{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XXJH3VV46IUWXH3LUORKCLHAEG","short_pith_number":"pith:XXJH3VV4","schema_version":"1.0","canonical_sha256":"bdd27dd6bcf2296b9f6ba3a2a12ce021845ede0319045ed18cce97df9388d488","source":{"kind":"arxiv","id":"2012.15409","version":4},"attestation_state":"computed","paper":{"title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Gao, Guocheng Niu, HaiFeng Wang, Hao Liu, Hua Wu, Jiachen Liu, Wei Li, Xinyan Xiao","submitted_at":"2020-12-31T02:46:47Z","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"},"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":"2012.15409","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T02:46:47Z","cross_cats_sorted":[],"title_canon_sha256":"8b8716a39564aec20fe84f3ae61b415a4279e7e93cdaf626140ba30c8c541dbb","abstract_canon_sha256":"2162058c0089867a04612a9977df296452eb44b55581fb39180f5ddf563463fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:37.530011Z","signature_b64":"yS+sWp+v11NoauliOK5PykpeZpeaCkMQlZId3/FdubWqoJh2e85WKkj83I72e/1NfuyaoyDaGS/t1b3A+uM6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdd27dd6bcf2296b9f6ba3a2a12ce021845ede0319045ed18cce97df9388d488","last_reissued_at":"2026-07-05T04:04:37.529534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:37.529534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Gao, Guocheng Niu, HaiFeng Wang, Hao Liu, Hua Wu, Jiachen Liu, Wei Li, Xinyan Xiao","submitted_at":"2020-12-31T02:46:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15409","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/2012.15409/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":"2012.15409","created_at":"2026-07-05T04:04:37.529592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.15409v4","created_at":"2026-07-05T04:04:37.529592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15409","created_at":"2026-07-05T04:04:37.529592+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXJH3VV46IUW","created_at":"2026-07-05T04:04:37.529592+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXJH3VV46IUWXH3L","created_at":"2026-07-05T04:04:37.529592+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXJH3VV4","created_at":"2026-07-05T04:04:37.529592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04061","citing_title":"Intra-Modal Neighbors Never Lie: Rectifying Inter-Modal Noisy Correspondence via Graph-Based Intra-Modal Reasoning","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08600","citing_title":"Gaze2Report: Radiology Report Generation via Visual-Gaze Prompt Tuning of LLMs","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XXJH3VV46IUWXH3LUORKCLHAEG","json":"https://pith.science/pith/XXJH3VV46IUWXH3LUORKCLHAEG.json","graph_json":"https://pith.science/api/pith-number/XXJH3VV46IUWXH3LUORKCLHAEG/graph.json","events_json":"https://pith.science/api/pith-number/XXJH3VV46IUWXH3LUORKCLHAEG/events.json","paper":"https://pith.science/paper/XXJH3VV4"},"agent_actions":{"view_html":"https://pith.science/pith/XXJH3VV46IUWXH3LUORKCLHAEG","download_json":"https://pith.science/pith/XXJH3VV46IUWXH3LUORKCLHAEG.json","view_paper":"https://pith.science/paper/XXJH3VV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.15409&json=true","fetch_graph":"https://pith.science/api/pith-number/XXJH3VV46IUWXH3LUORKCLHAEG/graph.json","fetch_events":"https://pith.science/api/pith-number/XXJH3VV46IUWXH3LUORKCLHAEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXJH3VV46IUWXH3LUORKCLHAEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXJH3VV46IUWXH3LUORKCLHAEG/action/storage_attestation","attest_author":"https://pith.science/pith/XXJH3VV46IUWXH3LUORKCLHAEG/action/author_attestation","sign_citation":"https://pith.science/pith/XXJH3VV46IUWXH3LUORKCLHAEG/action/citation_signature","submit_replication":"https://pith.science/pith/XXJH3VV46IUWXH3LUORKCLHAEG/action/replication_record"}},"created_at":"2026-07-05T04:04:37.529592+00:00","updated_at":"2026-07-05T04:04:37.529592+00:00"}