{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:44XQNZFDCRJYN6LXKSAS5XUBRI","short_pith_number":"pith:44XQNZFD","schema_version":"1.0","canonical_sha256":"e72f06e4a3145386f97754812ede818a325fcf70b0505bd58e5c5a1bc205ac1e","source":{"kind":"arxiv","id":"2507.06603","version":2},"attestation_state":"computed","paper":{"title":"Cross-Modal Dual-Causal Learning for Long-Term Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Jing, Fan Chao, Gao Junyu, Jia Xibin, Sun Qianmei, Xu Shaowu","submitted_at":"2025-07-09T07:22:54Z","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 "},"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":"2507.06603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T07:22:54Z","cross_cats_sorted":[],"title_canon_sha256":"36d998cb842a29cc26dd2f78fa77b326f9dcd6a7f2ec77575be821332b119ff5","abstract_canon_sha256":"55fbf0b10fd027e26d452adf982b4e69e44bfbbf522afc47b0657fbe30d7acc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:44.886003Z","signature_b64":"t5EeZbgDKm4eUgBjwujfnrgTChECqd3gqdLMqb5LgtGrqfOIrYI6B9/OvHO83jdbk4hkjCBnLIcJ9z4I+S5vAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e72f06e4a3145386f97754812ede818a325fcf70b0505bd58e5c5a1bc205ac1e","last_reissued_at":"2026-07-05T11:46:44.885653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:44.885653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Dual-Causal Learning for Long-Term Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Jing, Fan Chao, Gao Junyu, Jia Xibin, Sun Qianmei, Xu Shaowu","submitted_at":"2025-07-09T07:22:54Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06603","kind":"arxiv","version":2},"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/2507.06603/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":"2507.06603","created_at":"2026-07-05T11:46:44.885711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06603v2","created_at":"2026-07-05T11:46:44.885711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06603","created_at":"2026-07-05T11:46:44.885711+00:00"},{"alias_kind":"pith_short_12","alias_value":"44XQNZFDCRJY","created_at":"2026-07-05T11:46:44.885711+00:00"},{"alias_kind":"pith_short_16","alias_value":"44XQNZFDCRJYN6LX","created_at":"2026-07-05T11:46:44.885711+00:00"},{"alias_kind":"pith_short_8","alias_value":"44XQNZFD","created_at":"2026-07-05T11:46:44.885711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/44XQNZFDCRJYN6LXKSAS5XUBRI","json":"https://pith.science/pith/44XQNZFDCRJYN6LXKSAS5XUBRI.json","graph_json":"https://pith.science/api/pith-number/44XQNZFDCRJYN6LXKSAS5XUBRI/graph.json","events_json":"https://pith.science/api/pith-number/44XQNZFDCRJYN6LXKSAS5XUBRI/events.json","paper":"https://pith.science/paper/44XQNZFD"},"agent_actions":{"view_html":"https://pith.science/pith/44XQNZFDCRJYN6LXKSAS5XUBRI","download_json":"https://pith.science/pith/44XQNZFDCRJYN6LXKSAS5XUBRI.json","view_paper":"https://pith.science/paper/44XQNZFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06603&json=true","fetch_graph":"https://pith.science/api/pith-number/44XQNZFDCRJYN6LXKSAS5XUBRI/graph.json","fetch_events":"https://pith.science/api/pith-number/44XQNZFDCRJYN6LXKSAS5XUBRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44XQNZFDCRJYN6LXKSAS5XUBRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44XQNZFDCRJYN6LXKSAS5XUBRI/action/storage_attestation","attest_author":"https://pith.science/pith/44XQNZFDCRJYN6LXKSAS5XUBRI/action/author_attestation","sign_citation":"https://pith.science/pith/44XQNZFDCRJYN6LXKSAS5XUBRI/action/citation_signature","submit_replication":"https://pith.science/pith/44XQNZFDCRJYN6LXKSAS5XUBRI/action/replication_record"}},"created_at":"2026-07-05T11:46:44.885711+00:00","updated_at":"2026-07-05T11:46:44.885711+00:00"}