{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:AAHRJHDNO544N2SQA24H6TTHIG","short_pith_number":"pith:AAHRJHDN","schema_version":"1.0","canonical_sha256":"000f149c6d7779c6ea5006b87f4e6741ba6e91dfb492fe6091b851aff169a10d","source":{"kind":"arxiv","id":"1611.05760","version":2},"attestation_state":"computed","paper":{"title":"Examining the Impact of Blur on Recognition by Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayan Chakrabarti, Gregory Shakhnarovich, Igor Vasiljevic","submitted_at":"2016-11-17T16:17:10Z","abstract_excerpt":"State-of-the-art algorithms for many semantic visual tasks are based on the use of convolutional neural networks. These networks are commonly trained, and evaluated, on large annotated datasets of artifact-free high-quality images. In this paper, we investigate the effect of one such artifact that is quite common in natural capture settings: optical blur. We show that standard network models, trained only on high-quality images, suffer a significant degradation in performance when applied to those degraded by blur due to defocus, or subject or camera motion. We investigate the extent to which "},"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":"1611.05760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-17T16:17:10Z","cross_cats_sorted":[],"title_canon_sha256":"35ee807feb55fd761930d43919051c88926626ee0bd6e54d509c53d09c0eecb0","abstract_canon_sha256":"a07002417f0ba538e5d00140da31e05c239d6bd98961a347c761bca3fe7a1c19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:29.968742Z","signature_b64":"K/kBc+AapoAX8RcCKCH2f8r6YVOfl2bnlNU18zrhS07qx9lLahGHf8S2TWjWes7tUKwieb20XkzSLPZlR7X6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"000f149c6d7779c6ea5006b87f4e6741ba6e91dfb492fe6091b851aff169a10d","last_reissued_at":"2026-05-18T00:43:29.968089Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:29.968089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Examining the Impact of Blur on Recognition by Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayan Chakrabarti, Gregory Shakhnarovich, Igor Vasiljevic","submitted_at":"2016-11-17T16:17:10Z","abstract_excerpt":"State-of-the-art algorithms for many semantic visual tasks are based on the use of convolutional neural networks. These networks are commonly trained, and evaluated, on large annotated datasets of artifact-free high-quality images. In this paper, we investigate the effect of one such artifact that is quite common in natural capture settings: optical blur. We show that standard network models, trained only on high-quality images, suffer a significant degradation in performance when applied to those degraded by blur due to defocus, or subject or camera motion. We investigate the extent to which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05760","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":""},"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":"1611.05760","created_at":"2026-05-18T00:43:29.968186+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.05760v2","created_at":"2026-05-18T00:43:29.968186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05760","created_at":"2026-05-18T00:43:29.968186+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAHRJHDNO544","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAHRJHDNO544N2SQ","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAHRJHDN","created_at":"2026-05-18T12:30:04.600751+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/AAHRJHDNO544N2SQA24H6TTHIG","json":"https://pith.science/pith/AAHRJHDNO544N2SQA24H6TTHIG.json","graph_json":"https://pith.science/api/pith-number/AAHRJHDNO544N2SQA24H6TTHIG/graph.json","events_json":"https://pith.science/api/pith-number/AAHRJHDNO544N2SQA24H6TTHIG/events.json","paper":"https://pith.science/paper/AAHRJHDN"},"agent_actions":{"view_html":"https://pith.science/pith/AAHRJHDNO544N2SQA24H6TTHIG","download_json":"https://pith.science/pith/AAHRJHDNO544N2SQA24H6TTHIG.json","view_paper":"https://pith.science/paper/AAHRJHDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.05760&json=true","fetch_graph":"https://pith.science/api/pith-number/AAHRJHDNO544N2SQA24H6TTHIG/graph.json","fetch_events":"https://pith.science/api/pith-number/AAHRJHDNO544N2SQA24H6TTHIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAHRJHDNO544N2SQA24H6TTHIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAHRJHDNO544N2SQA24H6TTHIG/action/storage_attestation","attest_author":"https://pith.science/pith/AAHRJHDNO544N2SQA24H6TTHIG/action/author_attestation","sign_citation":"https://pith.science/pith/AAHRJHDNO544N2SQA24H6TTHIG/action/citation_signature","submit_replication":"https://pith.science/pith/AAHRJHDNO544N2SQA24H6TTHIG/action/replication_record"}},"created_at":"2026-05-18T00:43:29.968186+00:00","updated_at":"2026-05-18T00:43:29.968186+00:00"}