{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IWOPIHRGSYWO32V3M4CVWQVWLT","short_pith_number":"pith:IWOPIHRG","schema_version":"1.0","canonical_sha256":"459cf41e26962cedeabb67055b42b65ce150f1c834afd2b7b9769f98bcf617c3","source":{"kind":"arxiv","id":"2211.14451","version":1},"attestation_state":"computed","paper":{"title":"GLAMI-1M: A Multilingual Image-Text Fashion Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anton\\'in Hoskovec, Milan \\v{S}ulc, Radek Bartyzal, Vaclav Kosar","submitted_at":"2022-11-17T13:19:07Z","abstract_excerpt":"We introduce GLAMI-1M: the largest multilingual image-text classification dataset and benchmark. The dataset contains images of fashion products with item descriptions, each in 1 of 13 languages. Categorization into 191 classes has high-quality annotations: all 100k images in the test set and 75% of the 1M training set were human-labeled. The paper presents baselines for image-text classification showing that the dataset presents a challenging fine-grained classification problem: The best scoring EmbraceNet model using both visual and textual features achieves 69.7% accuracy. Experiments with "},"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":"2211.14451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T13:19:07Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"dfb1a1666b7717a2c7dddf523808266630a7fc2b91ae15a75e9cc0ba30f4f9cb","abstract_canon_sha256":"55b688c6225f738c0101797080119f2bc13fb45c186c592ec514be9be039b54b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:39.834256Z","signature_b64":"DOKAygdGOBbm7RMpJE+QWfnvNQHGDr3PMxOVaYODWZ7vJ4KwTu4YUPg0ULUw4VYt36LkKg8VF2IBOD/Ldc6vAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"459cf41e26962cedeabb67055b42b65ce150f1c834afd2b7b9769f98bcf617c3","last_reissued_at":"2026-07-05T05:19:39.833919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:39.833919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLAMI-1M: A Multilingual Image-Text Fashion Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anton\\'in Hoskovec, Milan \\v{S}ulc, Radek Bartyzal, Vaclav Kosar","submitted_at":"2022-11-17T13:19:07Z","abstract_excerpt":"We introduce GLAMI-1M: the largest multilingual image-text classification dataset and benchmark. The dataset contains images of fashion products with item descriptions, each in 1 of 13 languages. Categorization into 191 classes has high-quality annotations: all 100k images in the test set and 75% of the 1M training set were human-labeled. The paper presents baselines for image-text classification showing that the dataset presents a challenging fine-grained classification problem: The best scoring EmbraceNet model using both visual and textual features achieves 69.7% accuracy. Experiments with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14451","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/2211.14451/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":"2211.14451","created_at":"2026-07-05T05:19:39.833980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.14451v1","created_at":"2026-07-05T05:19:39.833980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14451","created_at":"2026-07-05T05:19:39.833980+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWOPIHRGSYWO","created_at":"2026-07-05T05:19:39.833980+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWOPIHRGSYWO32V3","created_at":"2026-07-05T05:19:39.833980+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWOPIHRG","created_at":"2026-07-05T05:19:39.833980+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/IWOPIHRGSYWO32V3M4CVWQVWLT","json":"https://pith.science/pith/IWOPIHRGSYWO32V3M4CVWQVWLT.json","graph_json":"https://pith.science/api/pith-number/IWOPIHRGSYWO32V3M4CVWQVWLT/graph.json","events_json":"https://pith.science/api/pith-number/IWOPIHRGSYWO32V3M4CVWQVWLT/events.json","paper":"https://pith.science/paper/IWOPIHRG"},"agent_actions":{"view_html":"https://pith.science/pith/IWOPIHRGSYWO32V3M4CVWQVWLT","download_json":"https://pith.science/pith/IWOPIHRGSYWO32V3M4CVWQVWLT.json","view_paper":"https://pith.science/paper/IWOPIHRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.14451&json=true","fetch_graph":"https://pith.science/api/pith-number/IWOPIHRGSYWO32V3M4CVWQVWLT/graph.json","fetch_events":"https://pith.science/api/pith-number/IWOPIHRGSYWO32V3M4CVWQVWLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWOPIHRGSYWO32V3M4CVWQVWLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWOPIHRGSYWO32V3M4CVWQVWLT/action/storage_attestation","attest_author":"https://pith.science/pith/IWOPIHRGSYWO32V3M4CVWQVWLT/action/author_attestation","sign_citation":"https://pith.science/pith/IWOPIHRGSYWO32V3M4CVWQVWLT/action/citation_signature","submit_replication":"https://pith.science/pith/IWOPIHRGSYWO32V3M4CVWQVWLT/action/replication_record"}},"created_at":"2026-07-05T05:19:39.833980+00:00","updated_at":"2026-07-05T05:19:39.833980+00:00"}