{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:UM6KUYZEZ3CONQGEGRHGIQGKYT","short_pith_number":"pith:UM6KUYZE","schema_version":"1.0","canonical_sha256":"a33caa6324cec4e6c0c4344e6440cac4fa919007699163ef4e38d7ba6fed1ab9","source":{"kind":"arxiv","id":"1703.07928","version":2},"attestation_state":"computed","paper":{"title":"Self corrective Perturbations for Semantic Segmentation and Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Arpit Jain, Ser Nam Lim, Swami Sankaranarayanan","submitted_at":"2017-03-23T04:25:48Z","abstract_excerpt":"Convolutional Neural Networks have been a subject of great importance over the past decade and great strides have been made in their utility for producing state of the art performance in many computer vision problems. However, the behavior of deep networks is yet to be fully understood and is still an active area of research. In this work, we present an intriguing behavior: pre-trained CNNs can be made to improve their predictions by structurally perturbing the input. We observe that these perturbations - referred as Guided Perturbations - enable a trained network to improve its prediction per"},"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":"1703.07928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T04:25:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e8138a1d694a7b70fd6dd7b3f88996c0ef8a4688913c2323c62f9ed8822aa6a0","abstract_canon_sha256":"a4e0d86029933a48be8d994fc0a777bc3168a390a19b71c186d13d57aa167da0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:41.676237Z","signature_b64":"KeKyG8GMShgqfFJ1UmxNxlhAOPyx7hOuHbcgTwwaZy5YuTb91iCjlu3U8Sz3DUPorsgXcyhyd6Rs6cCQu7NpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a33caa6324cec4e6c0c4344e6440cac4fa919007699163ef4e38d7ba6fed1ab9","last_reissued_at":"2026-05-18T00:38:41.675609Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:41.675609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self corrective Perturbations for Semantic Segmentation and Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Arpit Jain, Ser Nam Lim, Swami Sankaranarayanan","submitted_at":"2017-03-23T04:25:48Z","abstract_excerpt":"Convolutional Neural Networks have been a subject of great importance over the past decade and great strides have been made in their utility for producing state of the art performance in many computer vision problems. However, the behavior of deep networks is yet to be fully understood and is still an active area of research. In this work, we present an intriguing behavior: pre-trained CNNs can be made to improve their predictions by structurally perturbing the input. We observe that these perturbations - referred as Guided Perturbations - enable a trained network to improve its prediction per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07928","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":"1703.07928","created_at":"2026-05-18T00:38:41.675728+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.07928v2","created_at":"2026-05-18T00:38:41.675728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07928","created_at":"2026-05-18T00:38:41.675728+00:00"},{"alias_kind":"pith_short_12","alias_value":"UM6KUYZEZ3CO","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"UM6KUYZEZ3CONQGE","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"UM6KUYZE","created_at":"2026-05-18T12:31:46.661854+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/UM6KUYZEZ3CONQGEGRHGIQGKYT","json":"https://pith.science/pith/UM6KUYZEZ3CONQGEGRHGIQGKYT.json","graph_json":"https://pith.science/api/pith-number/UM6KUYZEZ3CONQGEGRHGIQGKYT/graph.json","events_json":"https://pith.science/api/pith-number/UM6KUYZEZ3CONQGEGRHGIQGKYT/events.json","paper":"https://pith.science/paper/UM6KUYZE"},"agent_actions":{"view_html":"https://pith.science/pith/UM6KUYZEZ3CONQGEGRHGIQGKYT","download_json":"https://pith.science/pith/UM6KUYZEZ3CONQGEGRHGIQGKYT.json","view_paper":"https://pith.science/paper/UM6KUYZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.07928&json=true","fetch_graph":"https://pith.science/api/pith-number/UM6KUYZEZ3CONQGEGRHGIQGKYT/graph.json","fetch_events":"https://pith.science/api/pith-number/UM6KUYZEZ3CONQGEGRHGIQGKYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UM6KUYZEZ3CONQGEGRHGIQGKYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UM6KUYZEZ3CONQGEGRHGIQGKYT/action/storage_attestation","attest_author":"https://pith.science/pith/UM6KUYZEZ3CONQGEGRHGIQGKYT/action/author_attestation","sign_citation":"https://pith.science/pith/UM6KUYZEZ3CONQGEGRHGIQGKYT/action/citation_signature","submit_replication":"https://pith.science/pith/UM6KUYZEZ3CONQGEGRHGIQGKYT/action/replication_record"}},"created_at":"2026-05-18T00:38:41.675728+00:00","updated_at":"2026-05-18T00:38:41.675728+00:00"}