{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XUPE6OCLN7XSCP4RPVKMMP4PBD","short_pith_number":"pith:XUPE6OCL","schema_version":"1.0","canonical_sha256":"bd1e4f384b6fef213f917d54c63f8f08ebebb10aa4c75c176f79ab68aba0859e","source":{"kind":"arxiv","id":"2203.06107","version":1},"attestation_state":"computed","paper":{"title":"REX: Reasoning-aware and Grounded Explanation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qi Zhao, Shi Chen","submitted_at":"2022-03-11T17:28:42Z","abstract_excerpt":"Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the rationales behind the decisions. As a result, they commonly take advantage of spurious biases instead of actually reasoning on the visual-textual data, and have yet developed the capability to explain their decision making by considering key information from both modalities. This paper aims to close the gap from three distinct perspectives: first, we define a"},"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":"2203.06107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-11T17:28:42Z","cross_cats_sorted":[],"title_canon_sha256":"21439629dbe5057bdfcc85c193a143904ab5f09595d6a561dc65208ea7449f3d","abstract_canon_sha256":"0b72458ca4d795c2a1b75807315306618ef754ee12fe0e1f0be46e54cfb98445"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:12.813348Z","signature_b64":"0hcunZDehoUc2FD16XYFvw2S+sfECWzYfO6i6RiKQ3AYhoZlsbm4U1TukmeTn8cXEzicde3YUMVTwWH+fA7YBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd1e4f384b6fef213f917d54c63f8f08ebebb10aa4c75c176f79ab68aba0859e","last_reissued_at":"2026-07-05T04:04:12.812957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:12.812957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REX: Reasoning-aware and Grounded Explanation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qi Zhao, Shi Chen","submitted_at":"2022-03-11T17:28:42Z","abstract_excerpt":"Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the rationales behind the decisions. As a result, they commonly take advantage of spurious biases instead of actually reasoning on the visual-textual data, and have yet developed the capability to explain their decision making by considering key information from both modalities. This paper aims to close the gap from three distinct perspectives: first, we define a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06107","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/2203.06107/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":"2203.06107","created_at":"2026-07-05T04:04:12.813014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.06107v1","created_at":"2026-07-05T04:04:12.813014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06107","created_at":"2026-07-05T04:04:12.813014+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUPE6OCLN7XS","created_at":"2026-07-05T04:04:12.813014+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUPE6OCLN7XSCP4R","created_at":"2026-07-05T04:04:12.813014+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUPE6OCL","created_at":"2026-07-05T04:04:12.813014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06253","citing_title":"The State of Post-Hoc Local XAI Techniques for Image Processing: Challenges and Motivations","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUPE6OCLN7XSCP4RPVKMMP4PBD","json":"https://pith.science/pith/XUPE6OCLN7XSCP4RPVKMMP4PBD.json","graph_json":"https://pith.science/api/pith-number/XUPE6OCLN7XSCP4RPVKMMP4PBD/graph.json","events_json":"https://pith.science/api/pith-number/XUPE6OCLN7XSCP4RPVKMMP4PBD/events.json","paper":"https://pith.science/paper/XUPE6OCL"},"agent_actions":{"view_html":"https://pith.science/pith/XUPE6OCLN7XSCP4RPVKMMP4PBD","download_json":"https://pith.science/pith/XUPE6OCLN7XSCP4RPVKMMP4PBD.json","view_paper":"https://pith.science/paper/XUPE6OCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.06107&json=true","fetch_graph":"https://pith.science/api/pith-number/XUPE6OCLN7XSCP4RPVKMMP4PBD/graph.json","fetch_events":"https://pith.science/api/pith-number/XUPE6OCLN7XSCP4RPVKMMP4PBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUPE6OCLN7XSCP4RPVKMMP4PBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUPE6OCLN7XSCP4RPVKMMP4PBD/action/storage_attestation","attest_author":"https://pith.science/pith/XUPE6OCLN7XSCP4RPVKMMP4PBD/action/author_attestation","sign_citation":"https://pith.science/pith/XUPE6OCLN7XSCP4RPVKMMP4PBD/action/citation_signature","submit_replication":"https://pith.science/pith/XUPE6OCLN7XSCP4RPVKMMP4PBD/action/replication_record"}},"created_at":"2026-07-05T04:04:12.813014+00:00","updated_at":"2026-07-05T04:04:12.813014+00:00"}