{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DNGF466Q4HZFIHZFGXYCQLGQFV","short_pith_number":"pith:DNGF466Q","schema_version":"1.0","canonical_sha256":"1b4c5e7bd0e1f2541f2535f0282cd02d75407c1639ebb8b758bf6ee1962d17ec","source":{"kind":"arxiv","id":"2506.11380","version":1},"attestation_state":"computed","paper":{"title":"Enhance Multimodal Consistency and Coherence for Text-Image Plan Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ranran Haoran Zhang, Rui Zhang, Xiaoxin Lu, Yusen Zhang","submitted_at":"2025-06-13T01:03:29Z","abstract_excerpt":"People get informed of a daily task plan through diverse media involving both texts and images. However, most prior research only focuses on LLM's capability of textual plan generation. The potential of large-scale models in providing text-image plans remains understudied. Generating high-quality text-image plans faces two main challenges: ensuring consistent alignment between two modalities and keeping coherence among visual steps. To address these challenges, we propose a novel framework that generates and refines text-image plans step-by-step. At each iteration, our framework (1) drafts the"},"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":"2506.11380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T01:03:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8df581a964650aa0750192fb6a2daf0836c2ebe31a67dab3d023d3d3c2ff6fc2","abstract_canon_sha256":"941d19b5f61799a26b9bd2823301d9d1835c741e0661a93716fd287305cfc00f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:03.380132Z","signature_b64":"U7XEiX3QtJzZBr4aTs3bDmC1S3HVkwpcPtr0PJjPq7uOpEqXoLYSVLui6S6QJDYw5Od9SsVEHWqP7kdh9uaNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b4c5e7bd0e1f2541f2535f0282cd02d75407c1639ebb8b758bf6ee1962d17ec","last_reissued_at":"2026-07-05T11:21:03.379669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:03.379669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhance Multimodal Consistency and Coherence for Text-Image Plan Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ranran Haoran Zhang, Rui Zhang, Xiaoxin Lu, Yusen Zhang","submitted_at":"2025-06-13T01:03:29Z","abstract_excerpt":"People get informed of a daily task plan through diverse media involving both texts and images. However, most prior research only focuses on LLM's capability of textual plan generation. The potential of large-scale models in providing text-image plans remains understudied. Generating high-quality text-image plans faces two main challenges: ensuring consistent alignment between two modalities and keeping coherence among visual steps. To address these challenges, we propose a novel framework that generates and refines text-image plans step-by-step. At each iteration, our framework (1) drafts the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11380","kind":"arxiv","version":1},"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/2506.11380/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":"2506.11380","created_at":"2026-07-05T11:21:03.379729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11380v1","created_at":"2026-07-05T11:21:03.379729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11380","created_at":"2026-07-05T11:21:03.379729+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNGF466Q4HZF","created_at":"2026-07-05T11:21:03.379729+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNGF466Q4HZFIHZF","created_at":"2026-07-05T11:21:03.379729+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNGF466Q","created_at":"2026-07-05T11:21:03.379729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNGF466Q4HZFIHZFGXYCQLGQFV","json":"https://pith.science/pith/DNGF466Q4HZFIHZFGXYCQLGQFV.json","graph_json":"https://pith.science/api/pith-number/DNGF466Q4HZFIHZFGXYCQLGQFV/graph.json","events_json":"https://pith.science/api/pith-number/DNGF466Q4HZFIHZFGXYCQLGQFV/events.json","paper":"https://pith.science/paper/DNGF466Q"},"agent_actions":{"view_html":"https://pith.science/pith/DNGF466Q4HZFIHZFGXYCQLGQFV","download_json":"https://pith.science/pith/DNGF466Q4HZFIHZFGXYCQLGQFV.json","view_paper":"https://pith.science/paper/DNGF466Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11380&json=true","fetch_graph":"https://pith.science/api/pith-number/DNGF466Q4HZFIHZFGXYCQLGQFV/graph.json","fetch_events":"https://pith.science/api/pith-number/DNGF466Q4HZFIHZFGXYCQLGQFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNGF466Q4HZFIHZFGXYCQLGQFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNGF466Q4HZFIHZFGXYCQLGQFV/action/storage_attestation","attest_author":"https://pith.science/pith/DNGF466Q4HZFIHZFGXYCQLGQFV/action/author_attestation","sign_citation":"https://pith.science/pith/DNGF466Q4HZFIHZFGXYCQLGQFV/action/citation_signature","submit_replication":"https://pith.science/pith/DNGF466Q4HZFIHZFGXYCQLGQFV/action/replication_record"}},"created_at":"2026-07-05T11:21:03.379729+00:00","updated_at":"2026-07-05T11:21:03.379729+00:00"}