{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GU66MLO6JSTLPIPMEBSWXQXCJP","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":"eb827abd1607a2a1f08d50511b597032a1302c85aec2e90e05bd18346ff581b8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-20T03:59:54Z","title_canon_sha256":"d2781c852872e325c186658d5742a187c6db2271307fad4a56e5bf8c89c26ada"},"schema_version":"1.0","source":{"id":"2410.15270","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15270","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15270v2","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15270","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"pith_short_12","alias_value":"GU66MLO6JSTL","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"pith_short_16","alias_value":"GU66MLO6JSTLPIPM","created_at":"2026-07-05T11:05:21Z"},{"alias_kind":"pith_short_8","alias_value":"GU66MLO6","created_at":"2026-07-05T11:05:21Z"}],"graph_snapshots":[{"event_id":"sha256:ad8ebf2ecb10f1cf6a8898075792215cbe44af3aed69f5012c510f054dafd54d","target":"graph","created_at":"2026-07-05T11:05:21Z","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/2410.15270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jing Zhang, Kang Hao Cheong, Shiyu Hu, Xin Zhao, Xuchen Li, Xuzhao Li, Yipei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-20T03:59:54Z","title":"FIOVA: A Multi-Annotator Benchmark for Human-Aligned Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15270","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:fe483e98ff057d2ead2aeda040c51585dc633493b90b4cae15519721ab16c4bd","target":"record","created_at":"2026-07-05T11:05:21Z","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":"eb827abd1607a2a1f08d50511b597032a1302c85aec2e90e05bd18346ff581b8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-20T03:59:54Z","title_canon_sha256":"d2781c852872e325c186658d5742a187c6db2271307fad4a56e5bf8c89c26ada"},"schema_version":"1.0","source":{"id":"2410.15270","kind":"arxiv","version":2}},"canonical_sha256":"353de62dde4ca6b7a1ec20656bc2e24bc461998084acef44c1d4af559a616062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"353de62dde4ca6b7a1ec20656bc2e24bc461998084acef44c1d4af559a616062","first_computed_at":"2026-07-05T11:05:21.926298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:21.926298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g1+bNME1uMc4b3jFS1wjDYduYCi5zpsw398yHKYzTcBEjX9wvNMEVAKIcfjPO3cXdw+SJzZTRM375q9ljvnmDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:21.926796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15270","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe483e98ff057d2ead2aeda040c51585dc633493b90b4cae15519721ab16c4bd","sha256:ad8ebf2ecb10f1cf6a8898075792215cbe44af3aed69f5012c510f054dafd54d"],"state_sha256":"10e1631d3451281859d8e1d0c1b97ef02101607b23ac4189af2556d23d685b7f"}