{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G2R2UOPIJVHX7IFPSWKJRCDQAY","short_pith_number":"pith:G2R2UOPI","schema_version":"1.0","canonical_sha256":"36a3aa39e84d4f7fa0af959498887006161f43c5d846a648d9ce34c0ad19a32f","source":{"kind":"arxiv","id":"2101.03771","version":1},"attestation_state":"computed","paper":{"title":"Investigating the Vision Transformer Model for Image Retrieval Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.RO"],"primary_cat":"cs.CV","authors_text":"Savvas A. Chatzichristofis, Socratis Gkelios, Yiannis Boutalis","submitted_at":"2021-01-11T08:59:54Z","abstract_excerpt":"This paper introduces a plug-and-play descriptor that can be effectively adopted for image retrieval tasks without prior initialization or preparation. The description method utilizes the recently proposed Vision Transformer network while it does not require any training data to adjust parameters. In image retrieval tasks, the use of Handcrafted global and local descriptors has been very successfully replaced, over the last years, by the Convolutional Neural Networks (CNN)-based methods. However, the experimental evaluation conducted in this paper on several benchmarking datasets against 36 st"},"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":"2101.03771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-11T08:59:54Z","cross_cats_sorted":["cs.IR","cs.RO"],"title_canon_sha256":"129a580a31c36b1eee38bc8f0bbf2a809bf63815fe4c00c300bc4af01020a5de","abstract_canon_sha256":"292bf5f7a1ef5deb8e9662b7ac2e4bcd6b40e3caa3bb2509abdaa04462a3231d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:53.733346Z","signature_b64":"WLKG17GLCzzDcSkOIHkWwQDoNBEnzyqIuVDI++sFtbCe7Cy5fq6s5SZIpPrMtIRvplDQOiGdShnpWPWhy7fxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36a3aa39e84d4f7fa0af959498887006161f43c5d846a648d9ce34c0ad19a32f","last_reissued_at":"2026-07-05T02:05:53.732874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:53.732874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating the Vision Transformer Model for Image Retrieval Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.RO"],"primary_cat":"cs.CV","authors_text":"Savvas A. Chatzichristofis, Socratis Gkelios, Yiannis Boutalis","submitted_at":"2021-01-11T08:59:54Z","abstract_excerpt":"This paper introduces a plug-and-play descriptor that can be effectively adopted for image retrieval tasks without prior initialization or preparation. The description method utilizes the recently proposed Vision Transformer network while it does not require any training data to adjust parameters. In image retrieval tasks, the use of Handcrafted global and local descriptors has been very successfully replaced, over the last years, by the Convolutional Neural Networks (CNN)-based methods. However, the experimental evaluation conducted in this paper on several benchmarking datasets against 36 st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03771","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/2101.03771/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":"2101.03771","created_at":"2026-07-05T02:05:53.732934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.03771v1","created_at":"2026-07-05T02:05:53.732934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03771","created_at":"2026-07-05T02:05:53.732934+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2R2UOPIJVHX","created_at":"2026-07-05T02:05:53.732934+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2R2UOPIJVHX7IFP","created_at":"2026-07-05T02:05:53.732934+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2R2UOPI","created_at":"2026-07-05T02:05:53.732934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13794","citing_title":"MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G2R2UOPIJVHX7IFPSWKJRCDQAY","json":"https://pith.science/pith/G2R2UOPIJVHX7IFPSWKJRCDQAY.json","graph_json":"https://pith.science/api/pith-number/G2R2UOPIJVHX7IFPSWKJRCDQAY/graph.json","events_json":"https://pith.science/api/pith-number/G2R2UOPIJVHX7IFPSWKJRCDQAY/events.json","paper":"https://pith.science/paper/G2R2UOPI"},"agent_actions":{"view_html":"https://pith.science/pith/G2R2UOPIJVHX7IFPSWKJRCDQAY","download_json":"https://pith.science/pith/G2R2UOPIJVHX7IFPSWKJRCDQAY.json","view_paper":"https://pith.science/paper/G2R2UOPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.03771&json=true","fetch_graph":"https://pith.science/api/pith-number/G2R2UOPIJVHX7IFPSWKJRCDQAY/graph.json","fetch_events":"https://pith.science/api/pith-number/G2R2UOPIJVHX7IFPSWKJRCDQAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2R2UOPIJVHX7IFPSWKJRCDQAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2R2UOPIJVHX7IFPSWKJRCDQAY/action/storage_attestation","attest_author":"https://pith.science/pith/G2R2UOPIJVHX7IFPSWKJRCDQAY/action/author_attestation","sign_citation":"https://pith.science/pith/G2R2UOPIJVHX7IFPSWKJRCDQAY/action/citation_signature","submit_replication":"https://pith.science/pith/G2R2UOPIJVHX7IFPSWKJRCDQAY/action/replication_record"}},"created_at":"2026-07-05T02:05:53.732934+00:00","updated_at":"2026-07-05T02:05:53.732934+00:00"}