{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H5HLHXWGUXRFDJPT5ZHDNUIKUT","short_pith_number":"pith:H5HLHXWG","schema_version":"1.0","canonical_sha256":"3f4eb3dec6a5e251a5f3ee4e36d10aa4f062b3410b0fbeb1efc6402f79adb625","source":{"kind":"arxiv","id":"2508.03625","version":1},"attestation_state":"computed","paper":{"title":"AttZoom: Attention Zoom for Better Visual Features","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aythami Morales, Daniel DeAlcala, Julian Fierrez, Ruben Tolosana","submitted_at":"2025-08-05T16:42:08Z","abstract_excerpt":"We present Attention Zoom, a modular and model-agnostic spatial attention mechanism designed to improve feature extraction in convolutional neural networks (CNNs). Unlike traditional attention approaches that require architecture-specific integration, our method introduces a standalone layer that spatially emphasizes high-importance regions in the input. We evaluated Attention Zoom on multiple CNN backbones using CIFAR-100 and TinyImageNet, showing consistent improvements in Top-1 and Top-5 classification accuracy. Visual analyses using Grad-CAM and spatial warping reveal that our method encou"},"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":"2508.03625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T16:42:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ecc322207c3a0f35278f9d511f8d366ea60b5208cd2841aacddde8f5cbfea8a7","abstract_canon_sha256":"5b8b0df850cacf5221f40917e7989a0725a4e645b96a32820de92980f9e71367"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:00.104915Z","signature_b64":"rR6u+YDak1SFOHfNi9/cATV5Gurqf/Mi64D6cxebQmzmcnrKktlJLX36vmTE6+GeVR+Kyqt7Cjs+I1hNMJhRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f4eb3dec6a5e251a5f3ee4e36d10aa4f062b3410b0fbeb1efc6402f79adb625","last_reissued_at":"2026-07-05T11:49:00.104472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:00.104472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AttZoom: Attention Zoom for Better Visual Features","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aythami Morales, Daniel DeAlcala, Julian Fierrez, Ruben Tolosana","submitted_at":"2025-08-05T16:42:08Z","abstract_excerpt":"We present Attention Zoom, a modular and model-agnostic spatial attention mechanism designed to improve feature extraction in convolutional neural networks (CNNs). Unlike traditional attention approaches that require architecture-specific integration, our method introduces a standalone layer that spatially emphasizes high-importance regions in the input. We evaluated Attention Zoom on multiple CNN backbones using CIFAR-100 and TinyImageNet, showing consistent improvements in Top-1 and Top-5 classification accuracy. Visual analyses using Grad-CAM and spatial warping reveal that our method encou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03625","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/2508.03625/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":"2508.03625","created_at":"2026-07-05T11:49:00.104526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03625v1","created_at":"2026-07-05T11:49:00.104526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03625","created_at":"2026-07-05T11:49:00.104526+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5HLHXWGUXRF","created_at":"2026-07-05T11:49:00.104526+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5HLHXWGUXRFDJPT","created_at":"2026-07-05T11:49:00.104526+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5HLHXWG","created_at":"2026-07-05T11:49:00.104526+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11716","citing_title":"Privacy-Aware Detection of Fake Identity Documents: Methodology, Benchmark, and Improved Algorithms (FakeIDet2)","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5HLHXWGUXRFDJPT5ZHDNUIKUT","json":"https://pith.science/pith/H5HLHXWGUXRFDJPT5ZHDNUIKUT.json","graph_json":"https://pith.science/api/pith-number/H5HLHXWGUXRFDJPT5ZHDNUIKUT/graph.json","events_json":"https://pith.science/api/pith-number/H5HLHXWGUXRFDJPT5ZHDNUIKUT/events.json","paper":"https://pith.science/paper/H5HLHXWG"},"agent_actions":{"view_html":"https://pith.science/pith/H5HLHXWGUXRFDJPT5ZHDNUIKUT","download_json":"https://pith.science/pith/H5HLHXWGUXRFDJPT5ZHDNUIKUT.json","view_paper":"https://pith.science/paper/H5HLHXWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03625&json=true","fetch_graph":"https://pith.science/api/pith-number/H5HLHXWGUXRFDJPT5ZHDNUIKUT/graph.json","fetch_events":"https://pith.science/api/pith-number/H5HLHXWGUXRFDJPT5ZHDNUIKUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5HLHXWGUXRFDJPT5ZHDNUIKUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5HLHXWGUXRFDJPT5ZHDNUIKUT/action/storage_attestation","attest_author":"https://pith.science/pith/H5HLHXWGUXRFDJPT5ZHDNUIKUT/action/author_attestation","sign_citation":"https://pith.science/pith/H5HLHXWGUXRFDJPT5ZHDNUIKUT/action/citation_signature","submit_replication":"https://pith.science/pith/H5HLHXWGUXRFDJPT5ZHDNUIKUT/action/replication_record"}},"created_at":"2026-07-05T11:49:00.104526+00:00","updated_at":"2026-07-05T11:49:00.104526+00:00"}