{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KKQDT73LWU7JO5V2EC2CXZRF7E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b61fccdb4cf6fbf724c184ac4c73dfc2c54f5572dea28f0cef1a1ebbe7ca2643","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-04T22:48:46Z","title_canon_sha256":"e3716aa7258344e8e3d316bc8958b8b14b588c77d39bbe91456ea06a2a2a5fcc"},"schema_version":"1.0","source":{"id":"2109.04993","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04993","created_at":"2026-07-05T09:14:16Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04993v4","created_at":"2026-07-05T09:14:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04993","created_at":"2026-07-05T09:14:16Z"},{"alias_kind":"pith_short_12","alias_value":"KKQDT73LWU7J","created_at":"2026-07-05T09:14:16Z"},{"alias_kind":"pith_short_16","alias_value":"KKQDT73LWU7JO5V2","created_at":"2026-07-05T09:14:16Z"},{"alias_kind":"pith_short_8","alias_value":"KKQDT73L","created_at":"2026-07-05T09:14:16Z"}],"graph_snapshots":[{"event_id":"sha256:6c1229099ee5aed5bee1c398ecfb019950023870354294c093bc24991c9d956b","target":"graph","created_at":"2026-07-05T09:14:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.04993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Abhishek Satbhai, Mihir Chauhan, Mingchen Gao, Mir Basheer Ali, Mohammad Abuzar Hashemi, Sargur Srihari, Yan Shen, Zhanghexuan Li","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-04T22:48:46Z","title":"LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04993","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:61339fadc95ee987247331db8a2dfc8c6c92260825883cf4454545b7433c2904","target":"record","created_at":"2026-07-05T09:14:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b61fccdb4cf6fbf724c184ac4c73dfc2c54f5572dea28f0cef1a1ebbe7ca2643","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-04T22:48:46Z","title_canon_sha256":"e3716aa7258344e8e3d316bc8958b8b14b588c77d39bbe91456ea06a2a2a5fcc"},"schema_version":"1.0","source":{"id":"2109.04993","kind":"arxiv","version":4}},"canonical_sha256":"52a039ff6bb53e9776ba20b42be625f923e06fc6025295c629a59b166a607877","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52a039ff6bb53e9776ba20b42be625f923e06fc6025295c629a59b166a607877","first_computed_at":"2026-07-05T09:14:16.221000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:16.221000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A2R2fJKTDnSPGPVexYAit6n9sbQvc8XL8gEElldD/XUyqC0UJ2pK42pML+5H2FHmxWhy0MMOj8y4axNS8SEjBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:16.221555Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.04993","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61339fadc95ee987247331db8a2dfc8c6c92260825883cf4454545b7433c2904","sha256:6c1229099ee5aed5bee1c398ecfb019950023870354294c093bc24991c9d956b"],"state_sha256":"6b729fcc47524c7578ff29c679f4222e94ccdfefb529d6f22ad3da13ff04ae70"}