{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BUMLJQ7WX5OKKU6FLHQPMI4GMR","short_pith_number":"pith:BUMLJQ7W","canonical_record":{"source":{"id":"1904.00760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-20T16:37:17Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2248255d56b7977005ab2d704a79e775a9843044e0b0cb6e6a36b1795d2074df","abstract_canon_sha256":"a7ebe51468110905c6f1029e56489edbd7fe87bd55b43805d5d2b85b68d6aca9"},"schema_version":"1.0"},"canonical_sha256":"0d18b4c3f6bf5ca553c559e0f623866453af2c877ca03b6ed7e62aabfe5be32c","source":{"kind":"arxiv","id":"1904.00760","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.00760","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"1904.00760v1","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.00760","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"BUMLJQ7WX5OK","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BUMLJQ7WX5OKKU6F","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BUMLJQ7W","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BUMLJQ7WX5OKKU6FLHQPMI4GMR","target":"record","payload":{"canonical_record":{"source":{"id":"1904.00760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-20T16:37:17Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2248255d56b7977005ab2d704a79e775a9843044e0b0cb6e6a36b1795d2074df","abstract_canon_sha256":"a7ebe51468110905c6f1029e56489edbd7fe87bd55b43805d5d2b85b68d6aca9"},"schema_version":"1.0"},"canonical_sha256":"0d18b4c3f6bf5ca553c559e0f623866453af2c877ca03b6ed7e62aabfe5be32c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:45.552356Z","signature_b64":"NJQejdV4NS/ywTXbO/M7FYocpaX0JM1u/Gc/j6ka8lg9Mrl6fQbcFcu8YH3iu8tAls50dqJeFD3/ehSdk7i7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d18b4c3f6bf5ca553c559e0f623866453af2c877ca03b6ed7e62aabfe5be32c","last_reissued_at":"2026-05-17T23:49:45.551789Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:45.551789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.00760","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":"2026-05-17T23:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ey1lRgqeqGoWd3zRWDgVTbYNh8sGwvWND7mYsZkd0Cq9Eli9nEeVmIjh6Fn4NZWACV6snDY5iDDEstvEupr5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:40:27.996190Z"},"content_sha256":"5dbbf30be06b6c8af2b6b0c6689931feaf3ce780e984547854aee52ac3e239d5","schema_version":"1.0","event_id":"sha256:5dbbf30be06b6c8af2b6b0c6689931feaf3ce780e984547854aee52ac3e239d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BUMLJQ7WX5OKKU6FLHQPMI4GMR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Matthias Bethge, Wieland Brendel","submitted_at":"2019-03-20T16:37:17Z","abstract_excerpt":"Deep Neural Networks (DNNs) excel on many complex perceptual tasks but it has proven notoriously difficult to understand how they reach their decisions. We here introduce a high-performance DNN architecture on ImageNet whose decisions are considerably easier to explain. Our model, a simple variant of the ResNet-50 architecture called BagNet, classifies an image based on the occurrences of small local image features without taking into account their spatial ordering. This strategy is closely related to the bag-of-feature (BoF) models popular before the onset of deep learning and reaches a surpr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.00760","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":"2026-05-17T23:49:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n20tlK9FPApD7iO3TKKirvSstmJze4Iz1yab1CPLXjOKjNFENfeQjYR247YcgJlX3FrEh9MT+binDhtQOR7BCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:40:27.996649Z"},"content_sha256":"ef6353504e402f2f5629e9c2bb87a6a917afe481f336974495e7a008f17315b4","schema_version":"1.0","event_id":"sha256:ef6353504e402f2f5629e9c2bb87a6a917afe481f336974495e7a008f17315b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BUMLJQ7WX5OKKU6FLHQPMI4GMR/bundle.json","state_url":"https://pith.science/pith/BUMLJQ7WX5OKKU6FLHQPMI4GMR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BUMLJQ7WX5OKKU6FLHQPMI4GMR/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":"2026-08-03T20:40:27Z","links":{"resolver":"https://pith.science/pith/BUMLJQ7WX5OKKU6FLHQPMI4GMR","bundle":"https://pith.science/pith/BUMLJQ7WX5OKKU6FLHQPMI4GMR/bundle.json","state":"https://pith.science/pith/BUMLJQ7WX5OKKU6FLHQPMI4GMR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BUMLJQ7WX5OKKU6FLHQPMI4GMR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BUMLJQ7WX5OKKU6FLHQPMI4GMR","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":"a7ebe51468110905c6f1029e56489edbd7fe87bd55b43805d5d2b85b68d6aca9","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-20T16:37:17Z","title_canon_sha256":"2248255d56b7977005ab2d704a79e775a9843044e0b0cb6e6a36b1795d2074df"},"schema_version":"1.0","source":{"id":"1904.00760","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.00760","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"arxiv_version","alias_value":"1904.00760v1","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.00760","created_at":"2026-05-17T23:49:45Z"},{"alias_kind":"pith_short_12","alias_value":"BUMLJQ7WX5OK","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BUMLJQ7WX5OKKU6F","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BUMLJQ7W","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:ef6353504e402f2f5629e9c2bb87a6a917afe481f336974495e7a008f17315b4","target":"graph","created_at":"2026-05-17T23:49:45Z","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":"Deep Neural Networks (DNNs) excel on many complex perceptual tasks but it has proven notoriously difficult to understand how they reach their decisions. We here introduce a high-performance DNN architecture on ImageNet whose decisions are considerably easier to explain. Our model, a simple variant of the ResNet-50 architecture called BagNet, classifies an image based on the occurrences of small local image features without taking into account their spatial ordering. This strategy is closely related to the bag-of-feature (BoF) models popular before the onset of deep learning and reaches a surpr","authors_text":"Matthias Bethge, Wieland Brendel","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-20T16:37:17Z","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.00760","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":"sha256:5dbbf30be06b6c8af2b6b0c6689931feaf3ce780e984547854aee52ac3e239d5","target":"record","created_at":"2026-05-17T23:49:45Z","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":"a7ebe51468110905c6f1029e56489edbd7fe87bd55b43805d5d2b85b68d6aca9","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-20T16:37:17Z","title_canon_sha256":"2248255d56b7977005ab2d704a79e775a9843044e0b0cb6e6a36b1795d2074df"},"schema_version":"1.0","source":{"id":"1904.00760","kind":"arxiv","version":1}},"canonical_sha256":"0d18b4c3f6bf5ca553c559e0f623866453af2c877ca03b6ed7e62aabfe5be32c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d18b4c3f6bf5ca553c559e0f623866453af2c877ca03b6ed7e62aabfe5be32c","first_computed_at":"2026-05-17T23:49:45.551789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:45.551789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NJQejdV4NS/ywTXbO/M7FYocpaX0JM1u/Gc/j6ka8lg9Mrl6fQbcFcu8YH3iu8tAls50dqJeFD3/ehSdk7i7DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:45.552356Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.00760","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dbbf30be06b6c8af2b6b0c6689931feaf3ce780e984547854aee52ac3e239d5","sha256:ef6353504e402f2f5629e9c2bb87a6a917afe481f336974495e7a008f17315b4"],"state_sha256":"e519280b733fffe546252d21596d555ba0db1d29bcb83ebaad856268d7f4cf4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e3P4LX0aWQHPSdjR4M03rl18CR2TPKpe2AC+zB7dpaZDaikSk0ofXm1JKN0AdXX3yDg5tY4W6Btw8aTZyBfuAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:40:28.001162Z","bundle_sha256":"8e9dc279862bfb15f404bd96e2f48ed0ad3827291dbdfe12cbcc55605816f5d8"}}