{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:74DQKTX4VVYJQGCNNKN4CH5D5O","short_pith_number":"pith:74DQKTX4","canonical_record":{"source":{"id":"1802.07672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T17:11:31Z","cross_cats_sorted":[],"title_canon_sha256":"6e68030bed6d5bb87b63747a9c8eb6a199a7bc200e6ee3e7503d46d685283493","abstract_canon_sha256":"932cb3ca41a5ef1648e4bcb140efb331cd2c7da9291fec04f503bf1b20ac6c82"},"schema_version":"1.0"},"canonical_sha256":"ff07054efcad7098184d6a9bc11fa3eb882676c43fa1acf7515972f11f466056","source":{"kind":"arxiv","id":"1802.07672","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07672","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07672v1","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07672","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"74DQKTX4VVYJ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"74DQKTX4VVYJQGCN","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"74DQKTX4","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:74DQKTX4VVYJQGCNNKN4CH5D5O","target":"record","payload":{"canonical_record":{"source":{"id":"1802.07672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T17:11:31Z","cross_cats_sorted":[],"title_canon_sha256":"6e68030bed6d5bb87b63747a9c8eb6a199a7bc200e6ee3e7503d46d685283493","abstract_canon_sha256":"932cb3ca41a5ef1648e4bcb140efb331cd2c7da9291fec04f503bf1b20ac6c82"},"schema_version":"1.0"},"canonical_sha256":"ff07054efcad7098184d6a9bc11fa3eb882676c43fa1acf7515972f11f466056","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:49.657505Z","signature_b64":"HKB9zkLdeZkGaAtmJXcQWB71cteqoXDWM4uhv1rawuLlSnlaRNft37gqmOsRozl9gq0wr9Kq2z8oqEUyyScxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff07054efcad7098184d6a9bc11fa3eb882676c43fa1acf7515972f11f466056","last_reissued_at":"2026-05-18T00:22:49.657084Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:49.657084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.07672","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tu8fn+69Kl5HRnuVffgePA3vTloCrR23xjn+KvlypP17nS3CDNExZqXNL35aapE+YpZrzT0CwxP39hnPerAQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T18:47:57.355058Z"},"content_sha256":"3e7f7011804758f660463449844623c30c4f59d1cdd6a282a00c6d2c6ad5b8b6","schema_version":"1.0","event_id":"sha256:3e7f7011804758f660463449844623c30c4f59d1cdd6a282a00c6d2c6ad5b8b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:74DQKTX4VVYJQGCNNKN4CH5D5O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Multiple Categories on Deep Convolution Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duncan Gillies, Mohamed Hajaj","submitted_at":"2018-02-21T17:11:31Z","abstract_excerpt":"Deep convolution networks have proved very successful with big datasets such as the 1000-classes ImageNet. Results show that the error rate increases slowly as the size of the dataset increases. Experiments presented here may explain why these networks are very effective in solving big recognition problems. If the big task is made up of multiple smaller tasks, then the results show the ability of deep convolution networks to decompose the complex task into a number of smaller tasks and to learn them simultaneously. The results show that the performance of solving the big task on a single netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07672","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yMfBgKH14Wpi8TNG1vi79SptiIp+H1bK5Y9Z6UMbJmeiDR+HB+WlGKVVKV+Qt26B/BPtavfwfTKo7WFDEpkICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T18:47:57.355787Z"},"content_sha256":"0a8ffa2453af1af142865a9494258057fcccabf67d6ca232b302fcffce3ee674","schema_version":"1.0","event_id":"sha256:0a8ffa2453af1af142865a9494258057fcccabf67d6ca232b302fcffce3ee674"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/74DQKTX4VVYJQGCNNKN4CH5D5O/bundle.json","state_url":"https://pith.science/pith/74DQKTX4VVYJQGCNNKN4CH5D5O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/74DQKTX4VVYJQGCNNKN4CH5D5O/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":"2026-06-08T18:47:57Z","links":{"resolver":"https://pith.science/pith/74DQKTX4VVYJQGCNNKN4CH5D5O","bundle":"https://pith.science/pith/74DQKTX4VVYJQGCNNKN4CH5D5O/bundle.json","state":"https://pith.science/pith/74DQKTX4VVYJQGCNNKN4CH5D5O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/74DQKTX4VVYJQGCNNKN4CH5D5O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:74DQKTX4VVYJQGCNNKN4CH5D5O","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":"932cb3ca41a5ef1648e4bcb140efb331cd2c7da9291fec04f503bf1b20ac6c82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T17:11:31Z","title_canon_sha256":"6e68030bed6d5bb87b63747a9c8eb6a199a7bc200e6ee3e7503d46d685283493"},"schema_version":"1.0","source":{"id":"1802.07672","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07672","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07672v1","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07672","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"74DQKTX4VVYJ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"74DQKTX4VVYJQGCN","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"74DQKTX4","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:0a8ffa2453af1af142865a9494258057fcccabf67d6ca232b302fcffce3ee674","target":"graph","created_at":"2026-05-18T00:22:49Z","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 convolution networks have proved very successful with big datasets such as the 1000-classes ImageNet. Results show that the error rate increases slowly as the size of the dataset increases. Experiments presented here may explain why these networks are very effective in solving big recognition problems. If the big task is made up of multiple smaller tasks, then the results show the ability of deep convolution networks to decompose the complex task into a number of smaller tasks and to learn them simultaneously. The results show that the performance of solving the big task on a single netwo","authors_text":"Duncan Gillies, Mohamed Hajaj","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T17:11:31Z","title":"Learning Multiple Categories on Deep Convolution Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07672","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":"sha256:3e7f7011804758f660463449844623c30c4f59d1cdd6a282a00c6d2c6ad5b8b6","target":"record","created_at":"2026-05-18T00:22:49Z","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":"932cb3ca41a5ef1648e4bcb140efb331cd2c7da9291fec04f503bf1b20ac6c82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T17:11:31Z","title_canon_sha256":"6e68030bed6d5bb87b63747a9c8eb6a199a7bc200e6ee3e7503d46d685283493"},"schema_version":"1.0","source":{"id":"1802.07672","kind":"arxiv","version":1}},"canonical_sha256":"ff07054efcad7098184d6a9bc11fa3eb882676c43fa1acf7515972f11f466056","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff07054efcad7098184d6a9bc11fa3eb882676c43fa1acf7515972f11f466056","first_computed_at":"2026-05-18T00:22:49.657084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:49.657084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HKB9zkLdeZkGaAtmJXcQWB71cteqoXDWM4uhv1rawuLlSnlaRNft37gqmOsRozl9gq0wr9Kq2z8oqEUyyScxDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:49.657505Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.07672","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e7f7011804758f660463449844623c30c4f59d1cdd6a282a00c6d2c6ad5b8b6","sha256:0a8ffa2453af1af142865a9494258057fcccabf67d6ca232b302fcffce3ee674"],"state_sha256":"74f3db7cfad9229a17812e657a7bfcec5153beb379b030f9f99cbae00f04a447"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TpwunMkKH453hOz8iaDq+FhZBwMoY5vMMWMosxVDbMdA45itLXJbtubeAJLxK04ShXXJdotEKy7szbouwMMuBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T18:47:57.359515Z","bundle_sha256":"fd4e8b545ef3ca0544a0c288f24c19a0fd3655e18bf81723eea58f85034129cb"}}