{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F5UJRJW7GLJZSGUNW3FHEXNUTT","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":"96a57fa4168174048bd0411d190f390594f0999efc4c38a82351fb9c26a7f35e","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T10:54:54Z","title_canon_sha256":"67cfda736647f9c2bc06b63adfb8ab5382776342165494795c55ecacbe6b65fc"},"schema_version":"1.0","source":{"id":"2210.05335","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05335","created_at":"2026-07-05T06:33:02Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05335v3","created_at":"2026-07-05T06:33:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05335","created_at":"2026-07-05T06:33:02Z"},{"alias_kind":"pith_short_12","alias_value":"F5UJRJW7GLJZ","created_at":"2026-07-05T06:33:02Z"},{"alias_kind":"pith_short_16","alias_value":"F5UJRJW7GLJZSGUN","created_at":"2026-07-05T06:33:02Z"},{"alias_kind":"pith_short_8","alias_value":"F5UJRJW7","created_at":"2026-07-05T06:33:02Z"}],"graph_snapshots":[{"event_id":"sha256:bf5d7f521a1271645dd505a0c86b80e76ec7d3c2d5cb07efcf7d438dc8035ced","target":"graph","created_at":"2026-07-05T06:33:02Z","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/2210.05335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal semantic understanding often has to deal with uncertainty, which means the obtained messages tend to refer to multiple targets. Such uncertainty is problematic for our interpretation, including inter- and intra-modal uncertainty. Little effort has studied the modeling of this uncertainty, particularly in pre-training on unlabeled datasets and fine-tuning in task-specific downstream datasets. In this paper, we project the representations of all modalities as probabilistic distributions via a Probability Distribution Encoder (PDE) by utilizing sequence-level interactions. Compared to ","authors_text":"Hongfa Wang, Jiaxing Zhang, Junjie Wang, Lin Zhang, Tetsuya Sakai, Yanru Zhu, Yatai Ji, Yuan Gong, Yujiu Yang","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T10:54:54Z","title":"MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05335","kind":"arxiv","version":3},"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":"sha256:83e4ff1c3bcb4edf279b67d632f5db9b5382746e515236c989579177d8ea8529","target":"record","created_at":"2026-07-05T06:33:02Z","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":"96a57fa4168174048bd0411d190f390594f0999efc4c38a82351fb9c26a7f35e","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T10:54:54Z","title_canon_sha256":"67cfda736647f9c2bc06b63adfb8ab5382776342165494795c55ecacbe6b65fc"},"schema_version":"1.0","source":{"id":"2210.05335","kind":"arxiv","version":3}},"canonical_sha256":"2f6898a6df32d3991a8db6ca725db49cc8acb8ec973998070e145f09d312e3d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f6898a6df32d3991a8db6ca725db49cc8acb8ec973998070e145f09d312e3d5","first_computed_at":"2026-07-05T06:33:02.828019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:02.828019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"//nLdmTqgr/6KrYNDdqrELab4SWWsc2bnCJrIanf+CK12mXBuGOdOq/kkvAAqAZRXBUbeRtHj+iKjVihY3dIBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:02.828521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05335","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83e4ff1c3bcb4edf279b67d632f5db9b5382746e515236c989579177d8ea8529","sha256:bf5d7f521a1271645dd505a0c86b80e76ec7d3c2d5cb07efcf7d438dc8035ced"],"state_sha256":"b4a9fa9d1221834123d891797a8ed35a4642c44d3a7352d92fcd10fce701467c"}