{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XMDBFPVSSYOVFWSWINUBSHN6AA","short_pith_number":"pith:XMDBFPVS","schema_version":"1.0","canonical_sha256":"bb0612beb2961d52da564368191dbe00337f0b2e27d4d045cbe57ba066d79e36","source":{"kind":"arxiv","id":"2508.09709","version":1},"attestation_state":"computed","paper":{"title":"MangaDiT: Reference-Guided Line Art Colorization with Hierarchical Attention in Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiafeng Mao, Kento Masui, Qianru Qiu, Xueting Wang","submitted_at":"2025-08-13T11:02:11Z","abstract_excerpt":"Recent advances in diffusion models have significantly improved the performance of reference-guided line art colorization. However, existing methods still struggle with region-level color consistency, especially when the reference and target images differ in character pose or motion. Instead of relying on external matching annotations between the reference and target, we propose to discover semantic correspondences implicitly through internal attention mechanisms. In this paper, we present MangaDiT, a powerful model for reference-guided line art colorization based on Diffusion Transformers (Di"},"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":"2508.09709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-13T11:02:11Z","cross_cats_sorted":[],"title_canon_sha256":"ecf9402c1df5dccb1ad9700407c01c77b7efb503a833fd2275f3e76d0148ba59","abstract_canon_sha256":"c767a359b379a906cb9e12717f826208f4048471b0d20ce4cbaebf383da33932"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:20.318223Z","signature_b64":"HO1/Q+zlZZxS065B8R0/PHkcZhlKZ2mxPZuJXmTMkCh7w4HwKL+jq27x/e4SHqAltGTuHxMogESkMcsl6OIYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb0612beb2961d52da564368191dbe00337f0b2e27d4d045cbe57ba066d79e36","last_reissued_at":"2026-07-05T11:53:20.317641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:20.317641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MangaDiT: Reference-Guided Line Art Colorization with Hierarchical Attention in Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiafeng Mao, Kento Masui, Qianru Qiu, Xueting Wang","submitted_at":"2025-08-13T11:02:11Z","abstract_excerpt":"Recent advances in diffusion models have significantly improved the performance of reference-guided line art colorization. However, existing methods still struggle with region-level color consistency, especially when the reference and target images differ in character pose or motion. Instead of relying on external matching annotations between the reference and target, we propose to discover semantic correspondences implicitly through internal attention mechanisms. In this paper, we present MangaDiT, a powerful model for reference-guided line art colorization based on Diffusion Transformers (Di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09709","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/2508.09709/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":"2508.09709","created_at":"2026-07-05T11:53:20.317706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09709v1","created_at":"2026-07-05T11:53:20.317706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09709","created_at":"2026-07-05T11:53:20.317706+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMDBFPVSSYOV","created_at":"2026-07-05T11:53:20.317706+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMDBFPVSSYOVFWSW","created_at":"2026-07-05T11:53:20.317706+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMDBFPVS","created_at":"2026-07-05T11:53:20.317706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMDBFPVSSYOVFWSWINUBSHN6AA","json":"https://pith.science/pith/XMDBFPVSSYOVFWSWINUBSHN6AA.json","graph_json":"https://pith.science/api/pith-number/XMDBFPVSSYOVFWSWINUBSHN6AA/graph.json","events_json":"https://pith.science/api/pith-number/XMDBFPVSSYOVFWSWINUBSHN6AA/events.json","paper":"https://pith.science/paper/XMDBFPVS"},"agent_actions":{"view_html":"https://pith.science/pith/XMDBFPVSSYOVFWSWINUBSHN6AA","download_json":"https://pith.science/pith/XMDBFPVSSYOVFWSWINUBSHN6AA.json","view_paper":"https://pith.science/paper/XMDBFPVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09709&json=true","fetch_graph":"https://pith.science/api/pith-number/XMDBFPVSSYOVFWSWINUBSHN6AA/graph.json","fetch_events":"https://pith.science/api/pith-number/XMDBFPVSSYOVFWSWINUBSHN6AA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMDBFPVSSYOVFWSWINUBSHN6AA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMDBFPVSSYOVFWSWINUBSHN6AA/action/storage_attestation","attest_author":"https://pith.science/pith/XMDBFPVSSYOVFWSWINUBSHN6AA/action/author_attestation","sign_citation":"https://pith.science/pith/XMDBFPVSSYOVFWSWINUBSHN6AA/action/citation_signature","submit_replication":"https://pith.science/pith/XMDBFPVSSYOVFWSWINUBSHN6AA/action/replication_record"}},"created_at":"2026-07-05T11:53:20.317706+00:00","updated_at":"2026-07-05T11:53:20.317706+00:00"}