{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:44XQNZFDCRJYN6LXKSAS5XUBRI","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":"55fbf0b10fd027e26d452adf982b4e69e44bfbbf522afc47b0657fbe30d7acc4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T07:22:54Z","title_canon_sha256":"36d998cb842a29cc26dd2f78fa77b326f9dcd6a7f2ec77575be821332b119ff5"},"schema_version":"1.0","source":{"id":"2507.06603","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06603","created_at":"2026-07-05T11:46:44Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06603v2","created_at":"2026-07-05T11:46:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06603","created_at":"2026-07-05T11:46:44Z"},{"alias_kind":"pith_short_12","alias_value":"44XQNZFDCRJY","created_at":"2026-07-05T11:46:44Z"},{"alias_kind":"pith_short_16","alias_value":"44XQNZFDCRJYN6LX","created_at":"2026-07-05T11:46:44Z"},{"alias_kind":"pith_short_8","alias_value":"44XQNZFD","created_at":"2026-07-05T11:46:44Z"}],"graph_snapshots":[{"event_id":"sha256:7bab146ea4624ef102e6e88098375f9716f95bafd24bfc462a78bd1dbb2c521a","target":"graph","created_at":"2026-07-05T11:46:44Z","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/2507.06603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-term action recognition (LTAR) is challenging due to extended temporal spans with complex atomic action correlations and visual confounders. Although vision-language models (VLMs) have shown promise, they often rely on statistical correlations instead of causal mechanisms. Moreover, existing causality-based methods address modal-specific biases but lack cross-modal causal modeling, limiting their utility in VLM-based LTAR. This paper proposes \\textbf{C}ross-\\textbf{M}odal \\textbf{D}ual-\\textbf{C}ausal \\textbf{L}earning (CMDCL), which introduces a structural causal model to uncover causal ","authors_text":"Chang Jing, Fan Chao, Gao Junyu, Jia Xibin, Sun Qianmei, Xu Shaowu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T07:22:54Z","title":"Cross-Modal Dual-Causal Learning for Long-Term Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06603","kind":"arxiv","version":2},"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:e1494501b0d4c6dc18a1a703086873fdf33cc84ca0df639d27807a4d62a4a9c2","target":"record","created_at":"2026-07-05T11:46:44Z","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":"55fbf0b10fd027e26d452adf982b4e69e44bfbbf522afc47b0657fbe30d7acc4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T07:22:54Z","title_canon_sha256":"36d998cb842a29cc26dd2f78fa77b326f9dcd6a7f2ec77575be821332b119ff5"},"schema_version":"1.0","source":{"id":"2507.06603","kind":"arxiv","version":2}},"canonical_sha256":"e72f06e4a3145386f97754812ede818a325fcf70b0505bd58e5c5a1bc205ac1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e72f06e4a3145386f97754812ede818a325fcf70b0505bd58e5c5a1bc205ac1e","first_computed_at":"2026-07-05T11:46:44.885653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:44.885653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t5EeZbgDKm4eUgBjwujfnrgTChECqd3gqdLMqb5LgtGrqfOIrYI6B9/OvHO83jdbk4hkjCBnLIcJ9z4I+S5vAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:44.886003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06603","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1494501b0d4c6dc18a1a703086873fdf33cc84ca0df639d27807a4d62a4a9c2","sha256:7bab146ea4624ef102e6e88098375f9716f95bafd24bfc462a78bd1dbb2c521a"],"state_sha256":"115829b57875bb921a35f290f7e694f051686d7f80e85fb32f2aab2b09960ad2"}