{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GYAHVPEQNT3BLRWENWOJIGQCTC","short_pith_number":"pith:GYAHVPEQ","schema_version":"1.0","canonical_sha256":"36007abc906cf615c6c46d9c941a0298bae3fde7fb4bc1b5e47a24bbcaab28c9","source":{"kind":"arxiv","id":"2304.01196","version":4},"attestation_state":"computed","paper":{"title":"Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Canwen Xu, Daya Guo, Julian McAuley, Nan Duan","submitted_at":"2023-04-03T17:59:09Z","abstract_excerpt":"Chat models, such as ChatGPT, have shown impressive capabilities and have been rapidly adopted across numerous domains. However, these models are only accessible through a restricted API, creating barriers for new research and progress in the field. We propose a pipeline that can automatically generate a high-quality multi-turn chat corpus by leveraging ChatGPT to engage in a conversation with itself. Subsequently, we employ parameter-efficient tuning to enhance LLaMA, an open-source large language model. The resulting model, named Baize, demonstrates good performance in multi-turn dialogues w"},"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":"2304.01196","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-03T17:59:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f8ee067c4609203f07d0bad67b8eac405e1dddcfdce165a5cc617a7f43280a95","abstract_canon_sha256":"eedb3985984d0ff335ab41c46c9a44376a62317b24ea0be9be2ed5a41a695db1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:19.051169Z","signature_b64":"qHzs2ErymsY7nhwdhFHqgswEWLCSOdx/AnRfou46jidAg7qA5OAmDKPtsmzYX2TLjUO6+1U2BxqRBrsSEnUBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36007abc906cf615c6c46d9c941a0298bae3fde7fb4bc1b5e47a24bbcaab28c9","last_reissued_at":"2026-07-05T07:19:19.050623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:19.050623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Canwen Xu, Daya Guo, Julian McAuley, Nan Duan","submitted_at":"2023-04-03T17:59:09Z","abstract_excerpt":"Chat models, such as ChatGPT, have shown impressive capabilities and have been rapidly adopted across numerous domains. However, these models are only accessible through a restricted API, creating barriers for new research and progress in the field. We propose a pipeline that can automatically generate a high-quality multi-turn chat corpus by leveraging ChatGPT to engage in a conversation with itself. Subsequently, we employ parameter-efficient tuning to enhance LLaMA, an open-source large language model. The resulting model, named Baize, demonstrates good performance in multi-turn dialogues w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01196","kind":"arxiv","version":4},"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/2304.01196/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":"2304.01196","created_at":"2026-07-05T07:19:19.050687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01196v4","created_at":"2026-07-05T07:19:19.050687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01196","created_at":"2026-07-05T07:19:19.050687+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYAHVPEQNT3B","created_at":"2026-07-05T07:19:19.050687+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYAHVPEQNT3BLRWE","created_at":"2026-07-05T07:19:19.050687+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYAHVPEQ","created_at":"2026-07-05T07:19:19.050687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2304.14178","citing_title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18027","citing_title":"PDF Retrieval Augmented Question Answering","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2408.00724","citing_title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2305.17926","citing_title":"Large Language Models are not Fair Evaluators","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2402.00838","citing_title":"OLMo: Accelerating the Science of Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2305.14233","citing_title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","ref_index":262,"is_internal_anchor":false},{"citing_arxiv_id":"2304.15010","citing_title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07892","citing_title":"Data Selection for Multi-turn Dialogue Instruction Tuning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09212","citing_title":"SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2303.18223","citing_title":"A Survey of Large Language Models","ref_index":192,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYAHVPEQNT3BLRWENWOJIGQCTC","json":"https://pith.science/pith/GYAHVPEQNT3BLRWENWOJIGQCTC.json","graph_json":"https://pith.science/api/pith-number/GYAHVPEQNT3BLRWENWOJIGQCTC/graph.json","events_json":"https://pith.science/api/pith-number/GYAHVPEQNT3BLRWENWOJIGQCTC/events.json","paper":"https://pith.science/paper/GYAHVPEQ"},"agent_actions":{"view_html":"https://pith.science/pith/GYAHVPEQNT3BLRWENWOJIGQCTC","download_json":"https://pith.science/pith/GYAHVPEQNT3BLRWENWOJIGQCTC.json","view_paper":"https://pith.science/paper/GYAHVPEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01196&json=true","fetch_graph":"https://pith.science/api/pith-number/GYAHVPEQNT3BLRWENWOJIGQCTC/graph.json","fetch_events":"https://pith.science/api/pith-number/GYAHVPEQNT3BLRWENWOJIGQCTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYAHVPEQNT3BLRWENWOJIGQCTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYAHVPEQNT3BLRWENWOJIGQCTC/action/storage_attestation","attest_author":"https://pith.science/pith/GYAHVPEQNT3BLRWENWOJIGQCTC/action/author_attestation","sign_citation":"https://pith.science/pith/GYAHVPEQNT3BLRWENWOJIGQCTC/action/citation_signature","submit_replication":"https://pith.science/pith/GYAHVPEQNT3BLRWENWOJIGQCTC/action/replication_record"}},"created_at":"2026-07-05T07:19:19.050687+00:00","updated_at":"2026-07-05T07:19:19.050687+00:00"}