{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UHWIONLHUIZOXH7BBVOKZ6VEN7","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":"1eef53904ffb3b490c044f0fc639699473a54dc53b18e26e8e700ac36ce20e37","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T08:42:53Z","title_canon_sha256":"e901aafabb3e7fe62959c0948b3f81e8a49470aaa501eb1100205be84311d46d"},"schema_version":"1.0","source":{"id":"2305.10049","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10049","created_at":"2026-07-05T06:11:22Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10049v2","created_at":"2026-07-05T06:11:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10049","created_at":"2026-07-05T06:11:22Z"},{"alias_kind":"pith_short_12","alias_value":"UHWIONLHUIZO","created_at":"2026-07-05T06:11:22Z"},{"alias_kind":"pith_short_16","alias_value":"UHWIONLHUIZOXH7B","created_at":"2026-07-05T06:11:22Z"},{"alias_kind":"pith_short_8","alias_value":"UHWIONLH","created_at":"2026-07-05T06:11:22Z"}],"graph_snapshots":[{"event_id":"sha256:f5b1903c9703d6ed93c96345dbb48c4b39abcf5dd5137c8bcf9e718ac578dd64","target":"graph","created_at":"2026-07-05T06:11:22Z","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/2305.10049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video question answering aims at answering a question about the video content by reasoning the alignment semantics within them. However, since relying heavily on human instructions, i.e., annotations or priors, current contrastive learning-based VideoQA methods remains challenging to perform fine-grained visual-linguistic alignments. In this work, we innovatively resort to game theory, which can simulate complicated relationships among multiple players with specific interaction strategies, e.g., video, question, and answer as ternary players, to achieve fine-grained alignment for VideoQA task.","authors_text":"Chang Liu, Hao Li, Jie Chen, Kai Chen, Peng Jin, Songyang Zhang, Zesen Cheng, Zhennan Wang","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T08:42:53Z","title":"TG-VQA: Ternary Game of Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10049","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:f6ec2c23238c41272bd67891b9acf62ab1d0e1fc32d338e34682ba00eebdc26f","target":"record","created_at":"2026-07-05T06:11:22Z","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":"1eef53904ffb3b490c044f0fc639699473a54dc53b18e26e8e700ac36ce20e37","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T08:42:53Z","title_canon_sha256":"e901aafabb3e7fe62959c0948b3f81e8a49470aaa501eb1100205be84311d46d"},"schema_version":"1.0","source":{"id":"2305.10049","kind":"arxiv","version":2}},"canonical_sha256":"a1ec873567a232eb9fe10d5cacfaa46fcc73691f85f83bc1e9652af6c4cedb95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1ec873567a232eb9fe10d5cacfaa46fcc73691f85f83bc1e9652af6c4cedb95","first_computed_at":"2026-07-05T06:11:22.166202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:22.166202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mR06tTm5rhsjwI+QxsAYaWxuK4IEpfuolIcyJ3vWMpd2DyQy8pdciRt5CDUsshaB6pH8NRh793bGQUg42wq3BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:22.166616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10049","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6ec2c23238c41272bd67891b9acf62ab1d0e1fc32d338e34682ba00eebdc26f","sha256:f5b1903c9703d6ed93c96345dbb48c4b39abcf5dd5137c8bcf9e718ac578dd64"],"state_sha256":"d3f0e240b14742d8de7d984542fab18e98283ef3608bda733f2809aca8ed20d3"}