{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5URC2PYNLUZBZW3FTK6Y2LXEMN","short_pith_number":"pith:5URC2PYN","schema_version":"1.0","canonical_sha256":"ed222d3f0d5d321cdb659abd8d2ee463575dd65fee733d6db0fe0614a9e0ba53","source":{"kind":"arxiv","id":"2404.05979","version":1},"attestation_state":"computed","paper":{"title":"StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing-Kun Bao, Changsheng Xu, Hao Tang, Ming Tao, Yaowei Wang","submitted_at":"2024-04-09T03:22:36Z","abstract_excerpt":"Story visualization aims to generate a series of realistic and coherent images based on a storyline. Current models adopt a frame-by-frame architecture by transforming the pre-trained text-to-image model into an auto-regressive manner. Although these models have shown notable progress, there are still three flaws. 1) The unidirectional generation of auto-regressive manner restricts the usability in many scenarios. 2) The additional introduced story history encoders bring an extremely high computational cost. 3) The story visualization and continuation models are trained and inferred independen"},"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":"2404.05979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-09T03:22:36Z","cross_cats_sorted":[],"title_canon_sha256":"9f2bc32efe8ea2af3f7ba05a6d028be9094694a688f575692e25e35380afe5a3","abstract_canon_sha256":"59d9c7b4293842ebc4110fe78a853236c40e14943eb9ad07950b6d1d331fccd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:01.870187Z","signature_b64":"mQsAeQ8h2QmSYSqjiVfRDSNBGLNbd7oNL8IHOzxqJR0vbELWFzQl5dBcl+lwGjqRZXi//qCoV1JoZ9MrPjANBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed222d3f0d5d321cdb659abd8d2ee463575dd65fee733d6db0fe0614a9e0ba53","last_reissued_at":"2026-07-05T08:06:01.869707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:01.869707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing-Kun Bao, Changsheng Xu, Hao Tang, Ming Tao, Yaowei Wang","submitted_at":"2024-04-09T03:22:36Z","abstract_excerpt":"Story visualization aims to generate a series of realistic and coherent images based on a storyline. Current models adopt a frame-by-frame architecture by transforming the pre-trained text-to-image model into an auto-regressive manner. Although these models have shown notable progress, there are still three flaws. 1) The unidirectional generation of auto-regressive manner restricts the usability in many scenarios. 2) The additional introduced story history encoders bring an extremely high computational cost. 3) The story visualization and continuation models are trained and inferred independen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05979","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/2404.05979/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":"2404.05979","created_at":"2026-07-05T08:06:01.869766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05979v1","created_at":"2026-07-05T08:06:01.869766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05979","created_at":"2026-07-05T08:06:01.869766+00:00"},{"alias_kind":"pith_short_12","alias_value":"5URC2PYNLUZB","created_at":"2026-07-05T08:06:01.869766+00:00"},{"alias_kind":"pith_short_16","alias_value":"5URC2PYNLUZBZW3F","created_at":"2026-07-05T08:06:01.869766+00:00"},{"alias_kind":"pith_short_8","alias_value":"5URC2PYN","created_at":"2026-07-05T08:06:01.869766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.04123","citing_title":"TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5URC2PYNLUZBZW3FTK6Y2LXEMN","json":"https://pith.science/pith/5URC2PYNLUZBZW3FTK6Y2LXEMN.json","graph_json":"https://pith.science/api/pith-number/5URC2PYNLUZBZW3FTK6Y2LXEMN/graph.json","events_json":"https://pith.science/api/pith-number/5URC2PYNLUZBZW3FTK6Y2LXEMN/events.json","paper":"https://pith.science/paper/5URC2PYN"},"agent_actions":{"view_html":"https://pith.science/pith/5URC2PYNLUZBZW3FTK6Y2LXEMN","download_json":"https://pith.science/pith/5URC2PYNLUZBZW3FTK6Y2LXEMN.json","view_paper":"https://pith.science/paper/5URC2PYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05979&json=true","fetch_graph":"https://pith.science/api/pith-number/5URC2PYNLUZBZW3FTK6Y2LXEMN/graph.json","fetch_events":"https://pith.science/api/pith-number/5URC2PYNLUZBZW3FTK6Y2LXEMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5URC2PYNLUZBZW3FTK6Y2LXEMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5URC2PYNLUZBZW3FTK6Y2LXEMN/action/storage_attestation","attest_author":"https://pith.science/pith/5URC2PYNLUZBZW3FTK6Y2LXEMN/action/author_attestation","sign_citation":"https://pith.science/pith/5URC2PYNLUZBZW3FTK6Y2LXEMN/action/citation_signature","submit_replication":"https://pith.science/pith/5URC2PYNLUZBZW3FTK6Y2LXEMN/action/replication_record"}},"created_at":"2026-07-05T08:06:01.869766+00:00","updated_at":"2026-07-05T08:06:01.869766+00:00"}