{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CMG7RLWO34QFINWGXYH42QXB5P","short_pith_number":"pith:CMG7RLWO","schema_version":"1.0","canonical_sha256":"130df8aecedf205436c6be0fcd42e1ebdd98fb1ba9473e1e917791e1e64727a0","source":{"kind":"arxiv","id":"2207.12647","version":8},"attestation_state":"computed","paper":{"title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Liang Lin, Yang Liu","submitted_at":"2022-07-26T04:25:54Z","abstract_excerpt":"Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video. In this work, to address the task of event-level visual question answering, we propose a framework for cross-modal causal relational reasoning. In particular, a set of causal intervention operations is introduced to discover the underlying causal structures across visual and linguistic modalities. Our framework, named Cross-Modal Causal RelatIonal Reasoning (CMCI"},"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":"2207.12647","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T04:25:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aea0b59c6d6ec95b071eacc88271f2a459bf5de687fd740a544103b420ea4902","abstract_canon_sha256":"400a6ed8001c760805b62c5a1340fdd85273ff372f35735c6a254b53b73904ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:17.256135Z","signature_b64":"v/RP5P6ufVjCNFWGi211mnrk+Qswr5ubz9RbUWrHECbki8Gii6iZpUNdm91ZjUz0+qa0rv5mnJ5dQtzGVw5bCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"130df8aecedf205436c6be0fcd42e1ebdd98fb1ba9473e1e917791e1e64727a0","last_reissued_at":"2026-07-05T06:18:17.255730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:17.255730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Liang Lin, Yang Liu","submitted_at":"2022-07-26T04:25:54Z","abstract_excerpt":"Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video. In this work, to address the task of event-level visual question answering, we propose a framework for cross-modal causal relational reasoning. In particular, a set of causal intervention operations is introduced to discover the underlying causal structures across visual and linguistic modalities. Our framework, named Cross-Modal Causal RelatIonal Reasoning (CMCI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12647","kind":"arxiv","version":8},"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/2207.12647/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":"2207.12647","created_at":"2026-07-05T06:18:17.255797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.12647v8","created_at":"2026-07-05T06:18:17.255797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12647","created_at":"2026-07-05T06:18:17.255797+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMG7RLWO34QF","created_at":"2026-07-05T06:18:17.255797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMG7RLWO34QFINWG","created_at":"2026-07-05T06:18:17.255797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMG7RLWO","created_at":"2026-07-05T06:18:17.255797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07292","citing_title":"Multimodal Sentiment Analysis Based on Causal Reasoning","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMG7RLWO34QFINWGXYH42QXB5P","json":"https://pith.science/pith/CMG7RLWO34QFINWGXYH42QXB5P.json","graph_json":"https://pith.science/api/pith-number/CMG7RLWO34QFINWGXYH42QXB5P/graph.json","events_json":"https://pith.science/api/pith-number/CMG7RLWO34QFINWGXYH42QXB5P/events.json","paper":"https://pith.science/paper/CMG7RLWO"},"agent_actions":{"view_html":"https://pith.science/pith/CMG7RLWO34QFINWGXYH42QXB5P","download_json":"https://pith.science/pith/CMG7RLWO34QFINWGXYH42QXB5P.json","view_paper":"https://pith.science/paper/CMG7RLWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.12647&json=true","fetch_graph":"https://pith.science/api/pith-number/CMG7RLWO34QFINWGXYH42QXB5P/graph.json","fetch_events":"https://pith.science/api/pith-number/CMG7RLWO34QFINWGXYH42QXB5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMG7RLWO34QFINWGXYH42QXB5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMG7RLWO34QFINWGXYH42QXB5P/action/storage_attestation","attest_author":"https://pith.science/pith/CMG7RLWO34QFINWGXYH42QXB5P/action/author_attestation","sign_citation":"https://pith.science/pith/CMG7RLWO34QFINWGXYH42QXB5P/action/citation_signature","submit_replication":"https://pith.science/pith/CMG7RLWO34QFINWGXYH42QXB5P/action/replication_record"}},"created_at":"2026-07-05T06:18:17.255797+00:00","updated_at":"2026-07-05T06:18:17.255797+00:00"}