{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FIS3QYUS4XGJQTJ3GO2BYGR4ST","short_pith_number":"pith:FIS3QYUS","schema_version":"1.0","canonical_sha256":"2a25b86292e5cc984d3b33b41c1a3c94d509004607f65d2b16799c779fb938e1","source":{"kind":"arxiv","id":"2103.16241","version":1},"attestation_state":"computed","paper":{"title":"Improving robustness against common corruptions with frequency biased models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Thomas Brox, Tonmoy Saikia","submitted_at":"2021-03-30T10:44:50Z","abstract_excerpt":"CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real scenarios, unexpected distortions, such as random noise, compression artefacts, or weather distortions are common phenomena. Improving performance on corrupted images must not result in degraded i.i.d performance - a challenge faced by many state-of-the-art robust approaches. Image corruption types have different characteristics in the frequency spectrum and would benefit from a targeted type of data augmentation, whic"},"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":"2103.16241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T10:44:50Z","cross_cats_sorted":[],"title_canon_sha256":"9117e1dab09782041b32c833e524e2db9c36fbd16eb5ed6f6244be38325205d7","abstract_canon_sha256":"1e0d96a93a903d4b4d66b92458ebff0885d3104de30790a8879906d899609554"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:49.820717Z","signature_b64":"22O2ys43p0xDZzPfc2H7cSCF5UDkXX3mtYS4R4DgWQ8HHz0Y2v0keWrgENkq/OQyhvTmHl7+JJySYiLpgUjqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a25b86292e5cc984d3b33b41c1a3c94d509004607f65d2b16799c779fb938e1","last_reissued_at":"2026-07-05T02:27:49.820247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:49.820247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving robustness against common corruptions with frequency biased models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Thomas Brox, Tonmoy Saikia","submitted_at":"2021-03-30T10:44:50Z","abstract_excerpt":"CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real scenarios, unexpected distortions, such as random noise, compression artefacts, or weather distortions are common phenomena. Improving performance on corrupted images must not result in degraded i.i.d performance - a challenge faced by many state-of-the-art robust approaches. Image corruption types have different characteristics in the frequency spectrum and would benefit from a targeted type of data augmentation, whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16241","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/2103.16241/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":"2103.16241","created_at":"2026-07-05T02:27:49.820325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.16241v1","created_at":"2026-07-05T02:27:49.820325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16241","created_at":"2026-07-05T02:27:49.820325+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIS3QYUS4XGJ","created_at":"2026-07-05T02:27:49.820325+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIS3QYUS4XGJQTJ3","created_at":"2026-07-05T02:27:49.820325+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIS3QYUS","created_at":"2026-07-05T02:27:49.820325+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/FIS3QYUS4XGJQTJ3GO2BYGR4ST","json":"https://pith.science/pith/FIS3QYUS4XGJQTJ3GO2BYGR4ST.json","graph_json":"https://pith.science/api/pith-number/FIS3QYUS4XGJQTJ3GO2BYGR4ST/graph.json","events_json":"https://pith.science/api/pith-number/FIS3QYUS4XGJQTJ3GO2BYGR4ST/events.json","paper":"https://pith.science/paper/FIS3QYUS"},"agent_actions":{"view_html":"https://pith.science/pith/FIS3QYUS4XGJQTJ3GO2BYGR4ST","download_json":"https://pith.science/pith/FIS3QYUS4XGJQTJ3GO2BYGR4ST.json","view_paper":"https://pith.science/paper/FIS3QYUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.16241&json=true","fetch_graph":"https://pith.science/api/pith-number/FIS3QYUS4XGJQTJ3GO2BYGR4ST/graph.json","fetch_events":"https://pith.science/api/pith-number/FIS3QYUS4XGJQTJ3GO2BYGR4ST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIS3QYUS4XGJQTJ3GO2BYGR4ST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIS3QYUS4XGJQTJ3GO2BYGR4ST/action/storage_attestation","attest_author":"https://pith.science/pith/FIS3QYUS4XGJQTJ3GO2BYGR4ST/action/author_attestation","sign_citation":"https://pith.science/pith/FIS3QYUS4XGJQTJ3GO2BYGR4ST/action/citation_signature","submit_replication":"https://pith.science/pith/FIS3QYUS4XGJQTJ3GO2BYGR4ST/action/replication_record"}},"created_at":"2026-07-05T02:27:49.820325+00:00","updated_at":"2026-07-05T02:27:49.820325+00:00"}