{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GQUANC4TYEUC4KGUZAVLTFJREL","short_pith_number":"pith:GQUANC4T","schema_version":"1.0","canonical_sha256":"3428068b93c1282e28d4c82ab9953122f34d2d810b13404f0bae47270f66cad3","source":{"kind":"arxiv","id":"2106.13488","version":4},"attestation_state":"computed","paper":{"title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Liu, Hongwei Xue, Houqiang Li, Houwen Peng, Jianlong Fu, Jiebo Luo, Yupan Huang","submitted_at":"2021-06-25T08:04:25Z","abstract_excerpt":"Vision-Language Pre-training (VLP) aims to learn multi-modal representations from image-text pairs and serves for downstream vision-language tasks in a fine-tuning fashion. The dominant VLP models adopt a CNN-Transformer architecture, which embeds images with a CNN, and then aligns images and text with a Transformer. Visual relationship between visual contents plays an important role in image understanding and is the basic for inter-modal alignment learning. However, CNNs have limitations in visual relation learning due to local receptive field's weakness in modeling long-range dependencies. T"},"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":"2106.13488","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-25T08:04:25Z","cross_cats_sorted":[],"title_canon_sha256":"e1ae491c2fdb2f550fbe1d265d46fb1e2321cb9b4dbbcb8eccebdf01af2dbf76","abstract_canon_sha256":"69bc26fb5568cc1925f31ac566e9cb0ecb91936fc85ac32dedb3f333daed151e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:13.225266Z","signature_b64":"XShHCPQ4irjZDwsVxx02JG3yAk9RKas9/MiCBk9Z6NA8kheFWOJnNiUhwb2U/aBMCmC/SaLCE/7wIMSXJ6yhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3428068b93c1282e28d4c82ab9953122f34d2d810b13404f0bae47270f66cad3","last_reissued_at":"2026-07-05T03:30:13.224790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:13.224790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Liu, Hongwei Xue, Houqiang Li, Houwen Peng, Jianlong Fu, Jiebo Luo, Yupan Huang","submitted_at":"2021-06-25T08:04:25Z","abstract_excerpt":"Vision-Language Pre-training (VLP) aims to learn multi-modal representations from image-text pairs and serves for downstream vision-language tasks in a fine-tuning fashion. The dominant VLP models adopt a CNN-Transformer architecture, which embeds images with a CNN, and then aligns images and text with a Transformer. Visual relationship between visual contents plays an important role in image understanding and is the basic for inter-modal alignment learning. However, CNNs have limitations in visual relation learning due to local receptive field's weakness in modeling long-range dependencies. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13488","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/2106.13488/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":"2106.13488","created_at":"2026-07-05T03:30:13.224850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13488v4","created_at":"2026-07-05T03:30:13.224850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13488","created_at":"2026-07-05T03:30:13.224850+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQUANC4TYEUC","created_at":"2026-07-05T03:30:13.224850+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQUANC4TYEUC4KGU","created_at":"2026-07-05T03:30:13.224850+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQUANC4T","created_at":"2026-07-05T03:30:13.224850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2205.14100","citing_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL","json":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL.json","graph_json":"https://pith.science/api/pith-number/GQUANC4TYEUC4KGUZAVLTFJREL/graph.json","events_json":"https://pith.science/api/pith-number/GQUANC4TYEUC4KGUZAVLTFJREL/events.json","paper":"https://pith.science/paper/GQUANC4T"},"agent_actions":{"view_html":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL","download_json":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL.json","view_paper":"https://pith.science/paper/GQUANC4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13488&json=true","fetch_graph":"https://pith.science/api/pith-number/GQUANC4TYEUC4KGUZAVLTFJREL/graph.json","fetch_events":"https://pith.science/api/pith-number/GQUANC4TYEUC4KGUZAVLTFJREL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL/action/storage_attestation","attest_author":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL/action/author_attestation","sign_citation":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL/action/citation_signature","submit_replication":"https://pith.science/pith/GQUANC4TYEUC4KGUZAVLTFJREL/action/replication_record"}},"created_at":"2026-07-05T03:30:13.224850+00:00","updated_at":"2026-07-05T03:30:13.224850+00:00"}