{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6RGGXSV7M3SBTBY2IF3ULU67NZ","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":"d036fa30b4b53796efe78b00f3d0428bcd6e1eb8071150386fc85b3a6ce73df4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T15:24:12Z","title_canon_sha256":"cd7fc50574e9ef005511766b077ef5a4d9b9f47704037fb190a555a693eddb76"},"schema_version":"1.0","source":{"id":"2412.07589","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07589","created_at":"2026-07-05T10:30:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07589v2","created_at":"2026-07-05T10:30:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07589","created_at":"2026-07-05T10:30:27Z"},{"alias_kind":"pith_short_12","alias_value":"6RGGXSV7M3SB","created_at":"2026-07-05T10:30:27Z"},{"alias_kind":"pith_short_16","alias_value":"6RGGXSV7M3SBTBY2","created_at":"2026-07-05T10:30:27Z"},{"alias_kind":"pith_short_8","alias_value":"6RGGXSV7","created_at":"2026-07-05T10:30:27Z"}],"graph_snapshots":[{"event_id":"sha256:57500bd04682433dfeb3a72b9c1fd362e8fee81e8f865f0d342867978da998df","target":"graph","created_at":"2026-07-05T10:30:27Z","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/2412.07589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Story visualization, the task of creating visual narratives from textual descriptions, has seen progress with text-to-image generation models. However, these models often lack effective control over character appearances and interactions, particularly in multi-character scenes. To address these limitations, we propose a new task: \\textbf{customized manga generation} and introduce \\textbf{DiffSensei}, an innovative framework specifically designed for generating manga with dynamic multi-character control. DiffSensei integrates a diffusion-based image generator with a multimodal large language mo","authors_text":"Chao Tang, Jianzong Wu, Jingbo Wang, Xiangtai Li, Yanhong Zeng, Yunhai Tong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T15:24:12Z","title":"DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07589","kind":"arxiv","version":2},"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":"sha256:5514c6b0a8b39e73743f0535d9c52666244d0307f6b8ae0fd459b0de5698d276","target":"record","created_at":"2026-07-05T10:30:27Z","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":"d036fa30b4b53796efe78b00f3d0428bcd6e1eb8071150386fc85b3a6ce73df4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T15:24:12Z","title_canon_sha256":"cd7fc50574e9ef005511766b077ef5a4d9b9f47704037fb190a555a693eddb76"},"schema_version":"1.0","source":{"id":"2412.07589","kind":"arxiv","version":2}},"canonical_sha256":"f44c6bcabf66e419871a417745d3df6e4c0fff66fdd6246822af532b05cefc17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f44c6bcabf66e419871a417745d3df6e4c0fff66fdd6246822af532b05cefc17","first_computed_at":"2026-07-05T10:30:27.991894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:27.991894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"agEPZfw5cgpQhlmH4DLZxTvqho0RY5rmgZQ81+Ov86knLz3BgAi4rFOPeubbOjf2NGZA/5G0EKAZXGWLUEpmBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:27.992402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07589","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5514c6b0a8b39e73743f0535d9c52666244d0307f6b8ae0fd459b0de5698d276","sha256:57500bd04682433dfeb3a72b9c1fd362e8fee81e8f865f0d342867978da998df"],"state_sha256":"9df6cab09811a583fbd84ab455bdc57bc627c46efc210b2b689ede5928ec6b0d"}