{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6GQHCGYAUQUE7RHZ7VVTRYTJC7","short_pith_number":"pith:6GQHCGYA","schema_version":"1.0","canonical_sha256":"f1a0711b00a4284fc4f9fd6b38e26917fbb4bf80caac550e4721b51ae710374a","source":{"kind":"arxiv","id":"1908.05040","version":2},"attestation_state":"computed","paper":{"title":"Deep Generalized Max Pooling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Maier, Anguelos Nicolaou, Lukas Spranger, Mathias Seuret, Pavel Kr\\'al, Vincent Christlein","submitted_at":"2019-08-14T09:33:41Z","abstract_excerpt":"Global pooling layers are an essential part of Convolutional Neural Networks (CNN). They are used to aggregate activations of spatial locations to produce a fixed-size vector in several state-of-the-art CNNs. Global average pooling or global max pooling are commonly used for converting convolutional features of variable size images to a fix-sized embedding. However, both pooling layer types are computed spatially independent: each individual activation map is pooled and thus activations of different locations are pooled together. In contrast, we propose Deep Generalized Max Pooling that balanc"},"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":"1908.05040","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-14T09:33:41Z","cross_cats_sorted":[],"title_canon_sha256":"4403eabdb936a3e6e853b5f25fc4514cc0a175a6884c61c2b72602756ecb4579","abstract_canon_sha256":"db6782173de83d84108c1cd3af3fc10fcf22955b144b832fa95a0156b8c2045a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:27.114956Z","signature_b64":"6pfmHwDNNg6xBG6HrHX7NMTFzBFnEwC5z4/IpkInzfukjn0ynlz0dhRnhp0molPd8gU7KHdCVv9IXGW7X3hLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1a0711b00a4284fc4f9fd6b38e26917fbb4bf80caac550e4721b51ae710374a","last_reissued_at":"2026-07-05T07:49:27.114527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:27.114527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Generalized Max Pooling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Maier, Anguelos Nicolaou, Lukas Spranger, Mathias Seuret, Pavel Kr\\'al, Vincent Christlein","submitted_at":"2019-08-14T09:33:41Z","abstract_excerpt":"Global pooling layers are an essential part of Convolutional Neural Networks (CNN). They are used to aggregate activations of spatial locations to produce a fixed-size vector in several state-of-the-art CNNs. Global average pooling or global max pooling are commonly used for converting convolutional features of variable size images to a fix-sized embedding. However, both pooling layer types are computed spatially independent: each individual activation map is pooled and thus activations of different locations are pooled together. In contrast, we propose Deep Generalized Max Pooling that balanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05040","kind":"arxiv","version":2},"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/1908.05040/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":"1908.05040","created_at":"2026-07-05T07:49:27.114586+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05040v2","created_at":"2026-07-05T07:49:27.114586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05040","created_at":"2026-07-05T07:49:27.114586+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GQHCGYAUQUE","created_at":"2026-07-05T07:49:27.114586+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GQHCGYAUQUE7RHZ","created_at":"2026-07-05T07:49:27.114586+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GQHCGYA","created_at":"2026-07-05T07:49:27.114586+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GQHCGYAUQUE7RHZ7VVTRYTJC7","json":"https://pith.science/pith/6GQHCGYAUQUE7RHZ7VVTRYTJC7.json","graph_json":"https://pith.science/api/pith-number/6GQHCGYAUQUE7RHZ7VVTRYTJC7/graph.json","events_json":"https://pith.science/api/pith-number/6GQHCGYAUQUE7RHZ7VVTRYTJC7/events.json","paper":"https://pith.science/paper/6GQHCGYA"},"agent_actions":{"view_html":"https://pith.science/pith/6GQHCGYAUQUE7RHZ7VVTRYTJC7","download_json":"https://pith.science/pith/6GQHCGYAUQUE7RHZ7VVTRYTJC7.json","view_paper":"https://pith.science/paper/6GQHCGYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05040&json=true","fetch_graph":"https://pith.science/api/pith-number/6GQHCGYAUQUE7RHZ7VVTRYTJC7/graph.json","fetch_events":"https://pith.science/api/pith-number/6GQHCGYAUQUE7RHZ7VVTRYTJC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GQHCGYAUQUE7RHZ7VVTRYTJC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GQHCGYAUQUE7RHZ7VVTRYTJC7/action/storage_attestation","attest_author":"https://pith.science/pith/6GQHCGYAUQUE7RHZ7VVTRYTJC7/action/author_attestation","sign_citation":"https://pith.science/pith/6GQHCGYAUQUE7RHZ7VVTRYTJC7/action/citation_signature","submit_replication":"https://pith.science/pith/6GQHCGYAUQUE7RHZ7VVTRYTJC7/action/replication_record"}},"created_at":"2026-07-05T07:49:27.114586+00:00","updated_at":"2026-07-05T07:49:27.114586+00:00"}