{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4EP7KBIDUIOQLVS2WTWKVYDJHQ","short_pith_number":"pith:4EP7KBID","canonical_record":{"source":{"id":"1703.08119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T15:56:33Z","cross_cats_sorted":[],"title_canon_sha256":"f36eb2b32ac2e7da3afc21e8d1ec2a9331a8a0d6eb2f4dd9f0ad382d7f31a1ea","abstract_canon_sha256":"2c8459b44d4f95aedc04457d6f35916287359a10251d652d8e26318037bd39e1"},"schema_version":"1.0"},"canonical_sha256":"e11ff50503a21d05d65ab4ecaae0693c16ca82259080ab1d9ee3f030092c59a0","source":{"kind":"arxiv","id":"1703.08119","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08119","created_at":"2026-05-18T00:48:03Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08119v1","created_at":"2026-05-18T00:48:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08119","created_at":"2026-05-18T00:48:03Z"},{"alias_kind":"pith_short_12","alias_value":"4EP7KBIDUIOQ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4EP7KBIDUIOQLVS2","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4EP7KBID","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4EP7KBIDUIOQLVS2WTWKVYDJHQ","target":"record","payload":{"canonical_record":{"source":{"id":"1703.08119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T15:56:33Z","cross_cats_sorted":[],"title_canon_sha256":"f36eb2b32ac2e7da3afc21e8d1ec2a9331a8a0d6eb2f4dd9f0ad382d7f31a1ea","abstract_canon_sha256":"2c8459b44d4f95aedc04457d6f35916287359a10251d652d8e26318037bd39e1"},"schema_version":"1.0"},"canonical_sha256":"e11ff50503a21d05d65ab4ecaae0693c16ca82259080ab1d9ee3f030092c59a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:03.837968Z","signature_b64":"oFYFowLKJCGHqGSQmLB6sbE2hFxqjfrcnI4VwRb9+dmg9jJciByMFibhb6k/0/p7yYq9EzoegqE1d2JWNhBsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e11ff50503a21d05d65ab4ecaae0693c16ca82259080ab1d9ee3f030092c59a0","last_reissued_at":"2026-05-18T00:48:03.837327Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:03.837327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.08119","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GY554ci6am9uJe/Bv8F1c0TqmQTyWj4b6HPngMfT4udcEAdA6PEOkzU1JnD3WPOEGEJnI+mljsmm399ZNs2jCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:50:27.048078Z"},"content_sha256":"6ce9dce390ebef8b606a5aec2a928063b040c6419cd40571ac2a3c9551eddfe6","schema_version":"1.0","event_id":"sha256:6ce9dce390ebef8b606a5aec2a928063b040c6419cd40571ac2a3c9551eddfe6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4EP7KBIDUIOQLVS2WTWKVYDJHQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quality Resilient 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":"2017-03-23T15:56:33Z","abstract_excerpt":"We study deep neural networks for classification of images with quality distortions. We first show that networks fine-tuned on distorted data greatly outperform the original networks when tested on distorted data. However, fine-tuned networks perform poorly on quality distortions that they have not been trained for. We propose a mixture of experts ensemble method that is robust to different types of distortions. The \"experts\" in our model are trained on a particular type of distortion. The output of the model is a weighted sum of the expert models, where the weights are determined by a separat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08119","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":""},"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":"2026-05-18T00:48:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e78n5oT4f5bChSRTbqxLJGfZHgTz4rf7RgdzKR1CVjqiV04wTsaI2V5e3Tu1NzhuB71ODE64cY7WEXbq/gbOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:50:27.048611Z"},"content_sha256":"e9cab48c1f925b6b617019ab859ca9f8fab2dc77fd73da9f326492eaedb04032","schema_version":"1.0","event_id":"sha256:e9cab48c1f925b6b617019ab859ca9f8fab2dc77fd73da9f326492eaedb04032"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4EP7KBIDUIOQLVS2WTWKVYDJHQ/bundle.json","state_url":"https://pith.science/pith/4EP7KBIDUIOQLVS2WTWKVYDJHQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4EP7KBIDUIOQLVS2WTWKVYDJHQ/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":"2026-08-21T17:50:27Z","links":{"resolver":"https://pith.science/pith/4EP7KBIDUIOQLVS2WTWKVYDJHQ","bundle":"https://pith.science/pith/4EP7KBIDUIOQLVS2WTWKVYDJHQ/bundle.json","state":"https://pith.science/pith/4EP7KBIDUIOQLVS2WTWKVYDJHQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4EP7KBIDUIOQLVS2WTWKVYDJHQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4EP7KBIDUIOQLVS2WTWKVYDJHQ","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":"2c8459b44d4f95aedc04457d6f35916287359a10251d652d8e26318037bd39e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T15:56:33Z","title_canon_sha256":"f36eb2b32ac2e7da3afc21e8d1ec2a9331a8a0d6eb2f4dd9f0ad382d7f31a1ea"},"schema_version":"1.0","source":{"id":"1703.08119","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08119","created_at":"2026-05-18T00:48:03Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08119v1","created_at":"2026-05-18T00:48:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08119","created_at":"2026-05-18T00:48:03Z"},{"alias_kind":"pith_short_12","alias_value":"4EP7KBIDUIOQ","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"4EP7KBIDUIOQLVS2","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"4EP7KBID","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:e9cab48c1f925b6b617019ab859ca9f8fab2dc77fd73da9f326492eaedb04032","target":"graph","created_at":"2026-05-18T00:48:03Z","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":"We study deep neural networks for classification of images with quality distortions. We first show that networks fine-tuned on distorted data greatly outperform the original networks when tested on distorted data. However, fine-tuned networks perform poorly on quality distortions that they have not been trained for. We propose a mixture of experts ensemble method that is robust to different types of distortions. The \"experts\" in our model are trained on a particular type of distortion. The output of the model is a weighted sum of the expert models, where the weights are determined by a separat","authors_text":"Lina Karam, Samuel Dodge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T15:56:33Z","title":"Quality Resilient Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08119","kind":"arxiv","version":1},"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":"sha256:6ce9dce390ebef8b606a5aec2a928063b040c6419cd40571ac2a3c9551eddfe6","target":"record","created_at":"2026-05-18T00:48:03Z","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":"2c8459b44d4f95aedc04457d6f35916287359a10251d652d8e26318037bd39e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T15:56:33Z","title_canon_sha256":"f36eb2b32ac2e7da3afc21e8d1ec2a9331a8a0d6eb2f4dd9f0ad382d7f31a1ea"},"schema_version":"1.0","source":{"id":"1703.08119","kind":"arxiv","version":1}},"canonical_sha256":"e11ff50503a21d05d65ab4ecaae0693c16ca82259080ab1d9ee3f030092c59a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e11ff50503a21d05d65ab4ecaae0693c16ca82259080ab1d9ee3f030092c59a0","first_computed_at":"2026-05-18T00:48:03.837327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:03.837327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oFYFowLKJCGHqGSQmLB6sbE2hFxqjfrcnI4VwRb9+dmg9jJciByMFibhb6k/0/p7yYq9EzoegqE1d2JWNhBsAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:03.837968Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.08119","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ce9dce390ebef8b606a5aec2a928063b040c6419cd40571ac2a3c9551eddfe6","sha256:e9cab48c1f925b6b617019ab859ca9f8fab2dc77fd73da9f326492eaedb04032"],"state_sha256":"8a193f0bef2ef696fa8a6fec8f0255f82a51bebb5d9bbb85a8d2f13049a570d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+BBzsD+ertaIK+Hff7oMnZBkTvAE7A3WwQq1ON7CI4bYGfHaERm8HP6q5URjfyBFT0fQDYL8/i1A57TNJzOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:50:27.052043Z","bundle_sha256":"c44695f047bc3f26a540d3d81bf7404c81a32e84bd76387c03ddc86b90905f46"}}