{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GQS4UME7QOK3JDMYUVTAW2XGRU","short_pith_number":"pith:GQS4UME7","schema_version":"1.0","canonical_sha256":"3425ca309f8395b48d98a5660b6ae68d03f5bb74701596e29c3deeee38a97cf7","source":{"kind":"arxiv","id":"2009.07485","version":1},"attestation_state":"computed","paper":{"title":"Pooling Methods in Deep Neural Networks, a Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hossein Gholamalinezhad, Hossein Khosravi","submitted_at":"2020-09-16T06:11:40Z","abstract_excerpt":"Nowadays, Deep Neural Networks are among the main tools used in various sciences. Convolutional Neural Network is a special type of DNN consisting of several convolution layers, each followed by an activation function and a pooling layer. The pooling layer is an important layer that executes the down-sampling on the feature maps coming from the previous layer and produces new feature maps with a condensed resolution. This layer drastically reduces the spatial dimension of input. It serves two main purposes. The first is to reduce the number of parameters or weights, thus lessening the computat"},"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":"2009.07485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-16T06:11:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ffe59222733468c6704f5805bbe46423ea7fbdc545d67c31deeaa761876247d","abstract_canon_sha256":"b6700f68c982aa5f68ef7894fff9bd5bdd1fe06580ec32346dad419cce681c24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:53.107719Z","signature_b64":"1y3tB/209itQsR+mCJFDCtD8cqyXb0+HxyDZlztXGVAtkA2LaRe2ONRxah8pU6VmsZ+BPsPntYitHY21ghKpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3425ca309f8395b48d98a5660b6ae68d03f5bb74701596e29c3deeee38a97cf7","last_reissued_at":"2026-07-05T01:35:53.107267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:53.107267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pooling Methods in Deep Neural Networks, a Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hossein Gholamalinezhad, Hossein Khosravi","submitted_at":"2020-09-16T06:11:40Z","abstract_excerpt":"Nowadays, Deep Neural Networks are among the main tools used in various sciences. Convolutional Neural Network is a special type of DNN consisting of several convolution layers, each followed by an activation function and a pooling layer. The pooling layer is an important layer that executes the down-sampling on the feature maps coming from the previous layer and produces new feature maps with a condensed resolution. This layer drastically reduces the spatial dimension of input. It serves two main purposes. The first is to reduce the number of parameters or weights, thus lessening the computat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.07485","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.07485/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":"2009.07485","created_at":"2026-07-05T01:35:53.107323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.07485v1","created_at":"2026-07-05T01:35:53.107323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.07485","created_at":"2026-07-05T01:35:53.107323+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQS4UME7QOK3","created_at":"2026-07-05T01:35:53.107323+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQS4UME7QOK3JDMY","created_at":"2026-07-05T01:35:53.107323+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQS4UME7","created_at":"2026-07-05T01:35:53.107323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07685","citing_title":"Decoding magnetic texture","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11490","citing_title":"OmniLoc: A Geometry-Aware Foundation Model for Anchor-Free UE Localization Across Diverse Indoor Environments","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26937","citing_title":"Designing Solutions to Geophysical Inverse Problems by Changing Variables","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQS4UME7QOK3JDMYUVTAW2XGRU","json":"https://pith.science/pith/GQS4UME7QOK3JDMYUVTAW2XGRU.json","graph_json":"https://pith.science/api/pith-number/GQS4UME7QOK3JDMYUVTAW2XGRU/graph.json","events_json":"https://pith.science/api/pith-number/GQS4UME7QOK3JDMYUVTAW2XGRU/events.json","paper":"https://pith.science/paper/GQS4UME7"},"agent_actions":{"view_html":"https://pith.science/pith/GQS4UME7QOK3JDMYUVTAW2XGRU","download_json":"https://pith.science/pith/GQS4UME7QOK3JDMYUVTAW2XGRU.json","view_paper":"https://pith.science/paper/GQS4UME7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.07485&json=true","fetch_graph":"https://pith.science/api/pith-number/GQS4UME7QOK3JDMYUVTAW2XGRU/graph.json","fetch_events":"https://pith.science/api/pith-number/GQS4UME7QOK3JDMYUVTAW2XGRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQS4UME7QOK3JDMYUVTAW2XGRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQS4UME7QOK3JDMYUVTAW2XGRU/action/storage_attestation","attest_author":"https://pith.science/pith/GQS4UME7QOK3JDMYUVTAW2XGRU/action/author_attestation","sign_citation":"https://pith.science/pith/GQS4UME7QOK3JDMYUVTAW2XGRU/action/citation_signature","submit_replication":"https://pith.science/pith/GQS4UME7QOK3JDMYUVTAW2XGRU/action/replication_record"}},"created_at":"2026-07-05T01:35:53.107323+00:00","updated_at":"2026-07-05T01:35:53.107323+00:00"}