{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AD7XP56ZAGBUCYGE3BHGUVM442","short_pith_number":"pith:AD7XP56Z","schema_version":"1.0","canonical_sha256":"00ff77f7d901834160c4d84e6a559ce6ab779ac9d470c4e25176f5e66d17e4bf","source":{"kind":"arxiv","id":"2304.03754","version":1},"attestation_state":"computed","paper":{"title":"Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Hung-Ting Su, Shih-Fu Chang, Winston H. Hsu, Xudong Lin, Yulei Niu","submitted_at":"2023-04-07T17:45:49Z","abstract_excerpt":"Causal Video Question Answering (CVidQA) queries not only association or temporal relations but also causal relations in a video. Existing question synthesis methods pre-trained question generation (QG) systems on reading comprehension datasets with text descriptions as inputs. However, QG models only learn to ask association questions (e.g., ``what is someone doing...'') and result in inferior performance due to the poor transfer of association knowledge to CVidQA, which focuses on causal questions like ``why is someone doing ...''. Observing this, we proposed to exploit causal knowledge to g"},"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":"2304.03754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-07T17:45:49Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"aa7636773f1b836be3e8f627460ea185ae1aed14dfccc7edeccde57fb601206b","abstract_canon_sha256":"428845d0b760e5aaac949ec5110a03e0a76766578406a32c3c09f2bd75f8b69c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:59.927491Z","signature_b64":"DCiTPxjAjwM4uX/S9/NpUs88WssYhBSld5rN0Af3EHH3eWX4e+nKmvstvbn5SVVR+nqYDMhy4ZZYvcq5LvrbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00ff77f7d901834160c4d84e6a559ce6ab779ac9d470c4e25176f5e66d17e4bf","last_reissued_at":"2026-07-05T05:58:59.926949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:59.926949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Hung-Ting Su, Shih-Fu Chang, Winston H. Hsu, Xudong Lin, Yulei Niu","submitted_at":"2023-04-07T17:45:49Z","abstract_excerpt":"Causal Video Question Answering (CVidQA) queries not only association or temporal relations but also causal relations in a video. Existing question synthesis methods pre-trained question generation (QG) systems on reading comprehension datasets with text descriptions as inputs. However, QG models only learn to ask association questions (e.g., ``what is someone doing...'') and result in inferior performance due to the poor transfer of association knowledge to CVidQA, which focuses on causal questions like ``why is someone doing ...''. Observing this, we proposed to exploit causal knowledge to g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03754","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/2304.03754/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":"2304.03754","created_at":"2026-07-05T05:58:59.927007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03754v1","created_at":"2026-07-05T05:58:59.927007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03754","created_at":"2026-07-05T05:58:59.927007+00:00"},{"alias_kind":"pith_short_12","alias_value":"AD7XP56ZAGBU","created_at":"2026-07-05T05:58:59.927007+00:00"},{"alias_kind":"pith_short_16","alias_value":"AD7XP56ZAGBUCYGE","created_at":"2026-07-05T05:58:59.927007+00:00"},{"alias_kind":"pith_short_8","alias_value":"AD7XP56Z","created_at":"2026-07-05T05:58:59.927007+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/AD7XP56ZAGBUCYGE3BHGUVM442","json":"https://pith.science/pith/AD7XP56ZAGBUCYGE3BHGUVM442.json","graph_json":"https://pith.science/api/pith-number/AD7XP56ZAGBUCYGE3BHGUVM442/graph.json","events_json":"https://pith.science/api/pith-number/AD7XP56ZAGBUCYGE3BHGUVM442/events.json","paper":"https://pith.science/paper/AD7XP56Z"},"agent_actions":{"view_html":"https://pith.science/pith/AD7XP56ZAGBUCYGE3BHGUVM442","download_json":"https://pith.science/pith/AD7XP56ZAGBUCYGE3BHGUVM442.json","view_paper":"https://pith.science/paper/AD7XP56Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03754&json=true","fetch_graph":"https://pith.science/api/pith-number/AD7XP56ZAGBUCYGE3BHGUVM442/graph.json","fetch_events":"https://pith.science/api/pith-number/AD7XP56ZAGBUCYGE3BHGUVM442/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AD7XP56ZAGBUCYGE3BHGUVM442/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AD7XP56ZAGBUCYGE3BHGUVM442/action/storage_attestation","attest_author":"https://pith.science/pith/AD7XP56ZAGBUCYGE3BHGUVM442/action/author_attestation","sign_citation":"https://pith.science/pith/AD7XP56ZAGBUCYGE3BHGUVM442/action/citation_signature","submit_replication":"https://pith.science/pith/AD7XP56ZAGBUCYGE3BHGUVM442/action/replication_record"}},"created_at":"2026-07-05T05:58:59.927007+00:00","updated_at":"2026-07-05T05:58:59.927007+00:00"}