{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5WAANWMFD7PYEQN7TFNHOIYDOG","short_pith_number":"pith:5WAANWMF","schema_version":"1.0","canonical_sha256":"ed8006d9851fdf8241bf995a772303719c36846bd183ba6f58f4206cf625c654","source":{"kind":"arxiv","id":"2108.10335","version":2},"attestation_state":"computed","paper":{"title":"edge-SR: Super-Resolution For The Masses","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.IV","eess.SP"],"primary_cat":"cs.CV","authors_text":"Pablo Navarrete Michelini, Xingqun Jiang, Yunhua Lu","submitted_at":"2021-08-23T18:00:19Z","abstract_excerpt":"Classic image scaling (e.g. bicubic) can be seen as one convolutional layer and a single upscaling filter. Its implementation is ubiquitous in all display devices and image processing software. In the last decade deep learning systems have been introduced for the task of image super-resolution (SR), using several convolutional layers and numerous filters. These methods have taken over the benchmarks of image quality for upscaling tasks. Would it be possible to replace classic upscalers with deep learning architectures on edge devices such as display panels, tablets, laptop computers, etc.? On "},"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":"2108.10335","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-23T18:00:19Z","cross_cats_sorted":["cs.LG","eess.IV","eess.SP"],"title_canon_sha256":"b6de9ff8a15f39a5ce639a0a14e99da11cae812c9e3e9ef5d1a984c0219f25f0","abstract_canon_sha256":"e895aed0a5483a70ff54122ac93c9323afafea254efb3c1a7fb6e261eaa3dd0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:58.585233Z","signature_b64":"RDr6XHtpUwOPaVTeoEIJIbqAdjRXbAxZywGQskUiljEM107b0fCYVe9PbZa+bWi2kKGQCPPWW6jecnWWWkFxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed8006d9851fdf8241bf995a772303719c36846bd183ba6f58f4206cf625c654","last_reissued_at":"2026-07-05T03:22:58.584733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:58.584733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"edge-SR: Super-Resolution For The Masses","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.IV","eess.SP"],"primary_cat":"cs.CV","authors_text":"Pablo Navarrete Michelini, Xingqun Jiang, Yunhua Lu","submitted_at":"2021-08-23T18:00:19Z","abstract_excerpt":"Classic image scaling (e.g. bicubic) can be seen as one convolutional layer and a single upscaling filter. Its implementation is ubiquitous in all display devices and image processing software. In the last decade deep learning systems have been introduced for the task of image super-resolution (SR), using several convolutional layers and numerous filters. These methods have taken over the benchmarks of image quality for upscaling tasks. Would it be possible to replace classic upscalers with deep learning architectures on edge devices such as display panels, tablets, laptop computers, etc.? On "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.10335","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/2108.10335/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":"2108.10335","created_at":"2026-07-05T03:22:58.584794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.10335v2","created_at":"2026-07-05T03:22:58.584794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.10335","created_at":"2026-07-05T03:22:58.584794+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WAANWMFD7PY","created_at":"2026-07-05T03:22:58.584794+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WAANWMFD7PYEQN7","created_at":"2026-07-05T03:22:58.584794+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WAANWMF","created_at":"2026-07-05T03:22:58.584794+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/5WAANWMFD7PYEQN7TFNHOIYDOG","json":"https://pith.science/pith/5WAANWMFD7PYEQN7TFNHOIYDOG.json","graph_json":"https://pith.science/api/pith-number/5WAANWMFD7PYEQN7TFNHOIYDOG/graph.json","events_json":"https://pith.science/api/pith-number/5WAANWMFD7PYEQN7TFNHOIYDOG/events.json","paper":"https://pith.science/paper/5WAANWMF"},"agent_actions":{"view_html":"https://pith.science/pith/5WAANWMFD7PYEQN7TFNHOIYDOG","download_json":"https://pith.science/pith/5WAANWMFD7PYEQN7TFNHOIYDOG.json","view_paper":"https://pith.science/paper/5WAANWMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.10335&json=true","fetch_graph":"https://pith.science/api/pith-number/5WAANWMFD7PYEQN7TFNHOIYDOG/graph.json","fetch_events":"https://pith.science/api/pith-number/5WAANWMFD7PYEQN7TFNHOIYDOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WAANWMFD7PYEQN7TFNHOIYDOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WAANWMFD7PYEQN7TFNHOIYDOG/action/storage_attestation","attest_author":"https://pith.science/pith/5WAANWMFD7PYEQN7TFNHOIYDOG/action/author_attestation","sign_citation":"https://pith.science/pith/5WAANWMFD7PYEQN7TFNHOIYDOG/action/citation_signature","submit_replication":"https://pith.science/pith/5WAANWMFD7PYEQN7TFNHOIYDOG/action/replication_record"}},"created_at":"2026-07-05T03:22:58.584794+00:00","updated_at":"2026-07-05T03:22:58.584794+00:00"}