{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QQ76WJIFBE27S5MUZNAPEVZ5ZB","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":"e342a2697aab09c42c9389b3f4675cd2c8367ead63b6b117ab7e91c6ca09030c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T13:40:26Z","title_canon_sha256":"31656001af3177282a82962ef5f07ebd7dcc640b4c35dbc3ecfed8216b31e731"},"schema_version":"1.0","source":{"id":"2605.19846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19846","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19846v1","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19846","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"QQ76WJIFBE27","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"pith_short_16","alias_value":"QQ76WJIFBE27S5MU","created_at":"2026-05-20T01:06:17Z"},{"alias_kind":"pith_short_8","alias_value":"QQ76WJIF","created_at":"2026-05-20T01:06:17Z"}],"graph_snapshots":[{"event_id":"sha256:9ee8b0a934a768d72e22aa64bba3a9a7378bc569ca97aa94b7545f34fe7e5cc8","target":"graph","created_at":"2026-05-20T01:06:17Z","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/2605.19846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained comprehension crucial for real-world applications requiring nuanced interpretation of human actions and interactions. While some recent human-centric benchmarks evaluate aspects of model behaviour such as fairness/ethics, emotion perception, and broader human-centric metrics, they do not combine long-form videos, very dense QA coverage, and frame-level spatial/temporal grounding at scale. To bridge this gap, we introduce FineBench, a human-centri","authors_text":"Gueter Josmy Faure, Hung-Ting Su, Jia-Fong Yeh, Min-Hung Chen, Winston H. Hsu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T13:40:26Z","title":"FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19846","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":"sha256:48c168352712c1d6d3a6df234ec26532d589f3c0cae4442feb01b0995b87163e","target":"record","created_at":"2026-05-20T01:06:17Z","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":"e342a2697aab09c42c9389b3f4675cd2c8367ead63b6b117ab7e91c6ca09030c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T13:40:26Z","title_canon_sha256":"31656001af3177282a82962ef5f07ebd7dcc640b4c35dbc3ecfed8216b31e731"},"schema_version":"1.0","source":{"id":"2605.19846","kind":"arxiv","version":1}},"canonical_sha256":"843feb25050935f97594cb40f2573dc879b6e348e1d3a98656a138de4337776d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"843feb25050935f97594cb40f2573dc879b6e348e1d3a98656a138de4337776d","first_computed_at":"2026-05-20T01:06:17.391875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:06:17.391875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dDZb0CZvlylTRK+5dEtBFU1NaOAmdeOzOlONHXXuu4Z5y4CMz6P6MWhFd64eJljfAD4CU9WzqTx39s7Zr9QcBg==","signature_status":"signed_v1","signed_at":"2026-05-20T01:06:17.392644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48c168352712c1d6d3a6df234ec26532d589f3c0cae4442feb01b0995b87163e","sha256:9ee8b0a934a768d72e22aa64bba3a9a7378bc569ca97aa94b7545f34fe7e5cc8"],"state_sha256":"c695de4f8193bf4e866f41da864ce6addcf5dbd519cc976e1d494091809b81d6"}