{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RLLNASXFVH7UTBFDUHJZWXANA7","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":"14c331b7b40c125d681181d8c26dac606087e3067dccedd307a74de4d1c5d591","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:59:09Z","title_canon_sha256":"ce2f7016c92997ea6733d1f5368d1d7627aa09608dabd056757e682bd0ec4618"},"schema_version":"1.0","source":{"id":"2407.18908","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18908","created_at":"2026-07-05T10:36:14Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18908v2","created_at":"2026-07-05T10:36:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18908","created_at":"2026-07-05T10:36:14Z"},{"alias_kind":"pith_short_12","alias_value":"RLLNASXFVH7U","created_at":"2026-07-05T10:36:14Z"},{"alias_kind":"pith_short_16","alias_value":"RLLNASXFVH7UTBFD","created_at":"2026-07-05T10:36:14Z"},{"alias_kind":"pith_short_8","alias_value":"RLLNASXF","created_at":"2026-07-05T10:36:14Z"}],"graph_snapshots":[{"event_id":"sha256:c595a1d131ed871f72d913b0a8def8f13aaa8d4e7e3b7c36ba72c5f954a4ed66","target":"graph","created_at":"2026-07-05T10:36:14Z","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/2407.18908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Wolf, a WOrLd summarization Framework for accurate video captioning. Wolf is an automated captioning framework that adopts a mixture-of-experts approach, leveraging complementary strengths of Vision Language Models (VLMs). By utilizing both image and video models, our framework captures different levels of information and summarizes them efficiently. Our approach can be applied to enhance video understanding, auto-labeling, and captioning. To evaluate caption quality, we introduce CapScore, an LLM-based metric to assess the similarity and quality of generated captions compared to th","authors_text":"Andrew Tao, Boris Ivanovic, Boyi Li, Fuzhao Xue, Jan Kautz, Jitendra Malik, Jonah Philion, Ligeng Zhu, Linxi Fan, Marco Pavone, Max Ehrlich, Ming-Yu Liu, Ran Tian, Sanja Fidler, Shuhan Tan, Song Han, Sushant Veer, Trevor Darrell, Xinshuo Weng, Yao Lu, Yin Cui, Yuke Zhu, Yuxiao Chen","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:59:09Z","title":"Wolf: Dense Video Captioning with a World Summarization Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18908","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":"sha256:5a9911d56b6bf166da2604d2131192fe1921c92687124b4210e1ecc801fa17f7","target":"record","created_at":"2026-07-05T10:36:14Z","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":"14c331b7b40c125d681181d8c26dac606087e3067dccedd307a74de4d1c5d591","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T17:59:09Z","title_canon_sha256":"ce2f7016c92997ea6733d1f5368d1d7627aa09608dabd056757e682bd0ec4618"},"schema_version":"1.0","source":{"id":"2407.18908","kind":"arxiv","version":2}},"canonical_sha256":"8ad6d04ae5a9ff4984a3a1d39b5c0d07fdbfb77c5240fd12cb3cadf9c70a556a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ad6d04ae5a9ff4984a3a1d39b5c0d07fdbfb77c5240fd12cb3cadf9c70a556a","first_computed_at":"2026-07-05T10:36:14.851040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:14.851040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eu4Z/ZgHcipZzhogPRDAZ7hpoawuB6TVL4kyJydmyw21jb2QVSNpdOYgsFAldoeId28ZTU813JwCk+Xi5zjbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:14.851548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18908","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a9911d56b6bf166da2604d2131192fe1921c92687124b4210e1ecc801fa17f7","sha256:c595a1d131ed871f72d913b0a8def8f13aaa8d4e7e3b7c36ba72c5f954a4ed66"],"state_sha256":"2148b71d0bce17de13c4b1bec92660d435692e7bd751701565600ffb2a838464"}