{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BCIO2UMI3TLHEMPKEPDNJ27G4T","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":"db36a6286c89731138415916a012f06c7f13d4da632bf1bfddf3cfc91472fe82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T07:45:10Z","title_canon_sha256":"fd88d14e6877fbe555fbe5adabf0b2ac8d6ede4c294cd093d84dbdd0270b9877"},"schema_version":"1.0","source":{"id":"2308.09363","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09363","created_at":"2026-07-05T06:42:31Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09363v1","created_at":"2026-07-05T06:42:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09363","created_at":"2026-07-05T06:42:31Z"},{"alias_kind":"pith_short_12","alias_value":"BCIO2UMI3TLH","created_at":"2026-07-05T06:42:31Z"},{"alias_kind":"pith_short_16","alias_value":"BCIO2UMI3TLHEMPK","created_at":"2026-07-05T06:42:31Z"},{"alias_kind":"pith_short_8","alias_value":"BCIO2UMI","created_at":"2026-07-05T06:42:31Z"}],"graph_snapshots":[{"event_id":"sha256:f8438ab81c522b3f251072fcd28cf2e5f470270ce8ed480e1b61c44bf7fedfdb","target":"graph","created_at":"2026-07-05T06:42:31Z","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/2308.09363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Question Answering (VideoQA) is a challenging task that entails complex multi-modal reasoning. In contrast to multiple-choice VideoQA which aims to predict the answer given several options, the goal of open-ended VideoQA is to answer questions without restricting candidate answers. However, the majority of previous VideoQA models formulate open-ended VideoQA as a classification task to classify the video-question pairs into a fixed answer set, i.e., closed-vocabulary, which contains only frequent answers (e.g., top-1000 answers). This leads the model to be biased toward only frequent ans","authors_text":"Dohwan Ko, Hyunwoo J. Kim, Jaewon Chu, Jihwan Park, Ji Soo Lee, Miso Choi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T07:45:10Z","title":"Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09363","kind":"arxiv","version":1},"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":"sha256:327ee24d61cb8bf084a1643cc7d557ce1894a30e3af69c156605ae1c719b67a8","target":"record","created_at":"2026-07-05T06:42:31Z","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":"db36a6286c89731138415916a012f06c7f13d4da632bf1bfddf3cfc91472fe82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T07:45:10Z","title_canon_sha256":"fd88d14e6877fbe555fbe5adabf0b2ac8d6ede4c294cd093d84dbdd0270b9877"},"schema_version":"1.0","source":{"id":"2308.09363","kind":"arxiv","version":1}},"canonical_sha256":"0890ed5188dcd67231ea23c6d4ebe6e4d7e8823c567a20246b8711cb865789ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0890ed5188dcd67231ea23c6d4ebe6e4d7e8823c567a20246b8711cb865789ee","first_computed_at":"2026-07-05T06:42:31.417938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:31.417938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2p2v+XIVvyGE/Cu3DyqGR0a9Ls8EnAUhYb0hSxEeXRtXD4T7f04NREOKjlOYOPrxglf7N/3RJLi4xPdtxiBgDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:31.418344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.09363","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:327ee24d61cb8bf084a1643cc7d557ce1894a30e3af69c156605ae1c719b67a8","sha256:f8438ab81c522b3f251072fcd28cf2e5f470270ce8ed480e1b61c44bf7fedfdb"],"state_sha256":"7e381f5ae0a8526c074c46b5a2b05fc6391b53c35a67dbc659cf7b908a0a9e3a"}