{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:REHXDFSR5HD3UCG5NYARUZD64J","short_pith_number":"pith:REHXDFSR","schema_version":"1.0","canonical_sha256":"890f719651e9c7ba08dd6e011a647ee24b67588969e7536fd8cfcc4ac2da9dd2","source":{"kind":"arxiv","id":"2506.03162","version":3},"attestation_state":"computed","paper":{"title":"FuseMamba-VD: Dual Branch VideoMamba with Gated Class Token Fusion for Violence Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Damith Chamalke Senadeera, Dimitrios Kollias, Gregory Slabaugh, Muhammad Awais, Shibo Li","submitted_at":"2025-05-23T10:41:45Z","abstract_excerpt":"The rapid proliferation of surveillance cameras has increased the demand for automated violence detection. While CNNs and Transformers have shown success in extracting spatio-temporal features, they struggle with long-term dependencies and computational efficiency. We propose FuseMamba-VD: Dual Branch VideoMamba with Gated Class Token Fusion (GCTF), an efficient architecture combining a dual-branch design and a state-space model (SSM) backbone where one branch captures spatial features, while the other focuses on temporal dynamics. The model performs continuous fusion via a gating mechanism fr"},"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":"2506.03162","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T10:41:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"952a49c5bf9384fb223ed76d74f2aba9ac11e24736e27ef48f034e2e27c500be","abstract_canon_sha256":"3aac1133e079271afc20897a4bdb1f879f51e7a42fda1f22f6dc30a61e00e0d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:15:48.373981Z","signature_b64":"RJVPY5bPxebMTMjeKlehn7FQ7/4b5/M5qlcn1q4y2bKl1DXin3NFiTjNlw360upMKcOR1FQdYX2Op5f3xrIaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"890f719651e9c7ba08dd6e011a647ee24b67588969e7536fd8cfcc4ac2da9dd2","last_reissued_at":"2026-07-07T00:15:48.373215Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:15:48.373215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FuseMamba-VD: Dual Branch VideoMamba with Gated Class Token Fusion for Violence Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Damith Chamalke Senadeera, Dimitrios Kollias, Gregory Slabaugh, Muhammad Awais, Shibo Li","submitted_at":"2025-05-23T10:41:45Z","abstract_excerpt":"The rapid proliferation of surveillance cameras has increased the demand for automated violence detection. While CNNs and Transformers have shown success in extracting spatio-temporal features, they struggle with long-term dependencies and computational efficiency. We propose FuseMamba-VD: Dual Branch VideoMamba with Gated Class Token Fusion (GCTF), an efficient architecture combining a dual-branch design and a state-space model (SSM) backbone where one branch captures spatial features, while the other focuses on temporal dynamics. The model performs continuous fusion via a gating mechanism fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03162","kind":"arxiv","version":3},"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/2506.03162/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":"2506.03162","created_at":"2026-07-07T00:15:48.373329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03162v3","created_at":"2026-07-07T00:15:48.373329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03162","created_at":"2026-07-07T00:15:48.373329+00:00"},{"alias_kind":"pith_short_12","alias_value":"REHXDFSR5HD3","created_at":"2026-07-07T00:15:48.373329+00:00"},{"alias_kind":"pith_short_16","alias_value":"REHXDFSR5HD3UCG5","created_at":"2026-07-07T00:15:48.373329+00:00"},{"alias_kind":"pith_short_8","alias_value":"REHXDFSR","created_at":"2026-07-07T00:15:48.373329+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.03329","citing_title":"AViS-Mamba: Adaptive Visual Steering of Audio State-Space Dynamics for Violence Detection","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/REHXDFSR5HD3UCG5NYARUZD64J","json":"https://pith.science/pith/REHXDFSR5HD3UCG5NYARUZD64J.json","graph_json":"https://pith.science/api/pith-number/REHXDFSR5HD3UCG5NYARUZD64J/graph.json","events_json":"https://pith.science/api/pith-number/REHXDFSR5HD3UCG5NYARUZD64J/events.json","paper":"https://pith.science/paper/REHXDFSR"},"agent_actions":{"view_html":"https://pith.science/pith/REHXDFSR5HD3UCG5NYARUZD64J","download_json":"https://pith.science/pith/REHXDFSR5HD3UCG5NYARUZD64J.json","view_paper":"https://pith.science/paper/REHXDFSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03162&json=true","fetch_graph":"https://pith.science/api/pith-number/REHXDFSR5HD3UCG5NYARUZD64J/graph.json","fetch_events":"https://pith.science/api/pith-number/REHXDFSR5HD3UCG5NYARUZD64J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REHXDFSR5HD3UCG5NYARUZD64J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REHXDFSR5HD3UCG5NYARUZD64J/action/storage_attestation","attest_author":"https://pith.science/pith/REHXDFSR5HD3UCG5NYARUZD64J/action/author_attestation","sign_citation":"https://pith.science/pith/REHXDFSR5HD3UCG5NYARUZD64J/action/citation_signature","submit_replication":"https://pith.science/pith/REHXDFSR5HD3UCG5NYARUZD64J/action/replication_record"}},"created_at":"2026-07-07T00:15:48.373329+00:00","updated_at":"2026-07-07T00:15:48.373329+00:00"}