{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VOVXHCYACGVDHCBZTZIDLYCWOU","short_pith_number":"pith:VOVXHCYA","schema_version":"1.0","canonical_sha256":"abab738b0011aa3388399e5035e05675344c0492d374db985d39660653ef4d34","source":{"kind":"arxiv","id":"2605.24302","version":1},"attestation_state":"computed","paper":{"title":"Cross-Modal Action Recognition in Egocentric Video Using Mamba: Integrating RGB and Hand Skeleton Streams via CLS Token Fusion Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juan Ignacio Bustos Gorostegui, Maria Elena Buemi","submitted_at":"2026-05-23T00:13:27Z","abstract_excerpt":"Egocentric action recognition is a challenging task due to erratic camera motion, frequent hand occlusion, and the difficulty of maintaining consistent visual representations over time. In this work, we propose a cross-modal architecture that combines RGB video and temporal hand skeleton data within a unified Mamba-based framework, exploiting the linear time complexity of State Space Models (SSMs). Our architecture consists of three components: a VideoMamba module for visual feature extraction, a skeleton encoder built on a stack of Mamba blocks, and a fusion module that integrates both modali"},"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":"2605.24302","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T00:13:27Z","cross_cats_sorted":[],"title_canon_sha256":"ce7271f5101cc9ae5f19dde4f2d131724b3eeb9b224e54ee361bb40189147880","abstract_canon_sha256":"30eadc13c27bb5c4567bcba9fb323c8444db94c76302c98b2e3c1fc8bea3a892"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:58.691443Z","signature_b64":"wfY1s/YOOv+5DyaCRT6gPv1h4gVBttQkcvX0JrrU1GKzdlGLCUnchY6LOWd2Cw1fwqUQzpQyqUJal1fFTVMbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abab738b0011aa3388399e5035e05675344c0492d374db985d39660653ef4d34","last_reissued_at":"2026-05-26T01:02:58.690820Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:58.690820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Action Recognition in Egocentric Video Using Mamba: Integrating RGB and Hand Skeleton Streams via CLS Token Fusion Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juan Ignacio Bustos Gorostegui, Maria Elena Buemi","submitted_at":"2026-05-23T00:13:27Z","abstract_excerpt":"Egocentric action recognition is a challenging task due to erratic camera motion, frequent hand occlusion, and the difficulty of maintaining consistent visual representations over time. In this work, we propose a cross-modal architecture that combines RGB video and temporal hand skeleton data within a unified Mamba-based framework, exploiting the linear time complexity of State Space Models (SSMs). Our architecture consists of three components: a VideoMamba module for visual feature extraction, a skeleton encoder built on a stack of Mamba blocks, and a fusion module that integrates both modali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24302","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/2605.24302/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":"2605.24302","created_at":"2026-05-26T01:02:58.690902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24302v1","created_at":"2026-05-26T01:02:58.690902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24302","created_at":"2026-05-26T01:02:58.690902+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOVXHCYACGVD","created_at":"2026-05-26T01:02:58.690902+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOVXHCYACGVDHCBZ","created_at":"2026-05-26T01:02:58.690902+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOVXHCYA","created_at":"2026-05-26T01:02:58.690902+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/VOVXHCYACGVDHCBZTZIDLYCWOU","json":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU.json","graph_json":"https://pith.science/api/pith-number/VOVXHCYACGVDHCBZTZIDLYCWOU/graph.json","events_json":"https://pith.science/api/pith-number/VOVXHCYACGVDHCBZTZIDLYCWOU/events.json","paper":"https://pith.science/paper/VOVXHCYA"},"agent_actions":{"view_html":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU","download_json":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU.json","view_paper":"https://pith.science/paper/VOVXHCYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24302&json=true","fetch_graph":"https://pith.science/api/pith-number/VOVXHCYACGVDHCBZTZIDLYCWOU/graph.json","fetch_events":"https://pith.science/api/pith-number/VOVXHCYACGVDHCBZTZIDLYCWOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/action/storage_attestation","attest_author":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/action/author_attestation","sign_citation":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/action/citation_signature","submit_replication":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/action/replication_record"}},"created_at":"2026-05-26T01:02:58.690902+00:00","updated_at":"2026-05-26T01:02:58.690902+00:00"}