{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HQRPYPJ5UE7EYLD7KKWBLLJA57","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":"9b8dcde7ab2e31da166777f2258c646e7520c2a2f5c7d5f2b7c85e47f2b8cf3c","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T02:45:37Z","title_canon_sha256":"134373944145ac1e54a57bbbd60ce802f8882bd6cac36f2d3e28ec474cc121a2"},"schema_version":"1.0","source":{"id":"2412.15509","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15509","created_at":"2026-07-05T10:05:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15509v3","created_at":"2026-07-05T10:05:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15509","created_at":"2026-07-05T10:05:15Z"},{"alias_kind":"pith_short_12","alias_value":"HQRPYPJ5UE7E","created_at":"2026-07-05T10:05:15Z"},{"alias_kind":"pith_short_16","alias_value":"HQRPYPJ5UE7EYLD7","created_at":"2026-07-05T10:05:15Z"},{"alias_kind":"pith_short_8","alias_value":"HQRPYPJ5","created_at":"2026-07-05T10:05:15Z"}],"graph_snapshots":[{"event_id":"sha256:e8b7891a39df6b69afe4d37488bd4447534a32ddd9021f697f9647f43b7e28a7","target":"graph","created_at":"2026-07-05T10:05:15Z","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/2412.15509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present our methods and results for the Video-To-Text (VTT) task at TRECVid 2024, exploring the capabilities of Vision-Language Models (VLMs) like LLaVA and LLaVA-NeXT-Video in generating natural language descriptions for video content. We investigate the impact of fine-tuning VLMs on VTT datasets to enhance description accuracy, contextual relevance, and linguistic consistency. Our analysis reveals that fine-tuning substantially improves the model's ability to produce more detailed and domain-aligned text, bridging the gap between generic VLM tasks and the specialized needs ","authors_text":"Jiaxin Wu, Qing Li, Wengyu Zhang, Xiao-Yong Wei","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T02:45:37Z","title":"PolySmart @ TRECVid 2024 Video Captioning (VTT)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15509","kind":"arxiv","version":3},"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:e56f313efd3b7fbec87ab7ff152d4992a577e57e79c6a81e7b098b87cc4138ac","target":"record","created_at":"2026-07-05T10:05:15Z","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":"9b8dcde7ab2e31da166777f2258c646e7520c2a2f5c7d5f2b7c85e47f2b8cf3c","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T02:45:37Z","title_canon_sha256":"134373944145ac1e54a57bbbd60ce802f8882bd6cac36f2d3e28ec474cc121a2"},"schema_version":"1.0","source":{"id":"2412.15509","kind":"arxiv","version":3}},"canonical_sha256":"3c22fc3d3da13e4c2c7f52ac15ad20efceb09a389441f1a6521940e326424257","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c22fc3d3da13e4c2c7f52ac15ad20efceb09a389441f1a6521940e326424257","first_computed_at":"2026-07-05T10:05:15.534426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:15.534426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9/UeU2E+eO6WnsMHHyeeq+e0UYC3NYPYjSb6/8elzFRvQYwkZ2gvehAt1H4FMm2ohQC4EVufaFgcqexpb0TNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:15.534920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15509","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e56f313efd3b7fbec87ab7ff152d4992a577e57e79c6a81e7b098b87cc4138ac","sha256:e8b7891a39df6b69afe4d37488bd4447534a32ddd9021f697f9647f43b7e28a7"],"state_sha256":"4b092e5d1aec02832e48d4c28b17730570dca483964394fb3ac2c95ebb83ea19"}