{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:C26REIRBHQCPQYKNFNGCMIHVKQ","short_pith_number":"pith:C26REIRB","canonical_record":{"source":{"id":"1506.02753","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-06-09T02:31:40Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"f98a741bd13dd221c627a828d86cb59712e3870ccf7bba144496feb72278820d","abstract_canon_sha256":"5ed3ec2d3b1cfaf260c245ba4f9f90ad67cd76cf623ddf2882c4a63a0663097d"},"schema_version":"1.0"},"canonical_sha256":"16bd1222213c04f8614d2b4c2620f5541360af8f9ae314c7e5a66b48aa5ca4cc","source":{"kind":"arxiv","id":"1506.02753","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02753","created_at":"2026-05-18T01:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02753v4","created_at":"2026-05-18T01:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02753","created_at":"2026-05-18T01:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"C26REIRBHQCP","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"C26REIRBHQCPQYKN","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"C26REIRB","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:C26REIRBHQCPQYKNFNGCMIHVKQ","target":"record","payload":{"canonical_record":{"source":{"id":"1506.02753","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-06-09T02:31:40Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"f98a741bd13dd221c627a828d86cb59712e3870ccf7bba144496feb72278820d","abstract_canon_sha256":"5ed3ec2d3b1cfaf260c245ba4f9f90ad67cd76cf623ddf2882c4a63a0663097d"},"schema_version":"1.0"},"canonical_sha256":"16bd1222213c04f8614d2b4c2620f5541360af8f9ae314c7e5a66b48aa5ca4cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:09.804487Z","signature_b64":"prpQdlez3gfjncSlybLwvSz3nLEEZef1/UaJihOKbCmwrJpLBHx+thT7k52DLWtKDzfCDC9jnNzs+3TwivpqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16bd1222213c04f8614d2b4c2620f5541360af8f9ae314c7e5a66b48aa5ca4cc","last_reissued_at":"2026-05-18T01:16:09.804027Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:09.804027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.02753","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:16:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JtsUJAztF9Vc0VdnWbZbmMloLmGX3guXqWwoFCx/kfvaGR39f50Lne1QwWi7kX8Jg+tM5Gun5wyP8BLC1ntZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:41:47.539443Z"},"content_sha256":"d4c339a2b36b019884f56f863e63e09324164d42f491163b737995b17574a4f6","schema_version":"1.0","event_id":"sha256:d4c339a2b36b019884f56f863e63e09324164d42f491163b737995b17574a4f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:C26REIRBHQCPQYKNFNGCMIHVKQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inverting Visual Representations with Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"Alexey Dosovitskiy, Thomas Brox","submitted_at":"2015-06-09T02:31:40Z","abstract_excerpt":"Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an up-convolutional neural network. We apply the method to shallow representations (HOG, SIFT, LBP), as well as to deep networks. For shallow representations our approach provides significantly better reconstructions than existing methods, revealing that there is surprisingly rich information contained in these features. Inverting a deep network trained on ImageNet pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02753","kind":"arxiv","version":4},"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":"2026-05-18T01:16:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4AnPJjCHKHw+m6doUBxdctHydIjro1/5uWEsFIofPUx9/aqnfaM31agVSdlmGp8kis2RflwJ1I7SSYvSoUJTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T05:41:47.539793Z"},"content_sha256":"f3ee3393c61c5dac5cf76de1fc60fc4ac247037f9be10a2bee43ea30987c74ab","schema_version":"1.0","event_id":"sha256:f3ee3393c61c5dac5cf76de1fc60fc4ac247037f9be10a2bee43ea30987c74ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C26REIRBHQCPQYKNFNGCMIHVKQ/bundle.json","state_url":"https://pith.science/pith/C26REIRBHQCPQYKNFNGCMIHVKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C26REIRBHQCPQYKNFNGCMIHVKQ/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":"2026-06-01T05:41:47Z","links":{"resolver":"https://pith.science/pith/C26REIRBHQCPQYKNFNGCMIHVKQ","bundle":"https://pith.science/pith/C26REIRBHQCPQYKNFNGCMIHVKQ/bundle.json","state":"https://pith.science/pith/C26REIRBHQCPQYKNFNGCMIHVKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C26REIRBHQCPQYKNFNGCMIHVKQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:C26REIRBHQCPQYKNFNGCMIHVKQ","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":"5ed3ec2d3b1cfaf260c245ba4f9f90ad67cd76cf623ddf2882c4a63a0663097d","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-06-09T02:31:40Z","title_canon_sha256":"f98a741bd13dd221c627a828d86cb59712e3870ccf7bba144496feb72278820d"},"schema_version":"1.0","source":{"id":"1506.02753","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.02753","created_at":"2026-05-18T01:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"1506.02753v4","created_at":"2026-05-18T01:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02753","created_at":"2026-05-18T01:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"C26REIRBHQCP","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"C26REIRBHQCPQYKN","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"C26REIRB","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:f3ee3393c61c5dac5cf76de1fc60fc4ac247037f9be10a2bee43ea30987c74ab","target":"graph","created_at":"2026-05-18T01:16:09Z","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":"Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an up-convolutional neural network. We apply the method to shallow representations (HOG, SIFT, LBP), as well as to deep networks. For shallow representations our approach provides significantly better reconstructions than existing methods, revealing that there is surprisingly rich information contained in these features. Inverting a deep network trained on ImageNet pr","authors_text":"Alexey Dosovitskiy, Thomas Brox","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-06-09T02:31:40Z","title":"Inverting Visual Representations with Convolutional Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02753","kind":"arxiv","version":4},"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:d4c339a2b36b019884f56f863e63e09324164d42f491163b737995b17574a4f6","target":"record","created_at":"2026-05-18T01:16:09Z","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":"5ed3ec2d3b1cfaf260c245ba4f9f90ad67cd76cf623ddf2882c4a63a0663097d","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-06-09T02:31:40Z","title_canon_sha256":"f98a741bd13dd221c627a828d86cb59712e3870ccf7bba144496feb72278820d"},"schema_version":"1.0","source":{"id":"1506.02753","kind":"arxiv","version":4}},"canonical_sha256":"16bd1222213c04f8614d2b4c2620f5541360af8f9ae314c7e5a66b48aa5ca4cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16bd1222213c04f8614d2b4c2620f5541360af8f9ae314c7e5a66b48aa5ca4cc","first_computed_at":"2026-05-18T01:16:09.804027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:16:09.804027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"prpQdlez3gfjncSlybLwvSz3nLEEZef1/UaJihOKbCmwrJpLBHx+thT7k52DLWtKDzfCDC9jnNzs+3TwivpqDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:16:09.804487Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.02753","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4c339a2b36b019884f56f863e63e09324164d42f491163b737995b17574a4f6","sha256:f3ee3393c61c5dac5cf76de1fc60fc4ac247037f9be10a2bee43ea30987c74ab"],"state_sha256":"542db5022a405a918a919d64f6440e372aa12073001b77062fc4aa29750549ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sE2MwhF9xRWqy3eU5Vzrzcu+K86SVl+WOqSw0+Omte8gZdEquPP39c0YU9olTNK+fx/d+z+of5D+ZDV4EELRAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T05:41:47.541754Z","bundle_sha256":"b98bffe60c41a0a870ab141354c39d3f852c7cd557f22e0b088ce45e0ffdee9f"}}