{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5LRDWUDFJ26DRAZG2B6G5FXNC7","short_pith_number":"pith:5LRDWUDF","canonical_record":{"source":{"id":"2305.14233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T16:49:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9a780193da84cb1bd703e08534f7722eac8065f6a9ac320fa71c8cf18bfefcbb","abstract_canon_sha256":"2b60115e306281141dee36bead52e70a84f177e6a39969bb78c069fb103e628b"},"schema_version":"1.0"},"canonical_sha256":"eae23b50654ebc388326d07c6e96ed17e20055d87fbcbff8ab4e06501dafc418","source":{"kind":"arxiv","id":"2305.14233","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14233","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14233v1","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14233","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"5LRDWUDFJ26D","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"5LRDWUDFJ26DRAZG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"5LRDWUDF","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5LRDWUDFJ26DRAZG2B6G5FXNC7","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T16:49:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9a780193da84cb1bd703e08534f7722eac8065f6a9ac320fa71c8cf18bfefcbb","abstract_canon_sha256":"2b60115e306281141dee36bead52e70a84f177e6a39969bb78c069fb103e628b"},"schema_version":"1.0"},"canonical_sha256":"eae23b50654ebc388326d07c6e96ed17e20055d87fbcbff8ab4e06501dafc418","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.735610Z","signature_b64":"Zv3t3Nl3xnpDxSuG23cR6wp2NbcQijYpEi3vlOv/eIJIgMy5LI6SN1PMXoQURdxjpYBPqrS18ra5ilsoNowrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eae23b50654ebc388326d07c6e96ed17e20055d87fbcbff8ab4e06501dafc418","last_reissued_at":"2026-05-17T23:38:50.734984Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.734984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14233","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hOmn1zPIZFJtmb1+aESIBHF0Ilk5ZVJcBTf71aNKwPVm9AgYtF/bb4AWilZJhASbDaSvtnaDpYpS0jySZOYkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:45:30.825148Z"},"content_sha256":"f76bb0a5830ca3d26a7202d3245dbf7f12a0766aa6e175c4e8be30e3169ea1fc","schema_version":"1.0","event_id":"sha256:f76bb0a5830ca3d26a7202d3245dbf7f12a0766aa6e175c4e8be30e3169ea1fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5LRDWUDFJ26DRAZG2B6G5FXNC7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Scaling AI-generated multi-turn conversations to 1.5 million dialogues produces a fine-tuned LLaMA that outperforms Vicuna.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bokai Xu, Bowen Zhou, Maosong Sun, Ning Ding, Shengding Hu, Yujia Qin, Yulin Chen, Zhiyuan Liu, Zhi Zheng","submitted_at":"2023-05-23T16:49:14Z","abstract_excerpt":"Fine-tuning on instruction data has been widely validated as an effective practice for implementing chat language models like ChatGPT. Scaling the diversity and quality of such data, although straightforward, stands a great chance of leading to improved performance. This paper aims to improve the upper bound of open-source models further. We first provide a systematically designed, diverse, informative, large-scale dataset of instructional conversations, UltraChat, which does not involve human queries. Our objective is to capture the breadth of interactions that a human might have with an AI a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Building upon UltraChat, we fine-tune a LLaMA model to create a powerful conversational model, UltraLLaMA. Our evaluations indicate that UltraLLaMA consistently outperforms other open-source models, including Vicuna, the previously recognized state-of-the-art open-source model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That conversations generated entirely by AI without any human queries can still capture the breadth, coherence, and instructional quality needed to produce measurable gains over prior open-source chat models.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Scaling AI-generated multi-turn conversations to 1.5 million dialogues produces a fine-tuned LLaMA that outperforms Vicuna.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"710d1919331528367595cc8c28e4f88a12b26bdc3eb5f33175453f7168b100c1"},"source":{"id":"2305.14233","kind":"arxiv","version":1},"verdict":{"id":"4be4ab91-40da-4c60-a141-588a1401e04d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T17:19:38.619498Z","strongest_claim":"Building upon UltraChat, we fine-tune a LLaMA model to create a powerful conversational model, UltraLLaMA. Our evaluations indicate that UltraLLaMA consistently outperforms other open-source models, including Vicuna, the previously recognized state-of-the-art open-source model.","one_line_summary":"UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That conversations generated entirely by AI without any human queries can still capture the breadth, coherence, and instructional quality needed to produce measurable gains over prior open-source chat models.","pith_extraction_headline":"Scaling AI-generated multi-turn conversations to 1.5 million dialogues produces a fine-tuned LLaMA that outperforms Vicuna."},"references":{"count":253,"sample":[{"doi":"","year":null,"title":"Chatgpt: Optimizing language models for dialogue , author=. OpenAI , year=","work_id":"ceca96b6-f726-4375-9ecd-a618818dd235","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"GPT-4 technical report , author=. arXiv , year=","work_id":"ffcdf3f4-14c8-40b3-b4ba-f95863a04266","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Stanford Center for Research on Foundation Models","work_id":"69b724c0-6bc6-406f-a710-5779cc2425cd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Advances in neural information processing systems , volume=","work_id":"12f5a236-ef7a-4d13-b4de-b51465a6f977","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Compacter: Efficient low-rank hypercomplex adapter layers , url =","work_id":"1e0b0a38-cc01-4f8a-88af-b43a76d028dd","ref_index":7,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":253,"snapshot_sha256":"b2f9963ccc66510d58c8ba06b2ff4a484ae289dbf3d9077a1eed30fef0926e0b","internal_anchors":15},"formal_canon":{"evidence_count":2,"snapshot_sha256":"216d8e1ee014aa0646de0cd14051631c255f8505af1955361ba88631b13cb39e"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"4be4ab91-40da-4c60-a141-588a1401e04d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xKQc0HLeQ8GMrlPo8AhzTzXovwXZNw+4fmnG5d8S85pNvlgpDNqOumhGJbTuhSEb625yncz5WFgXXI7X3p3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:45:30.825719Z"},"content_sha256":"5d8f687e37c7fcd4ab8244bfd9cb268077fd5666d1e10729f46e3dd4627aadd9","schema_version":"1.0","event_id":"sha256:5d8f687e37c7fcd4ab8244bfd9cb268077fd5666d1e10729f46e3dd4627aadd9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5LRDWUDFJ26DRAZG2B6G5FXNC7/bundle.json","state_url":"https://pith.science/pith/5LRDWUDFJ26DRAZG2B6G5FXNC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5LRDWUDFJ26DRAZG2B6G5FXNC7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T21:45:30Z","links":{"resolver":"https://pith.science/pith/5LRDWUDFJ26DRAZG2B6G5FXNC7","bundle":"https://pith.science/pith/5LRDWUDFJ26DRAZG2B6G5FXNC7/bundle.json","state":"https://pith.science/pith/5LRDWUDFJ26DRAZG2B6G5FXNC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5LRDWUDFJ26DRAZG2B6G5FXNC7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5LRDWUDFJ26DRAZG2B6G5FXNC7","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":"2b60115e306281141dee36bead52e70a84f177e6a39969bb78c069fb103e628b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T16:49:14Z","title_canon_sha256":"9a780193da84cb1bd703e08534f7722eac8065f6a9ac320fa71c8cf18bfefcbb"},"schema_version":"1.0","source":{"id":"2305.14233","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14233","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14233v1","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14233","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"5LRDWUDFJ26D","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"5LRDWUDFJ26DRAZG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"5LRDWUDF","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:5d8f687e37c7fcd4ab8244bfd9cb268077fd5666d1e10729f46e3dd4627aadd9","target":"graph","created_at":"2026-05-17T23:38:50Z","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":"Building upon UltraChat, we fine-tune a LLaMA model to create a powerful conversational model, UltraLLaMA. Our evaluations indicate that UltraLLaMA consistently outperforms other open-source models, including Vicuna, the previously recognized state-of-the-art open-source model."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That conversations generated entirely by AI without any human queries can still capture the breadth, coherence, and instructional quality needed to produce measurable gains over prior open-source chat models."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Scaling AI-generated multi-turn conversations to 1.5 million dialogues produces a fine-tuned LLaMA that outperforms Vicuna."}],"snapshot_sha256":"710d1919331528367595cc8c28e4f88a12b26bdc3eb5f33175453f7168b100c1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"216d8e1ee014aa0646de0cd14051631c255f8505af1955361ba88631b13cb39e"},"paper":{"abstract_excerpt":"Fine-tuning on instruction data has been widely validated as an effective practice for implementing chat language models like ChatGPT. Scaling the diversity and quality of such data, although straightforward, stands a great chance of leading to improved performance. This paper aims to improve the upper bound of open-source models further. We first provide a systematically designed, diverse, informative, large-scale dataset of instructional conversations, UltraChat, which does not involve human queries. Our objective is to capture the breadth of interactions that a human might have with an AI a","authors_text":"Bokai Xu, Bowen Zhou, Maosong Sun, Ning Ding, Shengding Hu, Yujia Qin, Yulin Chen, Zhiyuan Liu, Zhi Zheng","cross_cats":["cs.AI"],"headline":"Scaling AI-generated multi-turn conversations to 1.5 million dialogues produces a fine-tuned LLaMA that outperforms Vicuna.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T16:49:14Z","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations"},"references":{"count":253,"internal_anchors":15,"resolved_work":253,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Chatgpt: Optimizing language models for dialogue , author=. OpenAI , year=","work_id":"ceca96b6-f726-4375-9ecd-a618818dd235","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"GPT-4 technical report , author=. arXiv , year=","work_id":"ffcdf3f4-14c8-40b3-b4ba-f95863a04266","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Stanford Center for Research on Foundation Models","work_id":"69b724c0-6bc6-406f-a710-5779cc2425cd","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":6,"title":"Advances in neural information processing systems , volume=","work_id":"12f5a236-ef7a-4d13-b4de-b51465a6f977","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":7,"title":"Compacter: Efficient low-rank hypercomplex adapter layers , url =","work_id":"1e0b0a38-cc01-4f8a-88af-b43a76d028dd","year":null}],"snapshot_sha256":"b2f9963ccc66510d58c8ba06b2ff4a484ae289dbf3d9077a1eed30fef0926e0b"},"source":{"id":"2305.14233","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T17:19:38.619498Z","id":"4be4ab91-40da-4c60-a141-588a1401e04d","model_set":{"reader":"grok-4.3"},"one_line_summary":"UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Scaling AI-generated multi-turn conversations to 1.5 million dialogues produces a fine-tuned LLaMA that outperforms Vicuna.","strongest_claim":"Building upon UltraChat, we fine-tune a LLaMA model to create a powerful conversational model, UltraLLaMA. Our evaluations indicate that UltraLLaMA consistently outperforms other open-source models, including Vicuna, the previously recognized state-of-the-art open-source model.","weakest_assumption":"That conversations generated entirely by AI without any human queries can still capture the breadth, coherence, and instructional quality needed to produce measurable gains over prior open-source chat models."}},"verdict_id":"4be4ab91-40da-4c60-a141-588a1401e04d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f76bb0a5830ca3d26a7202d3245dbf7f12a0766aa6e175c4e8be30e3169ea1fc","target":"record","created_at":"2026-05-17T23:38:50Z","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":"2b60115e306281141dee36bead52e70a84f177e6a39969bb78c069fb103e628b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T16:49:14Z","title_canon_sha256":"9a780193da84cb1bd703e08534f7722eac8065f6a9ac320fa71c8cf18bfefcbb"},"schema_version":"1.0","source":{"id":"2305.14233","kind":"arxiv","version":1}},"canonical_sha256":"eae23b50654ebc388326d07c6e96ed17e20055d87fbcbff8ab4e06501dafc418","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eae23b50654ebc388326d07c6e96ed17e20055d87fbcbff8ab4e06501dafc418","first_computed_at":"2026-05-17T23:38:50.734984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:50.734984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zv3t3Nl3xnpDxSuG23cR6wp2NbcQijYpEi3vlOv/eIJIgMy5LI6SN1PMXoQURdxjpYBPqrS18ra5ilsoNowrCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:50.735610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14233","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f76bb0a5830ca3d26a7202d3245dbf7f12a0766aa6e175c4e8be30e3169ea1fc","sha256:5d8f687e37c7fcd4ab8244bfd9cb268077fd5666d1e10729f46e3dd4627aadd9"],"state_sha256":"1cb175a04255192574b08e874f64bcf695a76b41220d252b20a466839debac92"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ii1gfo1+QJ4GMIsjdMjvWmDOqvZh28bGpWOJP8/miOexB5jEn/yubzRdu9TJiY5Pmx2nY12aaeCfhTKsVqkLAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T21:45:30.828874Z","bundle_sha256":"746af151eb87d5bc472a72833b25aacd04fd3ca940e7421a99be1be2e0838049"}}