{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:R272YF2X5IJLTJAIWHQPPQZFGL","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":"de20c3e1830fe8e9da799b42467b923888c6a91362d29228d875a6fd98e2caf1","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T19:48:02Z","title_canon_sha256":"e4510c2b1311d17b3338d6f00b867f92483e7c03bd6708c254b9fa7aa3a77db0"},"schema_version":"1.0","source":{"id":"2312.02310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02310","created_at":"2026-07-05T07:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02310v1","created_at":"2026-07-05T07:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02310","created_at":"2026-07-05T07:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"R272YF2X5IJL","created_at":"2026-07-05T07:20:16Z"},{"alias_kind":"pith_short_16","alias_value":"R272YF2X5IJLTJAI","created_at":"2026-07-05T07:20:16Z"},{"alias_kind":"pith_short_8","alias_value":"R272YF2X","created_at":"2026-07-05T07:20:16Z"}],"graph_snapshots":[{"event_id":"sha256:bc58f4627ad006270f40873105a22b1d1c45062d33d03270780e915bd534475d","target":"graph","created_at":"2026-07-05T07:20:16Z","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/2312.02310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in language-model-based video understanding have been progressing at a remarkable pace, spurred by the introduction of Large Language Models (LLMs). However, the focus of prior research has been predominantly on devising a projection layer that maps video features to tokens, an approach that is both rudimentary and inefficient. In our study, we introduce a cutting-edge framework, VaQuitA, designed to refine the synergy between video and textual information. At the data level, instead of sampling frames uniformly, we implement a sampling method guided by CLIP-score rankings,","authors_text":"Gang Wu, Haoliang Wang, Ruiyi Zhang, Uttaran Bhattacharya, Yizhou Wang, Yun Fu","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T19:48:02Z","title":"VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02310","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":"sha256:1266d1cd2029ecc1c1a1725a775e6a87939d8d70f160615e42f995480b087c99","target":"record","created_at":"2026-07-05T07:20:16Z","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":"de20c3e1830fe8e9da799b42467b923888c6a91362d29228d875a6fd98e2caf1","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T19:48:02Z","title_canon_sha256":"e4510c2b1311d17b3338d6f00b867f92483e7c03bd6708c254b9fa7aa3a77db0"},"schema_version":"1.0","source":{"id":"2312.02310","kind":"arxiv","version":1}},"canonical_sha256":"8ebfac1757ea12b9a408b1e0f7c32532fd204ba3d6025e314751830098aaefea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ebfac1757ea12b9a408b1e0f7c32532fd204ba3d6025e314751830098aaefea","first_computed_at":"2026-07-05T07:20:16.214740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:16.214740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5XQFLMT1pT9D4fj3RzyRykgzIPDEcWWtuL5e8GQlL2kdCVfbaJOspyzcXYKqiO9je5rEKDlW6NhoyJV3+JOmAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:16.215226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1266d1cd2029ecc1c1a1725a775e6a87939d8d70f160615e42f995480b087c99","sha256:bc58f4627ad006270f40873105a22b1d1c45062d33d03270780e915bd534475d"],"state_sha256":"c2276487baebe076046be96cdf3fc89edbd73177536ff98248be26a61ea13dc4"}