{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XULSDZJQCYNT3D4GPTP4DKVBWV","short_pith_number":"pith:XULSDZJQ","schema_version":"1.0","canonical_sha256":"bd1721e530161b3d8f867cdfc1aaa1b5675b85cfafcfdcd8a962cce21ad631b3","source":{"kind":"arxiv","id":"2504.08222","version":2},"attestation_state":"computed","paper":{"title":"F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jin Song Dong, Kan Jiang, Murong Ma, Yun Lin, Zhaoyu Liu, Zhe Hou","submitted_at":"2025-04-11T03:05:35Z","abstract_excerpt":"Analyzing Fast, Frequent, and Fine-grained (F$^3$) events presents a significant challenge in video analytics and multi-modal LLMs. Current methods struggle to identify events that satisfy all the F$^3$ criteria with high accuracy due to challenges such as motion blur and subtle visual discrepancies. To advance research in video understanding, we introduce F$^3$Set, a benchmark that consists of video datasets for precise F$^3$ event detection. Datasets in F$^3$Set are characterized by their extensive scale and comprehensive detail, usually encompassing over 1,000 event types with precise times"},"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":"2504.08222","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T03:05:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"999794f39e55ca2e4e5237e421a504d318a8cde4146ddc2e108ce0f414564c3e","abstract_canon_sha256":"34e30912b53f7ca502728df43502791fb967fda959608bb0c5eece3398c8860d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:17.259520Z","signature_b64":"hQGj/UAnHRPvZjR1ck4Ktf227vdxegtZC/5EoLBt5laKSXCI8l5TeIDVVkShQ1ycPR8NJHbkqnz9+kVyAu08Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd1721e530161b3d8f867cdfc1aaa1b5675b85cfafcfdcd8a962cce21ad631b3","last_reissued_at":"2026-07-05T10:49:17.258974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:17.258974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jin Song Dong, Kan Jiang, Murong Ma, Yun Lin, Zhaoyu Liu, Zhe Hou","submitted_at":"2025-04-11T03:05:35Z","abstract_excerpt":"Analyzing Fast, Frequent, and Fine-grained (F$^3$) events presents a significant challenge in video analytics and multi-modal LLMs. Current methods struggle to identify events that satisfy all the F$^3$ criteria with high accuracy due to challenges such as motion blur and subtle visual discrepancies. To advance research in video understanding, we introduce F$^3$Set, a benchmark that consists of video datasets for precise F$^3$ event detection. Datasets in F$^3$Set are characterized by their extensive scale and comprehensive detail, usually encompassing over 1,000 event types with precise times"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08222","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/2504.08222/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":"2504.08222","created_at":"2026-07-05T10:49:17.259035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08222v2","created_at":"2026-07-05T10:49:17.259035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08222","created_at":"2026-07-05T10:49:17.259035+00:00"},{"alias_kind":"pith_short_12","alias_value":"XULSDZJQCYNT","created_at":"2026-07-05T10:49:17.259035+00:00"},{"alias_kind":"pith_short_16","alias_value":"XULSDZJQCYNT3D4G","created_at":"2026-07-05T10:49:17.259035+00:00"},{"alias_kind":"pith_short_8","alias_value":"XULSDZJQ","created_at":"2026-07-05T10:49:17.259035+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.15602","citing_title":"TennisTV: Do Multimodal Large Language Models Understand Tennis Rallies?","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15736","citing_title":"RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XULSDZJQCYNT3D4GPTP4DKVBWV","json":"https://pith.science/pith/XULSDZJQCYNT3D4GPTP4DKVBWV.json","graph_json":"https://pith.science/api/pith-number/XULSDZJQCYNT3D4GPTP4DKVBWV/graph.json","events_json":"https://pith.science/api/pith-number/XULSDZJQCYNT3D4GPTP4DKVBWV/events.json","paper":"https://pith.science/paper/XULSDZJQ"},"agent_actions":{"view_html":"https://pith.science/pith/XULSDZJQCYNT3D4GPTP4DKVBWV","download_json":"https://pith.science/pith/XULSDZJQCYNT3D4GPTP4DKVBWV.json","view_paper":"https://pith.science/paper/XULSDZJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08222&json=true","fetch_graph":"https://pith.science/api/pith-number/XULSDZJQCYNT3D4GPTP4DKVBWV/graph.json","fetch_events":"https://pith.science/api/pith-number/XULSDZJQCYNT3D4GPTP4DKVBWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XULSDZJQCYNT3D4GPTP4DKVBWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XULSDZJQCYNT3D4GPTP4DKVBWV/action/storage_attestation","attest_author":"https://pith.science/pith/XULSDZJQCYNT3D4GPTP4DKVBWV/action/author_attestation","sign_citation":"https://pith.science/pith/XULSDZJQCYNT3D4GPTP4DKVBWV/action/citation_signature","submit_replication":"https://pith.science/pith/XULSDZJQCYNT3D4GPTP4DKVBWV/action/replication_record"}},"created_at":"2026-07-05T10:49:17.259035+00:00","updated_at":"2026-07-05T10:49:17.259035+00:00"}