{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z74TN3FAK35IVPDIIRSG7DHHGH","short_pith_number":"pith:Z74TN3FA","schema_version":"1.0","canonical_sha256":"cff936eca056fa8abc6844646f8ce731e81661554aa657e33f5ce084f926f268","source":{"kind":"arxiv","id":"2102.01582","version":2},"attestation_state":"computed","paper":{"title":"Size Matters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Justin Shenk, Ludwdig Schallner, Mats L. Richter, Ulf Krumnack, Wolf Byttner","submitted_at":"2021-02-02T16:17:52Z","abstract_excerpt":"Fully convolutional neural networks can process input of arbitrary size by applying a combination of downsampling and pooling. However, we find that fully convolutional image classifiers are not agnostic to the input size but rather show significant differences in performance: presenting the same image at different scales can result in different outcomes. A closer look reveals that there is no simple relationship between input size and model performance (no `bigger is better'), but that each each network has a preferred input size, for which it shows best results. We investigate this phenomeno"},"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":"2102.01582","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-02T16:17:52Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"429bee261809e10271457c635c32a29da9948670f7d4de15b7d209a316f73267","abstract_canon_sha256":"be7c6de61dba7b3c3369e80dd46447669ec989d0164ef228085d068c0c4b609c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:43.214426Z","signature_b64":"Vu8JTAwqxfUoYZNwOgKrw7qgGBcMkDLmcWKO0xn07wkZsHiEMjzrO7xSPMG0+CfX77SCCyCPTO82XFMdjWceBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cff936eca056fa8abc6844646f8ce731e81661554aa657e33f5ce084f926f268","last_reissued_at":"2026-07-05T03:21:43.213917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:43.213917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Size Matters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Justin Shenk, Ludwdig Schallner, Mats L. Richter, Ulf Krumnack, Wolf Byttner","submitted_at":"2021-02-02T16:17:52Z","abstract_excerpt":"Fully convolutional neural networks can process input of arbitrary size by applying a combination of downsampling and pooling. However, we find that fully convolutional image classifiers are not agnostic to the input size but rather show significant differences in performance: presenting the same image at different scales can result in different outcomes. A closer look reveals that there is no simple relationship between input size and model performance (no `bigger is better'), but that each each network has a preferred input size, for which it shows best results. We investigate this phenomeno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01582","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/2102.01582/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":"2102.01582","created_at":"2026-07-05T03:21:43.213976+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.01582v2","created_at":"2026-07-05T03:21:43.213976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01582","created_at":"2026-07-05T03:21:43.213976+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z74TN3FAK35I","created_at":"2026-07-05T03:21:43.213976+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z74TN3FAK35IVPDI","created_at":"2026-07-05T03:21:43.213976+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z74TN3FA","created_at":"2026-07-05T03:21:43.213976+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/Z74TN3FAK35IVPDIIRSG7DHHGH","json":"https://pith.science/pith/Z74TN3FAK35IVPDIIRSG7DHHGH.json","graph_json":"https://pith.science/api/pith-number/Z74TN3FAK35IVPDIIRSG7DHHGH/graph.json","events_json":"https://pith.science/api/pith-number/Z74TN3FAK35IVPDIIRSG7DHHGH/events.json","paper":"https://pith.science/paper/Z74TN3FA"},"agent_actions":{"view_html":"https://pith.science/pith/Z74TN3FAK35IVPDIIRSG7DHHGH","download_json":"https://pith.science/pith/Z74TN3FAK35IVPDIIRSG7DHHGH.json","view_paper":"https://pith.science/paper/Z74TN3FA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.01582&json=true","fetch_graph":"https://pith.science/api/pith-number/Z74TN3FAK35IVPDIIRSG7DHHGH/graph.json","fetch_events":"https://pith.science/api/pith-number/Z74TN3FAK35IVPDIIRSG7DHHGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z74TN3FAK35IVPDIIRSG7DHHGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z74TN3FAK35IVPDIIRSG7DHHGH/action/storage_attestation","attest_author":"https://pith.science/pith/Z74TN3FAK35IVPDIIRSG7DHHGH/action/author_attestation","sign_citation":"https://pith.science/pith/Z74TN3FAK35IVPDIIRSG7DHHGH/action/citation_signature","submit_replication":"https://pith.science/pith/Z74TN3FAK35IVPDIIRSG7DHHGH/action/replication_record"}},"created_at":"2026-07-05T03:21:43.213976+00:00","updated_at":"2026-07-05T03:21:43.213976+00:00"}