{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S4DYHTWPJCNCEDIU6MUH6EV2BQ","short_pith_number":"pith:S4DYHTWP","schema_version":"1.0","canonical_sha256":"970783cecf489a220d14f3287f12ba0c15cddff8bb643195f34e38751e9111fc","source":{"kind":"arxiv","id":"2501.08332","version":1},"attestation_state":"computed","paper":{"title":"MangaNinja: Line Art Colorization with Precise Reference Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Ouyang, Jie Xiao, Kai Zhu, Ka Leong Cheng, Ping Luo, Qifeng Chen, Xi Chen, Yujun Shen, Yu Liu, Zhiheng Liu","submitted_at":"2025-01-14T18:59:55Z","abstract_excerpt":"Derived from diffusion models, MangaNinjia specializes in the task of reference-guided line art colorization. We incorporate two thoughtful designs to ensure precise character detail transcription, including a patch shuffling module to facilitate correspondence learning between the reference color image and the target line art, and a point-driven control scheme to enable fine-grained color matching. Experiments on a self-collected benchmark demonstrate the superiority of our model over current solutions in terms of precise colorization. We further showcase the potential of the proposed interac"},"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":"2501.08332","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T18:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"0e6de796b0ee275c1e6a3e92d86425b4baa53a12d44093bc02da7e3f496fffb6","abstract_canon_sha256":"ae29a1880151d6932a413cf7c72707bddfd3f7e3439f2118392710dc91d9edb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:59.584358Z","signature_b64":"g+RZfOHBnpBsFhthsJcbmmYWxmT6/2SyEkHDE95KY0pZRdWUdqL7KER17FGfIahmeAT37PcQG7NHW99HMYijAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"970783cecf489a220d14f3287f12ba0c15cddff8bb643195f34e38751e9111fc","last_reissued_at":"2026-07-05T10:00:59.583917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:59.583917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MangaNinja: Line Art Colorization with Precise Reference Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Ouyang, Jie Xiao, Kai Zhu, Ka Leong Cheng, Ping Luo, Qifeng Chen, Xi Chen, Yujun Shen, Yu Liu, Zhiheng Liu","submitted_at":"2025-01-14T18:59:55Z","abstract_excerpt":"Derived from diffusion models, MangaNinjia specializes in the task of reference-guided line art colorization. We incorporate two thoughtful designs to ensure precise character detail transcription, including a patch shuffling module to facilitate correspondence learning between the reference color image and the target line art, and a point-driven control scheme to enable fine-grained color matching. Experiments on a self-collected benchmark demonstrate the superiority of our model over current solutions in terms of precise colorization. We further showcase the potential of the proposed interac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08332","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/2501.08332/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":"2501.08332","created_at":"2026-07-05T10:00:59.583973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08332v1","created_at":"2026-07-05T10:00:59.583973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08332","created_at":"2026-07-05T10:00:59.583973+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4DYHTWPJCNC","created_at":"2026-07-05T10:00:59.583973+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4DYHTWPJCNCEDIU","created_at":"2026-07-05T10:00:59.583973+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4DYHTWP","created_at":"2026-07-05T10:00:59.583973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20368","citing_title":"MagicAnime: A Hierarchically Annotated, Multimodal and Multitasking Dataset with Benchmarks for Cartoon Animation Generation","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4DYHTWPJCNCEDIU6MUH6EV2BQ","json":"https://pith.science/pith/S4DYHTWPJCNCEDIU6MUH6EV2BQ.json","graph_json":"https://pith.science/api/pith-number/S4DYHTWPJCNCEDIU6MUH6EV2BQ/graph.json","events_json":"https://pith.science/api/pith-number/S4DYHTWPJCNCEDIU6MUH6EV2BQ/events.json","paper":"https://pith.science/paper/S4DYHTWP"},"agent_actions":{"view_html":"https://pith.science/pith/S4DYHTWPJCNCEDIU6MUH6EV2BQ","download_json":"https://pith.science/pith/S4DYHTWPJCNCEDIU6MUH6EV2BQ.json","view_paper":"https://pith.science/paper/S4DYHTWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08332&json=true","fetch_graph":"https://pith.science/api/pith-number/S4DYHTWPJCNCEDIU6MUH6EV2BQ/graph.json","fetch_events":"https://pith.science/api/pith-number/S4DYHTWPJCNCEDIU6MUH6EV2BQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4DYHTWPJCNCEDIU6MUH6EV2BQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4DYHTWPJCNCEDIU6MUH6EV2BQ/action/storage_attestation","attest_author":"https://pith.science/pith/S4DYHTWPJCNCEDIU6MUH6EV2BQ/action/author_attestation","sign_citation":"https://pith.science/pith/S4DYHTWPJCNCEDIU6MUH6EV2BQ/action/citation_signature","submit_replication":"https://pith.science/pith/S4DYHTWPJCNCEDIU6MUH6EV2BQ/action/replication_record"}},"created_at":"2026-07-05T10:00:59.583973+00:00","updated_at":"2026-07-05T10:00:59.583973+00:00"}