{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CMG7RLWO34QFINWGXYH42QXB5P","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"400a6ed8001c760805b62c5a1340fdd85273ff372f35735c6a254b53b73904ad","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T04:25:54Z","title_canon_sha256":"aea0b59c6d6ec95b071eacc88271f2a459bf5de687fd740a544103b420ea4902"},"schema_version":"1.0","source":{"id":"2207.12647","kind":"arxiv","version":8}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.12647","created_at":"2026-07-05T06:18:17Z"},{"alias_kind":"arxiv_version","alias_value":"2207.12647v8","created_at":"2026-07-05T06:18:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12647","created_at":"2026-07-05T06:18:17Z"},{"alias_kind":"pith_short_12","alias_value":"CMG7RLWO34QF","created_at":"2026-07-05T06:18:17Z"},{"alias_kind":"pith_short_16","alias_value":"CMG7RLWO34QFINWG","created_at":"2026-07-05T06:18:17Z"},{"alias_kind":"pith_short_8","alias_value":"CMG7RLWO","created_at":"2026-07-05T06:18:17Z"}],"graph_snapshots":[{"event_id":"sha256:3f56c549e8f65504be96ac4a58bcbf0c0840a61c66563d9d381941e5d12038b2","target":"graph","created_at":"2026-07-05T06:18:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2207.12647/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guanbin Li, Liang Lin, Yang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T04:25:54Z","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12647","kind":"arxiv","version":8},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ef042d613127c72da62634c828450ecddb5781fbc293eafbfb4a26bf1c41b43b","target":"record","created_at":"2026-07-05T06:18:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"400a6ed8001c760805b62c5a1340fdd85273ff372f35735c6a254b53b73904ad","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-26T04:25:54Z","title_canon_sha256":"aea0b59c6d6ec95b071eacc88271f2a459bf5de687fd740a544103b420ea4902"},"schema_version":"1.0","source":{"id":"2207.12647","kind":"arxiv","version":8}},"canonical_sha256":"130df8aecedf205436c6be0fcd42e1ebdd98fb1ba9473e1e917791e1e64727a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"130df8aecedf205436c6be0fcd42e1ebdd98fb1ba9473e1e917791e1e64727a0","first_computed_at":"2026-07-05T06:18:17.255730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:17.255730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v/RP5P6ufVjCNFWGi211mnrk+Qswr5ubz9RbUWrHECbki8Gii6iZpUNdm91ZjUz0+qa0rv5mnJ5dQtzGVw5bCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:17.256135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.12647","source_kind":"arxiv","source_version":8}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef042d613127c72da62634c828450ecddb5781fbc293eafbfb4a26bf1c41b43b","sha256:3f56c549e8f65504be96ac4a58bcbf0c0840a61c66563d9d381941e5d12038b2"],"state_sha256":"600aaf114a3dd3f65c1e305a08f57b75df0b29354fb4c1cc9883e64abe17de1e"}