{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DAC33UYXZZC3YCCRKE3QITGWVH","short_pith_number":"pith:DAC33UYX","schema_version":"1.0","canonical_sha256":"1805bdd317ce45bc08515137044cd6a9fd20670a9f68496188ec98471506a8eb","source":{"kind":"arxiv","id":"2308.06909","version":1},"attestation_state":"computed","paper":{"title":"Hierarchy Flow For High-Fidelity Image-to-Image Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jinghuan Chen, Weichen Fan, Ziwei Liu","submitted_at":"2023-08-14T03:11:17Z","abstract_excerpt":"Image-to-image (I2I) translation comprises a wide spectrum of tasks. Here we divide this problem into three levels: strong-fidelity translation, normal-fidelity translation, and weak-fidelity translation, indicating the extent to which the content of the original image is preserved. Although existing methods achieve good performance in weak-fidelity translation, they fail to fully preserve the content in both strong- and normal-fidelity tasks, e.g. sim2real, style transfer and low-level vision. In this work, we propose Hierarchy Flow, a novel flow-based model to achieve better content preserva"},"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":"2308.06909","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-14T03:11:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"075f2c16cae627788fbc92f7c240131fcdc31f2a64dab7582fe515504971e670","abstract_canon_sha256":"0a756b0cab54ae2bd2435454119fb389e10af23528346daa7377330273239eec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:46.967506Z","signature_b64":"QwzqPFFGGkjpdUnYjzMLsb2/nuv048V4IcJsATbBdtOy2ABsZVAbmgFGLdtKzS35027zppt6yRtFjY2HMRKqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1805bdd317ce45bc08515137044cd6a9fd20670a9f68496188ec98471506a8eb","last_reissued_at":"2026-07-05T06:40:46.967043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:46.967043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchy Flow For High-Fidelity Image-to-Image Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jinghuan Chen, Weichen Fan, Ziwei Liu","submitted_at":"2023-08-14T03:11:17Z","abstract_excerpt":"Image-to-image (I2I) translation comprises a wide spectrum of tasks. Here we divide this problem into three levels: strong-fidelity translation, normal-fidelity translation, and weak-fidelity translation, indicating the extent to which the content of the original image is preserved. Although existing methods achieve good performance in weak-fidelity translation, they fail to fully preserve the content in both strong- and normal-fidelity tasks, e.g. sim2real, style transfer and low-level vision. In this work, we propose Hierarchy Flow, a novel flow-based model to achieve better content preserva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06909","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/2308.06909/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":"2308.06909","created_at":"2026-07-05T06:40:46.967100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06909v1","created_at":"2026-07-05T06:40:46.967100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06909","created_at":"2026-07-05T06:40:46.967100+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAC33UYXZZC3","created_at":"2026-07-05T06:40:46.967100+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAC33UYXZZC3YCCR","created_at":"2026-07-05T06:40:46.967100+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAC33UYX","created_at":"2026-07-05T06:40:46.967100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.21536","citing_title":"IHF-Harmony: Multi-Modality Magnetic Resonance Images Harmonization using Invertible Hierarchy Flow Model","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2508.21435","citing_title":"MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAC33UYXZZC3YCCRKE3QITGWVH","json":"https://pith.science/pith/DAC33UYXZZC3YCCRKE3QITGWVH.json","graph_json":"https://pith.science/api/pith-number/DAC33UYXZZC3YCCRKE3QITGWVH/graph.json","events_json":"https://pith.science/api/pith-number/DAC33UYXZZC3YCCRKE3QITGWVH/events.json","paper":"https://pith.science/paper/DAC33UYX"},"agent_actions":{"view_html":"https://pith.science/pith/DAC33UYXZZC3YCCRKE3QITGWVH","download_json":"https://pith.science/pith/DAC33UYXZZC3YCCRKE3QITGWVH.json","view_paper":"https://pith.science/paper/DAC33UYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06909&json=true","fetch_graph":"https://pith.science/api/pith-number/DAC33UYXZZC3YCCRKE3QITGWVH/graph.json","fetch_events":"https://pith.science/api/pith-number/DAC33UYXZZC3YCCRKE3QITGWVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAC33UYXZZC3YCCRKE3QITGWVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAC33UYXZZC3YCCRKE3QITGWVH/action/storage_attestation","attest_author":"https://pith.science/pith/DAC33UYXZZC3YCCRKE3QITGWVH/action/author_attestation","sign_citation":"https://pith.science/pith/DAC33UYXZZC3YCCRKE3QITGWVH/action/citation_signature","submit_replication":"https://pith.science/pith/DAC33UYXZZC3YCCRKE3QITGWVH/action/replication_record"}},"created_at":"2026-07-05T06:40:46.967100+00:00","updated_at":"2026-07-05T06:40:46.967100+00:00"}