{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WRV7F5MVJ2R2FXZNT5W2I3SSX4","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":"9726f5a4352d8129c28e49838526b148461cce23fd0900e0c39f32789a5c18dc","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-11T22:26:10Z","title_canon_sha256":"8d49badf87b84ab8a1e2e43f57c78bc82f34f0204c37685b7f74d326ccf388c6"},"schema_version":"1.0","source":{"id":"2304.05523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05523","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05523v1","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05523","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"WRV7F5MVJ2R2","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"WRV7F5MVJ2R2FXZN","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"WRV7F5MV","created_at":"2026-07-05T06:00:19Z"}],"graph_snapshots":[{"event_id":"sha256:6ce5da3226ab0c1d2d23006663a0e87a035d2cf9c3ae1e75265a31eb191b3c16","target":"graph","created_at":"2026-07-05T06:00:19Z","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/2304.05523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a self-supervised shared encoder model that achieves strong results on several visual, language and multimodal benchmarks while being data, memory and run-time efficient. We make three key contributions. First, in contrast to most existing works, we use a single transformer with all the encoder layers processing both the text and the image modalities. Second, we propose a stage-wise training strategy where the model is first trained on images, then jointly with unimodal text and image datasets and finally jointly with text and text-image datasets. Third, to preserve information acro","authors_text":"Pradeep Natarajan, Rakesh Chada, Zhaoheng Zheng","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-11T22:26:10Z","title":"MoMo: A shared encoder Model for text, image and multi-Modal representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05523","kind":"arxiv","version":1},"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:dd80a222d43bc64426e8acdac432cee197e4d420c40829c55bc47d5317776391","target":"record","created_at":"2026-07-05T06:00:19Z","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":"9726f5a4352d8129c28e49838526b148461cce23fd0900e0c39f32789a5c18dc","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-11T22:26:10Z","title_canon_sha256":"8d49badf87b84ab8a1e2e43f57c78bc82f34f0204c37685b7f74d326ccf388c6"},"schema_version":"1.0","source":{"id":"2304.05523","kind":"arxiv","version":1}},"canonical_sha256":"b46bf2f5954ea3a2df2d9f6da46e52bf049a10a97602c994c2eddfb66a1be3e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b46bf2f5954ea3a2df2d9f6da46e52bf049a10a97602c994c2eddfb66a1be3e5","first_computed_at":"2026-07-05T06:00:19.789586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:00:19.789586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nSLaYOGXOwrHKIouzaZUSrhyJjoKCFXikFFlyccYQV4oQBwT1J2Xfsj8vsYf3x9mRjD8QJyHKjLGrg/oake+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:00:19.790059Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.05523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd80a222d43bc64426e8acdac432cee197e4d420c40829c55bc47d5317776391","sha256:6ce5da3226ab0c1d2d23006663a0e87a035d2cf9c3ae1e75265a31eb191b3c16"],"state_sha256":"1fbf1f6762e0ce77585c64b3fcac75d51dab9aea5cc8bb15eb9cdd0f68cdd4b8"}