{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NN7FI44JJD55FNBQYX625GNU63","short_pith_number":"pith:NN7FI44J","schema_version":"1.0","canonical_sha256":"6b7e54738948fbd2b430c5fdae99b4f6e1a0d3f5fdb3e69cdd7a8e15d2c966e3","source":{"kind":"arxiv","id":"2305.13697","version":1},"attestation_state":"computed","paper":{"title":"UNIMO-3: Multi-granularity Interaction for Vision-Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Can Gao, Hao L\\'iu, Hao Yang, Xinyan Xiao, Yanyan Zhao","submitted_at":"2023-05-23T05:11:34Z","abstract_excerpt":"Vision-and-language (VL) pre-training, which aims to learn a general representation of image-text pairs that can be transferred to various vision-and-language tasks. Compared with modeling uni-modal data, the main challenge of the VL model is: how to learn the cross-modal interaction from multimodal data, especially the fine-grained interaction. Existing works have shown that fully transformer-based models that adopt attention mechanisms to learn in-layer cross-model interaction can demonstrate impressive performance on various cross-modal downstream tasks. However, they ignored that the seman"},"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":"2305.13697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T05:11:34Z","cross_cats_sorted":[],"title_canon_sha256":"2dd16c6027283dd62a35083b506d8e2fe4a361cdc75e616c4054e7839ec3e900","abstract_canon_sha256":"8d448523530773be8870d768cc0ec6ea1bee7f213fae3a2962c1b5f2740f02f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:56.228438Z","signature_b64":"q8AlJfzSczqQ19fFzHx1YvGQFUDUq768Y0KmqMsZqYIoseWZ5YxQZ9iylh6NbxAk5ZeaseIuWNpqtDEGSm5EAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b7e54738948fbd2b430c5fdae99b4f6e1a0d3f5fdb3e69cdd7a8e15d2c966e3","last_reissued_at":"2026-07-05T06:12:56.228092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:56.228092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UNIMO-3: Multi-granularity Interaction for Vision-Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Can Gao, Hao L\\'iu, Hao Yang, Xinyan Xiao, Yanyan Zhao","submitted_at":"2023-05-23T05:11:34Z","abstract_excerpt":"Vision-and-language (VL) pre-training, which aims to learn a general representation of image-text pairs that can be transferred to various vision-and-language tasks. Compared with modeling uni-modal data, the main challenge of the VL model is: how to learn the cross-modal interaction from multimodal data, especially the fine-grained interaction. Existing works have shown that fully transformer-based models that adopt attention mechanisms to learn in-layer cross-model interaction can demonstrate impressive performance on various cross-modal downstream tasks. However, they ignored that the seman"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13697","kind":"arxiv","version":1},"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/2305.13697/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":"2305.13697","created_at":"2026-07-05T06:12:56.228147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13697v1","created_at":"2026-07-05T06:12:56.228147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13697","created_at":"2026-07-05T06:12:56.228147+00:00"},{"alias_kind":"pith_short_12","alias_value":"NN7FI44JJD55","created_at":"2026-07-05T06:12:56.228147+00:00"},{"alias_kind":"pith_short_16","alias_value":"NN7FI44JJD55FNBQ","created_at":"2026-07-05T06:12:56.228147+00:00"},{"alias_kind":"pith_short_8","alias_value":"NN7FI44J","created_at":"2026-07-05T06:12:56.228147+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63","json":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63.json","graph_json":"https://pith.science/api/pith-number/NN7FI44JJD55FNBQYX625GNU63/graph.json","events_json":"https://pith.science/api/pith-number/NN7FI44JJD55FNBQYX625GNU63/events.json","paper":"https://pith.science/paper/NN7FI44J"},"agent_actions":{"view_html":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63","download_json":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63.json","view_paper":"https://pith.science/paper/NN7FI44J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13697&json=true","fetch_graph":"https://pith.science/api/pith-number/NN7FI44JJD55FNBQYX625GNU63/graph.json","fetch_events":"https://pith.science/api/pith-number/NN7FI44JJD55FNBQYX625GNU63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63/action/storage_attestation","attest_author":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63/action/author_attestation","sign_citation":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63/action/citation_signature","submit_replication":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63/action/replication_record"}},"created_at":"2026-07-05T06:12:56.228147+00:00","updated_at":"2026-07-05T06:12:56.228147+00:00"}