{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QGU6ZBWUJGX4T4LXVDH2XE7AQP","short_pith_number":"pith:QGU6ZBWU","canonical_record":{"source":{"id":"1704.03557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T22:35:58Z","cross_cats_sorted":[],"title_canon_sha256":"b478c3196103cc9cfafba889d260dbc936ed97df204900ef32405c1619a50bb4","abstract_canon_sha256":"c67f1388771d02d89eb042f1a977ba9ff39efb7072cce8b682d3ab85e4b0c32c"},"schema_version":"1.0"},"canonical_sha256":"81a9ec86d449afc9f177a8cfab93e083cdc8a21fedbf5b27b286e3a089d11ef4","source":{"kind":"arxiv","id":"1704.03557","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.03557","created_at":"2026-05-18T00:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"1704.03557v1","created_at":"2026-05-18T00:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03557","created_at":"2026-05-18T00:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"QGU6ZBWUJGX4","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QGU6ZBWUJGX4T4LX","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QGU6ZBWU","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QGU6ZBWUJGX4T4LXVDH2XE7AQP","target":"record","payload":{"canonical_record":{"source":{"id":"1704.03557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T22:35:58Z","cross_cats_sorted":[],"title_canon_sha256":"b478c3196103cc9cfafba889d260dbc936ed97df204900ef32405c1619a50bb4","abstract_canon_sha256":"c67f1388771d02d89eb042f1a977ba9ff39efb7072cce8b682d3ab85e4b0c32c"},"schema_version":"1.0"},"canonical_sha256":"81a9ec86d449afc9f177a8cfab93e083cdc8a21fedbf5b27b286e3a089d11ef4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:07.030136Z","signature_b64":"UnEHaY7zWCYuW513I+ibL/Ot3+F6yS1MDJk6SftyB/u2FUi7e/HfWpZyq4PniE7RwCK24oaZpPsRHxNyEYNMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81a9ec86d449afc9f177a8cfab93e083cdc8a21fedbf5b27b286e3a089d11ef4","last_reissued_at":"2026-05-18T00:20:07.029485Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:07.029485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.03557","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":"2026-05-18T00:20:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1aUZhWqVsPWv0RXAl2WVR+UX+ZZpYyGlxhr0saFRPzsznrj0wDJLMzL7Xly6qkCBjM06qsSbTYEVIOlXrpdBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:25:20.784363Z"},"content_sha256":"aec3b2fda4c109023f07a722971a5b6ea88e38b1378ea2b6527de07e81eb605a","schema_version":"1.0","event_id":"sha256:aec3b2fda4c109023f07a722971a5b6ea88e38b1378ea2b6527de07e81eb605a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QGU6ZBWUJGX4T4LXVDH2XE7AQP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas K\\\"olsch, Marcus Liwicki, Muhammad Zeshan Afzal, Sheraz Ahmed","submitted_at":"2017-04-11T22:35:58Z","abstract_excerpt":"We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half. Existing approaches, such as the DeepDocClassifier, apply standard Convolutional Network architectures with transfer learning from the object recognition domain. The contribution of the paper is threefold: First, it investigates recently introduced very deep neural network architectures (GoogLeNet, VGG, ResNet) using transfer learning (from real images). Second, it proposes transfer learning from a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03557","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":"2026-05-18T00:20:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"trogm+mmEIb0kKHgcDO0Cju9KIxUjT14MvOjdCFRFK65OTRDXjkWnIUQO2v8mi/V5I18EqMaVw/jSFDnqVaYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:25:20.784754Z"},"content_sha256":"1023417625b9cd95c5e4b387d308ca18edd0dd4801263c350f4187e56d71e4c3","schema_version":"1.0","event_id":"sha256:1023417625b9cd95c5e4b387d308ca18edd0dd4801263c350f4187e56d71e4c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QGU6ZBWUJGX4T4LXVDH2XE7AQP/bundle.json","state_url":"https://pith.science/pith/QGU6ZBWUJGX4T4LXVDH2XE7AQP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QGU6ZBWUJGX4T4LXVDH2XE7AQP/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":"2026-05-30T17:25:20Z","links":{"resolver":"https://pith.science/pith/QGU6ZBWUJGX4T4LXVDH2XE7AQP","bundle":"https://pith.science/pith/QGU6ZBWUJGX4T4LXVDH2XE7AQP/bundle.json","state":"https://pith.science/pith/QGU6ZBWUJGX4T4LXVDH2XE7AQP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QGU6ZBWUJGX4T4LXVDH2XE7AQP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QGU6ZBWUJGX4T4LXVDH2XE7AQP","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":"c67f1388771d02d89eb042f1a977ba9ff39efb7072cce8b682d3ab85e4b0c32c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T22:35:58Z","title_canon_sha256":"b478c3196103cc9cfafba889d260dbc936ed97df204900ef32405c1619a50bb4"},"schema_version":"1.0","source":{"id":"1704.03557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.03557","created_at":"2026-05-18T00:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"1704.03557v1","created_at":"2026-05-18T00:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03557","created_at":"2026-05-18T00:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"QGU6ZBWUJGX4","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QGU6ZBWUJGX4T4LX","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QGU6ZBWU","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:1023417625b9cd95c5e4b387d308ca18edd0dd4801263c350f4187e56d71e4c3","target":"graph","created_at":"2026-05-18T00:20:07Z","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":"We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half. Existing approaches, such as the DeepDocClassifier, apply standard Convolutional Network architectures with transfer learning from the object recognition domain. The contribution of the paper is threefold: First, it investigates recently introduced very deep neural network architectures (GoogLeNet, VGG, ResNet) using transfer learning (from real images). Second, it proposes transfer learning from a ","authors_text":"Andreas K\\\"olsch, Marcus Liwicki, Muhammad Zeshan Afzal, Sheraz Ahmed","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T22:35:58Z","title":"Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03557","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:aec3b2fda4c109023f07a722971a5b6ea88e38b1378ea2b6527de07e81eb605a","target":"record","created_at":"2026-05-18T00:20:07Z","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":"c67f1388771d02d89eb042f1a977ba9ff39efb7072cce8b682d3ab85e4b0c32c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-11T22:35:58Z","title_canon_sha256":"b478c3196103cc9cfafba889d260dbc936ed97df204900ef32405c1619a50bb4"},"schema_version":"1.0","source":{"id":"1704.03557","kind":"arxiv","version":1}},"canonical_sha256":"81a9ec86d449afc9f177a8cfab93e083cdc8a21fedbf5b27b286e3a089d11ef4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81a9ec86d449afc9f177a8cfab93e083cdc8a21fedbf5b27b286e3a089d11ef4","first_computed_at":"2026-05-18T00:20:07.029485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:07.029485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UnEHaY7zWCYuW513I+ibL/Ot3+F6yS1MDJk6SftyB/u2FUi7e/HfWpZyq4PniE7RwCK24oaZpPsRHxNyEYNMBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:07.030136Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.03557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aec3b2fda4c109023f07a722971a5b6ea88e38b1378ea2b6527de07e81eb605a","sha256:1023417625b9cd95c5e4b387d308ca18edd0dd4801263c350f4187e56d71e4c3"],"state_sha256":"7e24a980775f57d5ae56136b6f38f6400c15c662df1fa7d7fab674c6bfcf0b75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dkUjRJ5YWEPu5J6LIZ79eeCEpfi8f1nvbGmnX+Wp7BfhMCgVdXvy2WdN3uUug/jBE1iUsPySP/CJLa08ACZxCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T17:25:20.786753Z","bundle_sha256":"f39a67748d6b3286e4102ecf9e82a6cb281b3e999077f2d52ed2ca1b23b489cd"}}