{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ID3GK7FZDMQ372OZB6LIHZGT6J","short_pith_number":"pith:ID3GK7FZ","schema_version":"1.0","canonical_sha256":"40f6657cb91b21bfe9d90f9683e4d3f254f5dd612bd0ba038b8d415f64ed2a87","source":{"kind":"arxiv","id":"2211.14487","version":1},"attestation_state":"computed","paper":{"title":"Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Christopher Pal, Mats L. Richter","submitted_at":"2022-11-26T05:27:44Z","abstract_excerpt":"Minimal changes to neural architectures (e.g. changing a single hyperparameter in a key layer), can lead to significant gains in predictive performance in Convolutional Neural Networks (CNNs). In this work, we present a new approach to receptive field analysis that can yield these types of theoretical and empirical performance gains across twenty well-known CNN architectures examined in our experiments. By further developing and formalizing the analysis of receptive field expansion in convolutional neural networks, we can predict unproductive layers in an automated manner before ever training "},"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":"2211.14487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-26T05:27:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dcec1d00189ca510df628ce84bbe1eb36b15c350fd6dd3825170652d00985e85","abstract_canon_sha256":"22b8ad48bb3fc703d40aedfd1fb8cb260293b6a72408cad2d74c40eeddac39cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:40.258359Z","signature_b64":"7iPt5Ymt5wtdrgrwq5yqcZT8nqFEoivfl9uNDpTH/kZ3YqtFgXEHOK3ggRGjvGU3jLgWIcgjr+SpRI1SLcF6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40f6657cb91b21bfe9d90f9683e4d3f254f5dd612bd0ba038b8d415f64ed2a87","last_reissued_at":"2026-07-05T05:19:40.257930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:40.257930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Christopher Pal, Mats L. Richter","submitted_at":"2022-11-26T05:27:44Z","abstract_excerpt":"Minimal changes to neural architectures (e.g. changing a single hyperparameter in a key layer), can lead to significant gains in predictive performance in Convolutional Neural Networks (CNNs). In this work, we present a new approach to receptive field analysis that can yield these types of theoretical and empirical performance gains across twenty well-known CNN architectures examined in our experiments. By further developing and formalizing the analysis of receptive field expansion in convolutional neural networks, we can predict unproductive layers in an automated manner before ever training "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14487","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/2211.14487/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":"2211.14487","created_at":"2026-07-05T05:19:40.257992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.14487v1","created_at":"2026-07-05T05:19:40.257992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14487","created_at":"2026-07-05T05:19:40.257992+00:00"},{"alias_kind":"pith_short_12","alias_value":"ID3GK7FZDMQ3","created_at":"2026-07-05T05:19:40.257992+00:00"},{"alias_kind":"pith_short_16","alias_value":"ID3GK7FZDMQ372OZ","created_at":"2026-07-05T05:19:40.257992+00:00"},{"alias_kind":"pith_short_8","alias_value":"ID3GK7FZ","created_at":"2026-07-05T05:19:40.257992+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02764","citing_title":"From Local Training to Large-Scale Mapping: A Comparative Assessment of Machine Learning and Deep Learning for Transferable Satellite-Derived Bathymetry","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ID3GK7FZDMQ372OZB6LIHZGT6J","json":"https://pith.science/pith/ID3GK7FZDMQ372OZB6LIHZGT6J.json","graph_json":"https://pith.science/api/pith-number/ID3GK7FZDMQ372OZB6LIHZGT6J/graph.json","events_json":"https://pith.science/api/pith-number/ID3GK7FZDMQ372OZB6LIHZGT6J/events.json","paper":"https://pith.science/paper/ID3GK7FZ"},"agent_actions":{"view_html":"https://pith.science/pith/ID3GK7FZDMQ372OZB6LIHZGT6J","download_json":"https://pith.science/pith/ID3GK7FZDMQ372OZB6LIHZGT6J.json","view_paper":"https://pith.science/paper/ID3GK7FZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.14487&json=true","fetch_graph":"https://pith.science/api/pith-number/ID3GK7FZDMQ372OZB6LIHZGT6J/graph.json","fetch_events":"https://pith.science/api/pith-number/ID3GK7FZDMQ372OZB6LIHZGT6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ID3GK7FZDMQ372OZB6LIHZGT6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ID3GK7FZDMQ372OZB6LIHZGT6J/action/storage_attestation","attest_author":"https://pith.science/pith/ID3GK7FZDMQ372OZB6LIHZGT6J/action/author_attestation","sign_citation":"https://pith.science/pith/ID3GK7FZDMQ372OZB6LIHZGT6J/action/citation_signature","submit_replication":"https://pith.science/pith/ID3GK7FZDMQ372OZB6LIHZGT6J/action/replication_record"}},"created_at":"2026-07-05T05:19:40.257992+00:00","updated_at":"2026-07-05T05:19:40.257992+00:00"}