{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UIL4MM6G6JFMJHVZTJOKMQJEWQ","short_pith_number":"pith:UIL4MM6G","schema_version":"1.0","canonical_sha256":"a217c633c6f24ac49eb99a5ca64124b41084f8cf9d3ab3a678676eca859db4ec","source":{"kind":"arxiv","id":"2101.00440","version":3},"attestation_state":"computed","paper":{"title":"Refining activation downsampling with SoftPool","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Grigorios Kalliatakis, Ronald Poppe","submitted_at":"2021-01-02T12:09:49Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requirements of subsequent convolutions. An important feature of the pooling operation is the minimization of information loss, with respect to the initial activation maps, without a significant impact on the computation and memory overhead. To meet these requirements, we propose SoftPool: a fast and efficient method for exponentially weighted activation downsampling. Through experiments across a range of architectures an"},"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":"2101.00440","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-02T12:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"eec07544ee675d9526fc328f3d665c49f626ebf5e8c64cd3e8a87d6a9cff36b0","abstract_canon_sha256":"e45591ecb6d2431e1ee3c12a6be61f658e67e4d359364a6289cc69d60a9ae127"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:13.231983Z","signature_b64":"hlYmTi+eAwIRdSJbyPxUCq8Lh3bi8RbaGqnW4U78QYjdDVBItbKWrr7Wx9LgB0OEXcgjCEJaS241kBIumw2JCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a217c633c6f24ac49eb99a5ca64124b41084f8cf9d3ab3a678676eca859db4ec","last_reissued_at":"2026-07-05T02:24:13.231621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:13.231621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refining activation downsampling with SoftPool","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Grigorios Kalliatakis, Ronald Poppe","submitted_at":"2021-01-02T12:09:49Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requirements of subsequent convolutions. An important feature of the pooling operation is the minimization of information loss, with respect to the initial activation maps, without a significant impact on the computation and memory overhead. To meet these requirements, we propose SoftPool: a fast and efficient method for exponentially weighted activation downsampling. Through experiments across a range of architectures an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00440","kind":"arxiv","version":3},"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/2101.00440/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":"2101.00440","created_at":"2026-07-05T02:24:13.231676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.00440v3","created_at":"2026-07-05T02:24:13.231676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00440","created_at":"2026-07-05T02:24:13.231676+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIL4MM6G6JFM","created_at":"2026-07-05T02:24:13.231676+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIL4MM6G6JFMJHVZ","created_at":"2026-07-05T02:24:13.231676+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIL4MM6G","created_at":"2026-07-05T02:24:13.231676+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/UIL4MM6G6JFMJHVZTJOKMQJEWQ","json":"https://pith.science/pith/UIL4MM6G6JFMJHVZTJOKMQJEWQ.json","graph_json":"https://pith.science/api/pith-number/UIL4MM6G6JFMJHVZTJOKMQJEWQ/graph.json","events_json":"https://pith.science/api/pith-number/UIL4MM6G6JFMJHVZTJOKMQJEWQ/events.json","paper":"https://pith.science/paper/UIL4MM6G"},"agent_actions":{"view_html":"https://pith.science/pith/UIL4MM6G6JFMJHVZTJOKMQJEWQ","download_json":"https://pith.science/pith/UIL4MM6G6JFMJHVZTJOKMQJEWQ.json","view_paper":"https://pith.science/paper/UIL4MM6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.00440&json=true","fetch_graph":"https://pith.science/api/pith-number/UIL4MM6G6JFMJHVZTJOKMQJEWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UIL4MM6G6JFMJHVZTJOKMQJEWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIL4MM6G6JFMJHVZTJOKMQJEWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIL4MM6G6JFMJHVZTJOKMQJEWQ/action/storage_attestation","attest_author":"https://pith.science/pith/UIL4MM6G6JFMJHVZTJOKMQJEWQ/action/author_attestation","sign_citation":"https://pith.science/pith/UIL4MM6G6JFMJHVZTJOKMQJEWQ/action/citation_signature","submit_replication":"https://pith.science/pith/UIL4MM6G6JFMJHVZTJOKMQJEWQ/action/replication_record"}},"created_at":"2026-07-05T02:24:13.231676+00:00","updated_at":"2026-07-05T02:24:13.231676+00:00"}