{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KKQDT73LWU7JO5V2EC2CXZRF7E","short_pith_number":"pith:KKQDT73L","schema_version":"1.0","canonical_sha256":"52a039ff6bb53e9776ba20b42be625f923e06fc6025295c629a59b166a607877","source":{"kind":"arxiv","id":"2109.04993","version":4},"attestation_state":"computed","paper":{"title":"LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhishek Satbhai, Mihir Chauhan, Mingchen Gao, Mir Basheer Ali, Mohammad Abuzar Hashemi, Sargur Srihari, Yan Shen, Zhanghexuan Li","submitted_at":"2021-09-04T22:48:46Z","abstract_excerpt":"Pre-training visual and textual representations from large-scale image-text pairs is becoming a standard approach for many downstream vision-language tasks. The transformer-based models learn inter and intra-modal attention through a list of self-supervised learning tasks. This paper proposes LAViTeR, a novel architecture for visual and textual representation learning. The main module, Visual Textual Alignment (VTA) will be assisted by two auxiliary tasks, GAN-based image synthesis and Image Captioning. We also propose a new evaluation metric measuring the similarity between the learnt visual "},"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":"2109.04993","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-04T22:48:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e3716aa7258344e8e3d316bc8958b8b14b588c77d39bbe91456ea06a2a2a5fcc","abstract_canon_sha256":"b61fccdb4cf6fbf724c184ac4c73dfc2c54f5572dea28f0cef1a1ebbe7ca2643"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:16.221555Z","signature_b64":"A2R2fJKTDnSPGPVexYAit6n9sbQvc8XL8gEElldD/XUyqC0UJ2pK42pML+5H2FHmxWhy0MMOj8y4axNS8SEjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52a039ff6bb53e9776ba20b42be625f923e06fc6025295c629a59b166a607877","last_reissued_at":"2026-07-05T09:14:16.221000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:16.221000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhishek Satbhai, Mihir Chauhan, Mingchen Gao, Mir Basheer Ali, Mohammad Abuzar Hashemi, Sargur Srihari, Yan Shen, Zhanghexuan Li","submitted_at":"2021-09-04T22:48:46Z","abstract_excerpt":"Pre-training visual and textual representations from large-scale image-text pairs is becoming a standard approach for many downstream vision-language tasks. The transformer-based models learn inter and intra-modal attention through a list of self-supervised learning tasks. This paper proposes LAViTeR, a novel architecture for visual and textual representation learning. The main module, Visual Textual Alignment (VTA) will be assisted by two auxiliary tasks, GAN-based image synthesis and Image Captioning. We also propose a new evaluation metric measuring the similarity between the learnt visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04993","kind":"arxiv","version":4},"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/2109.04993/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":"2109.04993","created_at":"2026-07-05T09:14:16.221090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.04993v4","created_at":"2026-07-05T09:14:16.221090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04993","created_at":"2026-07-05T09:14:16.221090+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKQDT73LWU7J","created_at":"2026-07-05T09:14:16.221090+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKQDT73LWU7JO5V2","created_at":"2026-07-05T09:14:16.221090+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKQDT73L","created_at":"2026-07-05T09:14:16.221090+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/KKQDT73LWU7JO5V2EC2CXZRF7E","json":"https://pith.science/pith/KKQDT73LWU7JO5V2EC2CXZRF7E.json","graph_json":"https://pith.science/api/pith-number/KKQDT73LWU7JO5V2EC2CXZRF7E/graph.json","events_json":"https://pith.science/api/pith-number/KKQDT73LWU7JO5V2EC2CXZRF7E/events.json","paper":"https://pith.science/paper/KKQDT73L"},"agent_actions":{"view_html":"https://pith.science/pith/KKQDT73LWU7JO5V2EC2CXZRF7E","download_json":"https://pith.science/pith/KKQDT73LWU7JO5V2EC2CXZRF7E.json","view_paper":"https://pith.science/paper/KKQDT73L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.04993&json=true","fetch_graph":"https://pith.science/api/pith-number/KKQDT73LWU7JO5V2EC2CXZRF7E/graph.json","fetch_events":"https://pith.science/api/pith-number/KKQDT73LWU7JO5V2EC2CXZRF7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKQDT73LWU7JO5V2EC2CXZRF7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKQDT73LWU7JO5V2EC2CXZRF7E/action/storage_attestation","attest_author":"https://pith.science/pith/KKQDT73LWU7JO5V2EC2CXZRF7E/action/author_attestation","sign_citation":"https://pith.science/pith/KKQDT73LWU7JO5V2EC2CXZRF7E/action/citation_signature","submit_replication":"https://pith.science/pith/KKQDT73LWU7JO5V2EC2CXZRF7E/action/replication_record"}},"created_at":"2026-07-05T09:14:16.221090+00:00","updated_at":"2026-07-05T09:14:16.221090+00:00"}