{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AW7XLBV5W3KNDARS4TF6TEPI5A","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":"061b34ec5de464bb59b438a4202a85c7be1b7454178536979d78a2c2799db480","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-15T01:27:58Z","title_canon_sha256":"6081c27dec7bb03274f321d0f624c10a884c970c733ca65dadda0f1413d686a5"},"schema_version":"1.0","source":{"id":"2406.10462","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10462","created_at":"2026-07-05T10:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10462v3","created_at":"2026-07-05T10:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10462","created_at":"2026-07-05T10:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"AW7XLBV5W3KN","created_at":"2026-07-05T10:43:24Z"},{"alias_kind":"pith_short_16","alias_value":"AW7XLBV5W3KNDARS","created_at":"2026-07-05T10:43:24Z"},{"alias_kind":"pith_short_8","alias_value":"AW7XLBV5","created_at":"2026-07-05T10:43:24Z"}],"graph_snapshots":[{"event_id":"sha256:08b645eeb246a780fa7a1d390ef1718d501d812b22685f289ecc4ceb78e8d759","target":"graph","created_at":"2026-07-05T10:43:24Z","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/2406.10462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Interleaved image-text generation has emerged as a crucial multimodal task, aiming at creating sequences of interleaved visual and textual content given a query. Despite notable advancements in recent multimodal large language models (MLLMs), generating integrated image-text sequences that exhibit narrative coherence and entity and style consistency remains challenging due to poor training data quality. To address this gap, we introduce CoMM, a high-quality Coherent interleaved image-text MultiModal dataset designed to enhance the coherence, consistency, and alignment of generated multimodal c","authors_text":"Bin Wen, Fan Yang, Lin Li, Long Chen, Tingting Gao, Wei Chen, Yongqi Yang, Yu Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-15T01:27:58Z","title":"CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10462","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:c7ce60834443f48347a9dc401df2c86eef3d6ccc30240bbd16cdb4892ca13253","target":"record","created_at":"2026-07-05T10:43:24Z","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":"061b34ec5de464bb59b438a4202a85c7be1b7454178536979d78a2c2799db480","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-15T01:27:58Z","title_canon_sha256":"6081c27dec7bb03274f321d0f624c10a884c970c733ca65dadda0f1413d686a5"},"schema_version":"1.0","source":{"id":"2406.10462","kind":"arxiv","version":3}},"canonical_sha256":"05bf7586bdb6d4d18232e4cbe991e8e83cbe0fadc7e5446363f9793ecf9fed3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05bf7586bdb6d4d18232e4cbe991e8e83cbe0fadc7e5446363f9793ecf9fed3e","first_computed_at":"2026-07-05T10:43:24.805069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:24.805069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2cdnbBjaamzT2Cso+KEHWDePBV5fpEyJ90C5HTePGHhaGaUpOoMhAyJUNBLZd4L/ZKKrGVtEu+RqsHj3HhPkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:24.805581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10462","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7ce60834443f48347a9dc401df2c86eef3d6ccc30240bbd16cdb4892ca13253","sha256:08b645eeb246a780fa7a1d390ef1718d501d812b22685f289ecc4ceb78e8d759"],"state_sha256":"04644d169cf1ffd6ea4819b2a07d5dc2f8d3cae030db6787dfb4cfc6b4d6ac4c"}