{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R272YF2X5IJLTJAIWHQPPQZFGL","short_pith_number":"pith:R272YF2X","schema_version":"1.0","canonical_sha256":"8ebfac1757ea12b9a408b1e0f7c32532fd204ba3d6025e314751830098aaefea","source":{"kind":"arxiv","id":"2312.02310","version":1},"attestation_state":"computed","paper":{"title":"VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gang Wu, Haoliang Wang, Ruiyi Zhang, Uttaran Bhattacharya, Yizhou Wang, Yun Fu","submitted_at":"2023-12-04T19:48:02Z","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,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.02310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T19:48:02Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e4510c2b1311d17b3338d6f00b867f92483e7c03bd6708c254b9fa7aa3a77db0","abstract_canon_sha256":"de20c3e1830fe8e9da799b42467b923888c6a91362d29228d875a6fd98e2caf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:16.215226Z","signature_b64":"5XQFLMT1pT9D4fj3RzyRykgzIPDEcWWtuL5e8GQlL2kdCVfbaJOspyzcXYKqiO9je5rEKDlW6NhoyJV3+JOmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ebfac1757ea12b9a408b1e0f7c32532fd204ba3d6025e314751830098aaefea","last_reissued_at":"2026-07-05T07:20:16.214740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:16.214740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gang Wu, Haoliang Wang, Ruiyi Zhang, Uttaran Bhattacharya, Yizhou Wang, Yun Fu","submitted_at":"2023-12-04T19:48:02Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02310","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.02310/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.02310","created_at":"2026-07-05T07:20:16.214794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.02310v1","created_at":"2026-07-05T07:20:16.214794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02310","created_at":"2026-07-05T07:20:16.214794+00:00"},{"alias_kind":"pith_short_12","alias_value":"R272YF2X5IJL","created_at":"2026-07-05T07:20:16.214794+00:00"},{"alias_kind":"pith_short_16","alias_value":"R272YF2X5IJLTJAI","created_at":"2026-07-05T07:20:16.214794+00:00"},{"alias_kind":"pith_short_8","alias_value":"R272YF2X","created_at":"2026-07-05T07:20:16.214794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R272YF2X5IJLTJAIWHQPPQZFGL","json":"https://pith.science/pith/R272YF2X5IJLTJAIWHQPPQZFGL.json","graph_json":"https://pith.science/api/pith-number/R272YF2X5IJLTJAIWHQPPQZFGL/graph.json","events_json":"https://pith.science/api/pith-number/R272YF2X5IJLTJAIWHQPPQZFGL/events.json","paper":"https://pith.science/paper/R272YF2X"},"agent_actions":{"view_html":"https://pith.science/pith/R272YF2X5IJLTJAIWHQPPQZFGL","download_json":"https://pith.science/pith/R272YF2X5IJLTJAIWHQPPQZFGL.json","view_paper":"https://pith.science/paper/R272YF2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.02310&json=true","fetch_graph":"https://pith.science/api/pith-number/R272YF2X5IJLTJAIWHQPPQZFGL/graph.json","fetch_events":"https://pith.science/api/pith-number/R272YF2X5IJLTJAIWHQPPQZFGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R272YF2X5IJLTJAIWHQPPQZFGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R272YF2X5IJLTJAIWHQPPQZFGL/action/storage_attestation","attest_author":"https://pith.science/pith/R272YF2X5IJLTJAIWHQPPQZFGL/action/author_attestation","sign_citation":"https://pith.science/pith/R272YF2X5IJLTJAIWHQPPQZFGL/action/citation_signature","submit_replication":"https://pith.science/pith/R272YF2X5IJLTJAIWHQPPQZFGL/action/replication_record"}},"created_at":"2026-07-05T07:20:16.214794+00:00","updated_at":"2026-07-05T07:20:16.214794+00:00"}