{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZTM4O6Z4PNHV7QZASEQYUNSFZE","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":"8a2d41c2411a59011980e4ac88d555b44b04695ad4ca26225bd6af9f1e41db23","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T05:15:27Z","title_canon_sha256":"93c4761e0a04f31443340178297c43f8abeda9334a979a60ff83f50d10d00378"},"schema_version":"1.0","source":{"id":"2308.16463","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16463","created_at":"2026-07-05T09:07:43Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16463v3","created_at":"2026-07-05T09:07:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16463","created_at":"2026-07-05T09:07:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZTM4O6Z4PNHV","created_at":"2026-07-05T09:07:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZTM4O6Z4PNHV7QZA","created_at":"2026-07-05T09:07:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZTM4O6Z4","created_at":"2026-07-05T09:07:43Z"}],"graph_snapshots":[{"event_id":"sha256:5e76348c68023c348b9f76c71abc8d4b10abfd887bb9ef7a399b2489d092d7b9","target":"graph","created_at":"2026-07-05T09:07:43Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.16463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fangyu Liu, Nigel Collier, Yixuan Su, Yupan Huang, Yutong Lu, Zaiqiao Meng","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T05:15:27Z","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16463","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f728432381bf7cf2ba6f76a206b1a683d9d561240d5652ad3b98448410a1b196","target":"record","created_at":"2026-07-05T09:07:43Z","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":"8a2d41c2411a59011980e4ac88d555b44b04695ad4ca26225bd6af9f1e41db23","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T05:15:27Z","title_canon_sha256":"93c4761e0a04f31443340178297c43f8abeda9334a979a60ff83f50d10d00378"},"schema_version":"1.0","source":{"id":"2308.16463","kind":"arxiv","version":3}},"canonical_sha256":"ccd9c77b3c7b4f5fc32091218a3645c91f65f45800e6cf5e33be502798fbafcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccd9c77b3c7b4f5fc32091218a3645c91f65f45800e6cf5e33be502798fbafcf","first_computed_at":"2026-07-05T09:07:43.910978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:43.910978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zC+lO/hxKcNgR0s5zzUPeMOMjtCSrm1NEa+SbbLjqSs67w8skQNTcAmlrdL8Aj8T7zlWJUx7UfgBJ8MGmBB3Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:43.911444Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.16463","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f728432381bf7cf2ba6f76a206b1a683d9d561240d5652ad3b98448410a1b196","sha256:5e76348c68023c348b9f76c71abc8d4b10abfd887bb9ef7a399b2489d092d7b9"],"state_sha256":"fed2d9c68cfcabdaf2fc21dec5c1d901842abdbe6bb9dcdd653dad34e33a3f2d"}