with GPT-4 and PaLM-2-Large."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the reported benchmark results reflect genuine capability gains rather than differences in evaluation protocols, data contamination, or undisclosed advantages in testing conditions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Falcon-180B is a 180B-parameter open decoder-only model trained on 3.5 trillion tokens that approaches PaLM-2-Large performance at lower cost and is released with dataset extracts."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Falcon-180B, trained on 3.5 trillion tokens from web data, nears PaLM-2-Large performance at lower pretraining and inference cost."}],"snapshot_sha256":"0687c859fbc9be277aa3c4ea2d20cfaedd6de9fcafb9d9aab4e5063b6a43463a"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"62a45dd550d22bac9d8e8a6648af1e09895b937d9fe0a7ae1665e4013a052026"},"paper":{"abstract_excerpt":"We introduce the Falcon series: 7B, 40B, and 180B parameters causal decoder-only models trained on a diverse high-quality corpora predominantly assembled from web data. The largest model, Falcon-180B, has been trained on over 3.5 trillion tokens of text--the largest openly documented pretraining run. Falcon-180B significantly outperforms models such as PaLM or Chinchilla, and improves upon concurrently developed models such as LLaMA 2 or Inflection-1. It nears the performance of PaLM-2-Large at a reduced pretraining and inference cost, making it, to our knowledge, one of the three best languag","authors_text":"Abdulaziz Alshamsi, Alessandro Cappelli, Badreddine Noune, Baptiste Pannier, Daniele Mazzotta, Daniel Hesslow, Ebtesam Almazrouei, \\'Etienne Goffinet, Guilherme Penedo, Hamza Alobeidli, Julien Launay, M\\'erouane Debbah, Quentin Malartic, Ruxandra Cojocaru","cross_cats":["cs.AI"],"headline":"Falcon-180B, trained on 3.5 trillion tokens from web data, nears PaLM-2-Large performance at lower pretraining and inference cost.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-28T15:12:47Z","title":"The Falcon Series of Open Language Models"},"references":{"count":269,"internal_anchors":66,"resolved_work":269,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Warp size impact in GPUs: large or small? , author=. GPGPU@ASPLOS , year=","work_id":"ba0323a5-dcd1-4d44-8ace-ad2a3c972e0e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization , author=. ArXiv , year=","work_id":"e4b3ee0a-80de-4f37-a4d9-bd3a21a97ed0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Yiwei Yang, Chung Peng Lee, Shangbin Feng, Dora Zhao, Bingbing Wen, Anthony Zhe Liu, Yulia Tsvetkov, and Bill Howe","work_id":"22ad4cec-5465-4cdb-a2aa-ace82b84b5e9","year":null},{"cited_arxiv_id":"2104.08691","doi":"","is_internal_anchor":true,"ref_index":4,"title":"The Power of Scale for Parameter-Efficient Prompt Tuning","work_id":"1056ba8e-7b3f-4811-be8e-9a3ed9269acb","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Bitfit: Simple parameter- efficient fine-tuning for transformer-based masked language-models","work_id":"8505729c-c88b-43bd-8e2c-2c94644ca438","year":null}],"snapshot_sha256":"30ebd1fba5e2e0751becb6abca6595982cf1005f242a49e527c4c6b3923e8ac5"},"source":{"id":"2311.16867","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T09:42:50.408969Z","id":"265a6f6c-7ccd-4c62-9c16-0eecd9b67950","model_set":{"reader":"grok-4.3"},"one_line_summary":"Falcon-180B is a 180B-parameter open decoder-only model trained on 3.5 trillion tokens that approaches PaLM-2-Large performance at lower cost and is released with dataset extracts.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Falcon-180B, trained on 3.5 trillion tokens from web data, nears PaLM-2-Large performance at lower pretraining and inference cost.","strongest_claim":"Falcon-180B significantly outperforms models such as PaLM or Chinchilla, improves upon LLaMA 2 or Inflection-1, and nears the performance of PaLM-2-Large at a reduced pretraining and inference cost, making it one of the three best language models in the world along with GPT-4 and PaLM-2-Large.","weakest_assumption":"The assumption that the reported benchmark results reflect genuine capability gains rather than differences in evaluation protocols, data contamination, or undisclosed advantages in testing conditions."}},"verdict_id":"265a6f6c-7ccd-4c62-9c16-0eecd9b67950"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a9d6045ca1cfb7a1b08e43806e0f47fb8f4b99e0a36fc129a1f455776314b0fb","target":"record","created_at":"2026-05-17T23:38:48Z","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":"342919fd21ebca51681577f339817650f22f777abcb6a8f6b53031456303dc3d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-28T15:12:47Z","title_canon_sha256":"f56e343e237f48a5d85c2195861ba0c78226381c90163fceb55741ea3be8ab05"},"schema_version":"1.0","source":{"id":"2311.16867","kind":"arxiv","version":2}},"canonical_sha256":"cafdb325f15b1e74f4e786742bb41e20181254537c6cae321499d2780ea3f22b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cafdb325f15b1e74f4e786742bb41e20181254537c6cae321499d2780ea3f22b","first_computed_at":"2026-05-17T23:38:48.300417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.300417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pq34RpVAK8P39nQgPFDnxAMem9S7XXBSi9fIa8VcyGUfhAVKZSO/G/YKqMi7MOd4mH5Tc/UAY65/LnD4uMhbBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.300965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.16867","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9d6045ca1cfb7a1b08e43806e0f47fb8f4b99e0a36fc129a1f455776314b0fb","sha256:19d55b342864393158ec51e70a833b8cee0e291c76cd51ffeb7356d10829ea87"],"state_sha256":"609ee43e2649db65dc59ef8d2ca821eb2c6700ce917c9ba76540c84056603ec9"}