{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HAOAJCDVNLVC5YDKQO2FSP56OW","short_pith_number":"pith:HAOAJCDV","schema_version":"1.0","canonical_sha256":"381c0488756aea2ee06a83b4593fbe7591f1f2497c5b1d42afda3425a1d6d363","source":{"kind":"arxiv","id":"1901.07878","version":1},"attestation_state":"computed","paper":{"title":"\"Is this an example image?\" -- Predicting the Relative Abstractness Level of Image and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Otto, Ralph Ewerth, Sebastian Holzki","submitted_at":"2019-01-23T13:42:02Z","abstract_excerpt":"Successful multimodal search and retrieval requires the automatic understanding of semantic cross-modal relations, which, however, is still an open research problem. Previous work has suggested the metrics cross-modal mutual information and semantic correlation to model and predict cross-modal semantic relations of image and text. In this paper, we present an approach to predict the (cross-modal) relative abstractness level of a given image-text pair, that is whether the image is an abstraction of the text or vice versa. For this purpose, we introduce a new metric that captures this specific r"},"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":"1901.07878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T13:42:02Z","cross_cats_sorted":["cs.CL","cs.CV","cs.IR","stat.ML"],"title_canon_sha256":"1e4af38ac2f414fb925b0ff082bc330c3640367b644120674abe5ad8162d461e","abstract_canon_sha256":"0a857f62fd812f29c63a778ada035a973c9f76d15aefed0335329c18eb45ea31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:07.019015Z","signature_b64":"/FdXrPf8s8Y5VMSYliIgBVZHY4vpE9nXxeMJSxmfn83K0j7+pc1/eH26IQcNtbxg222/3qw0EoLr1Jh1hvokBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"381c0488756aea2ee06a83b4593fbe7591f1f2497c5b1d42afda3425a1d6d363","last_reissued_at":"2026-05-17T23:55:07.018348Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:07.018348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Is this an example image?\" -- Predicting the Relative Abstractness Level of Image and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Otto, Ralph Ewerth, Sebastian Holzki","submitted_at":"2019-01-23T13:42:02Z","abstract_excerpt":"Successful multimodal search and retrieval requires the automatic understanding of semantic cross-modal relations, which, however, is still an open research problem. Previous work has suggested the metrics cross-modal mutual information and semantic correlation to model and predict cross-modal semantic relations of image and text. In this paper, we present an approach to predict the (cross-modal) relative abstractness level of a given image-text pair, that is whether the image is an abstraction of the text or vice versa. For this purpose, we introduce a new metric that captures this specific r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07878","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":""},"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":"1901.07878","created_at":"2026-05-17T23:55:07.018450+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.07878v1","created_at":"2026-05-17T23:55:07.018450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07878","created_at":"2026-05-17T23:55:07.018450+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAOAJCDVNLVC","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAOAJCDVNLVC5YDK","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAOAJCDV","created_at":"2026-05-18T12:33:18.533446+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/HAOAJCDVNLVC5YDKQO2FSP56OW","json":"https://pith.science/pith/HAOAJCDVNLVC5YDKQO2FSP56OW.json","graph_json":"https://pith.science/api/pith-number/HAOAJCDVNLVC5YDKQO2FSP56OW/graph.json","events_json":"https://pith.science/api/pith-number/HAOAJCDVNLVC5YDKQO2FSP56OW/events.json","paper":"https://pith.science/paper/HAOAJCDV"},"agent_actions":{"view_html":"https://pith.science/pith/HAOAJCDVNLVC5YDKQO2FSP56OW","download_json":"https://pith.science/pith/HAOAJCDVNLVC5YDKQO2FSP56OW.json","view_paper":"https://pith.science/paper/HAOAJCDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.07878&json=true","fetch_graph":"https://pith.science/api/pith-number/HAOAJCDVNLVC5YDKQO2FSP56OW/graph.json","fetch_events":"https://pith.science/api/pith-number/HAOAJCDVNLVC5YDKQO2FSP56OW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAOAJCDVNLVC5YDKQO2FSP56OW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAOAJCDVNLVC5YDKQO2FSP56OW/action/storage_attestation","attest_author":"https://pith.science/pith/HAOAJCDVNLVC5YDKQO2FSP56OW/action/author_attestation","sign_citation":"https://pith.science/pith/HAOAJCDVNLVC5YDKQO2FSP56OW/action/citation_signature","submit_replication":"https://pith.science/pith/HAOAJCDVNLVC5YDKQO2FSP56OW/action/replication_record"}},"created_at":"2026-05-17T23:55:07.018450+00:00","updated_at":"2026-05-17T23:55:07.018450+00:00"}