{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:E6CRSEMWAYADAEXJ2YLBFET5VU","short_pith_number":"pith:E6CRSEMW","schema_version":"1.0","canonical_sha256":"278519119606003012e9d61612927dad33bd4ff7a03c4d9c7e9735f6a3936fcf","source":{"kind":"arxiv","id":"1805.08819","version":4},"attestation_state":"computed","paper":{"title":"Learning what and where to attend","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Shiebler, Drew Linsley, Sven Eberhardt, Thomas Serre","submitted_at":"2018-05-22T19:12:47Z","abstract_excerpt":"Most recent gains in visual recognition have originated from the inclusion of attention mechanisms in deep convolutional networks (DCNs). Because these networks are optimized for object recognition, they learn where to attend using only a weak form of supervision derived from image class labels. Here, we demonstrate the benefit of using stronger supervisory signals by teaching DCNs to attend to image regions that humans deem important for object recognition. We first describe a large-scale online experiment (ClickMe) used to supplement ImageNet with nearly half a million human-derived \"top-dow"},"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":"1805.08819","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-22T19:12:47Z","cross_cats_sorted":[],"title_canon_sha256":"3943e014c500d4c5505e88c0c2728fd8b9d132437abb1cf49ab29c50b7c62ea9","abstract_canon_sha256":"0d317efb46ca7ae5054646a21cea6d4aa93a9a7b9240502da377cf309f072fcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:38.355392Z","signature_b64":"hkXoylh+NTQJydLPK0nFob4q9ZBT/jgcV3e9otxtA6jt3G6DFXOF2D/v7ysdl7Or+2G2Z4bw+FAJo2pk8RiUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"278519119606003012e9d61612927dad33bd4ff7a03c4d9c7e9735f6a3936fcf","last_reissued_at":"2026-05-17T23:43:38.354767Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:38.354767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning what and where to attend","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Shiebler, Drew Linsley, Sven Eberhardt, Thomas Serre","submitted_at":"2018-05-22T19:12:47Z","abstract_excerpt":"Most recent gains in visual recognition have originated from the inclusion of attention mechanisms in deep convolutional networks (DCNs). Because these networks are optimized for object recognition, they learn where to attend using only a weak form of supervision derived from image class labels. Here, we demonstrate the benefit of using stronger supervisory signals by teaching DCNs to attend to image regions that humans deem important for object recognition. We first describe a large-scale online experiment (ClickMe) used to supplement ImageNet with nearly half a million human-derived \"top-dow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08819","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":"1805.08819","created_at":"2026-05-17T23:43:38.354866+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08819v4","created_at":"2026-05-17T23:43:38.354866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08819","created_at":"2026-05-17T23:43:38.354866+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6CRSEMWAYAD","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6CRSEMWAYADAEXJ","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6CRSEMW","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23819","citing_title":"Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6CRSEMWAYADAEXJ2YLBFET5VU","json":"https://pith.science/pith/E6CRSEMWAYADAEXJ2YLBFET5VU.json","graph_json":"https://pith.science/api/pith-number/E6CRSEMWAYADAEXJ2YLBFET5VU/graph.json","events_json":"https://pith.science/api/pith-number/E6CRSEMWAYADAEXJ2YLBFET5VU/events.json","paper":"https://pith.science/paper/E6CRSEMW"},"agent_actions":{"view_html":"https://pith.science/pith/E6CRSEMWAYADAEXJ2YLBFET5VU","download_json":"https://pith.science/pith/E6CRSEMWAYADAEXJ2YLBFET5VU.json","view_paper":"https://pith.science/paper/E6CRSEMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08819&json=true","fetch_graph":"https://pith.science/api/pith-number/E6CRSEMWAYADAEXJ2YLBFET5VU/graph.json","fetch_events":"https://pith.science/api/pith-number/E6CRSEMWAYADAEXJ2YLBFET5VU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6CRSEMWAYADAEXJ2YLBFET5VU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6CRSEMWAYADAEXJ2YLBFET5VU/action/storage_attestation","attest_author":"https://pith.science/pith/E6CRSEMWAYADAEXJ2YLBFET5VU/action/author_attestation","sign_citation":"https://pith.science/pith/E6CRSEMWAYADAEXJ2YLBFET5VU/action/citation_signature","submit_replication":"https://pith.science/pith/E6CRSEMWAYADAEXJ2YLBFET5VU/action/replication_record"}},"created_at":"2026-05-17T23:43:38.354866+00:00","updated_at":"2026-05-17T23:43:38.354866+00:00"}