{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZNB5AHH6SLDTNAI65FPKY7NKJA","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":"3ce1c3d0fa62c2e4ef9df7b1c1d5b849a5da654ae4e5bf73c86b9980ee40a102","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-18T04:56:46Z","title_canon_sha256":"be6057f49ae626982ebf17425e8bfa9620bdb138edb092de4bb640dc7718c49a"},"schema_version":"1.0","source":{"id":"2105.08276","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.08276","created_at":"2026-07-05T02:42:31Z"},{"alias_kind":"arxiv_version","alias_value":"2105.08276v2","created_at":"2026-07-05T02:42:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08276","created_at":"2026-07-05T02:42:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZNB5AHH6SLDT","created_at":"2026-07-05T02:42:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZNB5AHH6SLDTNAI6","created_at":"2026-07-05T02:42:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZNB5AHH6","created_at":"2026-07-05T02:42:31Z"}],"graph_snapshots":[{"event_id":"sha256:9064e0884dccfba4c3915d37782ef65738b22048556d3abeb66a6690904e5d87","target":"graph","created_at":"2026-07-05T02:42:31Z","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/2105.08276/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Angela Yao, Junbin Xiao, Tat-Seng Chua, Xindi Shang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-18T04:56:46Z","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08276","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":"sha256:03f101d2e6a4b3e3722704ec7627b3ec1f01ac71efe9dacdf7cca3d095f58e22","target":"record","created_at":"2026-07-05T02:42:31Z","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":"3ce1c3d0fa62c2e4ef9df7b1c1d5b849a5da654ae4e5bf73c86b9980ee40a102","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-18T04:56:46Z","title_canon_sha256":"be6057f49ae626982ebf17425e8bfa9620bdb138edb092de4bb640dc7718c49a"},"schema_version":"1.0","source":{"id":"2105.08276","kind":"arxiv","version":2}},"canonical_sha256":"cb43d01cfe92c736811ee95eac7daa481c7bfe79b7ec3a5d2249a789ff84dc13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb43d01cfe92c736811ee95eac7daa481c7bfe79b7ec3a5d2249a789ff84dc13","first_computed_at":"2026-07-05T02:42:31.030539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:31.030539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VGgKEnwZftzTwCnDtcf8JgrLNWSkWnGsDItb7AoQm9fkXeLgjL3nCkX56OTZbRCy0rVHazEmLcoMve/uT4lPDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:31.031073Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.08276","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03f101d2e6a4b3e3722704ec7627b3ec1f01ac71efe9dacdf7cca3d095f58e22","sha256:9064e0884dccfba4c3915d37782ef65738b22048556d3abeb66a6690904e5d87"],"state_sha256":"69246d391a56bc480f7b8052f021c09dd7da282349abb12105594d9c5985f375"}