{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FITYZ6TZOXZO4BX7FJ77M47DAZ","short_pith_number":"pith:FITYZ6TZ","schema_version":"1.0","canonical_sha256":"2a278cfa7975f2ee06ff2a7ff673e3066b195880db8744f22f704653b59e11f6","source":{"kind":"arxiv","id":"2606.09181","version":1},"attestation_state":"computed","paper":{"title":"Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hamid Krim, Keisuke Fujii, Liangwei Li, Xiao Wu, Zhaoquan Yuan, Zhou Du","submitted_at":"2026-06-08T08:20:42Z","abstract_excerpt":"Recent advances in video multimodal models have significantly improved VideoQA performance. However, these systems often rely on spurious statistical correlations rather than answer-relevant causal evidence, resulting in unfaithful and brittle reasoning, especially in complex real-world scenarios. Existing methods either rely on cross-modality correlations, costly curated training resources, or insufficient causal assumptions and constraints, and typically operate at the time-interval level. As a result, they fail to explicitly disentangle causal visual cues from confounders and provide limite"},"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":"2606.09181","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T08:20:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"767c0c167ececbe0929fdbf667549bfc35f2d1c2a4b953bd8af9b83d9cbbeb87","abstract_canon_sha256":"9909396d7e5c805ae101a7117cad3c84e8467b20276d16d98ff52dc092a91f07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:05.575187Z","signature_b64":"r5ojJynBJ7MyxV8LSC+4IW4lx0DmspWxqd1QKC0n1LzaFrKfbe/9s+cjD6dja9pbDW1h4kfzJFNuIPbpUjjfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a278cfa7975f2ee06ff2a7ff673e3066b195880db8744f22f704653b59e11f6","last_reissued_at":"2026-06-09T02:08:05.574113Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:05.574113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hamid Krim, Keisuke Fujii, Liangwei Li, Xiao Wu, Zhaoquan Yuan, Zhou Du","submitted_at":"2026-06-08T08:20:42Z","abstract_excerpt":"Recent advances in video multimodal models have significantly improved VideoQA performance. However, these systems often rely on spurious statistical correlations rather than answer-relevant causal evidence, resulting in unfaithful and brittle reasoning, especially in complex real-world scenarios. Existing methods either rely on cross-modality correlations, costly curated training resources, or insufficient causal assumptions and constraints, and typically operate at the time-interval level. As a result, they fail to explicitly disentangle causal visual cues from confounders and provide limite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09181","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/2606.09181/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":"2606.09181","created_at":"2026-06-09T02:08:05.574287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09181v1","created_at":"2026-06-09T02:08:05.574287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09181","created_at":"2026-06-09T02:08:05.574287+00:00"},{"alias_kind":"pith_short_12","alias_value":"FITYZ6TZOXZO","created_at":"2026-06-09T02:08:05.574287+00:00"},{"alias_kind":"pith_short_16","alias_value":"FITYZ6TZOXZO4BX7","created_at":"2026-06-09T02:08:05.574287+00:00"},{"alias_kind":"pith_short_8","alias_value":"FITYZ6TZ","created_at":"2026-06-09T02:08:05.574287+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/FITYZ6TZOXZO4BX7FJ77M47DAZ","json":"https://pith.science/pith/FITYZ6TZOXZO4BX7FJ77M47DAZ.json","graph_json":"https://pith.science/api/pith-number/FITYZ6TZOXZO4BX7FJ77M47DAZ/graph.json","events_json":"https://pith.science/api/pith-number/FITYZ6TZOXZO4BX7FJ77M47DAZ/events.json","paper":"https://pith.science/paper/FITYZ6TZ"},"agent_actions":{"view_html":"https://pith.science/pith/FITYZ6TZOXZO4BX7FJ77M47DAZ","download_json":"https://pith.science/pith/FITYZ6TZOXZO4BX7FJ77M47DAZ.json","view_paper":"https://pith.science/paper/FITYZ6TZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09181&json=true","fetch_graph":"https://pith.science/api/pith-number/FITYZ6TZOXZO4BX7FJ77M47DAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FITYZ6TZOXZO4BX7FJ77M47DAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FITYZ6TZOXZO4BX7FJ77M47DAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FITYZ6TZOXZO4BX7FJ77M47DAZ/action/storage_attestation","attest_author":"https://pith.science/pith/FITYZ6TZOXZO4BX7FJ77M47DAZ/action/author_attestation","sign_citation":"https://pith.science/pith/FITYZ6TZOXZO4BX7FJ77M47DAZ/action/citation_signature","submit_replication":"https://pith.science/pith/FITYZ6TZOXZO4BX7FJ77M47DAZ/action/replication_record"}},"created_at":"2026-06-09T02:08:05.574287+00:00","updated_at":"2026-06-09T02:08:05.574287+00:00"}