{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ITJL6SXGHZGSD7GX7QCTGJHSUJ","short_pith_number":"pith:ITJL6SXG","schema_version":"1.0","canonical_sha256":"44d2bf4ae63e4d21fcd7fc053324f2a278a69917807af19c3e48e8721416511f","source":{"kind":"arxiv","id":"2409.10775","version":1},"attestation_state":"computed","paper":{"title":"Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Francesco Luzi, Jordan M. Malof, Kaleb Kassaw, Leslie M. Collins","submitted_at":"2024-09-16T23:21:22Z","abstract_excerpt":"Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under conditions of partial occlusion, i.e., conditions in which objects are partially covered from the view of a camera. Methods to improve performance under occlusion, including data augmentation, part-based clustering, and more inherently robust architectures, including Vision Transformer (ViT) models, have, to some extent, been evaluated on their ability to classify objects under partial occlusion. However, evaluations of these methods have largely rel"},"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":"2409.10775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T23:21:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d8c9fc184a6c201007de82cf5fbf67e1271c1f70c4a22f7585428bce906fe870","abstract_canon_sha256":"ab4d486a1f19536411de3b9420ea0fadc0247ff3796fc5d9d5002651a73b00ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:56.781420Z","signature_b64":"XGBYNahZxzYzi5No9+f8VpWFckdj7Mj/om7G6qalAKdKMShgVFf51PdBlJ9nD/CJfqECdCblU2QYS2jwm89fBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44d2bf4ae63e4d21fcd7fc053324f2a278a69917807af19c3e48e8721416511f","last_reissued_at":"2026-07-05T09:07:56.780729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:56.780729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Francesco Luzi, Jordan M. Malof, Kaleb Kassaw, Leslie M. Collins","submitted_at":"2024-09-16T23:21:22Z","abstract_excerpt":"Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under conditions of partial occlusion, i.e., conditions in which objects are partially covered from the view of a camera. Methods to improve performance under occlusion, including data augmentation, part-based clustering, and more inherently robust architectures, including Vision Transformer (ViT) models, have, to some extent, been evaluated on their ability to classify objects under partial occlusion. However, evaluations of these methods have largely rel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10775","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.10775/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2409.10775","created_at":"2026-07-05T09:07:56.780807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10775v1","created_at":"2026-07-05T09:07:56.780807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10775","created_at":"2026-07-05T09:07:56.780807+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITJL6SXGHZGS","created_at":"2026-07-05T09:07:56.780807+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITJL6SXGHZGSD7GX","created_at":"2026-07-05T09:07:56.780807+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITJL6SXG","created_at":"2026-07-05T09:07:56.780807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.15485","citing_title":"CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ITJL6SXGHZGSD7GX7QCTGJHSUJ","json":"https://pith.science/pith/ITJL6SXGHZGSD7GX7QCTGJHSUJ.json","graph_json":"https://pith.science/api/pith-number/ITJL6SXGHZGSD7GX7QCTGJHSUJ/graph.json","events_json":"https://pith.science/api/pith-number/ITJL6SXGHZGSD7GX7QCTGJHSUJ/events.json","paper":"https://pith.science/paper/ITJL6SXG"},"agent_actions":{"view_html":"https://pith.science/pith/ITJL6SXGHZGSD7GX7QCTGJHSUJ","download_json":"https://pith.science/pith/ITJL6SXGHZGSD7GX7QCTGJHSUJ.json","view_paper":"https://pith.science/paper/ITJL6SXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10775&json=true","fetch_graph":"https://pith.science/api/pith-number/ITJL6SXGHZGSD7GX7QCTGJHSUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ITJL6SXGHZGSD7GX7QCTGJHSUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITJL6SXGHZGSD7GX7QCTGJHSUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITJL6SXGHZGSD7GX7QCTGJHSUJ/action/storage_attestation","attest_author":"https://pith.science/pith/ITJL6SXGHZGSD7GX7QCTGJHSUJ/action/author_attestation","sign_citation":"https://pith.science/pith/ITJL6SXGHZGSD7GX7QCTGJHSUJ/action/citation_signature","submit_replication":"https://pith.science/pith/ITJL6SXGHZGSD7GX7QCTGJHSUJ/action/replication_record"}},"created_at":"2026-07-05T09:07:56.780807+00:00","updated_at":"2026-07-05T09:07:56.780807+00:00"}