{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:URYZUOFKMDKFTWS4CS6JFMY2OS","short_pith_number":"pith:URYZUOFK","schema_version":"1.0","canonical_sha256":"a4719a38aa60d459da5c14bc92b31a74b265010cbb069f3dca25b625f8e30e11","source":{"kind":"arxiv","id":"1611.06596","version":3},"attestation_state":"computed","paper":{"title":"Object Recognition with and without Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan L. Yuille, Lingxi Xie, Zhuotun Zhu","submitted_at":"2016-11-20T21:20:32Z","abstract_excerpt":"While recent deep neural networks have achieved a promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural net- works on the foreground (object) and background (context) regions of images respectively. Consider- ing human recognition in the same situations, net- works trained on the pure background without ob- jects achieves highly reasonable recognition performance that beats humans by a large margin if only given context. However, humans still outperform networks with pure object available, which indicate"},"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":"1611.06596","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-20T21:20:32Z","cross_cats_sorted":[],"title_canon_sha256":"6bd1061f69f7171f6ce81a9767c67b544d2be05e5d79ef5845a0280a1986b8d6","abstract_canon_sha256":"ccb53e98e2f96f63f91a521a376390ca5288e7e462c47e083001bb5a1be21848"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:39.499294Z","signature_b64":"VtcVAh2CJ/PuY2LsjMyb6sPUyh7pB4eoOj5IX1IDQdQBotR//+xqzWx/UmWN70aezekxEBY5/LfqivPA27TmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4719a38aa60d459da5c14bc92b31a74b265010cbb069f3dca25b625f8e30e11","last_reissued_at":"2026-05-18T00:43:39.498622Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:39.498622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object Recognition with and without Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan L. Yuille, Lingxi Xie, Zhuotun Zhu","submitted_at":"2016-11-20T21:20:32Z","abstract_excerpt":"While recent deep neural networks have achieved a promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural net- works on the foreground (object) and background (context) regions of images respectively. Consider- ing human recognition in the same situations, net- works trained on the pure background without ob- jects achieves highly reasonable recognition performance that beats humans by a large margin if only given context. However, humans still outperform networks with pure object available, which indicate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06596","kind":"arxiv","version":3},"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":"1611.06596","created_at":"2026-05-18T00:43:39.498752+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.06596v3","created_at":"2026-05-18T00:43:39.498752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06596","created_at":"2026-05-18T00:43:39.498752+00:00"},{"alias_kind":"pith_short_12","alias_value":"URYZUOFKMDKF","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"URYZUOFKMDKFTWS4","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"URYZUOFK","created_at":"2026-05-18T12:30:46.583412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20549","citing_title":"MAPS: A Synthetic Dataset for Probing Vision Models in a Controlled 3D Scene Space","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URYZUOFKMDKFTWS4CS6JFMY2OS","json":"https://pith.science/pith/URYZUOFKMDKFTWS4CS6JFMY2OS.json","graph_json":"https://pith.science/api/pith-number/URYZUOFKMDKFTWS4CS6JFMY2OS/graph.json","events_json":"https://pith.science/api/pith-number/URYZUOFKMDKFTWS4CS6JFMY2OS/events.json","paper":"https://pith.science/paper/URYZUOFK"},"agent_actions":{"view_html":"https://pith.science/pith/URYZUOFKMDKFTWS4CS6JFMY2OS","download_json":"https://pith.science/pith/URYZUOFKMDKFTWS4CS6JFMY2OS.json","view_paper":"https://pith.science/paper/URYZUOFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.06596&json=true","fetch_graph":"https://pith.science/api/pith-number/URYZUOFKMDKFTWS4CS6JFMY2OS/graph.json","fetch_events":"https://pith.science/api/pith-number/URYZUOFKMDKFTWS4CS6JFMY2OS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URYZUOFKMDKFTWS4CS6JFMY2OS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URYZUOFKMDKFTWS4CS6JFMY2OS/action/storage_attestation","attest_author":"https://pith.science/pith/URYZUOFKMDKFTWS4CS6JFMY2OS/action/author_attestation","sign_citation":"https://pith.science/pith/URYZUOFKMDKFTWS4CS6JFMY2OS/action/citation_signature","submit_replication":"https://pith.science/pith/URYZUOFKMDKFTWS4CS6JFMY2OS/action/replication_record"}},"created_at":"2026-05-18T00:43:39.498752+00:00","updated_at":"2026-05-18T00:43:39.498752+00:00"}