{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:T6TA4N7CKKKGVZCT52PXHIWRDW","short_pith_number":"pith:T6TA4N7C","schema_version":"1.0","canonical_sha256":"9fa60e37e252946ae453ee9f73a2d11dbb973769bca1acbb8102f7459a47a3b8","source":{"kind":"arxiv","id":"1810.12890","version":1},"attestation_state":"computed","paper":{"title":"DropBlock: A regularization method for convolutional networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Golnaz Ghiasi, Quoc V. Le, Tsung-Yi Lin","submitted_at":"2018-10-30T17:39:42Z","abstract_excerpt":"Deep neural networks often work well when they are over-parameterized and trained with a massive amount of noise and regularization, such as weight decay and dropout. Although dropout is widely used as a regularization technique for fully connected layers, it is often less effective for convolutional layers. This lack of success of dropout for convolutional layers is perhaps due to the fact that activation units in convolutional layers are spatially correlated so information can still flow through convolutional networks despite dropout. Thus a structured form of dropout is needed to regularize"},"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":"1810.12890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-30T17:39:42Z","cross_cats_sorted":[],"title_canon_sha256":"cc9dc76a0083a06e99fafb553b436210bdba5ebdcaf3acf05fe34c473b275ce6","abstract_canon_sha256":"29fed9fe196c2f4f70c7536dcdbe8d99a40c4d1b0a0d18a10574b420e4fcf333"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:53.908808Z","signature_b64":"TdxsmNV3EyibT8cYKNaacdjnCYwW51lpEXri9BRBEitBb+TkzFzYG8I11HOXo9AyYR8s20gGRqivdZoMvLi3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fa60e37e252946ae453ee9f73a2d11dbb973769bca1acbb8102f7459a47a3b8","last_reissued_at":"2026-05-18T00:01:53.908404Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:53.908404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DropBlock: A regularization method for convolutional networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Golnaz Ghiasi, Quoc V. Le, Tsung-Yi Lin","submitted_at":"2018-10-30T17:39:42Z","abstract_excerpt":"Deep neural networks often work well when they are over-parameterized and trained with a massive amount of noise and regularization, such as weight decay and dropout. Although dropout is widely used as a regularization technique for fully connected layers, it is often less effective for convolutional layers. This lack of success of dropout for convolutional layers is perhaps due to the fact that activation units in convolutional layers are spatially correlated so information can still flow through convolutional networks despite dropout. Thus a structured form of dropout is needed to regularize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12890","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":"1810.12890","created_at":"2026-05-18T00:01:53.908467+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12890v1","created_at":"2026-05-18T00:01:53.908467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12890","created_at":"2026-05-18T00:01:53.908467+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6TA4N7CKKKG","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6TA4N7CKKKGVZCT","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6TA4N7C","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2502.05564","citing_title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data","ref_index":177,"is_internal_anchor":true},{"citing_arxiv_id":"2602.13636","citing_title":"Layer-Guided UAV Tracking: Enhancing Efficiency and Occlusion Robustness","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6TA4N7CKKKGVZCT52PXHIWRDW","json":"https://pith.science/pith/T6TA4N7CKKKGVZCT52PXHIWRDW.json","graph_json":"https://pith.science/api/pith-number/T6TA4N7CKKKGVZCT52PXHIWRDW/graph.json","events_json":"https://pith.science/api/pith-number/T6TA4N7CKKKGVZCT52PXHIWRDW/events.json","paper":"https://pith.science/paper/T6TA4N7C"},"agent_actions":{"view_html":"https://pith.science/pith/T6TA4N7CKKKGVZCT52PXHIWRDW","download_json":"https://pith.science/pith/T6TA4N7CKKKGVZCT52PXHIWRDW.json","view_paper":"https://pith.science/paper/T6TA4N7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12890&json=true","fetch_graph":"https://pith.science/api/pith-number/T6TA4N7CKKKGVZCT52PXHIWRDW/graph.json","fetch_events":"https://pith.science/api/pith-number/T6TA4N7CKKKGVZCT52PXHIWRDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6TA4N7CKKKGVZCT52PXHIWRDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6TA4N7CKKKGVZCT52PXHIWRDW/action/storage_attestation","attest_author":"https://pith.science/pith/T6TA4N7CKKKGVZCT52PXHIWRDW/action/author_attestation","sign_citation":"https://pith.science/pith/T6TA4N7CKKKGVZCT52PXHIWRDW/action/citation_signature","submit_replication":"https://pith.science/pith/T6TA4N7CKKKGVZCT52PXHIWRDW/action/replication_record"}},"created_at":"2026-05-18T00:01:53.908467+00:00","updated_at":"2026-05-18T00:01:53.908467+00:00"}