{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:QINKRAKQYR3BAD3DEJVWZYIUW5","short_pith_number":"pith:QINKRAKQ","canonical_record":{"source":{"id":"1512.02017","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-07T12:38:13Z","cross_cats_sorted":[],"title_canon_sha256":"64feceaf62412d63860f976a2222112bdaaffc181a8131bdce9c8a1bc3a2efd4","abstract_canon_sha256":"99edab501d18e2a4dc2134ee41422feea19db405092efe81446fb95a9fca813c"},"schema_version":"1.0"},"canonical_sha256":"821aa88150c476100f63226b6ce114b746dcdb3450019a6728833b37bd186aeb","source":{"kind":"arxiv","id":"1512.02017","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.02017","created_at":"2026-05-18T01:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"1512.02017v3","created_at":"2026-05-18T01:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.02017","created_at":"2026-05-18T01:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"QINKRAKQYR3B","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"QINKRAKQYR3BAD3D","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"QINKRAKQ","created_at":"2026-05-18T12:29:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:QINKRAKQYR3BAD3DEJVWZYIUW5","target":"record","payload":{"canonical_record":{"source":{"id":"1512.02017","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-07T12:38:13Z","cross_cats_sorted":[],"title_canon_sha256":"64feceaf62412d63860f976a2222112bdaaffc181a8131bdce9c8a1bc3a2efd4","abstract_canon_sha256":"99edab501d18e2a4dc2134ee41422feea19db405092efe81446fb95a9fca813c"},"schema_version":"1.0"},"canonical_sha256":"821aa88150c476100f63226b6ce114b746dcdb3450019a6728833b37bd186aeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:17.562804Z","signature_b64":"FH+y/fOnnCtZ5xeL4Bsjyaq4rwEeigF8GY+Bns2YriRE5AZjr58mOX4JXKkkoNVlyMFzAV1U2gK8yTks+nN3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"821aa88150c476100f63226b6ce114b746dcdb3450019a6728833b37bd186aeb","last_reissued_at":"2026-05-18T01:14:17.562169Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:17.562169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.02017","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AMiymw5JOYFmWA5IxAL681nQhmGruEbEObUHlS3rVQhfF136ZzXrgnm5FJTKPi3deKRo2mUGm40J31SN2RvjDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T15:11:08.799570Z"},"content_sha256":"1552ce00f97d11a55aab92f1374229360182156ff5b4a308ac046968a265fecd","schema_version":"1.0","event_id":"sha256:1552ce00f97d11a55aab92f1374229360182156ff5b4a308ac046968a265fecd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:QINKRAKQYR3BAD3DEJVWZYIUW5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Aravindh Mahendran","submitted_at":"2015-12-07T12:38:13Z","abstract_excerpt":"Image representations, from SIFT and bag of visual words to Convolutional Neural Networks (CNNs) are a crucial component of almost all computer vision systems. However, our understanding of them remains limited. In this paper we study several landmark representations, both shallow and deep, by a number of complementary visualization techniques. These visualizations are based on the concept of \"natural pre-image\", namely a natural-looking image whose representation has some notable property. We study in particular three such visualizations: inversion, in which the aim is to reconstruct an image"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.02017","kind":"arxiv","version":3},"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":"2026-05-18T01:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rDk9UsBmp4hoh6GVR6nIZvn0DnPPDuADqCeDH5bxea7mOqYgPCD7rSfCo8meVPxt2BMn+VxyIW8eY0PwDOyaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T15:11:08.799915Z"},"content_sha256":"206fe7bd83d97157994b2c572d043015f84cadfae046237e7fce32ca49b54129","schema_version":"1.0","event_id":"sha256:206fe7bd83d97157994b2c572d043015f84cadfae046237e7fce32ca49b54129"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QINKRAKQYR3BAD3DEJVWZYIUW5/bundle.json","state_url":"https://pith.science/pith/QINKRAKQYR3BAD3DEJVWZYIUW5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QINKRAKQYR3BAD3DEJVWZYIUW5/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":"2026-06-10T15:11:08Z","links":{"resolver":"https://pith.science/pith/QINKRAKQYR3BAD3DEJVWZYIUW5","bundle":"https://pith.science/pith/QINKRAKQYR3BAD3DEJVWZYIUW5/bundle.json","state":"https://pith.science/pith/QINKRAKQYR3BAD3DEJVWZYIUW5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QINKRAKQYR3BAD3DEJVWZYIUW5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:QINKRAKQYR3BAD3DEJVWZYIUW5","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":"99edab501d18e2a4dc2134ee41422feea19db405092efe81446fb95a9fca813c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-07T12:38:13Z","title_canon_sha256":"64feceaf62412d63860f976a2222112bdaaffc181a8131bdce9c8a1bc3a2efd4"},"schema_version":"1.0","source":{"id":"1512.02017","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.02017","created_at":"2026-05-18T01:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"1512.02017v3","created_at":"2026-05-18T01:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.02017","created_at":"2026-05-18T01:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"QINKRAKQYR3B","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"QINKRAKQYR3BAD3D","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"QINKRAKQ","created_at":"2026-05-18T12:29:37Z"}],"graph_snapshots":[{"event_id":"sha256:206fe7bd83d97157994b2c572d043015f84cadfae046237e7fce32ca49b54129","target":"graph","created_at":"2026-05-18T01:14:17Z","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 representations, from SIFT and bag of visual words to Convolutional Neural Networks (CNNs) are a crucial component of almost all computer vision systems. However, our understanding of them remains limited. In this paper we study several landmark representations, both shallow and deep, by a number of complementary visualization techniques. These visualizations are based on the concept of \"natural pre-image\", namely a natural-looking image whose representation has some notable property. We study in particular three such visualizations: inversion, in which the aim is to reconstruct an image","authors_text":"Andrea Vedaldi, Aravindh Mahendran","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-07T12:38:13Z","title":"Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.02017","kind":"arxiv","version":3},"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":"sha256:1552ce00f97d11a55aab92f1374229360182156ff5b4a308ac046968a265fecd","target":"record","created_at":"2026-05-18T01:14:17Z","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":"99edab501d18e2a4dc2134ee41422feea19db405092efe81446fb95a9fca813c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-07T12:38:13Z","title_canon_sha256":"64feceaf62412d63860f976a2222112bdaaffc181a8131bdce9c8a1bc3a2efd4"},"schema_version":"1.0","source":{"id":"1512.02017","kind":"arxiv","version":3}},"canonical_sha256":"821aa88150c476100f63226b6ce114b746dcdb3450019a6728833b37bd186aeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"821aa88150c476100f63226b6ce114b746dcdb3450019a6728833b37bd186aeb","first_computed_at":"2026-05-18T01:14:17.562169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:14:17.562169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FH+y/fOnnCtZ5xeL4Bsjyaq4rwEeigF8GY+Bns2YriRE5AZjr58mOX4JXKkkoNVlyMFzAV1U2gK8yTks+nN3AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:14:17.562804Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.02017","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1552ce00f97d11a55aab92f1374229360182156ff5b4a308ac046968a265fecd","sha256:206fe7bd83d97157994b2c572d043015f84cadfae046237e7fce32ca49b54129"],"state_sha256":"b0791c7cf68792d6e708475c9ce95c2b1fb72ca63c55ac4d1c0cc6c60009e9ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LwmEm8wulZMCUrH+mS/9vq8QfLRHgzSLWRpVAscCgOu5JpTrlv54oinA2yswtId+Bb4DKmzHYxoRDuq5fyoUAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T15:11:08.801841Z","bundle_sha256":"21be1e5093b4805b5f766e7be0da76057eccee514de8cc2ef6dd7e25a0bdab05"}}