{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FAWHKPBGWUZDDRM5JC4DC2PN2I","short_pith_number":"pith:FAWHKPBG","schema_version":"1.0","canonical_sha256":"282c753c26b53231c59d48b83169edd20a5ee85109622e0033d3119f8adad01d","source":{"kind":"arxiv","id":"2201.10084","version":2},"attestation_state":"computed","paper":{"title":"Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Cheng, Xiangyu He","submitted_at":"2022-01-25T04:04:44Z","abstract_excerpt":"Super-resolution as an ill-posed problem has many high-resolution candidates for a low-resolution input. However, the popular $\\ell_1$ loss used to best fit the given HR image fails to consider this fundamental property of non-uniqueness in image restoration. In this work, we fix the missing piece in $\\ell_1$ loss by formulating super-resolution with neural networks as a probabilistic model. It shows that $\\ell_1$ loss is equivalent to a degraded likelihood function that removes the randomness from the learning process. By introducing a data-adaptive random variable, we present a new objective"},"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":"2201.10084","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-25T04:04:44Z","cross_cats_sorted":[],"title_canon_sha256":"47ea9eefb233c85d693b0c6779134980460455a7c1e2f46d7edbd467e60e0bab","abstract_canon_sha256":"91c144567cfe38559f0462219d9d82dbd7825be6fe8067c20ba3375ca108fa8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:02.050485Z","signature_b64":"CepjXUwutBnk+ODs68usdJIgFLeUaYei0YQJLxA0R3h7Wku6bPhoXmS4/EFPiuw84tNSjT8Oun87gBCpwaBpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"282c753c26b53231c59d48b83169edd20a5ee85109622e0033d3119f8adad01d","last_reissued_at":"2026-07-05T05:59:02.050047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:02.050047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Cheng, Xiangyu He","submitted_at":"2022-01-25T04:04:44Z","abstract_excerpt":"Super-resolution as an ill-posed problem has many high-resolution candidates for a low-resolution input. However, the popular $\\ell_1$ loss used to best fit the given HR image fails to consider this fundamental property of non-uniqueness in image restoration. In this work, we fix the missing piece in $\\ell_1$ loss by formulating super-resolution with neural networks as a probabilistic model. It shows that $\\ell_1$ loss is equivalent to a degraded likelihood function that removes the randomness from the learning process. By introducing a data-adaptive random variable, we present a new objective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10084","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/2201.10084/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":"2201.10084","created_at":"2026-07-05T05:59:02.050102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.10084v2","created_at":"2026-07-05T05:59:02.050102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10084","created_at":"2026-07-05T05:59:02.050102+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAWHKPBGWUZD","created_at":"2026-07-05T05:59:02.050102+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAWHKPBGWUZDDRM5","created_at":"2026-07-05T05:59:02.050102+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAWHKPBG","created_at":"2026-07-05T05:59:02.050102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22353","citing_title":"Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAWHKPBGWUZDDRM5JC4DC2PN2I","json":"https://pith.science/pith/FAWHKPBGWUZDDRM5JC4DC2PN2I.json","graph_json":"https://pith.science/api/pith-number/FAWHKPBGWUZDDRM5JC4DC2PN2I/graph.json","events_json":"https://pith.science/api/pith-number/FAWHKPBGWUZDDRM5JC4DC2PN2I/events.json","paper":"https://pith.science/paper/FAWHKPBG"},"agent_actions":{"view_html":"https://pith.science/pith/FAWHKPBGWUZDDRM5JC4DC2PN2I","download_json":"https://pith.science/pith/FAWHKPBGWUZDDRM5JC4DC2PN2I.json","view_paper":"https://pith.science/paper/FAWHKPBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.10084&json=true","fetch_graph":"https://pith.science/api/pith-number/FAWHKPBGWUZDDRM5JC4DC2PN2I/graph.json","fetch_events":"https://pith.science/api/pith-number/FAWHKPBGWUZDDRM5JC4DC2PN2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAWHKPBGWUZDDRM5JC4DC2PN2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAWHKPBGWUZDDRM5JC4DC2PN2I/action/storage_attestation","attest_author":"https://pith.science/pith/FAWHKPBGWUZDDRM5JC4DC2PN2I/action/author_attestation","sign_citation":"https://pith.science/pith/FAWHKPBGWUZDDRM5JC4DC2PN2I/action/citation_signature","submit_replication":"https://pith.science/pith/FAWHKPBGWUZDDRM5JC4DC2PN2I/action/replication_record"}},"created_at":"2026-07-05T05:59:02.050102+00:00","updated_at":"2026-07-05T05:59:02.050102+00:00"}