{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GU66MLO6JSTLPIPMEBSWXQXCJP","short_pith_number":"pith:GU66MLO6","schema_version":"1.0","canonical_sha256":"353de62dde4ca6b7a1ec20656bc2e24bc461998084acef44c1d4af559a616062","source":{"kind":"arxiv","id":"2410.15270","version":2},"attestation_state":"computed","paper":{"title":"FIOVA: A Multi-Annotator Benchmark for Human-Aligned Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Zhang, Kang Hao Cheong, Shiyu Hu, Xin Zhao, Xuchen Li, Xuzhao Li, Yipei Wang","submitted_at":"2024-10-20T03:59:54Z","abstract_excerpt":"Despite rapid progress in large vision-language models (LVLMs), existing video caption benchmarks remain limited in evaluating their alignment with human understanding. Most rely on a single annotation per video and lexical similarity-based metrics, failing to capture the variability in human perception and the cognitive importance of events. These limitations hinder accurate diagnosis of model capabilities in producing coherent, complete, and human-aligned descriptions. To address this, we introduce FIOVA (Five-In-One Video Annotations), a human-centric benchmark tailored for evaluation. It c"},"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":"2410.15270","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-20T03:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"d2781c852872e325c186658d5742a187c6db2271307fad4a56e5bf8c89c26ada","abstract_canon_sha256":"eb827abd1607a2a1f08d50511b597032a1302c85aec2e90e05bd18346ff581b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:21.926796Z","signature_b64":"g1+bNME1uMc4b3jFS1wjDYduYCi5zpsw398yHKYzTcBEjX9wvNMEVAKIcfjPO3cXdw+SJzZTRM375q9ljvnmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"353de62dde4ca6b7a1ec20656bc2e24bc461998084acef44c1d4af559a616062","last_reissued_at":"2026-07-05T11:05:21.926298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:21.926298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FIOVA: A Multi-Annotator Benchmark for Human-Aligned Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Zhang, Kang Hao Cheong, Shiyu Hu, Xin Zhao, Xuchen Li, Xuzhao Li, Yipei Wang","submitted_at":"2024-10-20T03:59:54Z","abstract_excerpt":"Despite rapid progress in large vision-language models (LVLMs), existing video caption benchmarks remain limited in evaluating their alignment with human understanding. Most rely on a single annotation per video and lexical similarity-based metrics, failing to capture the variability in human perception and the cognitive importance of events. These limitations hinder accurate diagnosis of model capabilities in producing coherent, complete, and human-aligned descriptions. To address this, we introduce FIOVA (Five-In-One Video Annotations), a human-centric benchmark tailored for evaluation. It c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15270","kind":"arxiv","version":2},"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/2410.15270/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":"2410.15270","created_at":"2026-07-05T11:05:21.926367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15270v2","created_at":"2026-07-05T11:05:21.926367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15270","created_at":"2026-07-05T11:05:21.926367+00:00"},{"alias_kind":"pith_short_12","alias_value":"GU66MLO6JSTL","created_at":"2026-07-05T11:05:21.926367+00:00"},{"alias_kind":"pith_short_16","alias_value":"GU66MLO6JSTLPIPM","created_at":"2026-07-05T11:05:21.926367+00:00"},{"alias_kind":"pith_short_8","alias_value":"GU66MLO6","created_at":"2026-07-05T11:05:21.926367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21949","citing_title":"CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GU66MLO6JSTLPIPMEBSWXQXCJP","json":"https://pith.science/pith/GU66MLO6JSTLPIPMEBSWXQXCJP.json","graph_json":"https://pith.science/api/pith-number/GU66MLO6JSTLPIPMEBSWXQXCJP/graph.json","events_json":"https://pith.science/api/pith-number/GU66MLO6JSTLPIPMEBSWXQXCJP/events.json","paper":"https://pith.science/paper/GU66MLO6"},"agent_actions":{"view_html":"https://pith.science/pith/GU66MLO6JSTLPIPMEBSWXQXCJP","download_json":"https://pith.science/pith/GU66MLO6JSTLPIPMEBSWXQXCJP.json","view_paper":"https://pith.science/paper/GU66MLO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15270&json=true","fetch_graph":"https://pith.science/api/pith-number/GU66MLO6JSTLPIPMEBSWXQXCJP/graph.json","fetch_events":"https://pith.science/api/pith-number/GU66MLO6JSTLPIPMEBSWXQXCJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GU66MLO6JSTLPIPMEBSWXQXCJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GU66MLO6JSTLPIPMEBSWXQXCJP/action/storage_attestation","attest_author":"https://pith.science/pith/GU66MLO6JSTLPIPMEBSWXQXCJP/action/author_attestation","sign_citation":"https://pith.science/pith/GU66MLO6JSTLPIPMEBSWXQXCJP/action/citation_signature","submit_replication":"https://pith.science/pith/GU66MLO6JSTLPIPMEBSWXQXCJP/action/replication_record"}},"created_at":"2026-07-05T11:05:21.926367+00:00","updated_at":"2026-07-05T11:05:21.926367+00:00"}