{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TPBWPPANWF3TY7DSKWNXPO7I3Y","short_pith_number":"pith:TPBWPPAN","schema_version":"1.0","canonical_sha256":"9bc367bc0db1773c7c72559b77bbe8de108eb9f340d5f7b8931a4bcb06dff054","source":{"kind":"arxiv","id":"2310.03108","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning-based Mixture of Vision Transformers for Video Violence Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ehsan Nazerfard, Hamid Mohammadi, Tahereh Firoozi","submitted_at":"2023-10-04T18:58:47Z","abstract_excerpt":"Video violence recognition based on deep learning concerns accurate yet scalable human violence recognition. Currently, most state-of-the-art video violence recognition studies use CNN-based models to represent and categorize videos. However, recent studies suggest that pre-trained transformers are more accurate than CNN-based models on various video analysis benchmarks. Yet these models are not thoroughly evaluated for video violence recognition. This paper introduces a novel transformer-based Mixture of Experts (MoE) video violence recognition system. Through an intelligent combination of la"},"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":"2310.03108","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-04T18:58:47Z","cross_cats_sorted":[],"title_canon_sha256":"949e84ade08f424cc620bee1c6970402ffb6cd03f823866ce364016832f60d54","abstract_canon_sha256":"87bf2a050515549d315eb91c5522dd0fc1b8849f0fe011b5645bed967e6552e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:28.862422Z","signature_b64":"TCSMAW66DtjW7/96cblKCk5uIF14PqBDBjXMbh+v8z6mf+tgsI0pU/S0mtqBMb/uv0YSmX2grz0SBjsGxQ0LAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bc367bc0db1773c7c72559b77bbe8de108eb9f340d5f7b8931a4bcb06dff054","last_reissued_at":"2026-07-05T06:57:28.861929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:28.861929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning-based Mixture of Vision Transformers for Video Violence Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ehsan Nazerfard, Hamid Mohammadi, Tahereh Firoozi","submitted_at":"2023-10-04T18:58:47Z","abstract_excerpt":"Video violence recognition based on deep learning concerns accurate yet scalable human violence recognition. Currently, most state-of-the-art video violence recognition studies use CNN-based models to represent and categorize videos. However, recent studies suggest that pre-trained transformers are more accurate than CNN-based models on various video analysis benchmarks. Yet these models are not thoroughly evaluated for video violence recognition. This paper introduces a novel transformer-based Mixture of Experts (MoE) video violence recognition system. Through an intelligent combination of la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03108","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/2310.03108/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":"2310.03108","created_at":"2026-07-05T06:57:28.861988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03108v1","created_at":"2026-07-05T06:57:28.861988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03108","created_at":"2026-07-05T06:57:28.861988+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPBWPPANWF3T","created_at":"2026-07-05T06:57:28.861988+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPBWPPANWF3TY7DS","created_at":"2026-07-05T06:57:28.861988+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPBWPPAN","created_at":"2026-07-05T06:57:28.861988+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/TPBWPPANWF3TY7DSKWNXPO7I3Y","json":"https://pith.science/pith/TPBWPPANWF3TY7DSKWNXPO7I3Y.json","graph_json":"https://pith.science/api/pith-number/TPBWPPANWF3TY7DSKWNXPO7I3Y/graph.json","events_json":"https://pith.science/api/pith-number/TPBWPPANWF3TY7DSKWNXPO7I3Y/events.json","paper":"https://pith.science/paper/TPBWPPAN"},"agent_actions":{"view_html":"https://pith.science/pith/TPBWPPANWF3TY7DSKWNXPO7I3Y","download_json":"https://pith.science/pith/TPBWPPANWF3TY7DSKWNXPO7I3Y.json","view_paper":"https://pith.science/paper/TPBWPPAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03108&json=true","fetch_graph":"https://pith.science/api/pith-number/TPBWPPANWF3TY7DSKWNXPO7I3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/TPBWPPANWF3TY7DSKWNXPO7I3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPBWPPANWF3TY7DSKWNXPO7I3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPBWPPANWF3TY7DSKWNXPO7I3Y/action/storage_attestation","attest_author":"https://pith.science/pith/TPBWPPANWF3TY7DSKWNXPO7I3Y/action/author_attestation","sign_citation":"https://pith.science/pith/TPBWPPANWF3TY7DSKWNXPO7I3Y/action/citation_signature","submit_replication":"https://pith.science/pith/TPBWPPANWF3TY7DSKWNXPO7I3Y/action/replication_record"}},"created_at":"2026-07-05T06:57:28.861988+00:00","updated_at":"2026-07-05T06:57:28.861988+00:00"}