{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QQ76WJIFBE27S5MUZNAPEVZ5ZB","short_pith_number":"pith:QQ76WJIF","schema_version":"1.0","canonical_sha256":"843feb25050935f97594cb40f2573dc879b6e348e1d3a98656a138de4337776d","source":{"kind":"arxiv","id":"2605.19846","version":1},"attestation_state":"computed","paper":{"title":"FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Gueter Josmy Faure, Hung-Ting Su, Jia-Fong Yeh, Min-Hung Chen, Winston H. Hsu","submitted_at":"2026-05-19T13:40:26Z","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"},"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":"2605.19846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T13:40:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"31656001af3177282a82962ef5f07ebd7dcc640b4c35dbc3ecfed8216b31e731","abstract_canon_sha256":"e342a2697aab09c42c9389b3f4675cd2c8367ead63b6b117ab7e91c6ca09030c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:17.392644Z","signature_b64":"dDZb0CZvlylTRK+5dEtBFU1NaOAmdeOzOlONHXXuu4Z5y4CMz6P6MWhFd64eJljfAD4CU9WzqTx39s7Zr9QcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"843feb25050935f97594cb40f2573dc879b6e348e1d3a98656a138de4337776d","last_reissued_at":"2026-05-20T01:06:17.391875Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:17.391875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Gueter Josmy Faure, Hung-Ting Su, Jia-Fong Yeh, Min-Hung Chen, Winston H. Hsu","submitted_at":"2026-05-19T13:40:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19846","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/2605.19846/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":"2605.19846","created_at":"2026-05-20T01:06:17.391992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19846v1","created_at":"2026-05-20T01:06:17.391992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19846","created_at":"2026-05-20T01:06:17.391992+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQ76WJIFBE27","created_at":"2026-05-20T01:06:17.391992+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQ76WJIFBE27S5MU","created_at":"2026-05-20T01:06:17.391992+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQ76WJIF","created_at":"2026-05-20T01:06:17.391992+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQ76WJIFBE27S5MUZNAPEVZ5ZB","json":"https://pith.science/pith/QQ76WJIFBE27S5MUZNAPEVZ5ZB.json","graph_json":"https://pith.science/api/pith-number/QQ76WJIFBE27S5MUZNAPEVZ5ZB/graph.json","events_json":"https://pith.science/api/pith-number/QQ76WJIFBE27S5MUZNAPEVZ5ZB/events.json","paper":"https://pith.science/paper/QQ76WJIF"},"agent_actions":{"view_html":"https://pith.science/pith/QQ76WJIFBE27S5MUZNAPEVZ5ZB","download_json":"https://pith.science/pith/QQ76WJIFBE27S5MUZNAPEVZ5ZB.json","view_paper":"https://pith.science/paper/QQ76WJIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19846&json=true","fetch_graph":"https://pith.science/api/pith-number/QQ76WJIFBE27S5MUZNAPEVZ5ZB/graph.json","fetch_events":"https://pith.science/api/pith-number/QQ76WJIFBE27S5MUZNAPEVZ5ZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQ76WJIFBE27S5MUZNAPEVZ5ZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQ76WJIFBE27S5MUZNAPEVZ5ZB/action/storage_attestation","attest_author":"https://pith.science/pith/QQ76WJIFBE27S5MUZNAPEVZ5ZB/action/author_attestation","sign_citation":"https://pith.science/pith/QQ76WJIFBE27S5MUZNAPEVZ5ZB/action/citation_signature","submit_replication":"https://pith.science/pith/QQ76WJIFBE27S5MUZNAPEVZ5ZB/action/replication_record"}},"created_at":"2026-05-20T01:06:17.391992+00:00","updated_at":"2026-05-20T01:06:17.391992+00:00"}