{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JGRT2YXXLF5EGIYXSYDYFAFS72","short_pith_number":"pith:JGRT2YXX","schema_version":"1.0","canonical_sha256":"49a33d62f7597a43231796078280b2febde997a7f4fdd4ae7fa7551822c82b39","source":{"kind":"arxiv","id":"2302.03900","version":1},"attestation_state":"computed","paper":{"title":"Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Gihyun Kwon, Hyeonho Jeong, Jong Chul Ye","submitted_at":"2023-02-08T06:24:06Z","abstract_excerpt":"Recent advancements in large scale text-to-image models have opened new possibilities for guiding the creation of images through human-devised natural language. However, while prior literature has primarily focused on the generation of individual images, it is essential to consider the capability of these models to ensure coherency within a sequence of images to fulfill the demands of real-world applications such as storytelling. To address this, here we present a novel neural pipeline for generating a coherent storybook from the plain text of a story. Specifically, we leverage a combination o"},"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":"2302.03900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-08T06:24:06Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"19110d21044f7f59c36ba8830502213eaa1ad77e16c5107096f2818160f67b30","abstract_canon_sha256":"c0235bcfba3673331ab2ae4be823532f52668fd12485d3385416769f1ca32713"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:58.875003Z","signature_b64":"aUsFESXEPo3fiG4flqadinFY1b9VK0Aq4szTI4gBCfmhvHSuEO2mPHnZgzXaWQPSl4cLaBCIEWfp0+/ifgkkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49a33d62f7597a43231796078280b2febde997a7f4fdd4ae7fa7551822c82b39","last_reissued_at":"2026-07-05T05:39:58.874578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:58.874578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Gihyun Kwon, Hyeonho Jeong, Jong Chul Ye","submitted_at":"2023-02-08T06:24:06Z","abstract_excerpt":"Recent advancements in large scale text-to-image models have opened new possibilities for guiding the creation of images through human-devised natural language. However, while prior literature has primarily focused on the generation of individual images, it is essential to consider the capability of these models to ensure coherency within a sequence of images to fulfill the demands of real-world applications such as storytelling. To address this, here we present a novel neural pipeline for generating a coherent storybook from the plain text of a story. Specifically, we leverage a combination o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03900","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/2302.03900/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":"2302.03900","created_at":"2026-07-05T05:39:58.874640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03900v1","created_at":"2026-07-05T05:39:58.874640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03900","created_at":"2026-07-05T05:39:58.874640+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGRT2YXXLF5E","created_at":"2026-07-05T05:39:58.874640+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGRT2YXXLF5EGIYX","created_at":"2026-07-05T05:39:58.874640+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGRT2YXX","created_at":"2026-07-05T05:39:58.874640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03735","citing_title":"StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGRT2YXXLF5EGIYXSYDYFAFS72","json":"https://pith.science/pith/JGRT2YXXLF5EGIYXSYDYFAFS72.json","graph_json":"https://pith.science/api/pith-number/JGRT2YXXLF5EGIYXSYDYFAFS72/graph.json","events_json":"https://pith.science/api/pith-number/JGRT2YXXLF5EGIYXSYDYFAFS72/events.json","paper":"https://pith.science/paper/JGRT2YXX"},"agent_actions":{"view_html":"https://pith.science/pith/JGRT2YXXLF5EGIYXSYDYFAFS72","download_json":"https://pith.science/pith/JGRT2YXXLF5EGIYXSYDYFAFS72.json","view_paper":"https://pith.science/paper/JGRT2YXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03900&json=true","fetch_graph":"https://pith.science/api/pith-number/JGRT2YXXLF5EGIYXSYDYFAFS72/graph.json","fetch_events":"https://pith.science/api/pith-number/JGRT2YXXLF5EGIYXSYDYFAFS72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGRT2YXXLF5EGIYXSYDYFAFS72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGRT2YXXLF5EGIYXSYDYFAFS72/action/storage_attestation","attest_author":"https://pith.science/pith/JGRT2YXXLF5EGIYXSYDYFAFS72/action/author_attestation","sign_citation":"https://pith.science/pith/JGRT2YXXLF5EGIYXSYDYFAFS72/action/citation_signature","submit_replication":"https://pith.science/pith/JGRT2YXXLF5EGIYXSYDYFAFS72/action/replication_record"}},"created_at":"2026-07-05T05:39:58.874640+00:00","updated_at":"2026-07-05T05:39:58.874640+00:00"}