{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZY77JK4A2C6E53TV2QCA422KYS","short_pith_number":"pith:ZY77JK4A","schema_version":"1.0","canonical_sha256":"ce3ff4ab80d0bc4eee75d4040e6b4ac4ab4e7779df0dc472accee5ec545e26b7","source":{"kind":"arxiv","id":"1803.00107","version":1},"attestation_state":"computed","paper":{"title":"Pulling Out All the Tops with Computer Vision and Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["hep-ex"],"primary_cat":"hep-ph","authors_text":"David Shih, Sebastian Macaluso","submitted_at":"2018-02-28T22:02:11Z","abstract_excerpt":"We apply computer vision with deep learning -- in the form of a convolutional neural network (CNN) -- to build a highly effective boosted top tagger. Previous work (the \"DeepTop\" tagger of Kasieczka et al) has shown that a CNN-based top tagger can achieve comparable performance to state-of-the-art conventional top taggers based on high-level inputs. Here, we introduce a number of improvements to the DeepTop tagger, including architecture, training, image preprocessing, sample size and color pixels. Our final CNN top tagger outperforms BDTs based on high-level inputs by a factor of $\\sim 2$--3 "},"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":"1803.00107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-ph","submitted_at":"2018-02-28T22:02:11Z","cross_cats_sorted":["hep-ex"],"title_canon_sha256":"b50805c423959ce61616f879f294e1b7fd6e056f3f51d299eb55d557b48c9ff9","abstract_canon_sha256":"c2f175086d71a466ac07b582ec01516345b9014357305c3eed33cfc3e3743b1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:57.278624Z","signature_b64":"5ql97I3yX7w2j5j+J6cwkYP8oWqhv5EOFsz7TqAmPxW8uQllREUF2aybxj02pHHGJkCwXZOP15zollpMLI7GDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce3ff4ab80d0bc4eee75d4040e6b4ac4ab4e7779df0dc472accee5ec545e26b7","last_reissued_at":"2026-05-18T00:00:57.278003Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:57.278003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pulling Out All the Tops with Computer Vision and Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["hep-ex"],"primary_cat":"hep-ph","authors_text":"David Shih, Sebastian Macaluso","submitted_at":"2018-02-28T22:02:11Z","abstract_excerpt":"We apply computer vision with deep learning -- in the form of a convolutional neural network (CNN) -- to build a highly effective boosted top tagger. Previous work (the \"DeepTop\" tagger of Kasieczka et al) has shown that a CNN-based top tagger can achieve comparable performance to state-of-the-art conventional top taggers based on high-level inputs. Here, we introduce a number of improvements to the DeepTop tagger, including architecture, training, image preprocessing, sample size and color pixels. Our final CNN top tagger outperforms BDTs based on high-level inputs by a factor of $\\sim 2$--3 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00107","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1803.00107","created_at":"2026-05-18T00:00:57.278081+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.00107v1","created_at":"2026-05-18T00:00:57.278081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00107","created_at":"2026-05-18T00:00:57.278081+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZY77JK4A2C6E","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZY77JK4A2C6E53TV","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZY77JK4A","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.01207","citing_title":"Feature Alignment Determines Fusion Strategy: A Comparative Study of Cross-Attention and Concatenation in Multimodal Learning","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZY77JK4A2C6E53TV2QCA422KYS","json":"https://pith.science/pith/ZY77JK4A2C6E53TV2QCA422KYS.json","graph_json":"https://pith.science/api/pith-number/ZY77JK4A2C6E53TV2QCA422KYS/graph.json","events_json":"https://pith.science/api/pith-number/ZY77JK4A2C6E53TV2QCA422KYS/events.json","paper":"https://pith.science/paper/ZY77JK4A"},"agent_actions":{"view_html":"https://pith.science/pith/ZY77JK4A2C6E53TV2QCA422KYS","download_json":"https://pith.science/pith/ZY77JK4A2C6E53TV2QCA422KYS.json","view_paper":"https://pith.science/paper/ZY77JK4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.00107&json=true","fetch_graph":"https://pith.science/api/pith-number/ZY77JK4A2C6E53TV2QCA422KYS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZY77JK4A2C6E53TV2QCA422KYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZY77JK4A2C6E53TV2QCA422KYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZY77JK4A2C6E53TV2QCA422KYS/action/storage_attestation","attest_author":"https://pith.science/pith/ZY77JK4A2C6E53TV2QCA422KYS/action/author_attestation","sign_citation":"https://pith.science/pith/ZY77JK4A2C6E53TV2QCA422KYS/action/citation_signature","submit_replication":"https://pith.science/pith/ZY77JK4A2C6E53TV2QCA422KYS/action/replication_record"}},"created_at":"2026-05-18T00:00:57.278081+00:00","updated_at":"2026-05-18T00:00:57.278081+00:00"}