{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:6O3OGO2F74ZRQQBN63X3LG3FN4","short_pith_number":"pith:6O3OGO2F","schema_version":"1.0","canonical_sha256":"f3b6e33b45ff3318402df6efb59b656f25b18fc2be9b6fe9eb5a9ee1f68d8299","source":{"kind":"arxiv","id":"1504.03083","version":2},"attestation_state":"computed","paper":{"title":"Joint Learning of Distributed Representations for Images and Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianfeng Gao, Li Deng, Rupesh Srivastava, Xiaodong He","submitted_at":"2015-04-13T07:36:08Z","abstract_excerpt":"This technical report provides extra details of the deep multimodal similarity model (DMSM) which was proposed in (Fang et al. 2015, arXiv:1411.4952). The model is trained via maximizing global semantic similarity between images and their captions in natural language using the public Microsoft COCO database, which consists of a large set of images and their corresponding captions. The learned representations attempt to capture the combination of various visual concepts and cues."},"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":"1504.03083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-13T07:36:08Z","cross_cats_sorted":[],"title_canon_sha256":"605ab6fe68daa0dce8a5a2e31ba8b3d87bc9324f28999fb7484da42ef7a633d3","abstract_canon_sha256":"6f40e69af00ab8082c56a49dd4bf682d3f0173f5e6fe2c6217f7e136db9552a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:17:35.520296Z","signature_b64":"/yp5RVq4sscP1mbOW6JEfCNtMsocznXLOOsIIENtM2T1RWiaUdezYnd2aMMxJaXmEG02S6hXE9E9fSbN+qs4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3b6e33b45ff3318402df6efb59b656f25b18fc2be9b6fe9eb5a9ee1f68d8299","last_reissued_at":"2026-05-18T02:17:35.519571Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:17:35.519571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Learning of Distributed Representations for Images and Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianfeng Gao, Li Deng, Rupesh Srivastava, Xiaodong He","submitted_at":"2015-04-13T07:36:08Z","abstract_excerpt":"This technical report provides extra details of the deep multimodal similarity model (DMSM) which was proposed in (Fang et al. 2015, arXiv:1411.4952). The model is trained via maximizing global semantic similarity between images and their captions in natural language using the public Microsoft COCO database, which consists of a large set of images and their corresponding captions. The learned representations attempt to capture the combination of various visual concepts and cues."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.03083","kind":"arxiv","version":2},"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":"1504.03083","created_at":"2026-05-18T02:17:35.519685+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.03083v2","created_at":"2026-05-18T02:17:35.519685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.03083","created_at":"2026-05-18T02:17:35.519685+00:00"},{"alias_kind":"pith_short_12","alias_value":"6O3OGO2F74ZR","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"6O3OGO2F74ZRQQBN","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"6O3OGO2F","created_at":"2026-05-18T12:29:07.941421+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/6O3OGO2F74ZRQQBN63X3LG3FN4","json":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4.json","graph_json":"https://pith.science/api/pith-number/6O3OGO2F74ZRQQBN63X3LG3FN4/graph.json","events_json":"https://pith.science/api/pith-number/6O3OGO2F74ZRQQBN63X3LG3FN4/events.json","paper":"https://pith.science/paper/6O3OGO2F"},"agent_actions":{"view_html":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4","download_json":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4.json","view_paper":"https://pith.science/paper/6O3OGO2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.03083&json=true","fetch_graph":"https://pith.science/api/pith-number/6O3OGO2F74ZRQQBN63X3LG3FN4/graph.json","fetch_events":"https://pith.science/api/pith-number/6O3OGO2F74ZRQQBN63X3LG3FN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/action/storage_attestation","attest_author":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/action/author_attestation","sign_citation":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/action/citation_signature","submit_replication":"https://pith.science/pith/6O3OGO2F74ZRQQBN63X3LG3FN4/action/replication_record"}},"created_at":"2026-05-18T02:17:35.519685+00:00","updated_at":"2026-05-18T02:17:35.519685+00:00"}