{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VOVXHCYACGVDHCBZTZIDLYCWOU","short_pith_number":"pith:VOVXHCYA","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"},"canonical_sha256":"abab738b0011aa3388399e5035e05675344c0492d374db985d39660653ef4d34","source":{"kind":"arxiv","id":"2605.24302","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24302","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24302v1","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24302","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"pith_short_12","alias_value":"VOVXHCYACGVD","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"pith_short_16","alias_value":"VOVXHCYACGVDHCBZ","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"pith_short_8","alias_value":"VOVXHCYA","created_at":"2026-05-26T01:02:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VOVXHCYACGVDHCBZTZIDLYCWOU","target":"record","payload":{"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"},"canonical_sha256":"abab738b0011aa3388399e5035e05675344c0492d374db985d39660653ef4d34","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"},"source_kind":"arxiv","source_id":"2605.24302","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:02:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5Zw+7Jja/oXGWx/zuHgPccKQvetHFRxp7SoMqMcRxVz/aY074UHrdacKrIBBEVE7E4vVuCLY2fanEivGb0mAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:19:38.930656Z"},"content_sha256":"8f48b6e9611ad92126d16a82d9ef17a8ae27a07a1cf3ec9e301f426390d8f09a","schema_version":"1.0","event_id":"sha256:8f48b6e9611ad92126d16a82d9ef17a8ae27a07a1cf3ec9e301f426390d8f09a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VOVXHCYACGVDHCBZTZIDLYCWOU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:02:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e1xxfp6Wp8eMgEsXDGWQXDOq+3usHGURMpe6rqD+O+GtwJ13K8tv+Rs9eJKTgH/IRILpuf/QrwTElSv9c8/1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:19:38.931660Z"},"content_sha256":"5627dd2c4f47a88d99ada4e7779d8151dfeb5538a41e2d6ce71eba94c221d7b2","schema_version":"1.0","event_id":"sha256:5627dd2c4f47a88d99ada4e7779d8151dfeb5538a41e2d6ce71eba94c221d7b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/bundle.json","state_url":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T15:19:38Z","links":{"resolver":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU","bundle":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/bundle.json","state":"https://pith.science/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VOVXHCYACGVDHCBZTZIDLYCWOU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VOVXHCYACGVDHCBZTZIDLYCWOU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"30eadc13c27bb5c4567bcba9fb323c8444db94c76302c98b2e3c1fc8bea3a892","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T00:13:27Z","title_canon_sha256":"ce7271f5101cc9ae5f19dde4f2d131724b3eeb9b224e54ee361bb40189147880"},"schema_version":"1.0","source":{"id":"2605.24302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24302","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24302v1","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24302","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"pith_short_12","alias_value":"VOVXHCYACGVD","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"pith_short_16","alias_value":"VOVXHCYACGVDHCBZ","created_at":"2026-05-26T01:02:58Z"},{"alias_kind":"pith_short_8","alias_value":"VOVXHCYA","created_at":"2026-05-26T01:02:58Z"}],"graph_snapshots":[{"event_id":"sha256:5627dd2c4f47a88d99ada4e7779d8151dfeb5538a41e2d6ce71eba94c221d7b2","target":"graph","created_at":"2026-05-26T01:02:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.24302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Juan Ignacio Bustos Gorostegui, Maria Elena Buemi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T00:13:27Z","title":"Cross-Modal Action Recognition in Egocentric Video Using Mamba: Integrating RGB and Hand Skeleton Streams via CLS Token Fusion Strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24302","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8f48b6e9611ad92126d16a82d9ef17a8ae27a07a1cf3ec9e301f426390d8f09a","target":"record","created_at":"2026-05-26T01:02:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"30eadc13c27bb5c4567bcba9fb323c8444db94c76302c98b2e3c1fc8bea3a892","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T00:13:27Z","title_canon_sha256":"ce7271f5101cc9ae5f19dde4f2d131724b3eeb9b224e54ee361bb40189147880"},"schema_version":"1.0","source":{"id":"2605.24302","kind":"arxiv","version":1}},"canonical_sha256":"abab738b0011aa3388399e5035e05675344c0492d374db985d39660653ef4d34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abab738b0011aa3388399e5035e05675344c0492d374db985d39660653ef4d34","first_computed_at":"2026-05-26T01:02:58.690820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:58.690820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wfY1s/YOOv+5DyaCRT6gPv1h4gVBttQkcvX0JrrU1GKzdlGLCUnchY6LOWd2Cw1fwqUQzpQyqUJal1fFTVMbBw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:58.691443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f48b6e9611ad92126d16a82d9ef17a8ae27a07a1cf3ec9e301f426390d8f09a","sha256:5627dd2c4f47a88d99ada4e7779d8151dfeb5538a41e2d6ce71eba94c221d7b2"],"state_sha256":"2c0847c5096d9bfce80743c10ed577897f0288550667f63e507ee5013515a006"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zvvad5pjL9VKHmP4ZVvfOvClhZ5sf4Ko2yHndZNX09lm2uDE3hOL+2U55vTOXf7Cm72SwCtcylxJbUpEQVU3Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:19:38.937093Z","bundle_sha256":"fbecefea3c0da4bfeedd6c77f0a7db55a4bf18f570db2ecb9c21218391a87dba"}}