{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZNB5AHH6SLDTNAI65FPKY7NKJA","short_pith_number":"pith:ZNB5AHH6","schema_version":"1.0","canonical_sha256":"cb43d01cfe92c736811ee95eac7daa481c7bfe79b7ec3a5d2249a789ff84dc13","source":{"kind":"arxiv","id":"2105.08276","version":2},"attestation_state":"computed","paper":{"title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Junbin Xiao, Tat-Seng Chua, Xindi Shang","submitted_at":"2021-05-18T04:56:46Z","abstract_excerpt":"We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. Based on the dataset, we set up multi-choice and open-ended QA tasks targeting causal action reasoning, temporal action reasoning, and common scene comprehension. Through extensive analysis of baselines and established VideoQA techniques, we find that top-performing methods excel at shallow scene descriptions but are weak in causal and temporal action reasoning. Furthermore, the models that are effective on multi-choice QA, "},"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":"2105.08276","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-18T04:56:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be6057f49ae626982ebf17425e8bfa9620bdb138edb092de4bb640dc7718c49a","abstract_canon_sha256":"3ce1c3d0fa62c2e4ef9df7b1c1d5b849a5da654ae4e5bf73c86b9980ee40a102"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:31.031073Z","signature_b64":"VGgKEnwZftzTwCnDtcf8JgrLNWSkWnGsDItb7AoQm9fkXeLgjL3nCkX56OTZbRCy0rVHazEmLcoMve/uT4lPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb43d01cfe92c736811ee95eac7daa481c7bfe79b7ec3a5d2249a789ff84dc13","last_reissued_at":"2026-07-05T02:42:31.030539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:31.030539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Junbin Xiao, Tat-Seng Chua, Xindi Shang","submitted_at":"2021-05-18T04:56:46Z","abstract_excerpt":"We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. Based on the dataset, we set up multi-choice and open-ended QA tasks targeting causal action reasoning, temporal action reasoning, and common scene comprehension. Through extensive analysis of baselines and established VideoQA techniques, we find that top-performing methods excel at shallow scene descriptions but are weak in causal and temporal action reasoning. Furthermore, the models that are effective on multi-choice QA, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08276","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/2105.08276/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":"2105.08276","created_at":"2026-07-05T02:42:31.030601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.08276v2","created_at":"2026-07-05T02:42:31.030601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08276","created_at":"2026-07-05T02:42:31.030601+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNB5AHH6SLDT","created_at":"2026-07-05T02:42:31.030601+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNB5AHH6SLDTNAI6","created_at":"2026-07-05T02:42:31.030601+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNB5AHH6","created_at":"2026-07-05T02:42:31.030601+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31529","citing_title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31529","citing_title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17283","citing_title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21420","citing_title":"ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNB5AHH6SLDTNAI65FPKY7NKJA","json":"https://pith.science/pith/ZNB5AHH6SLDTNAI65FPKY7NKJA.json","graph_json":"https://pith.science/api/pith-number/ZNB5AHH6SLDTNAI65FPKY7NKJA/graph.json","events_json":"https://pith.science/api/pith-number/ZNB5AHH6SLDTNAI65FPKY7NKJA/events.json","paper":"https://pith.science/paper/ZNB5AHH6"},"agent_actions":{"view_html":"https://pith.science/pith/ZNB5AHH6SLDTNAI65FPKY7NKJA","download_json":"https://pith.science/pith/ZNB5AHH6SLDTNAI65FPKY7NKJA.json","view_paper":"https://pith.science/paper/ZNB5AHH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.08276&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNB5AHH6SLDTNAI65FPKY7NKJA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNB5AHH6SLDTNAI65FPKY7NKJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNB5AHH6SLDTNAI65FPKY7NKJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNB5AHH6SLDTNAI65FPKY7NKJA/action/storage_attestation","attest_author":"https://pith.science/pith/ZNB5AHH6SLDTNAI65FPKY7NKJA/action/author_attestation","sign_citation":"https://pith.science/pith/ZNB5AHH6SLDTNAI65FPKY7NKJA/action/citation_signature","submit_replication":"https://pith.science/pith/ZNB5AHH6SLDTNAI65FPKY7NKJA/action/replication_record"}},"created_at":"2026-07-05T02:42:31.030601+00:00","updated_at":"2026-07-05T02:42:31.030601+00:00"}