{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NUZW3GHWHGHKWNLT4S56HS5CW6","short_pith_number":"pith:NUZW3GHW","schema_version":"1.0","canonical_sha256":"6d336d98f6398eab3573e4bbe3cba2b79cd0381546beec3387c8b1b8a51cd283","source":{"kind":"arxiv","id":"1908.08239","version":1},"attestation_state":"computed","paper":{"title":"Progressive Face Super-Resolution via Attention to Facial Landmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dae-shik Kim, Deokyun Kim, Gihyun Kwon, Minseon Kim","submitted_at":"2019-08-22T07:50:41Z","abstract_excerpt":"Face Super-Resolution (SR) is a subfield of the SR domain that specifically targets the reconstruction of face images. The main challenge of face SR is to restore essential facial features without distortion. We propose a novel face SR method that generates photo-realistic 8x super-resolved face images with fully retained facial details. To that end, we adopt a progressive training method, which allows stable training by splitting the network into successive steps, each producing output with a progressively higher resolution. We also propose a novel facial attention loss and apply it at each s"},"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":"1908.08239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-22T07:50:41Z","cross_cats_sorted":[],"title_canon_sha256":"9ca7601735a8cc4e2465fdb1d6a63d0fe0995a8eb3a2846523039a1d33a8e4d9","abstract_canon_sha256":"3c1238735d63988bab6f62776bba202e7e3c425a59c7338c22831b02a8b525a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:10.943077Z","signature_b64":"EYq9cVIU/Gj2vgKb366Hiz1eIVUTGRQ7Q2p0uzvAZerw2XKMh9YyRjIxuJPQZHSjVePeJG3aW5wdAor/bxywCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d336d98f6398eab3573e4bbe3cba2b79cd0381546beec3387c8b1b8a51cd283","last_reissued_at":"2026-07-04T23:59:10.942643Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:10.942643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Face Super-Resolution via Attention to Facial Landmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dae-shik Kim, Deokyun Kim, Gihyun Kwon, Minseon Kim","submitted_at":"2019-08-22T07:50:41Z","abstract_excerpt":"Face Super-Resolution (SR) is a subfield of the SR domain that specifically targets the reconstruction of face images. The main challenge of face SR is to restore essential facial features without distortion. We propose a novel face SR method that generates photo-realistic 8x super-resolved face images with fully retained facial details. To that end, we adopt a progressive training method, which allows stable training by splitting the network into successive steps, each producing output with a progressively higher resolution. We also propose a novel facial attention loss and apply it at each s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08239","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/1908.08239/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":"1908.08239","created_at":"2026-07-04T23:59:10.942701+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.08239v1","created_at":"2026-07-04T23:59:10.942701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08239","created_at":"2026-07-04T23:59:10.942701+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUZW3GHWHGHK","created_at":"2026-07-04T23:59:10.942701+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUZW3GHWHGHKWNLT","created_at":"2026-07-04T23:59:10.942701+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUZW3GHW","created_at":"2026-07-04T23:59:10.942701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10943","citing_title":"Robust ID-Specific Face Restoration via Alignment Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NUZW3GHWHGHKWNLT4S56HS5CW6","json":"https://pith.science/pith/NUZW3GHWHGHKWNLT4S56HS5CW6.json","graph_json":"https://pith.science/api/pith-number/NUZW3GHWHGHKWNLT4S56HS5CW6/graph.json","events_json":"https://pith.science/api/pith-number/NUZW3GHWHGHKWNLT4S56HS5CW6/events.json","paper":"https://pith.science/paper/NUZW3GHW"},"agent_actions":{"view_html":"https://pith.science/pith/NUZW3GHWHGHKWNLT4S56HS5CW6","download_json":"https://pith.science/pith/NUZW3GHWHGHKWNLT4S56HS5CW6.json","view_paper":"https://pith.science/paper/NUZW3GHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.08239&json=true","fetch_graph":"https://pith.science/api/pith-number/NUZW3GHWHGHKWNLT4S56HS5CW6/graph.json","fetch_events":"https://pith.science/api/pith-number/NUZW3GHWHGHKWNLT4S56HS5CW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUZW3GHWHGHKWNLT4S56HS5CW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUZW3GHWHGHKWNLT4S56HS5CW6/action/storage_attestation","attest_author":"https://pith.science/pith/NUZW3GHWHGHKWNLT4S56HS5CW6/action/author_attestation","sign_citation":"https://pith.science/pith/NUZW3GHWHGHKWNLT4S56HS5CW6/action/citation_signature","submit_replication":"https://pith.science/pith/NUZW3GHWHGHKWNLT4S56HS5CW6/action/replication_record"}},"created_at":"2026-07-04T23:59:10.942701+00:00","updated_at":"2026-07-04T23:59:10.942701+00:00"}