{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5JQVIKBXEADQUVDI6MWPMANDTR","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":"d8f65157215d57923e2b41616f0229f07aa899227618d24a3d31cc6881ef3c2a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T04:09:37Z","title_canon_sha256":"723fc753be110e95a7e645c253b56e97c77ba1c7d2d7bc37e0e11fbbd647385d"},"schema_version":"1.0","source":{"id":"2407.15047","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15047","created_at":"2026-07-05T08:47:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15047v2","created_at":"2026-07-05T08:47:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15047","created_at":"2026-07-05T08:47:22Z"},{"alias_kind":"pith_short_12","alias_value":"5JQVIKBXEADQ","created_at":"2026-07-05T08:47:22Z"},{"alias_kind":"pith_short_16","alias_value":"5JQVIKBXEADQUVDI","created_at":"2026-07-05T08:47:22Z"},{"alias_kind":"pith_short_8","alias_value":"5JQVIKBX","created_at":"2026-07-05T08:47:22Z"}],"graph_snapshots":[{"event_id":"sha256:c519757724dfb4eb7cf45d3be574d9f004cb03cfb515370dc109b63620c735ce","target":"graph","created_at":"2026-07-05T08:47:22Z","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/2407.15047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Question Answering (VideoQA) has emerged as a challenging frontier in the field of multimedia processing, requiring intricate interactions between visual and textual modalities. Simply uniformly sampling frames or indiscriminately aggregating frame-level visual features often falls short in capturing the nuanced and relevant contexts of videos to well perform VideoQA. To mitigate these issues, we propose VidF4, a novel VideoQA framework equipped with tailored frame selection strategy for effective and efficient VideoQA. We propose three frame-scoring mechanisms that consider both questio","authors_text":"Chang Liu, Dongyan Zhao, Jianxin Liang, Qun Liu, Xiaojun Meng, Yueqian Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T04:09:37Z","title":"End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15047","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:d90539e286de73b74776a121af0a199342453f44bc43ee0559a571bf35c7fd06","target":"record","created_at":"2026-07-05T08:47:22Z","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":"d8f65157215d57923e2b41616f0229f07aa899227618d24a3d31cc6881ef3c2a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T04:09:37Z","title_canon_sha256":"723fc753be110e95a7e645c253b56e97c77ba1c7d2d7bc37e0e11fbbd647385d"},"schema_version":"1.0","source":{"id":"2407.15047","kind":"arxiv","version":2}},"canonical_sha256":"ea6154283720070a5468f32cf601a39c72867b05e3e86eb91b6333d3b1babc03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea6154283720070a5468f32cf601a39c72867b05e3e86eb91b6333d3b1babc03","first_computed_at":"2026-07-05T08:47:22.912061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:22.912061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/0YJ6AOGAYpcsnS6BH7BrZLxhurKjxd0FaPFETut0b8wUSIzop0VAVdIXxirnL+MB0e2LMEevGp9VAdKSK4fCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:22.912598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15047","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d90539e286de73b74776a121af0a199342453f44bc43ee0559a571bf35c7fd06","sha256:c519757724dfb4eb7cf45d3be574d9f004cb03cfb515370dc109b63620c735ce"],"state_sha256":"18720a19fbd964ce418fd68b2467fc1d8d92b94be54d58bae6614e4a41219e89"}