{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YIJQMQGIGTIY73WIV225SE6S7B","short_pith_number":"pith:YIJQMQGI","canonical_record":{"source":{"id":"1805.00071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T08:09:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d670e612125a4a0151b24adde45050c4c5b867fb90fa505c921194059ac5941b","abstract_canon_sha256":"9213b208ac0f2e7ae39083ca68232ffbb7e656b5e3681e457cf344309c86e831"},"schema_version":"1.0"},"canonical_sha256":"c2130640c834d18feec8aeb5d913d2f8633eca110734ef876fa0e85a9a0bc1c3","source":{"kind":"arxiv","id":"1805.00071","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.00071","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"1805.00071v1","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00071","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"YIJQMQGIGTIY","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YIJQMQGIGTIY73WI","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YIJQMQGI","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YIJQMQGIGTIY73WIV225SE6S7B","target":"record","payload":{"canonical_record":{"source":{"id":"1805.00071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T08:09:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d670e612125a4a0151b24adde45050c4c5b867fb90fa505c921194059ac5941b","abstract_canon_sha256":"9213b208ac0f2e7ae39083ca68232ffbb7e656b5e3681e457cf344309c86e831"},"schema_version":"1.0"},"canonical_sha256":"c2130640c834d18feec8aeb5d913d2f8633eca110734ef876fa0e85a9a0bc1c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:10.629736Z","signature_b64":"KjEC9bcWIDoQoJ8JDx0yFn8KMZWB2CkVZSPTVvXFUvorxziHXnQNEm02mlITSNL4eq7uWiqBPeEMKiAeE3msAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2130640c834d18feec8aeb5d913d2f8633eca110734ef876fa0e85a9a0bc1c3","last_reissued_at":"2026-05-18T00:17:10.628980Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:10.628980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.00071","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":"2026-05-18T00:17:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MazbV7kAlhqPJp65jfbbuFs8wL3/gYZDIPkToWGU9tGM6NlTtr7MkzdbFAebclY0iHdh9zK8IOzUCoNcfuKLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T11:27:50.587774Z"},"content_sha256":"bad5cbe2845c7c0f95db1bc6bd83f7b4514510104018dfaaa9f773f39864d563","schema_version":"1.0","event_id":"sha256:bad5cbe2845c7c0f95db1bc6bd83f7b4514510104018dfaaa9f773f39864d563"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YIJQMQGIGTIY73WIV225SE6S7B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Regularization to Visualize Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Rupprecht, Florian Ludwig, Matthias Kohl, Maximilian Baust, Stefan Braunewell","submitted_at":"2018-04-20T08:09:34Z","abstract_excerpt":"Variational methods for revealing visual concepts learned by convolutional neural networks have gained significant attention during the last years. Being based on noisy gradients obtained via back-propagation such methods require the application of regularization strategies. We present a mathematical framework unifying previously employed regularization methods. Within this framework, we propose a novel technique based on Sobolev gradients which can be implemented via convolutions and does not require specialized numerical treatment, such as total variation regularization. The experiments perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00071","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":"2026-05-18T00:17:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o2maIzRGfsBB6E+zv9WcBGvV7/NfWIrBgzoAzaYo85d8J5Ze4pu51upjO8M+Jo13OFVIfVaLsuXMKcRHDs/NDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T11:27:50.588151Z"},"content_sha256":"7e18ffb669ca5c21e785b7986282aa991f6d8d3eccee036d35b09360950bdf77","schema_version":"1.0","event_id":"sha256:7e18ffb669ca5c21e785b7986282aa991f6d8d3eccee036d35b09360950bdf77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIJQMQGIGTIY73WIV225SE6S7B/bundle.json","state_url":"https://pith.science/pith/YIJQMQGIGTIY73WIV225SE6S7B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIJQMQGIGTIY73WIV225SE6S7B/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":"2026-06-03T11:27:50Z","links":{"resolver":"https://pith.science/pith/YIJQMQGIGTIY73WIV225SE6S7B","bundle":"https://pith.science/pith/YIJQMQGIGTIY73WIV225SE6S7B/bundle.json","state":"https://pith.science/pith/YIJQMQGIGTIY73WIV225SE6S7B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIJQMQGIGTIY73WIV225SE6S7B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YIJQMQGIGTIY73WIV225SE6S7B","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":"9213b208ac0f2e7ae39083ca68232ffbb7e656b5e3681e457cf344309c86e831","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T08:09:34Z","title_canon_sha256":"d670e612125a4a0151b24adde45050c4c5b867fb90fa505c921194059ac5941b"},"schema_version":"1.0","source":{"id":"1805.00071","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.00071","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"1805.00071v1","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00071","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"YIJQMQGIGTIY","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YIJQMQGIGTIY73WI","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YIJQMQGI","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:7e18ffb669ca5c21e785b7986282aa991f6d8d3eccee036d35b09360950bdf77","target":"graph","created_at":"2026-05-18T00:17:10Z","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":"Variational methods for revealing visual concepts learned by convolutional neural networks have gained significant attention during the last years. Being based on noisy gradients obtained via back-propagation such methods require the application of regularization strategies. We present a mathematical framework unifying previously employed regularization methods. Within this framework, we propose a novel technique based on Sobolev gradients which can be implemented via convolutions and does not require specialized numerical treatment, such as total variation regularization. The experiments perf","authors_text":"Christian Rupprecht, Florian Ludwig, Matthias Kohl, Maximilian Baust, Stefan Braunewell","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T08:09:34Z","title":"Understanding Regularization to Visualize Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00071","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:bad5cbe2845c7c0f95db1bc6bd83f7b4514510104018dfaaa9f773f39864d563","target":"record","created_at":"2026-05-18T00:17:10Z","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":"9213b208ac0f2e7ae39083ca68232ffbb7e656b5e3681e457cf344309c86e831","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-20T08:09:34Z","title_canon_sha256":"d670e612125a4a0151b24adde45050c4c5b867fb90fa505c921194059ac5941b"},"schema_version":"1.0","source":{"id":"1805.00071","kind":"arxiv","version":1}},"canonical_sha256":"c2130640c834d18feec8aeb5d913d2f8633eca110734ef876fa0e85a9a0bc1c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2130640c834d18feec8aeb5d913d2f8633eca110734ef876fa0e85a9a0bc1c3","first_computed_at":"2026-05-18T00:17:10.628980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:10.628980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KjEC9bcWIDoQoJ8JDx0yFn8KMZWB2CkVZSPTVvXFUvorxziHXnQNEm02mlITSNL4eq7uWiqBPeEMKiAeE3msAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:10.629736Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.00071","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bad5cbe2845c7c0f95db1bc6bd83f7b4514510104018dfaaa9f773f39864d563","sha256:7e18ffb669ca5c21e785b7986282aa991f6d8d3eccee036d35b09360950bdf77"],"state_sha256":"d099819b5071b7da0a0080e491424ed917ba89bad96a6327b9b5e6449d1555ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D044QTEIM2CzhnlR5+R16hW6PvYU8Ve3/Ob2J/jHO5FkR5PbG/orLxUl3p5ISvi3iCUCu7dKrAOIHil9f/7UBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T11:27:50.590242Z","bundle_sha256":"ff8a20234cecfae9bf8eb45b010540ce4339f96f82a5871cc39b4e9ea6717e25"}}