{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GJBBHH2773TCKM2WFCJEWTEERY","short_pith_number":"pith:GJBBHH27","schema_version":"1.0","canonical_sha256":"3242139f5ffee625335628924b4c848e2fcbff276d107aa5718e32bc9e24b3f0","source":{"kind":"arxiv","id":"2403.17083","version":2},"attestation_state":"computed","paper":{"title":"A Study in Dataset Pruning for Image Super-Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.GR","cs.LG"],"primary_cat":"eess.IV","authors_text":"Andreas Dengel, Brian B. Moser, Federico Raue","submitted_at":"2024-03-25T18:16:34Z","abstract_excerpt":"In image Super-Resolution (SR), relying on large datasets for training is a double-edged sword. While offering rich training material, they also demand substantial computational and storage resources. In this work, we analyze dataset pruning to solve these challenges. We introduce a novel approach that reduces a dataset to a core-set of training samples, selected based on their loss values as determined by a simple pre-trained SR model. By focusing the training on just 50\\% of the original dataset, specifically on the samples characterized by the highest loss values, we achieve results compara"},"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":"2403.17083","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-03-25T18:16:34Z","cross_cats_sorted":["cs.AI","cs.CV","cs.GR","cs.LG"],"title_canon_sha256":"53a2ad8ff56ecbc40d3f651e766b0b39a9c809a06293a940a01584b23c5125d0","abstract_canon_sha256":"84e15f28176275ae96fd821102d06f05819826a9a60c4f906e0588eb63558fb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:00.077711Z","signature_b64":"Kk5JUViAgcI1VWuzwONVBsiAvlZO5kOGAu/8UHFRvuXKFqSEEZzdRkpRVL6kjzQqIIREyY4/ZRe8ebmBpTORDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3242139f5ffee625335628924b4c848e2fcbff276d107aa5718e32bc9e24b3f0","last_reissued_at":"2026-07-05T08:29:00.077228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:00.077228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Study in Dataset Pruning for Image Super-Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.GR","cs.LG"],"primary_cat":"eess.IV","authors_text":"Andreas Dengel, Brian B. Moser, Federico Raue","submitted_at":"2024-03-25T18:16:34Z","abstract_excerpt":"In image Super-Resolution (SR), relying on large datasets for training is a double-edged sword. While offering rich training material, they also demand substantial computational and storage resources. In this work, we analyze dataset pruning to solve these challenges. We introduce a novel approach that reduces a dataset to a core-set of training samples, selected based on their loss values as determined by a simple pre-trained SR model. By focusing the training on just 50\\% of the original dataset, specifically on the samples characterized by the highest loss values, we achieve results compara"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17083","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/2403.17083/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":"2403.17083","created_at":"2026-07-05T08:29:00.077289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17083v2","created_at":"2026-07-05T08:29:00.077289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17083","created_at":"2026-07-05T08:29:00.077289+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJBBHH2773TC","created_at":"2026-07-05T08:29:00.077289+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJBBHH2773TCKM2W","created_at":"2026-07-05T08:29:00.077289+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJBBHH27","created_at":"2026-07-05T08:29:00.077289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17040","citing_title":"Generalizing Large Language Model Usability Across Resource-Constrained","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJBBHH2773TCKM2WFCJEWTEERY","json":"https://pith.science/pith/GJBBHH2773TCKM2WFCJEWTEERY.json","graph_json":"https://pith.science/api/pith-number/GJBBHH2773TCKM2WFCJEWTEERY/graph.json","events_json":"https://pith.science/api/pith-number/GJBBHH2773TCKM2WFCJEWTEERY/events.json","paper":"https://pith.science/paper/GJBBHH27"},"agent_actions":{"view_html":"https://pith.science/pith/GJBBHH2773TCKM2WFCJEWTEERY","download_json":"https://pith.science/pith/GJBBHH2773TCKM2WFCJEWTEERY.json","view_paper":"https://pith.science/paper/GJBBHH27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17083&json=true","fetch_graph":"https://pith.science/api/pith-number/GJBBHH2773TCKM2WFCJEWTEERY/graph.json","fetch_events":"https://pith.science/api/pith-number/GJBBHH2773TCKM2WFCJEWTEERY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJBBHH2773TCKM2WFCJEWTEERY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJBBHH2773TCKM2WFCJEWTEERY/action/storage_attestation","attest_author":"https://pith.science/pith/GJBBHH2773TCKM2WFCJEWTEERY/action/author_attestation","sign_citation":"https://pith.science/pith/GJBBHH2773TCKM2WFCJEWTEERY/action/citation_signature","submit_replication":"https://pith.science/pith/GJBBHH2773TCKM2WFCJEWTEERY/action/replication_record"}},"created_at":"2026-07-05T08:29:00.077289+00:00","updated_at":"2026-07-05T08:29:00.077289+00:00"}