{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M6DJ2LP3FIV2QWK67324BUKY7B","short_pith_number":"pith:M6DJ2LP3","schema_version":"1.0","canonical_sha256":"67869d2dfb2a2ba8595efef5c0d158f8422b560a47d44d93e84a3fa360125d17","source":{"kind":"arxiv","id":"2407.02482","version":2},"attestation_state":"computed","paper":{"title":"Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wang, Fei Shen, Hu Ye, Jun Zhang, Sibo Liu, Wei Yang, Xiao Han","submitted_at":"2024-07-02T17:58:07Z","abstract_excerpt":"Recent research showcases the considerable potential of conditional diffusion models for generating consistent stories. However, current methods, which predominantly generate stories in an autoregressive and excessively caption-dependent manner, often underrate the contextual consistency and relevance of frames during sequential generation. To address this, we propose a novel Rich-contextual Conditional Diffusion Models (RCDMs), a two-stage approach designed to enhance story generation's semantic consistency and temporal consistency. Specifically, in the first stage, the frame-prior transforme"},"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":"2407.02482","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T17:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"38f044f448d58f65c1686b1d057259f3a13f1b697088ea34c09762d962fc14f6","abstract_canon_sha256":"1b5eea81669d9d310d02ddf5b8e7e47afb2de30a8b81910de519842ffda462a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:53.141982Z","signature_b64":"WYN1UsjC0oFIVztVpZLmjiw2Tt0nmrEABWoq39kydpW7nhY0CXpSRmYZwtOWohIHAk+twUzyfc6zle7ZGc2kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67869d2dfb2a2ba8595efef5c0d158f8422b560a47d44d93e84a3fa360125d17","last_reissued_at":"2026-07-05T08:39:53.141641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:53.141641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wang, Fei Shen, Hu Ye, Jun Zhang, Sibo Liu, Wei Yang, Xiao Han","submitted_at":"2024-07-02T17:58:07Z","abstract_excerpt":"Recent research showcases the considerable potential of conditional diffusion models for generating consistent stories. However, current methods, which predominantly generate stories in an autoregressive and excessively caption-dependent manner, often underrate the contextual consistency and relevance of frames during sequential generation. To address this, we propose a novel Rich-contextual Conditional Diffusion Models (RCDMs), a two-stage approach designed to enhance story generation's semantic consistency and temporal consistency. Specifically, in the first stage, the frame-prior transforme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02482","kind":"arxiv","version":2},"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/2407.02482/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":"2407.02482","created_at":"2026-07-05T08:39:53.141698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02482v2","created_at":"2026-07-05T08:39:53.141698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02482","created_at":"2026-07-05T08:39:53.141698+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6DJ2LP3FIV2","created_at":"2026-07-05T08:39:53.141698+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6DJ2LP3FIV2QWK6","created_at":"2026-07-05T08:39:53.141698+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6DJ2LP3","created_at":"2026-07-05T08:39:53.141698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17051","citing_title":"Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6DJ2LP3FIV2QWK67324BUKY7B","json":"https://pith.science/pith/M6DJ2LP3FIV2QWK67324BUKY7B.json","graph_json":"https://pith.science/api/pith-number/M6DJ2LP3FIV2QWK67324BUKY7B/graph.json","events_json":"https://pith.science/api/pith-number/M6DJ2LP3FIV2QWK67324BUKY7B/events.json","paper":"https://pith.science/paper/M6DJ2LP3"},"agent_actions":{"view_html":"https://pith.science/pith/M6DJ2LP3FIV2QWK67324BUKY7B","download_json":"https://pith.science/pith/M6DJ2LP3FIV2QWK67324BUKY7B.json","view_paper":"https://pith.science/paper/M6DJ2LP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02482&json=true","fetch_graph":"https://pith.science/api/pith-number/M6DJ2LP3FIV2QWK67324BUKY7B/graph.json","fetch_events":"https://pith.science/api/pith-number/M6DJ2LP3FIV2QWK67324BUKY7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6DJ2LP3FIV2QWK67324BUKY7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6DJ2LP3FIV2QWK67324BUKY7B/action/storage_attestation","attest_author":"https://pith.science/pith/M6DJ2LP3FIV2QWK67324BUKY7B/action/author_attestation","sign_citation":"https://pith.science/pith/M6DJ2LP3FIV2QWK67324BUKY7B/action/citation_signature","submit_replication":"https://pith.science/pith/M6DJ2LP3FIV2QWK67324BUKY7B/action/replication_record"}},"created_at":"2026-07-05T08:39:53.141698+00:00","updated_at":"2026-07-05T08:39:53.141698+00:00"}