{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ULYSJE2WWDU2NOVRPNLH7VFXNG","short_pith_number":"pith:ULYSJE2W","schema_version":"1.0","canonical_sha256":"a2f1249356b0e9a6bab17b567fd4b769a427156736988401b2b3a036e77abed8","source":{"kind":"arxiv","id":"2201.10654","version":1},"attestation_state":"computed","paper":{"title":"SA-VQA: Structured Alignment of Visual and Semantic Representations for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peixi Xiong, Pei Yu, Quanzeng You, Ying Wu, Zicheng Liu","submitted_at":"2022-01-25T22:26:09Z","abstract_excerpt":"Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality representations. Previous approaches extensively employ entity-level alignments, such as the correlations between the visual regions and their semantic labels, or the interactions across question words and object features. These attempts aim to improve the cross-modality representations, while ignoring their internal relations. Instead, we propose to apply st"},"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":"2201.10654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-25T22:26:09Z","cross_cats_sorted":[],"title_canon_sha256":"b27e93e98c7f552aed7f20c36f2296282ac26e84d5f5acdf5ac062087520e90f","abstract_canon_sha256":"94faaaff27329f4496059d9f80f9ca991f7a78f13fc8e2de723fa4cf407cb157"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:48.319072Z","signature_b64":"0jcWpNopfW3wIfJzP7vpPwPRjHZLyTKhnBhXpdogNdiBoBSCeHfaR9vGr0IIKIMQvQ889wG+WGvXmOJ+YZ5XBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2f1249356b0e9a6bab17b567fd4b769a427156736988401b2b3a036e77abed8","last_reissued_at":"2026-07-05T03:51:48.318519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:48.318519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SA-VQA: Structured Alignment of Visual and Semantic Representations for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peixi Xiong, Pei Yu, Quanzeng You, Ying Wu, Zicheng Liu","submitted_at":"2022-01-25T22:26:09Z","abstract_excerpt":"Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality representations. Previous approaches extensively employ entity-level alignments, such as the correlations between the visual regions and their semantic labels, or the interactions across question words and object features. These attempts aim to improve the cross-modality representations, while ignoring their internal relations. Instead, we propose to apply st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10654","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/2201.10654/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":"2201.10654","created_at":"2026-07-05T03:51:48.318603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.10654v1","created_at":"2026-07-05T03:51:48.318603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10654","created_at":"2026-07-05T03:51:48.318603+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULYSJE2WWDU2","created_at":"2026-07-05T03:51:48.318603+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULYSJE2WWDU2NOVR","created_at":"2026-07-05T03:51:48.318603+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULYSJE2W","created_at":"2026-07-05T03:51:48.318603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06100","citing_title":"HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ULYSJE2WWDU2NOVRPNLH7VFXNG","json":"https://pith.science/pith/ULYSJE2WWDU2NOVRPNLH7VFXNG.json","graph_json":"https://pith.science/api/pith-number/ULYSJE2WWDU2NOVRPNLH7VFXNG/graph.json","events_json":"https://pith.science/api/pith-number/ULYSJE2WWDU2NOVRPNLH7VFXNG/events.json","paper":"https://pith.science/paper/ULYSJE2W"},"agent_actions":{"view_html":"https://pith.science/pith/ULYSJE2WWDU2NOVRPNLH7VFXNG","download_json":"https://pith.science/pith/ULYSJE2WWDU2NOVRPNLH7VFXNG.json","view_paper":"https://pith.science/paper/ULYSJE2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.10654&json=true","fetch_graph":"https://pith.science/api/pith-number/ULYSJE2WWDU2NOVRPNLH7VFXNG/graph.json","fetch_events":"https://pith.science/api/pith-number/ULYSJE2WWDU2NOVRPNLH7VFXNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULYSJE2WWDU2NOVRPNLH7VFXNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULYSJE2WWDU2NOVRPNLH7VFXNG/action/storage_attestation","attest_author":"https://pith.science/pith/ULYSJE2WWDU2NOVRPNLH7VFXNG/action/author_attestation","sign_citation":"https://pith.science/pith/ULYSJE2WWDU2NOVRPNLH7VFXNG/action/citation_signature","submit_replication":"https://pith.science/pith/ULYSJE2WWDU2NOVRPNLH7VFXNG/action/replication_record"}},"created_at":"2026-07-05T03:51:48.318603+00:00","updated_at":"2026-07-05T03:51:48.318603+00:00"}