{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ODGWZKSQKFLYO2XZSY2REGQVTX","short_pith_number":"pith:ODGWZKSQ","schema_version":"1.0","canonical_sha256":"70cd6caa505157876af99635121a159dd6ed74773975e755a32e289fd66b9c8f","source":{"kind":"arxiv","id":"2005.05207","version":1},"attestation_state":"computed","paper":{"title":"Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongjun Kim, Eungyeup Kim, Jaegul Choo, Jaehyuk Chang, Junsoo Lee, Yunsung Lee","submitted_at":"2020-05-11T15:52:50Z","abstract_excerpt":"This paper tackles the automatic colorization task of a sketch image given an already-colored reference image. Colorizing a sketch image is in high demand in comics, animation, and other content creation applications, but it suffers from information scarcity of a sketch image. To address this, a reference image can render the colorization process in a reliable and user-driven manner. However, it is difficult to prepare for a training data set that has a sufficient amount of semantically meaningful pairs of images as well as the ground truth for a colored image reflecting a given reference (e.g"},"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":"2005.05207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-11T15:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"ff990d1c19aa774b4518d689989ab7c31c53a2dfb08108f06850308f605d34d9","abstract_canon_sha256":"8b0fd37fdbaaa0676204188bbd96efb64e78d4d2f293e8dbaa5c8f08a0b0af6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:58.056903Z","signature_b64":"KfsLtfKicdLmnE8HW1mUxOQjc0SFDDmt28+fDmeY8Jp48WF8ntoaPzPrjGuX94CFsW8jK4asT2IZV0yvHPwkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70cd6caa505157876af99635121a159dd6ed74773975e755a32e289fd66b9c8f","last_reissued_at":"2026-07-05T01:01:58.056500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:58.056500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongjun Kim, Eungyeup Kim, Jaegul Choo, Jaehyuk Chang, Junsoo Lee, Yunsung Lee","submitted_at":"2020-05-11T15:52:50Z","abstract_excerpt":"This paper tackles the automatic colorization task of a sketch image given an already-colored reference image. Colorizing a sketch image is in high demand in comics, animation, and other content creation applications, but it suffers from information scarcity of a sketch image. To address this, a reference image can render the colorization process in a reliable and user-driven manner. However, it is difficult to prepare for a training data set that has a sufficient amount of semantically meaningful pairs of images as well as the ground truth for a colored image reflecting a given reference (e.g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05207","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/2005.05207/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":"2005.05207","created_at":"2026-07-05T01:01:58.056564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.05207v1","created_at":"2026-07-05T01:01:58.056564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05207","created_at":"2026-07-05T01:01:58.056564+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODGWZKSQKFLY","created_at":"2026-07-05T01:01:58.056564+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODGWZKSQKFLYO2XZ","created_at":"2026-07-05T01:01:58.056564+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODGWZKSQ","created_at":"2026-07-05T01:01:58.056564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01977","citing_title":"MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODGWZKSQKFLYO2XZSY2REGQVTX","json":"https://pith.science/pith/ODGWZKSQKFLYO2XZSY2REGQVTX.json","graph_json":"https://pith.science/api/pith-number/ODGWZKSQKFLYO2XZSY2REGQVTX/graph.json","events_json":"https://pith.science/api/pith-number/ODGWZKSQKFLYO2XZSY2REGQVTX/events.json","paper":"https://pith.science/paper/ODGWZKSQ"},"agent_actions":{"view_html":"https://pith.science/pith/ODGWZKSQKFLYO2XZSY2REGQVTX","download_json":"https://pith.science/pith/ODGWZKSQKFLYO2XZSY2REGQVTX.json","view_paper":"https://pith.science/paper/ODGWZKSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.05207&json=true","fetch_graph":"https://pith.science/api/pith-number/ODGWZKSQKFLYO2XZSY2REGQVTX/graph.json","fetch_events":"https://pith.science/api/pith-number/ODGWZKSQKFLYO2XZSY2REGQVTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODGWZKSQKFLYO2XZSY2REGQVTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODGWZKSQKFLYO2XZSY2REGQVTX/action/storage_attestation","attest_author":"https://pith.science/pith/ODGWZKSQKFLYO2XZSY2REGQVTX/action/author_attestation","sign_citation":"https://pith.science/pith/ODGWZKSQKFLYO2XZSY2REGQVTX/action/citation_signature","submit_replication":"https://pith.science/pith/ODGWZKSQKFLYO2XZSY2REGQVTX/action/replication_record"}},"created_at":"2026-07-05T01:01:58.056564+00:00","updated_at":"2026-07-05T01:01:58.056564+00:00"}