{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:JH52FQ3YDI2EF23JAVRTPFBAIR","short_pith_number":"pith:JH52FQ3Y","schema_version":"1.0","canonical_sha256":"49fba2c3781a3442eb690563379420445d799fc9be0e60505ab028d28da0e0bc","source":{"kind":"arxiv","id":"1405.3531","version":4},"attestation_state":"computed","paper":{"title":"Return of the Devil in the Details: Delving Deep into Convolutional Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Karen Simonyan, Ken Chatfield","submitted_at":"2014-05-14T15:19:22Z","abstract_excerpt":"The latest generation of Convolutional Neural Networks (CNN) have achieved impressive results in challenging benchmarks on image recognition and object detection, significantly raising the interest of the community in these methods. Nevertheless, it is still unclear how different CNN methods compare with each other and with previous state-of-the-art shallow representations such as the Bag-of-Visual-Words and the Improved Fisher Vector. This paper conducts a rigorous evaluation of these new techniques, exploring different deep architectures and comparing them on a common ground, identifying and"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1405.3531","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-05-14T15:19:22Z","cross_cats_sorted":[],"title_canon_sha256":"04c8b8181dbc8eef698ecc2ecdf2d46533808d898f83e91eba37ce01ab165b8d","abstract_canon_sha256":"88ad71a62b734433b5e5c782257060e0f54d3d272e68f02865ba579731d6aa92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:38:36.926513Z","signature_b64":"yuuSyCrluPPS2zgxCFO3cSZ2qIXq/dCc9iz5HTyecCFKnfZcu2Y+fk5VOnixRhhrS3woDWr6SD3XGfGkp8WvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49fba2c3781a3442eb690563379420445d799fc9be0e60505ab028d28da0e0bc","last_reissued_at":"2026-05-18T02:38:36.925736Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:38:36.925736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Return of the Devil in the Details: Delving Deep into Convolutional Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Karen Simonyan, Ken Chatfield","submitted_at":"2014-05-14T15:19:22Z","abstract_excerpt":"The latest generation of Convolutional Neural Networks (CNN) have achieved impressive results in challenging benchmarks on image recognition and object detection, significantly raising the interest of the community in these methods. Nevertheless, it is still unclear how different CNN methods compare with each other and with previous state-of-the-art shallow representations such as the Bag-of-Visual-Words and the Improved Fisher Vector. This paper conducts a rigorous evaluation of these new techniques, exploring different deep architectures and comparing them on a common ground, identifying and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.3531","kind":"arxiv","version":4},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1405.3531","created_at":"2026-05-18T02:38:36.925858+00:00"},{"alias_kind":"arxiv_version","alias_value":"1405.3531v4","created_at":"2026-05-18T02:38:36.925858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.3531","created_at":"2026-05-18T02:38:36.925858+00:00"},{"alias_kind":"pith_short_12","alias_value":"JH52FQ3YDI2E","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_16","alias_value":"JH52FQ3YDI2EF23J","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_8","alias_value":"JH52FQ3Y","created_at":"2026-05-18T12:28:33.132498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.17131","citing_title":"A Systematic Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":133,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JH52FQ3YDI2EF23JAVRTPFBAIR","json":"https://pith.science/pith/JH52FQ3YDI2EF23JAVRTPFBAIR.json","graph_json":"https://pith.science/api/pith-number/JH52FQ3YDI2EF23JAVRTPFBAIR/graph.json","events_json":"https://pith.science/api/pith-number/JH52FQ3YDI2EF23JAVRTPFBAIR/events.json","paper":"https://pith.science/paper/JH52FQ3Y"},"agent_actions":{"view_html":"https://pith.science/pith/JH52FQ3YDI2EF23JAVRTPFBAIR","download_json":"https://pith.science/pith/JH52FQ3YDI2EF23JAVRTPFBAIR.json","view_paper":"https://pith.science/paper/JH52FQ3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1405.3531&json=true","fetch_graph":"https://pith.science/api/pith-number/JH52FQ3YDI2EF23JAVRTPFBAIR/graph.json","fetch_events":"https://pith.science/api/pith-number/JH52FQ3YDI2EF23JAVRTPFBAIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JH52FQ3YDI2EF23JAVRTPFBAIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JH52FQ3YDI2EF23JAVRTPFBAIR/action/storage_attestation","attest_author":"https://pith.science/pith/JH52FQ3YDI2EF23JAVRTPFBAIR/action/author_attestation","sign_citation":"https://pith.science/pith/JH52FQ3YDI2EF23JAVRTPFBAIR/action/citation_signature","submit_replication":"https://pith.science/pith/JH52FQ3YDI2EF23JAVRTPFBAIR/action/replication_record"}},"created_at":"2026-05-18T02:38:36.925858+00:00","updated_at":"2026-05-18T02:38:36.925858+00:00"}