{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CYZF266RG2NMJ2LISG3F25BWAJ","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":"34824a87dea1e96487ad53c678520c2b8bd274946e6de4d0e3838d490d025c25","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T18:58:15Z","title_canon_sha256":"072b03fdd86c2c08b1329ae71fe30f8836c4f947ea4ad9914d04e4b929d30048"},"schema_version":"1.0","source":{"id":"2312.08367","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08367","created_at":"2026-07-05T09:13:48Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08367v4","created_at":"2026-07-05T09:13:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08367","created_at":"2026-07-05T09:13:48Z"},{"alias_kind":"pith_short_12","alias_value":"CYZF266RG2NM","created_at":"2026-07-05T09:13:48Z"},{"alias_kind":"pith_short_16","alias_value":"CYZF266RG2NMJ2LI","created_at":"2026-07-05T09:13:48Z"},{"alias_kind":"pith_short_8","alias_value":"CYZF266R","created_at":"2026-07-05T09:13:48Z"}],"graph_snapshots":[{"event_id":"sha256:4bd236d4cfe197d2b7ed7da5ef20e499bb8a16343e4f3d16934929f6d9372c98","target":"graph","created_at":"2026-07-05T09:13:48Z","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/2312.08367/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable text-guided Frame-Prompter together with a new cross-modal distillation (QFormer-Distiller) module. Pre-trained large image-language models have shown promising results on problems such as visual question answering (VQA). However, how to efficiently and effectively sample video frames when adapting pre-trained large image-language model to video-language alignmen","authors_text":"Chun-Kai Wang, Junbang Liang, Kenan Deng, Ming Lin, Shan Yang, Xijun Wang, Yu Lou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T18:58:15Z","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08367","kind":"arxiv","version":4},"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":"sha256:77ddc4eb996dec22cefa0381733f9299a73a313b8ff1d0bc76305f54519c70c7","target":"record","created_at":"2026-07-05T09:13:48Z","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":"34824a87dea1e96487ad53c678520c2b8bd274946e6de4d0e3838d490d025c25","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T18:58:15Z","title_canon_sha256":"072b03fdd86c2c08b1329ae71fe30f8836c4f947ea4ad9914d04e4b929d30048"},"schema_version":"1.0","source":{"id":"2312.08367","kind":"arxiv","version":4}},"canonical_sha256":"16325d7bd1369ac4e96891b65d7436026da48559e1c942d284257ba16009e70e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16325d7bd1369ac4e96891b65d7436026da48559e1c942d284257ba16009e70e","first_computed_at":"2026-07-05T09:13:48.758618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:48.758618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"210ocigA/sVhzYTNV3vohFbngbpsbJVeMM8gA0QdWj8N6Jm6Zp6q/U/gljRgQ9H5Nltnajz8DtI9lJSz+nFKBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:48.759069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08367","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77ddc4eb996dec22cefa0381733f9299a73a313b8ff1d0bc76305f54519c70c7","sha256:4bd236d4cfe197d2b7ed7da5ef20e499bb8a16343e4f3d16934929f6d9372c98"],"state_sha256":"c01d027b80c76b7da3fa562ffe35176f7dbcfbbacbcc08e732a8de91e5b1edce"}