{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZTM4O6Z4PNHV7QZASEQYUNSFZE","short_pith_number":"pith:ZTM4O6Z4","schema_version":"1.0","canonical_sha256":"ccd9c77b3c7b4f5fc32091218a3645c91f65f45800e6cf5e33be502798fbafcf","source":{"kind":"arxiv","id":"2308.16463","version":3},"attestation_state":"computed","paper":{"title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fangyu Liu, Nigel Collier, Yixuan Su, Yupan Huang, Yutong Lu, Zaiqiao Meng","submitted_at":"2023-08-31T05:15:27Z","abstract_excerpt":"Large language models exhibit enhanced zero-shot performance on various tasks when fine-tuned with instruction-following data. Multimodal instruction-following models extend these capabilities by integrating both text and images. However, existing models such as MiniGPT-4 and LLaVA face challenges in maintaining dialogue coherence in scenarios involving multiple images. A primary reason is the lack of a specialized dataset for this critical application. To bridge these gaps, we introduce SparklesDialogue, the first machine-generated dialogue dataset tailored for word-level interleaved multi-im"},"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":"2308.16463","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T05:15:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"93c4761e0a04f31443340178297c43f8abeda9334a979a60ff83f50d10d00378","abstract_canon_sha256":"8a2d41c2411a59011980e4ac88d555b44b04695ad4ca26225bd6af9f1e41db23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:43.911444Z","signature_b64":"zC+lO/hxKcNgR0s5zzUPeMOMjtCSrm1NEa+SbbLjqSs67w8skQNTcAmlrdL8Aj8T7zlWJUx7UfgBJ8MGmBB3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccd9c77b3c7b4f5fc32091218a3645c91f65f45800e6cf5e33be502798fbafcf","last_reissued_at":"2026-07-05T09:07:43.910978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:43.910978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fangyu Liu, Nigel Collier, Yixuan Su, Yupan Huang, Yutong Lu, Zaiqiao Meng","submitted_at":"2023-08-31T05:15:27Z","abstract_excerpt":"Large language models exhibit enhanced zero-shot performance on various tasks when fine-tuned with instruction-following data. Multimodal instruction-following models extend these capabilities by integrating both text and images. However, existing models such as MiniGPT-4 and LLaVA face challenges in maintaining dialogue coherence in scenarios involving multiple images. A primary reason is the lack of a specialized dataset for this critical application. To bridge these gaps, we introduce SparklesDialogue, the first machine-generated dialogue dataset tailored for word-level interleaved multi-im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16463","kind":"arxiv","version":3},"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/2308.16463/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":"2308.16463","created_at":"2026-07-05T09:07:43.911034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.16463v3","created_at":"2026-07-05T09:07:43.911034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16463","created_at":"2026-07-05T09:07:43.911034+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTM4O6Z4PNHV","created_at":"2026-07-05T09:07:43.911034+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTM4O6Z4PNHV7QZA","created_at":"2026-07-05T09:07:43.911034+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTM4O6Z4","created_at":"2026-07-05T09:07:43.911034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2311.16502","citing_title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTM4O6Z4PNHV7QZASEQYUNSFZE","json":"https://pith.science/pith/ZTM4O6Z4PNHV7QZASEQYUNSFZE.json","graph_json":"https://pith.science/api/pith-number/ZTM4O6Z4PNHV7QZASEQYUNSFZE/graph.json","events_json":"https://pith.science/api/pith-number/ZTM4O6Z4PNHV7QZASEQYUNSFZE/events.json","paper":"https://pith.science/paper/ZTM4O6Z4"},"agent_actions":{"view_html":"https://pith.science/pith/ZTM4O6Z4PNHV7QZASEQYUNSFZE","download_json":"https://pith.science/pith/ZTM4O6Z4PNHV7QZASEQYUNSFZE.json","view_paper":"https://pith.science/paper/ZTM4O6Z4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.16463&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTM4O6Z4PNHV7QZASEQYUNSFZE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTM4O6Z4PNHV7QZASEQYUNSFZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTM4O6Z4PNHV7QZASEQYUNSFZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTM4O6Z4PNHV7QZASEQYUNSFZE/action/storage_attestation","attest_author":"https://pith.science/pith/ZTM4O6Z4PNHV7QZASEQYUNSFZE/action/author_attestation","sign_citation":"https://pith.science/pith/ZTM4O6Z4PNHV7QZASEQYUNSFZE/action/citation_signature","submit_replication":"https://pith.science/pith/ZTM4O6Z4PNHV7QZASEQYUNSFZE/action/replication_record"}},"created_at":"2026-07-05T09:07:43.911034+00:00","updated_at":"2026-07-05T09:07:43.911034+00:00"}