{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UIWDAWOY5DCRCTP32T3IICBH27","short_pith_number":"pith:UIWDAWOY","schema_version":"1.0","canonical_sha256":"a22c3059d8e8c5114dfbd4f6840827d7fc0c8756a1a8e20f8c9692b5242c4854","source":{"kind":"arxiv","id":"2308.07317","version":2},"attestation_state":"computed","paper":{"title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ariel N. Lee, Cole J. Hunter, Nataniel Ruiz","submitted_at":"2023-08-14T17:59:56Z","abstract_excerpt":"We present $\\textbf{Platypus}$, a family of fine-tuned and merged Large Language Models (LLMs) that achieves the strongest performance and currently stands at first place in HuggingFace's Open LLM Leaderboard as of the release date of this work. In this work we describe (1) our curated dataset $\\textbf{Open-Platypus}$, that is a subset of other open datasets and which $\\textit{we release to the public}$ (2) our process of fine-tuning and merging LoRA modules in order to conserve the strong prior of pretrained LLMs, while bringing specific domain knowledge to the surface (3) our efforts in chec"},"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":"2308.07317","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-14T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"48b687a6cf4bbec9304cd15375ec9b86c8126603f16f339c70958869cdb09104","abstract_canon_sha256":"ca20d982b4f6e4fb3784bfe7109f0d9827266b7e0ef11c10173e3ddad0af62bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:16.567193Z","signature_b64":"geuHmbL1Y9LZ7Cf9NvEmKx9btJzVVTY28wMccit+hyZisg4EqXiZHBTMHVg8iFrYfF2f+vZjmtcdLEmcG1bzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a22c3059d8e8c5114dfbd4f6840827d7fc0c8756a1a8e20f8c9692b5242c4854","last_reissued_at":"2026-07-05T07:56:16.566829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:16.566829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ariel N. Lee, Cole J. Hunter, Nataniel Ruiz","submitted_at":"2023-08-14T17:59:56Z","abstract_excerpt":"We present $\\textbf{Platypus}$, a family of fine-tuned and merged Large Language Models (LLMs) that achieves the strongest performance and currently stands at first place in HuggingFace's Open LLM Leaderboard as of the release date of this work. In this work we describe (1) our curated dataset $\\textbf{Open-Platypus}$, that is a subset of other open datasets and which $\\textit{we release to the public}$ (2) our process of fine-tuning and merging LoRA modules in order to conserve the strong prior of pretrained LLMs, while bringing specific domain knowledge to the surface (3) our efforts in chec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07317","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/2308.07317/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":"2308.07317","created_at":"2026-07-05T07:56:16.566885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07317v2","created_at":"2026-07-05T07:56:16.566885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07317","created_at":"2026-07-05T07:56:16.566885+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIWDAWOY5DCR","created_at":"2026-07-05T07:56:16.566885+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIWDAWOY5DCRCTP3","created_at":"2026-07-05T07:56:16.566885+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIWDAWOY","created_at":"2026-07-05T07:56:16.566885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01062","citing_title":"DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02606","citing_title":"ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24079","citing_title":"TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23171","citing_title":"Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2309.17452","citing_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2502.10248","citing_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2309.05653","citing_title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2308.14132","citing_title":"Detecting Language Model Attacks with Perplexity","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2309.12284","citing_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2309.01219","citing_title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07850","citing_title":"MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UIWDAWOY5DCRCTP32T3IICBH27","json":"https://pith.science/pith/UIWDAWOY5DCRCTP32T3IICBH27.json","graph_json":"https://pith.science/api/pith-number/UIWDAWOY5DCRCTP32T3IICBH27/graph.json","events_json":"https://pith.science/api/pith-number/UIWDAWOY5DCRCTP32T3IICBH27/events.json","paper":"https://pith.science/paper/UIWDAWOY"},"agent_actions":{"view_html":"https://pith.science/pith/UIWDAWOY5DCRCTP32T3IICBH27","download_json":"https://pith.science/pith/UIWDAWOY5DCRCTP32T3IICBH27.json","view_paper":"https://pith.science/paper/UIWDAWOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07317&json=true","fetch_graph":"https://pith.science/api/pith-number/UIWDAWOY5DCRCTP32T3IICBH27/graph.json","fetch_events":"https://pith.science/api/pith-number/UIWDAWOY5DCRCTP32T3IICBH27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIWDAWOY5DCRCTP32T3IICBH27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIWDAWOY5DCRCTP32T3IICBH27/action/storage_attestation","attest_author":"https://pith.science/pith/UIWDAWOY5DCRCTP32T3IICBH27/action/author_attestation","sign_citation":"https://pith.science/pith/UIWDAWOY5DCRCTP32T3IICBH27/action/citation_signature","submit_replication":"https://pith.science/pith/UIWDAWOY5DCRCTP32T3IICBH27/action/replication_record"}},"created_at":"2026-07-05T07:56:16.566885+00:00","updated_at":"2026-07-05T07:56:16.566885+00:00"}