{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AGOPFISTINX4XJMQOLQV6YK44T","short_pith_number":"pith:AGOPFIST","schema_version":"1.0","canonical_sha256":"019cf2a253436fcba59072e15f615ce4fd6a2c4007a3e752088bfb9d17b9140c","source":{"kind":"arxiv","id":"1901.02004","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Learning from Web Data for Multimodal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimosthenis Karatzas, Jaume Gibert, Lluis Gomez, Raul Gomez","submitted_at":"2019-01-07T14:34:49Z","abstract_excerpt":"Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal data. In this work we propose to exploit this free available data to learn a multimodal image and text embedding, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the proposed pipeline can learn from images with associated textwithout supervision and analy"},"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":"1901.02004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-07T14:34:49Z","cross_cats_sorted":[],"title_canon_sha256":"f47dea5cfa71e73d43ba7a501f8351e668db0b7459498a3480aa6b87e86b519c","abstract_canon_sha256":"99f470159b6b84c1277b5206fd626a35c2f8b28f328796d683fbd99fc8249fcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:44.186529Z","signature_b64":"tWOyVRExVTRhMHlfKFFl/bs7roeqG5CeS7VXjkaNPA/2Q1JbNwJlSxGsWzqd69J2x0hWTfTC+ZjJ6dKUGSjvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"019cf2a253436fcba59072e15f615ce4fd6a2c4007a3e752088bfb9d17b9140c","last_reissued_at":"2026-05-17T23:56:44.185945Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:44.185945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Learning from Web Data for Multimodal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimosthenis Karatzas, Jaume Gibert, Lluis Gomez, Raul Gomez","submitted_at":"2019-01-07T14:34:49Z","abstract_excerpt":"Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal data. In this work we propose to exploit this free available data to learn a multimodal image and text embedding, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the proposed pipeline can learn from images with associated textwithout supervision and analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02004","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":"1901.02004","created_at":"2026-05-17T23:56:44.186026+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.02004v1","created_at":"2026-05-17T23:56:44.186026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02004","created_at":"2026-05-17T23:56:44.186026+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGOPFISTINX4","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGOPFISTINX4XJMQ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGOPFIST","created_at":"2026-05-18T12:33:12.712433+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/AGOPFISTINX4XJMQOLQV6YK44T","json":"https://pith.science/pith/AGOPFISTINX4XJMQOLQV6YK44T.json","graph_json":"https://pith.science/api/pith-number/AGOPFISTINX4XJMQOLQV6YK44T/graph.json","events_json":"https://pith.science/api/pith-number/AGOPFISTINX4XJMQOLQV6YK44T/events.json","paper":"https://pith.science/paper/AGOPFIST"},"agent_actions":{"view_html":"https://pith.science/pith/AGOPFISTINX4XJMQOLQV6YK44T","download_json":"https://pith.science/pith/AGOPFISTINX4XJMQOLQV6YK44T.json","view_paper":"https://pith.science/paper/AGOPFIST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.02004&json=true","fetch_graph":"https://pith.science/api/pith-number/AGOPFISTINX4XJMQOLQV6YK44T/graph.json","fetch_events":"https://pith.science/api/pith-number/AGOPFISTINX4XJMQOLQV6YK44T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGOPFISTINX4XJMQOLQV6YK44T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGOPFISTINX4XJMQOLQV6YK44T/action/storage_attestation","attest_author":"https://pith.science/pith/AGOPFISTINX4XJMQOLQV6YK44T/action/author_attestation","sign_citation":"https://pith.science/pith/AGOPFISTINX4XJMQOLQV6YK44T/action/citation_signature","submit_replication":"https://pith.science/pith/AGOPFISTINX4XJMQOLQV6YK44T/action/replication_record"}},"created_at":"2026-05-17T23:56:44.186026+00:00","updated_at":"2026-05-17T23:56:44.186026+00:00"}