{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5JARR3UATQRUWPR3M7CFGFP5XV","short_pith_number":"pith:5JARR3UA","schema_version":"1.0","canonical_sha256":"ea4118ee809c234b3e3b67c45315fdbd7018c04b84209bf89d84ae5f095f7de5","source":{"kind":"arxiv","id":"2210.16431","version":1},"attestation_state":"computed","paper":{"title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fenglin Liu, Shen Ge, Wei Fan, Xian Wu, Xuancheng Ren, Xu Sun, Yuexian Zou","submitted_at":"2022-10-28T23:00:40Z","abstract_excerpt":"Vision-and-language (V-L) tasks require the system to understand both vision content and natural language, thus learning fine-grained joint representations of vision and language (a.k.a. V-L representations) is of paramount importance. Recently, various pre-trained V-L models are proposed to learn V-L representations and achieve improved results in many tasks. However, the mainstream models process both vision and language inputs with the same set of attention matrices. As a result, the generated V-L representations are entangled in one common latent space. To tackle this problem, we propose D"},"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":"2210.16431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-28T23:00:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"baddf14269608468206469601308e4f64013160afdef05cc1fc5a0fd7659c111","abstract_canon_sha256":"d589aff8300a57d6dc8f89956facc0820a2fc028784d92bd786f1ceb66463b33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:46.349977Z","signature_b64":"7v/wmYbWlcR2hqXrqqwLzASL/ytvIp5/Pywa2mbL1SXcW+2uIiqGL4CrESxy8/zmHdHbiRscYGfY6ux716d9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea4118ee809c234b3e3b67c45315fdbd7018c04b84209bf89d84ae5f095f7de5","last_reissued_at":"2026-07-05T05:11:46.349435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:46.349435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fenglin Liu, Shen Ge, Wei Fan, Xian Wu, Xuancheng Ren, Xu Sun, Yuexian Zou","submitted_at":"2022-10-28T23:00:40Z","abstract_excerpt":"Vision-and-language (V-L) tasks require the system to understand both vision content and natural language, thus learning fine-grained joint representations of vision and language (a.k.a. V-L representations) is of paramount importance. Recently, various pre-trained V-L models are proposed to learn V-L representations and achieve improved results in many tasks. However, the mainstream models process both vision and language inputs with the same set of attention matrices. As a result, the generated V-L representations are entangled in one common latent space. To tackle this problem, we propose D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16431","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/2210.16431/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":"2210.16431","created_at":"2026-07-05T05:11:46.349505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16431v1","created_at":"2026-07-05T05:11:46.349505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16431","created_at":"2026-07-05T05:11:46.349505+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JARR3UATQRU","created_at":"2026-07-05T05:11:46.349505+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JARR3UATQRUWPR3","created_at":"2026-07-05T05:11:46.349505+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JARR3UA","created_at":"2026-07-05T05:11:46.349505+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/5JARR3UATQRUWPR3M7CFGFP5XV","json":"https://pith.science/pith/5JARR3UATQRUWPR3M7CFGFP5XV.json","graph_json":"https://pith.science/api/pith-number/5JARR3UATQRUWPR3M7CFGFP5XV/graph.json","events_json":"https://pith.science/api/pith-number/5JARR3UATQRUWPR3M7CFGFP5XV/events.json","paper":"https://pith.science/paper/5JARR3UA"},"agent_actions":{"view_html":"https://pith.science/pith/5JARR3UATQRUWPR3M7CFGFP5XV","download_json":"https://pith.science/pith/5JARR3UATQRUWPR3M7CFGFP5XV.json","view_paper":"https://pith.science/paper/5JARR3UA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16431&json=true","fetch_graph":"https://pith.science/api/pith-number/5JARR3UATQRUWPR3M7CFGFP5XV/graph.json","fetch_events":"https://pith.science/api/pith-number/5JARR3UATQRUWPR3M7CFGFP5XV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JARR3UATQRUWPR3M7CFGFP5XV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JARR3UATQRUWPR3M7CFGFP5XV/action/storage_attestation","attest_author":"https://pith.science/pith/5JARR3UATQRUWPR3M7CFGFP5XV/action/author_attestation","sign_citation":"https://pith.science/pith/5JARR3UATQRUWPR3M7CFGFP5XV/action/citation_signature","submit_replication":"https://pith.science/pith/5JARR3UATQRUWPR3M7CFGFP5XV/action/replication_record"}},"created_at":"2026-07-05T05:11:46.349505+00:00","updated_at":"2026-07-05T05:11:46.349505+00:00"}