{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XXJH3VV46IUWXH3LUORKCLHAEG","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":"2162058c0089867a04612a9977df296452eb44b55581fb39180f5ddf563463fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T02:46:47Z","title_canon_sha256":"8b8716a39564aec20fe84f3ae61b415a4279e7e93cdaf626140ba30c8c541dbb"},"schema_version":"1.0","source":{"id":"2012.15409","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15409","created_at":"2026-07-05T04:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15409v4","created_at":"2026-07-05T04:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15409","created_at":"2026-07-05T04:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"XXJH3VV46IUW","created_at":"2026-07-05T04:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"XXJH3VV46IUWXH3L","created_at":"2026-07-05T04:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"XXJH3VV4","created_at":"2026-07-05T04:04:37Z"}],"graph_snapshots":[{"event_id":"sha256:3cf6f1e9ccfd292fbf68753bd47252f52e98df0113f45062f968310cb67cb553","target":"graph","created_at":"2026-07-05T04:04:37Z","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/2012.15409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other. They can only utilize single-modal data (i.e. text or image) or limited multi-modal data (i.e. image-text pairs). In this work, we propose a unified-modal pre-training architecture, namely UNIMO, which can effectively adapt to both single-modal and multi-modal understanding and generation tasks. Large scale of free text corpus and image collections can be utilized to improve the capability of visual and textual understanding, and cross-modal contrastive learning (CM","authors_text":"Can Gao, Guocheng Niu, HaiFeng Wang, Hao Liu, Hua Wu, Jiachen Liu, Wei Li, Xinyan Xiao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T02:46:47Z","title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15409","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:a61c1e756b308e72e5c0290d8c3117f6f12f89702f4aae07d5957f658ca2119b","target":"record","created_at":"2026-07-05T04:04:37Z","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":"2162058c0089867a04612a9977df296452eb44b55581fb39180f5ddf563463fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T02:46:47Z","title_canon_sha256":"8b8716a39564aec20fe84f3ae61b415a4279e7e93cdaf626140ba30c8c541dbb"},"schema_version":"1.0","source":{"id":"2012.15409","kind":"arxiv","version":4}},"canonical_sha256":"bdd27dd6bcf2296b9f6ba3a2a12ce021845ede0319045ed18cce97df9388d488","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdd27dd6bcf2296b9f6ba3a2a12ce021845ede0319045ed18cce97df9388d488","first_computed_at":"2026-07-05T04:04:37.529534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:37.529534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yS+sWp+v11NoauliOK5PykpeZpeaCkMQlZId3/FdubWqoJh2e85WKkj83I72e/1NfuyaoyDaGS/t1b3A+uM6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:37.530011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15409","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a61c1e756b308e72e5c0290d8c3117f6f12f89702f4aae07d5957f658ca2119b","sha256:3cf6f1e9ccfd292fbf68753bd47252f52e98df0113f45062f968310cb67cb553"],"state_sha256":"56841544e6db0b7a51796ea6a996e894ca02b4840b47cf36efe11a00df944567"}