{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IBHBQWX4AWYCWWA73T43NA6NH5","short_pith_number":"pith:IBHBQWX4","canonical_record":{"source":{"id":"1904.09533","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-21T02:54:33Z","cross_cats_sorted":["cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"6ad70829679e9d84fb32e10805a32705bf6497d52668fc22d97e1053cb9d94e2","abstract_canon_sha256":"2eb77b7a13bfc3044a6e555579352e6f7588cfb9fdeb921895fa35b5896c495a"},"schema_version":"1.0"},"canonical_sha256":"404e185afc05b02b581fdcf9b683cd3f51e6afe38cf0de260723656be17d5934","source":{"kind":"arxiv","id":"1904.09533","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09533","created_at":"2026-05-17T23:41:53Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09533v2","created_at":"2026-05-17T23:41:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09533","created_at":"2026-05-17T23:41:53Z"},{"alias_kind":"pith_short_12","alias_value":"IBHBQWX4AWYC","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IBHBQWX4AWYCWWA7","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IBHBQWX4","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IBHBQWX4AWYCWWA73T43NA6NH5","target":"record","payload":{"canonical_record":{"source":{"id":"1904.09533","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-21T02:54:33Z","cross_cats_sorted":["cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"6ad70829679e9d84fb32e10805a32705bf6497d52668fc22d97e1053cb9d94e2","abstract_canon_sha256":"2eb77b7a13bfc3044a6e555579352e6f7588cfb9fdeb921895fa35b5896c495a"},"schema_version":"1.0"},"canonical_sha256":"404e185afc05b02b581fdcf9b683cd3f51e6afe38cf0de260723656be17d5934","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:53.096223Z","signature_b64":"9BXcAXCfJ014hXkNOw7rtYqwMKYZ2Ck0zFxHWvtcSEjmbzJztMkhVdZejUV678D3Oo2GfVdhyJGDEHsdKCvdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"404e185afc05b02b581fdcf9b683cd3f51e6afe38cf0de260723656be17d5934","last_reissued_at":"2026-05-17T23:41:53.095664Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:53.095664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.09533","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6cP4G8dlGXHk220doMdVCgy6/xZR+mnzaxByD4RBRXvShuHiLhy4iRWCdRTt0KrbgMvEJsvkiQFdTbxwV3SiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:28:06.969300Z"},"content_sha256":"68dfb488c80d8929ee646f66c4ec76f52317b85aab53f11f6e9898b05549a329","schema_version":"1.0","event_id":"sha256:68dfb488c80d8929ee646f66c4ec76f52317b85aab53f11f6e9898b05549a329"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IBHBQWX4AWYCWWA73T43NA6NH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GAN-based Generation and Automatic Selection of Explanations for Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bob L. Sturm, Daniel Stoller, Emmanouil Benetos, Saumitra Mishra, Simon Dixon","submitted_at":"2019-04-21T02:54:33Z","abstract_excerpt":"One way to interpret trained deep neural networks (DNNs) is by inspecting characteristics that neurons in the model respond to, such as by iteratively optimising the model input (e.g., an image) to maximally activate specific neurons. However, this requires a careful selection of hyper-parameters to generate interpretable examples for each neuron of interest, and current methods rely on a manual, qualitative evaluation of each setting, which is prohibitively slow. We introduce a new metric that uses Fr\\'echet Inception Distance (FID) to encourage similarity between model activations for real a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09533","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5jTZlFZ3j9fAFK1sczwZvJL/crxb1cUcrunjfIs+qPT60OtOXVmk6pGF7J3ybPWIFP0IyIUQAGO3wOkpCGMaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:28:06.970005Z"},"content_sha256":"711ca421c379114ffcd3c7bee5c3dd8f97cfb922711440cbc1f7b83525f954d5","schema_version":"1.0","event_id":"sha256:711ca421c379114ffcd3c7bee5c3dd8f97cfb922711440cbc1f7b83525f954d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBHBQWX4AWYCWWA73T43NA6NH5/bundle.json","state_url":"https://pith.science/pith/IBHBQWX4AWYCWWA73T43NA6NH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBHBQWX4AWYCWWA73T43NA6NH5/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":"2026-06-08T02:28:06Z","links":{"resolver":"https://pith.science/pith/IBHBQWX4AWYCWWA73T43NA6NH5","bundle":"https://pith.science/pith/IBHBQWX4AWYCWWA73T43NA6NH5/bundle.json","state":"https://pith.science/pith/IBHBQWX4AWYCWWA73T43NA6NH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBHBQWX4AWYCWWA73T43NA6NH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IBHBQWX4AWYCWWA73T43NA6NH5","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":"2eb77b7a13bfc3044a6e555579352e6f7588cfb9fdeb921895fa35b5896c495a","cross_cats_sorted":["cs.SD","eess.AS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-21T02:54:33Z","title_canon_sha256":"6ad70829679e9d84fb32e10805a32705bf6497d52668fc22d97e1053cb9d94e2"},"schema_version":"1.0","source":{"id":"1904.09533","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09533","created_at":"2026-05-17T23:41:53Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09533v2","created_at":"2026-05-17T23:41:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09533","created_at":"2026-05-17T23:41:53Z"},{"alias_kind":"pith_short_12","alias_value":"IBHBQWX4AWYC","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IBHBQWX4AWYCWWA7","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IBHBQWX4","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:711ca421c379114ffcd3c7bee5c3dd8f97cfb922711440cbc1f7b83525f954d5","target":"graph","created_at":"2026-05-17T23:41:53Z","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":"One way to interpret trained deep neural networks (DNNs) is by inspecting characteristics that neurons in the model respond to, such as by iteratively optimising the model input (e.g., an image) to maximally activate specific neurons. However, this requires a careful selection of hyper-parameters to generate interpretable examples for each neuron of interest, and current methods rely on a manual, qualitative evaluation of each setting, which is prohibitively slow. We introduce a new metric that uses Fr\\'echet Inception Distance (FID) to encourage similarity between model activations for real a","authors_text":"Bob L. Sturm, Daniel Stoller, Emmanouil Benetos, Saumitra Mishra, Simon Dixon","cross_cats":["cs.SD","eess.AS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-21T02:54:33Z","title":"GAN-based Generation and Automatic Selection of Explanations for Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09533","kind":"arxiv","version":2},"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":"sha256:68dfb488c80d8929ee646f66c4ec76f52317b85aab53f11f6e9898b05549a329","target":"record","created_at":"2026-05-17T23:41:53Z","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":"2eb77b7a13bfc3044a6e555579352e6f7588cfb9fdeb921895fa35b5896c495a","cross_cats_sorted":["cs.SD","eess.AS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-21T02:54:33Z","title_canon_sha256":"6ad70829679e9d84fb32e10805a32705bf6497d52668fc22d97e1053cb9d94e2"},"schema_version":"1.0","source":{"id":"1904.09533","kind":"arxiv","version":2}},"canonical_sha256":"404e185afc05b02b581fdcf9b683cd3f51e6afe38cf0de260723656be17d5934","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"404e185afc05b02b581fdcf9b683cd3f51e6afe38cf0de260723656be17d5934","first_computed_at":"2026-05-17T23:41:53.095664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:53.095664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9BXcAXCfJ014hXkNOw7rtYqwMKYZ2Ck0zFxHWvtcSEjmbzJztMkhVdZejUV678D3Oo2GfVdhyJGDEHsdKCvdDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:53.096223Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.09533","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68dfb488c80d8929ee646f66c4ec76f52317b85aab53f11f6e9898b05549a329","sha256:711ca421c379114ffcd3c7bee5c3dd8f97cfb922711440cbc1f7b83525f954d5"],"state_sha256":"1274eb0cadccc397dad9fded1bb6034507850dd85435e90a84acb1f85c19dec1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKzhAMLVKQl/HavsVenMYaI11c1WelXkdCb/xUOwZF+CSgHkyvwJeez6YsKkkJN2e9u/GJ3XQvamDqod90rRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T02:28:06.974236Z","bundle_sha256":"598637a37e5720082a940c75b8cf420961dd899e258c4568c290d7fe75c3c665"}}