{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PBDEDK3XDEQJTSQ7UXAMMFIT6F","short_pith_number":"pith:PBDEDK3X","schema_version":"1.0","canonical_sha256":"784641ab77192099ca1fa5c0c61513f17a2589ca89aaf3134c6ededeb8ddfdc3","source":{"kind":"arxiv","id":"2412.11815","version":2},"attestation_state":"computed","paper":{"title":"ColorFlow: Retrieval-Augmented Image Sequence Colorization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Junhao Zhuang, Shiyi Zhang, Xuan Ju, Ying Shan, Yong Liu, Zhaoyang Zhang","submitted_at":"2024-12-16T14:32:49Z","abstract_excerpt":"Automatic black-and-white image sequence colorization while preserving character and object identity (ID) is a complex task with significant market demand, such as in cartoon or comic series colorization. Despite advancements in visual colorization using large-scale generative models like diffusion models, challenges with controllability and identity consistency persist, making current solutions unsuitable for industrial application.To address this, we propose ColorFlow, a three-stage diffusion-based framework tailored for image sequence colorization in industrial applications. Unlike existing"},"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":"2412.11815","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T14:32:49Z","cross_cats_sorted":[],"title_canon_sha256":"4f32aeb25a7490ff9056bc0f9403d3328d9bcac6ff540f564ddad721beadbfc2","abstract_canon_sha256":"60881d5043b79f5767799349fa934913701302388eabe3c07c0e12abe5a5bfa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:21.450442Z","signature_b64":"TKOYu3cSywW8iIT0x1j58lfSwPnfLTuaA1hU0zvpmIjIYgHbG1FD8ZYdTM8JABKnBzb6GucRl/U3y+vhyge5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"784641ab77192099ca1fa5c0c61513f17a2589ca89aaf3134c6ededeb8ddfdc3","last_reissued_at":"2026-07-05T10:58:21.449872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:21.449872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ColorFlow: Retrieval-Augmented Image Sequence Colorization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Junhao Zhuang, Shiyi Zhang, Xuan Ju, Ying Shan, Yong Liu, Zhaoyang Zhang","submitted_at":"2024-12-16T14:32:49Z","abstract_excerpt":"Automatic black-and-white image sequence colorization while preserving character and object identity (ID) is a complex task with significant market demand, such as in cartoon or comic series colorization. Despite advancements in visual colorization using large-scale generative models like diffusion models, challenges with controllability and identity consistency persist, making current solutions unsuitable for industrial application.To address this, we propose ColorFlow, a three-stage diffusion-based framework tailored for image sequence colorization in industrial applications. Unlike existing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11815","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/2412.11815/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":"2412.11815","created_at":"2026-07-05T10:58:21.449933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11815v2","created_at":"2026-07-05T10:58:21.449933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11815","created_at":"2026-07-05T10:58:21.449933+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBDEDK3XDEQJ","created_at":"2026-07-05T10:58:21.449933+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBDEDK3XDEQJTSQ7","created_at":"2026-07-05T10:58:21.449933+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBDEDK3X","created_at":"2026-07-05T10:58:21.449933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.18716","citing_title":"SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24625","citing_title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","ref_index":87,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBDEDK3XDEQJTSQ7UXAMMFIT6F","json":"https://pith.science/pith/PBDEDK3XDEQJTSQ7UXAMMFIT6F.json","graph_json":"https://pith.science/api/pith-number/PBDEDK3XDEQJTSQ7UXAMMFIT6F/graph.json","events_json":"https://pith.science/api/pith-number/PBDEDK3XDEQJTSQ7UXAMMFIT6F/events.json","paper":"https://pith.science/paper/PBDEDK3X"},"agent_actions":{"view_html":"https://pith.science/pith/PBDEDK3XDEQJTSQ7UXAMMFIT6F","download_json":"https://pith.science/pith/PBDEDK3XDEQJTSQ7UXAMMFIT6F.json","view_paper":"https://pith.science/paper/PBDEDK3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11815&json=true","fetch_graph":"https://pith.science/api/pith-number/PBDEDK3XDEQJTSQ7UXAMMFIT6F/graph.json","fetch_events":"https://pith.science/api/pith-number/PBDEDK3XDEQJTSQ7UXAMMFIT6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBDEDK3XDEQJTSQ7UXAMMFIT6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBDEDK3XDEQJTSQ7UXAMMFIT6F/action/storage_attestation","attest_author":"https://pith.science/pith/PBDEDK3XDEQJTSQ7UXAMMFIT6F/action/author_attestation","sign_citation":"https://pith.science/pith/PBDEDK3XDEQJTSQ7UXAMMFIT6F/action/citation_signature","submit_replication":"https://pith.science/pith/PBDEDK3XDEQJTSQ7UXAMMFIT6F/action/replication_record"}},"created_at":"2026-07-05T10:58:21.449933+00:00","updated_at":"2026-07-05T10:58:21.449933+00:00"}