{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4NWIO2QPUMXVZBJA6JHOWO573O","short_pith_number":"pith:4NWIO2QP","schema_version":"1.0","canonical_sha256":"e36c876a0fa32f5c8520f24eeb3bbfdba6dd93dfdfc239c2caa841f8d6c50dac","source":{"kind":"arxiv","id":"2503.06368","version":1},"attestation_state":"computed","paper":{"title":"VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Emir Konuk, Kallil M. Zielinski, Kevin Smith, Leonardo Scabini, Lucas C. Ribas, Odemir M. Bruno, Ricardo T. Fares","submitted_at":"2025-03-09T00:36:02Z","abstract_excerpt":"Texture recognition has recently been dominated by ImageNet-pre-trained deep Convolutional Neural Networks (CNNs), with specialized modifications and feature engineering required to achieve state-of-the-art (SOTA) performance. However, although Vision Transformers (ViTs) were introduced a few years ago, little is known about their texture recognition ability. Therefore, in this work, we introduce VORTEX (ViTs with Orderless and Randomized Token Encodings for Texture Recognition), a novel method that enables the effective use of ViTs for texture analysis. VORTEX extracts multi-depth token embed"},"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":"2503.06368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T00:36:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"04a4582ef897f71396909d55d7672f8d6891f9ac2b03ddb2e87866ce7a82318f","abstract_canon_sha256":"b07281436e9ac75277ff3d24d5b02c342c2f7159f96cdd6e92b03304be325da7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:31.706791Z","signature_b64":"KV1+McggEvF2sitMdmuRpgtTvlgXTYM+WvUxWWrIdyJ9Sh+FN7+gtaTuUBq2JUorqq5qqHpKpx2ZMUs4WKtSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e36c876a0fa32f5c8520f24eeb3bbfdba6dd93dfdfc239c2caa841f8d6c50dac","last_reissued_at":"2026-07-05T10:27:31.706229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:31.706229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Emir Konuk, Kallil M. Zielinski, Kevin Smith, Leonardo Scabini, Lucas C. Ribas, Odemir M. Bruno, Ricardo T. Fares","submitted_at":"2025-03-09T00:36:02Z","abstract_excerpt":"Texture recognition has recently been dominated by ImageNet-pre-trained deep Convolutional Neural Networks (CNNs), with specialized modifications and feature engineering required to achieve state-of-the-art (SOTA) performance. However, although Vision Transformers (ViTs) were introduced a few years ago, little is known about their texture recognition ability. Therefore, in this work, we introduce VORTEX (ViTs with Orderless and Randomized Token Encodings for Texture Recognition), a novel method that enables the effective use of ViTs for texture analysis. VORTEX extracts multi-depth token embed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06368","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/2503.06368/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":"2503.06368","created_at":"2026-07-05T10:27:31.706287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06368v1","created_at":"2026-07-05T10:27:31.706287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06368","created_at":"2026-07-05T10:27:31.706287+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NWIO2QPUMXV","created_at":"2026-07-05T10:27:31.706287+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NWIO2QPUMXVZBJA","created_at":"2026-07-05T10:27:31.706287+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NWIO2QP","created_at":"2026-07-05T10:27:31.706287+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/4NWIO2QPUMXVZBJA6JHOWO573O","json":"https://pith.science/pith/4NWIO2QPUMXVZBJA6JHOWO573O.json","graph_json":"https://pith.science/api/pith-number/4NWIO2QPUMXVZBJA6JHOWO573O/graph.json","events_json":"https://pith.science/api/pith-number/4NWIO2QPUMXVZBJA6JHOWO573O/events.json","paper":"https://pith.science/paper/4NWIO2QP"},"agent_actions":{"view_html":"https://pith.science/pith/4NWIO2QPUMXVZBJA6JHOWO573O","download_json":"https://pith.science/pith/4NWIO2QPUMXVZBJA6JHOWO573O.json","view_paper":"https://pith.science/paper/4NWIO2QP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06368&json=true","fetch_graph":"https://pith.science/api/pith-number/4NWIO2QPUMXVZBJA6JHOWO573O/graph.json","fetch_events":"https://pith.science/api/pith-number/4NWIO2QPUMXVZBJA6JHOWO573O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NWIO2QPUMXVZBJA6JHOWO573O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NWIO2QPUMXVZBJA6JHOWO573O/action/storage_attestation","attest_author":"https://pith.science/pith/4NWIO2QPUMXVZBJA6JHOWO573O/action/author_attestation","sign_citation":"https://pith.science/pith/4NWIO2QPUMXVZBJA6JHOWO573O/action/citation_signature","submit_replication":"https://pith.science/pith/4NWIO2QPUMXVZBJA6JHOWO573O/action/replication_record"}},"created_at":"2026-07-05T10:27:31.706287+00:00","updated_at":"2026-07-05T10:27:31.706287+00:00"}