{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WU6ETRTR7THRRUFRATF3XR6N24","short_pith_number":"pith:WU6ETRTR","schema_version":"1.0","canonical_sha256":"b53c49c671fccf18d0b104cbbbc7cdd70600d2c66dda80608347d9d113a8bc71","source":{"kind":"arxiv","id":"2406.00423","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Metadata Assignment for Cultural Heritage Artifacts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dunja Mladeni\\'c, Franz Rottensteiner, Jorge Sebasti\\'an Lozano, Luis Rei, Mareike Dorozynski, Mar Gait\\'an Salvatella, Rapha\\\"el Troncy, Thomas Schleider","submitted_at":"2024-06-01T12:41:03Z","abstract_excerpt":"We develop a multimodal classifier for the cultural heritage domain using a late fusion approach and introduce a novel dataset. The three modalities are Image, Text, and Tabular data. We based the image classifier on a ResNet convolutional neural network architecture and the text classifier on a multilingual transformer architecture (XML-Roberta). Both are trained as multitask classifiers and use the focal loss to handle class imbalance. Tabular data and late fusion are handled by Gradient Tree Boosting. We also show how we leveraged specific data models and taxonomy in a Knowledge Graph to cr"},"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":"2406.00423","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-01T12:41:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ace7536fda956e79ce8cae373e603f0760e8d213e9d04b548ceaf062e6a4412d","abstract_canon_sha256":"c5837b462c3f78967c8a7ef1a3e75a378ab5e64710783e4f91eb97385d57cfaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:01.781902Z","signature_b64":"jDcdQlSyl4cx4PAZDAuN0FCkbtPRfwlcdP1Zd9W/ggcGm56ht0L945vx2+U/ySy2HpaZYLwTMl+Fi+qz0O6BAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b53c49c671fccf18d0b104cbbbc7cdd70600d2c66dda80608347d9d113a8bc71","last_reissued_at":"2026-07-05T08:26:01.781361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:01.781361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Metadata Assignment for Cultural Heritage Artifacts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dunja Mladeni\\'c, Franz Rottensteiner, Jorge Sebasti\\'an Lozano, Luis Rei, Mareike Dorozynski, Mar Gait\\'an Salvatella, Rapha\\\"el Troncy, Thomas Schleider","submitted_at":"2024-06-01T12:41:03Z","abstract_excerpt":"We develop a multimodal classifier for the cultural heritage domain using a late fusion approach and introduce a novel dataset. The three modalities are Image, Text, and Tabular data. We based the image classifier on a ResNet convolutional neural network architecture and the text classifier on a multilingual transformer architecture (XML-Roberta). Both are trained as multitask classifiers and use the focal loss to handle class imbalance. Tabular data and late fusion are handled by Gradient Tree Boosting. We also show how we leveraged specific data models and taxonomy in a Knowledge Graph to cr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00423","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/2406.00423/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":"2406.00423","created_at":"2026-07-05T08:26:01.781426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00423v1","created_at":"2026-07-05T08:26:01.781426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00423","created_at":"2026-07-05T08:26:01.781426+00:00"},{"alias_kind":"pith_short_12","alias_value":"WU6ETRTR7THR","created_at":"2026-07-05T08:26:01.781426+00:00"},{"alias_kind":"pith_short_16","alias_value":"WU6ETRTR7THRRUFR","created_at":"2026-07-05T08:26:01.781426+00:00"},{"alias_kind":"pith_short_8","alias_value":"WU6ETRTR","created_at":"2026-07-05T08:26:01.781426+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/WU6ETRTR7THRRUFRATF3XR6N24","json":"https://pith.science/pith/WU6ETRTR7THRRUFRATF3XR6N24.json","graph_json":"https://pith.science/api/pith-number/WU6ETRTR7THRRUFRATF3XR6N24/graph.json","events_json":"https://pith.science/api/pith-number/WU6ETRTR7THRRUFRATF3XR6N24/events.json","paper":"https://pith.science/paper/WU6ETRTR"},"agent_actions":{"view_html":"https://pith.science/pith/WU6ETRTR7THRRUFRATF3XR6N24","download_json":"https://pith.science/pith/WU6ETRTR7THRRUFRATF3XR6N24.json","view_paper":"https://pith.science/paper/WU6ETRTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00423&json=true","fetch_graph":"https://pith.science/api/pith-number/WU6ETRTR7THRRUFRATF3XR6N24/graph.json","fetch_events":"https://pith.science/api/pith-number/WU6ETRTR7THRRUFRATF3XR6N24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WU6ETRTR7THRRUFRATF3XR6N24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WU6ETRTR7THRRUFRATF3XR6N24/action/storage_attestation","attest_author":"https://pith.science/pith/WU6ETRTR7THRRUFRATF3XR6N24/action/author_attestation","sign_citation":"https://pith.science/pith/WU6ETRTR7THRRUFRATF3XR6N24/action/citation_signature","submit_replication":"https://pith.science/pith/WU6ETRTR7THRRUFRATF3XR6N24/action/replication_record"}},"created_at":"2026-07-05T08:26:01.781426+00:00","updated_at":"2026-07-05T08:26:01.781426+00:00"}