{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:QRUJMAIEMRYCPT435VOO65BLC3","short_pith_number":"pith:QRUJMAIE","canonical_record":{"source":{"id":"1604.04004","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-14T00:47:50Z","cross_cats_sorted":[],"title_canon_sha256":"ec840d8c5c02c3471a0d5cb03a11241ad2a6a862f69d3ac9a3fd6f115ed2cd86","abstract_canon_sha256":"6eede4f6150d10027064277dfde56f95ac727ebea6bacbd042b521890ccf101b"},"schema_version":"1.0"},"canonical_sha256":"8468960104647027cf9bed5cef742b16c6076d88051c3e3ec3a76153cc5f3c4f","source":{"kind":"arxiv","id":"1604.04004","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.04004","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"1604.04004v2","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.04004","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"QRUJMAIEMRYC","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QRUJMAIEMRYCPT43","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QRUJMAIE","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:QRUJMAIEMRYCPT435VOO65BLC3","target":"record","payload":{"canonical_record":{"source":{"id":"1604.04004","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-14T00:47:50Z","cross_cats_sorted":[],"title_canon_sha256":"ec840d8c5c02c3471a0d5cb03a11241ad2a6a862f69d3ac9a3fd6f115ed2cd86","abstract_canon_sha256":"6eede4f6150d10027064277dfde56f95ac727ebea6bacbd042b521890ccf101b"},"schema_version":"1.0"},"canonical_sha256":"8468960104647027cf9bed5cef742b16c6076d88051c3e3ec3a76153cc5f3c4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:29.070006Z","signature_b64":"L/SpO0VpSV6GYSvFxvS+QY7df7JbTZupSn9wexBh4V3q+Nh43n2m1E9gTwBfJDmKJB7gFkxwYFU6jYKDgOisDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8468960104647027cf9bed5cef742b16c6076d88051c3e3ec3a76153cc5f3c4f","last_reissued_at":"2026-05-18T01:16:29.069120Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:29.069120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.04004","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:16:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k+HSJiHw/jaWUOkTq9lp1c3y5GzJyrs4tykzzOAmKSfLcZHFPrTKySZdRvxxb8+T0LYWQYfM61s6pgtJzXkDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T23:34:05.982563Z"},"content_sha256":"bd5908a6a82c1cc96a065aaeb4f1761647feb7be3f6bb27b7fb504f44673251f","schema_version":"1.0","event_id":"sha256:bd5908a6a82c1cc96a065aaeb4f1761647feb7be3f6bb27b7fb504f44673251f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:QRUJMAIEMRYCPT435VOO65BLC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding How Image Quality Affects Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lina Karam, Samuel Dodge","submitted_at":"2016-04-14T00:47:50Z","abstract_excerpt":"Image quality is an important practical challenge that is often overlooked in the design of machine vision systems. Commonly, machine vision systems are trained and tested on high quality image datasets, yet in practical applications the input images can not be assumed to be of high quality. Recently, deep neural networks have obtained state-of-the-art performance on many machine vision tasks. In this paper we provide an evaluation of 4 state-of-the-art deep neural network models for image classification under quality distortions. We consider five types of quality distortions: blur, noise, con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.04004","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:16:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gEoDqMsxKP++VU4Fn06ffJptmGavKHcG1INhRzIJF9tK+9ubqrucKmZb4Il2505J1kQLZJcIneexl84b5OgrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T23:34:05.983271Z"},"content_sha256":"e3a2d0bdd33a5dc564628f9f511ba56472e34f376daf6bb6d4bd2856fed14311","schema_version":"1.0","event_id":"sha256:e3a2d0bdd33a5dc564628f9f511ba56472e34f376daf6bb6d4bd2856fed14311"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QRUJMAIEMRYCPT435VOO65BLC3/bundle.json","state_url":"https://pith.science/pith/QRUJMAIEMRYCPT435VOO65BLC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QRUJMAIEMRYCPT435VOO65BLC3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T23:34:05Z","links":{"resolver":"https://pith.science/pith/QRUJMAIEMRYCPT435VOO65BLC3","bundle":"https://pith.science/pith/QRUJMAIEMRYCPT435VOO65BLC3/bundle.json","state":"https://pith.science/pith/QRUJMAIEMRYCPT435VOO65BLC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QRUJMAIEMRYCPT435VOO65BLC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QRUJMAIEMRYCPT435VOO65BLC3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6eede4f6150d10027064277dfde56f95ac727ebea6bacbd042b521890ccf101b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-14T00:47:50Z","title_canon_sha256":"ec840d8c5c02c3471a0d5cb03a11241ad2a6a862f69d3ac9a3fd6f115ed2cd86"},"schema_version":"1.0","source":{"id":"1604.04004","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.04004","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"1604.04004v2","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.04004","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"QRUJMAIEMRYC","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QRUJMAIEMRYCPT43","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QRUJMAIE","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:e3a2d0bdd33a5dc564628f9f511ba56472e34f376daf6bb6d4bd2856fed14311","target":"graph","created_at":"2026-05-18T01:16:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Image quality is an important practical challenge that is often overlooked in the design of machine vision systems. Commonly, machine vision systems are trained and tested on high quality image datasets, yet in practical applications the input images can not be assumed to be of high quality. Recently, deep neural networks have obtained state-of-the-art performance on many machine vision tasks. In this paper we provide an evaluation of 4 state-of-the-art deep neural network models for image classification under quality distortions. We consider five types of quality distortions: blur, noise, con","authors_text":"Lina Karam, Samuel Dodge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-14T00:47:50Z","title":"Understanding How Image Quality Affects Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.04004","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bd5908a6a82c1cc96a065aaeb4f1761647feb7be3f6bb27b7fb504f44673251f","target":"record","created_at":"2026-05-18T01:16:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6eede4f6150d10027064277dfde56f95ac727ebea6bacbd042b521890ccf101b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-14T00:47:50Z","title_canon_sha256":"ec840d8c5c02c3471a0d5cb03a11241ad2a6a862f69d3ac9a3fd6f115ed2cd86"},"schema_version":"1.0","source":{"id":"1604.04004","kind":"arxiv","version":2}},"canonical_sha256":"8468960104647027cf9bed5cef742b16c6076d88051c3e3ec3a76153cc5f3c4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8468960104647027cf9bed5cef742b16c6076d88051c3e3ec3a76153cc5f3c4f","first_computed_at":"2026-05-18T01:16:29.069120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:16:29.069120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L/SpO0VpSV6GYSvFxvS+QY7df7JbTZupSn9wexBh4V3q+Nh43n2m1E9gTwBfJDmKJB7gFkxwYFU6jYKDgOisDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:16:29.070006Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.04004","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd5908a6a82c1cc96a065aaeb4f1761647feb7be3f6bb27b7fb504f44673251f","sha256:e3a2d0bdd33a5dc564628f9f511ba56472e34f376daf6bb6d4bd2856fed14311"],"state_sha256":"f4e8e625aeebf6d0f03627794c5fa6b94a9d0a91cbf7c287fdada0eacdff63c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dof1uCLCYp3y5955gSqfLLFPCum7eqvqqibWq84oFwjfPnxo08gLCsYvhsEnmHyS3KQuRMO0y22jxgmRw8P4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T23:34:05.987694Z","bundle_sha256":"a0c88b65ab03c4eb840507e5c053a3db193fe4e12766e2992eb24e73545245ed"}}